The official Mbed 2 C/C++ SDK provides the software platform and libraries to build your applications.

Dependents:   hello SerialTestv11 SerialTestv12 Sierpinski ... more

mbed 2

This is the mbed 2 library. If you'd like to learn about Mbed OS please see the mbed-os docs.

Revision:
145:64910690c574
Parent:
110:165afa46840b
--- a/TARGET_ARM_MPS2_M0P/arm_math.h	Thu Jun 08 14:53:05 2017 +0100
+++ b/TARGET_ARM_MPS2_M0P/arm_math.h	Wed Jun 21 17:31:38 2017 +0100
@@ -1,42 +1,30 @@
 /* ----------------------------------------------------------------------
-* Copyright (C) 2010-2015 ARM Limited. All rights reserved.
-*
-* $Date:        19. March 2015
-* $Revision: 	V.1.4.5
-*
-* Project: 	    CMSIS DSP Library
-* Title:	    arm_math.h
-*
-* Description:	Public header file for CMSIS DSP Library
-*
-* Target Processor: Cortex-M7/Cortex-M4/Cortex-M3/Cortex-M0
-*
-* Redistribution and use in source and binary forms, with or without
-* modification, are permitted provided that the following conditions
-* are met:
-*   - Redistributions of source code must retain the above copyright
-*     notice, this list of conditions and the following disclaimer.
-*   - Redistributions in binary form must reproduce the above copyright
-*     notice, this list of conditions and the following disclaimer in
-*     the documentation and/or other materials provided with the
-*     distribution.
-*   - Neither the name of ARM LIMITED nor the names of its contributors
-*     may be used to endorse or promote products derived from this
-*     software without specific prior written permission.
-*
-* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
-* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
-* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
-* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
-* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
-* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
-* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
-* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
-* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-* POSSIBILITY OF SUCH DAMAGE.
+ * Project:      CMSIS DSP Library
+ * Title:        arm_math.h
+ * Description:  Public header file for CMSIS DSP Library
+ *
+ * $Date:        27. January 2017
+ * $Revision:    V.1.5.1
+ *
+ * Target Processor: Cortex-M cores
  * -------------------------------------------------------------------- */
+/*
+ * Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved.
+ *
+ * SPDX-License-Identifier: Apache-2.0
+ *
+ * Licensed under the Apache License, Version 2.0 (the License); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an AS IS BASIS, WITHOUT
+ * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
 
 /**
    \mainpage CMSIS DSP Software Library
@@ -66,26 +54,34 @@
    * ------------
    *
    * The library installer contains prebuilt versions of the libraries in the <code>Lib</code> folder.
-   * - arm_cortexM7lfdp_math.lib (Little endian and Double Precision Floating Point Unit on Cortex-M7)
-   * - arm_cortexM7bfdp_math.lib (Big endian and Double Precision Floating Point Unit on Cortex-M7)
-   * - arm_cortexM7lfsp_math.lib (Little endian and Single Precision Floating Point Unit on Cortex-M7)
-   * - arm_cortexM7bfsp_math.lib (Big endian and Single Precision Floating Point Unit on Cortex-M7)
-   * - arm_cortexM7l_math.lib (Little endian on Cortex-M7)
-   * - arm_cortexM7b_math.lib (Big endian on Cortex-M7)
-   * - arm_cortexM4lf_math.lib (Little endian and Floating Point Unit on Cortex-M4)
-   * - arm_cortexM4bf_math.lib (Big endian and Floating Point Unit on Cortex-M4)
-   * - arm_cortexM4l_math.lib (Little endian on Cortex-M4)
-   * - arm_cortexM4b_math.lib (Big endian on Cortex-M4)
-   * - arm_cortexM3l_math.lib (Little endian on Cortex-M3)
-   * - arm_cortexM3b_math.lib (Big endian on Cortex-M3)
-   * - arm_cortexM0l_math.lib (Little endian on Cortex-M0 / CortexM0+)
-   * - arm_cortexM0b_math.lib (Big endian on Cortex-M0 / CortexM0+)
+   * - arm_cortexM7lfdp_math.lib (Cortex-M7, Little endian, Double Precision Floating Point Unit)
+   * - arm_cortexM7bfdp_math.lib (Cortex-M7, Big endian, Double Precision Floating Point Unit)
+   * - arm_cortexM7lfsp_math.lib (Cortex-M7, Little endian, Single Precision Floating Point Unit)
+   * - arm_cortexM7bfsp_math.lib (Cortex-M7, Big endian and Single Precision Floating Point Unit on)
+   * - arm_cortexM7l_math.lib (Cortex-M7, Little endian)
+   * - arm_cortexM7b_math.lib (Cortex-M7, Big endian)
+   * - arm_cortexM4lf_math.lib (Cortex-M4, Little endian, Floating Point Unit)
+   * - arm_cortexM4bf_math.lib (Cortex-M4, Big endian, Floating Point Unit)
+   * - arm_cortexM4l_math.lib (Cortex-M4, Little endian)
+   * - arm_cortexM4b_math.lib (Cortex-M4, Big endian)
+   * - arm_cortexM3l_math.lib (Cortex-M3, Little endian)
+   * - arm_cortexM3b_math.lib (Cortex-M3, Big endian)
+   * - arm_cortexM0l_math.lib (Cortex-M0 / Cortex-M0+, Little endian)
+   * - arm_cortexM0b_math.lib (Cortex-M0 / Cortex-M0+, Big endian)
+   * - arm_ARMv8MBLl_math.lib (ARMv8M Baseline, Little endian)
+   * - arm_ARMv8MMLl_math.lib (ARMv8M Mainline, Little endian)
+   * - arm_ARMv8MMLlfsp_math.lib (ARMv8M Mainline, Little endian, Single Precision Floating Point Unit)
+   * - arm_ARMv8MMLld_math.lib (ARMv8M Mainline, Little endian, DSP instructions)
+   * - arm_ARMv8MMLldfsp_math.lib (ARMv8M Mainline, Little endian, DSP instructions, Single Precision Floating Point Unit)
    *
    * The library functions are declared in the public file <code>arm_math.h</code> which is placed in the <code>Include</code> folder.
    * Simply include this file and link the appropriate library in the application and begin calling the library functions. The Library supports single
-   * public header file <code> arm_math.h</code> for Cortex-M7/M4/M3/M0/M0+ with little endian and big endian. Same header file will be used for floating point unit(FPU) variants.
+   * public header file <code> arm_math.h</code> for Cortex-M cores with little endian and big endian. Same header file will be used for floating point unit(FPU) variants.
    * Define the appropriate pre processor MACRO ARM_MATH_CM7 or ARM_MATH_CM4 or  ARM_MATH_CM3 or
    * ARM_MATH_CM0 or ARM_MATH_CM0PLUS depending on the target processor in the application.
+   * For ARMv8M cores define pre processor MACRO ARM_MATH_ARMV8MBL or ARM_MATH_ARMV8MML.
+   * Set Pre processor MACRO __DSP_PRESENT if ARMv8M Mainline core supports DSP instructions.
+   * 
    *
    * Examples
    * --------
@@ -134,14 +130,23 @@
    * and ARM_MATH_CM0 for building library on Cortex-M0 target, ARM_MATH_CM0PLUS for building library on Cortex-M0+ target, and
    * ARM_MATH_CM7 for building the library on cortex-M7.
    *
+   * - ARM_MATH_ARMV8MxL:
+   *
+   * Define macro ARM_MATH_ARMV8MBL for building the library on ARMv8M Baseline target, ARM_MATH_ARMV8MBL for building library
+   * on ARMv8M Mainline target.
+   *
    * - __FPU_PRESENT:
    *
-   * Initialize macro __FPU_PRESENT = 1 when building on FPU supported Targets. Enable this macro for M4bf and M4lf libraries
+   * Initialize macro __FPU_PRESENT = 1 when building on FPU supported Targets. Enable this macro for floating point libraries.
+   *
+   * - __DSP_PRESENT:
+   *
+   * Initialize macro __DSP_PRESENT = 1 when ARMv8M Mainline core supports DSP instructions.
    *
    * <hr>
    * CMSIS-DSP in ARM::CMSIS Pack
    * -----------------------------
-   * 
+   *
    * The following files relevant to CMSIS-DSP are present in the <b>ARM::CMSIS</b> Pack directories:
    * |File/Folder                   |Content                                                                 |
    * |------------------------------|------------------------------------------------------------------------|
@@ -149,7 +154,7 @@
    * |\b CMSIS\\DSP_Lib             | Software license agreement (license.txt)                               |
    * |\b CMSIS\\DSP_Lib\\Examples   | Example projects demonstrating the usage of the library functions      |
    * |\b CMSIS\\DSP_Lib\\Source     | Source files for rebuilding the library                                |
-   * 
+   *
    * <hr>
    * Revision History of CMSIS-DSP
    * ------------
@@ -288,28 +293,62 @@
 #ifndef _ARM_MATH_H
 #define _ARM_MATH_H
 
+/* Compiler specific diagnostic adjustment */
+#if   defined ( __CC_ARM )
+
+#elif defined ( __ARMCC_VERSION ) && ( __ARMCC_VERSION >= 6010050 )
+
+#elif defined ( __GNUC__ )
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wsign-conversion"
+#pragma GCC diagnostic ignored "-Wconversion"
+#pragma GCC diagnostic ignored "-Wunused-parameter"
+
+#elif defined ( __ICCARM__ )
+
+#elif defined ( __TI_ARM__ )
+
+#elif defined ( __CSMC__ )
+
+#elif defined ( __TASKING__ )
+
+#else
+  #error Unknown compiler
+#endif
+
+
 #define __CMSIS_GENERIC         /* disable NVIC and Systick functions */
 
 #if defined(ARM_MATH_CM7)
   #include "core_cm7.h"
+  #define ARM_MATH_DSP
 #elif defined (ARM_MATH_CM4)
   #include "core_cm4.h"
+  #define ARM_MATH_DSP
 #elif defined (ARM_MATH_CM3)
   #include "core_cm3.h"
 #elif defined (ARM_MATH_CM0)
   #include "core_cm0.h"
-#define ARM_MATH_CM0_FAMILY
-  #elif defined (ARM_MATH_CM0PLUS)
-#include "core_cm0plus.h"
+  #define ARM_MATH_CM0_FAMILY
+#elif defined (ARM_MATH_CM0PLUS)
+  #include "core_cm0plus.h"
+  #define ARM_MATH_CM0_FAMILY
+#elif defined (ARM_MATH_ARMV8MBL)
+  #include "core_armv8mbl.h"
   #define ARM_MATH_CM0_FAMILY
+#elif defined (ARM_MATH_ARMV8MML)
+  #include "core_armv8mml.h"
+  #if (defined (__DSP_PRESENT) && (__DSP_PRESENT == 1))
+    #define ARM_MATH_DSP
+  #endif
 #else
-  #error "Define according the used Cortex core ARM_MATH_CM7, ARM_MATH_CM4, ARM_MATH_CM3, ARM_MATH_CM0PLUS or ARM_MATH_CM0"
+  #error "Define according the used Cortex core ARM_MATH_CM7, ARM_MATH_CM4, ARM_MATH_CM3, ARM_MATH_CM0PLUS, ARM_MATH_CM0, ARM_MATH_ARMV8MBL, ARM_MATH_ARMV8MML"
 #endif
 
 #undef  __CMSIS_GENERIC         /* enable NVIC and Systick functions */
 #include "string.h"
 #include "math.h"
-#ifdef	__cplusplus
+#ifdef   __cplusplus
 extern "C"
 {
 #endif
@@ -319,11 +358,11 @@
    * @brief Macros required for reciprocal calculation in Normalized LMS
    */
 
-#define DELTA_Q31 			(0x100)
-#define DELTA_Q15 			0x5
-#define INDEX_MASK 			0x0000003F
+#define DELTA_Q31          (0x100)
+#define DELTA_Q15          0x5
+#define INDEX_MASK         0x0000003F
 #ifndef PI
-#define PI					3.14159265358979f
+  #define PI               3.14159265358979f
 #endif
 
   /**
@@ -334,16 +373,15 @@
 #define FAST_MATH_Q31_SHIFT   (32 - 10)
 #define FAST_MATH_Q15_SHIFT   (16 - 10)
 #define CONTROLLER_Q31_SHIFT  (32 - 9)
-#define TABLE_SIZE  256
-#define TABLE_SPACING_Q31	   0x400000
-#define TABLE_SPACING_Q15	   0x80
+#define TABLE_SPACING_Q31     0x400000
+#define TABLE_SPACING_Q15     0x80
 
   /**
    * @brief Macros required for SINE and COSINE Controller functions
    */
   /* 1.31(q31) Fixed value of 2/360 */
   /* -1 to +1 is divided into 360 values so total spacing is (2/360) */
-#define INPUT_SPACING			0xB60B61
+#define INPUT_SPACING         0xB60B61
 
   /**
    * @brief Macro for Unaligned Support
@@ -356,7 +394,7 @@
   #else
     #define ALIGN4 __align(4)
   #endif
-#endif	/*	#ifndef UNALIGNED_SUPPORT_DISABLE	*/
+#endif   /* #ifndef UNALIGNED_SUPPORT_DISABLE */
 
   /**
    * @brief Error status returned by some functions in the library.
@@ -406,59 +444,78 @@
   /**
    * @brief definition to read/write two 16 bit values.
    */
-#if defined __CC_ARM
+#if   defined ( __CC_ARM )
   #define __SIMD32_TYPE int32_t __packed
   #define CMSIS_UNUSED __attribute__((unused))
-#elif defined __ICCARM__
+  #define CMSIS_INLINE __attribute__((always_inline))
+
+#elif defined ( __ARMCC_VERSION ) && ( __ARMCC_VERSION >= 6010050 )
+  #define __SIMD32_TYPE int32_t
+  #define CMSIS_UNUSED __attribute__((unused))
+  #define CMSIS_INLINE __attribute__((always_inline))
+
+#elif defined ( __GNUC__ )
+  #define __SIMD32_TYPE int32_t
+  #define CMSIS_UNUSED __attribute__((unused))
+  #define CMSIS_INLINE __attribute__((always_inline))
+
+#elif defined ( __ICCARM__ )
   #define __SIMD32_TYPE int32_t __packed
   #define CMSIS_UNUSED
-#elif defined __GNUC__
+  #define CMSIS_INLINE
+
+#elif defined ( __TI_ARM__ )
   #define __SIMD32_TYPE int32_t
   #define CMSIS_UNUSED __attribute__((unused))
-#elif defined __CSMC__			/* Cosmic */
+  #define CMSIS_INLINE
+
+#elif defined ( __CSMC__ )
   #define __SIMD32_TYPE int32_t
   #define CMSIS_UNUSED
-#elif defined __TASKING__
+  #define CMSIS_INLINE
+
+#elif defined ( __TASKING__ )
   #define __SIMD32_TYPE __unaligned int32_t
   #define CMSIS_UNUSED
+  #define CMSIS_INLINE
+
 #else
   #error Unknown compiler
 #endif
 
-#define __SIMD32(addr)  (*(__SIMD32_TYPE **) & (addr))
+#define __SIMD32(addr)        (*(__SIMD32_TYPE **) & (addr))
 #define __SIMD32_CONST(addr)  ((__SIMD32_TYPE *)(addr))
-
 #define _SIMD32_OFFSET(addr)  (*(__SIMD32_TYPE *)  (addr))
-
-#define __SIMD64(addr)  (*(int64_t **) & (addr))
-
-#if defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY)
+#define __SIMD64(addr)        (*(int64_t **) & (addr))
+
+/* #if defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY) */
+#if !defined (ARM_MATH_DSP)
   /**
    * @brief definition to pack two 16 bit values.
    */
-#define __PKHBT(ARG1, ARG2, ARG3)      ( (((int32_t)(ARG1) <<  0) & (int32_t)0x0000FFFF) | \
-                                         (((int32_t)(ARG2) << ARG3) & (int32_t)0xFFFF0000)  )
-#define __PKHTB(ARG1, ARG2, ARG3)      ( (((int32_t)(ARG1) <<  0) & (int32_t)0xFFFF0000) | \
-                                         (((int32_t)(ARG2) >> ARG3) & (int32_t)0x0000FFFF)  )
-
-#endif
-
+#define __PKHBT(ARG1, ARG2, ARG3) ( (((int32_t)(ARG1) <<    0) & (int32_t)0x0000FFFF) | \
+                                    (((int32_t)(ARG2) << ARG3) & (int32_t)0xFFFF0000)  )
+#define __PKHTB(ARG1, ARG2, ARG3) ( (((int32_t)(ARG1) <<    0) & (int32_t)0xFFFF0000) | \
+                                    (((int32_t)(ARG2) >> ARG3) & (int32_t)0x0000FFFF)  )
+
+/* #endif // defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY) */
+#endif /* !defined (ARM_MATH_DSP) */
 
    /**
    * @brief definition to pack four 8 bit values.
    */
 #ifndef ARM_MATH_BIG_ENDIAN
 
-#define __PACKq7(v0,v1,v2,v3) ( (((int32_t)(v0) <<  0) & (int32_t)0x000000FF) |	\
-                                (((int32_t)(v1) <<  8) & (int32_t)0x0000FF00) |	\
-							    (((int32_t)(v2) << 16) & (int32_t)0x00FF0000) |	\
-							    (((int32_t)(v3) << 24) & (int32_t)0xFF000000)  )
+#define __PACKq7(v0,v1,v2,v3) ( (((int32_t)(v0) <<  0) & (int32_t)0x000000FF) | \
+                                (((int32_t)(v1) <<  8) & (int32_t)0x0000FF00) | \
+                                (((int32_t)(v2) << 16) & (int32_t)0x00FF0000) | \
+                                (((int32_t)(v3) << 24) & (int32_t)0xFF000000)  )
 #else
 
-#define __PACKq7(v0,v1,v2,v3) ( (((int32_t)(v3) <<  0) & (int32_t)0x000000FF) |	\
-                                (((int32_t)(v2) <<  8) & (int32_t)0x0000FF00) |	\
-							    (((int32_t)(v1) << 16) & (int32_t)0x00FF0000) |	\
-							    (((int32_t)(v0) << 24) & (int32_t)0xFF000000)  )
+#define __PACKq7(v0,v1,v2,v3) ( (((int32_t)(v3) <<  0) & (int32_t)0x000000FF) | \
+                                (((int32_t)(v2) <<  8) & (int32_t)0x0000FF00) | \
+                                (((int32_t)(v1) << 16) & (int32_t)0x00FF0000) | \
+                                (((int32_t)(v0) << 24) & (int32_t)0xFF000000)  )
 
 #endif
 
@@ -466,7 +523,7 @@
   /**
    * @brief Clips Q63 to Q31 values.
    */
-  static __INLINE q31_t clip_q63_to_q31(
+  CMSIS_INLINE __STATIC_INLINE q31_t clip_q63_to_q31(
   q63_t x)
   {
     return ((q31_t) (x >> 32) != ((q31_t) x >> 31)) ?
@@ -476,7 +533,7 @@
   /**
    * @brief Clips Q63 to Q15 values.
    */
-  static __INLINE q15_t clip_q63_to_q15(
+  CMSIS_INLINE __STATIC_INLINE q15_t clip_q63_to_q15(
   q63_t x)
   {
     return ((q31_t) (x >> 32) != ((q31_t) x >> 31)) ?
@@ -486,7 +543,7 @@
   /**
    * @brief Clips Q31 to Q7 values.
    */
-  static __INLINE q7_t clip_q31_to_q7(
+  CMSIS_INLINE __STATIC_INLINE q7_t clip_q31_to_q7(
   q31_t x)
   {
     return ((q31_t) (x >> 24) != ((q31_t) x >> 23)) ?
@@ -496,7 +553,7 @@
   /**
    * @brief Clips Q31 to Q15 values.
    */
-  static __INLINE q15_t clip_q31_to_q15(
+  CMSIS_INLINE __STATIC_INLINE q15_t clip_q31_to_q15(
   q31_t x)
   {
     return ((q31_t) (x >> 16) != ((q31_t) x >> 15)) ?
@@ -507,7 +564,7 @@
    * @brief Multiplies 32 X 64 and returns 32 bit result in 2.30 format.
    */
 
-  static __INLINE q63_t mult32x64(
+  CMSIS_INLINE __STATIC_INLINE q63_t mult32x64(
   q63_t x,
   q31_t y)
   {
@@ -515,64 +572,60 @@
             (((q63_t) (x >> 32) * y)));
   }
 
-
-//#if defined (ARM_MATH_CM0_FAMILY) && defined ( __CC_ARM   )
-//#define __CLZ __clz
-//#endif
-
-//note: function can be removed when all toolchain support __CLZ for Cortex-M0
+/*
+  #if defined (ARM_MATH_CM0_FAMILY) && defined ( __CC_ARM   )
+  #define __CLZ __clz
+  #endif
+ */
+/* note: function can be removed when all toolchain support __CLZ for Cortex-M0 */
 #if defined (ARM_MATH_CM0_FAMILY) && ((defined (__ICCARM__))  )
-
-  static __INLINE uint32_t __CLZ(
+  CMSIS_INLINE __STATIC_INLINE uint32_t __CLZ(
   q31_t data);
 
-
-  static __INLINE uint32_t __CLZ(
+  CMSIS_INLINE __STATIC_INLINE uint32_t __CLZ(
   q31_t data)
   {
     uint32_t count = 0;
     uint32_t mask = 0x80000000;
 
-    while((data & mask) == 0)
+    while ((data & mask) == 0)
     {
       count += 1u;
       mask = mask >> 1u;
     }
 
     return (count);
-
   }
-
 #endif
 
   /**
    * @brief Function to Calculates 1/in (reciprocal) value of Q31 Data type.
    */
 
-  static __INLINE uint32_t arm_recip_q31(
+  CMSIS_INLINE __STATIC_INLINE uint32_t arm_recip_q31(
   q31_t in,
   q31_t * dst,
   q31_t * pRecipTable)
   {
-
-    uint32_t out, tempVal;
+    q31_t out;
+    uint32_t tempVal;
     uint32_t index, i;
     uint32_t signBits;
 
-    if(in > 0)
+    if (in > 0)
     {
-      signBits = __CLZ(in) - 1;
+      signBits = ((uint32_t) (__CLZ( in) - 1));
     }
     else
     {
-      signBits = __CLZ(-in) - 1;
+      signBits = ((uint32_t) (__CLZ(-in) - 1));
     }
 
     /* Convert input sample to 1.31 format */
-    in = in << signBits;
+    in = (in << signBits);
 
     /* calculation of index for initial approximated Val */
-    index = (uint32_t) (in >> 24u);
+    index = (uint32_t)(in >> 24);
     index = (index & INDEX_MASK);
 
     /* 1.31 with exp 1 */
@@ -582,11 +635,11 @@
     /* running approximation for two iterations */
     for (i = 0u; i < 2u; i++)
     {
-      tempVal = (q31_t) (((q63_t) in * out) >> 31u);
-      tempVal = 0x7FFFFFFF - tempVal;
+      tempVal = (uint32_t) (((q63_t) in * out) >> 31);
+      tempVal = 0x7FFFFFFFu - tempVal;
       /*      1.31 with exp 1 */
-      //out = (q31_t) (((q63_t) out * tempVal) >> 30u);
-      out = (q31_t) clip_q63_to_q31(((q63_t) out * tempVal) >> 30u);
+      /* out = (q31_t) (((q63_t) out * tempVal) >> 30); */
+      out = clip_q63_to_q31(((q63_t) out * tempVal) >> 30);
     }
 
     /* write output */
@@ -594,36 +647,36 @@
 
     /* return num of signbits of out = 1/in value */
     return (signBits + 1u);
-
   }
 
+
   /**
    * @brief Function to Calculates 1/in (reciprocal) value of Q15 Data type.
    */
-  static __INLINE uint32_t arm_recip_q15(
+  CMSIS_INLINE __STATIC_INLINE uint32_t arm_recip_q15(
   q15_t in,
   q15_t * dst,
   q15_t * pRecipTable)
   {
-
-    uint32_t out = 0, tempVal = 0;
+    q15_t out = 0;
+    uint32_t tempVal = 0;
     uint32_t index = 0, i = 0;
     uint32_t signBits = 0;
 
-    if(in > 0)
+    if (in > 0)
     {
-      signBits = __CLZ(in) - 17;
+      signBits = ((uint32_t)(__CLZ( in) - 17));
     }
     else
     {
-      signBits = __CLZ(-in) - 17;
+      signBits = ((uint32_t)(__CLZ(-in) - 17));
     }
 
     /* Convert input sample to 1.15 format */
-    in = in << signBits;
+    in = (in << signBits);
 
     /* calculation of index for initial approximated Val */
-    index = in >> 8;
+    index = (uint32_t)(in >>  8);
     index = (index & INDEX_MASK);
 
     /*      1.15 with exp 1  */
@@ -631,12 +684,13 @@
 
     /* calculation of reciprocal value */
     /* running approximation for two iterations */
-    for (i = 0; i < 2; i++)
+    for (i = 0u; i < 2u; i++)
     {
-      tempVal = (q15_t) (((q31_t) in * out) >> 15);
-      tempVal = 0x7FFF - tempVal;
+      tempVal = (uint32_t) (((q31_t) in * out) >> 15);
+      tempVal = 0x7FFFu - tempVal;
       /*      1.15 with exp 1 */
       out = (q15_t) (((q31_t) out * tempVal) >> 14);
+      /* out = clip_q31_to_q15(((q31_t) out * tempVal) >> 14); */
     }
 
     /* write output */
@@ -644,7 +698,6 @@
 
     /* return num of signbits of out = 1/in value */
     return (signBits + 1);
-
   }
 
 
@@ -652,8 +705,7 @@
    * @brief C custom defined intrinisic function for only M0 processors
    */
 #if defined(ARM_MATH_CM0_FAMILY)
-
-  static __INLINE q31_t __SSAT(
+  CMSIS_INLINE __STATIC_INLINE q31_t __SSAT(
   q31_t x,
   uint32_t y)
   {
@@ -666,11 +718,11 @@
       posMax = posMax * 2;
     }
 
-    if(x > 0)
+    if (x > 0)
     {
       posMax = (posMax - 1);
 
-      if(x > posMax)
+      if (x > posMax)
       {
         x = posMax;
       }
@@ -679,400 +731,377 @@
     {
       negMin = -posMax;
 
-      if(x < negMin)
+      if (x < negMin)
       {
         x = negMin;
       }
     }
     return (x);
-
-
   }
-
 #endif /* end of ARM_MATH_CM0_FAMILY */
 
 
-
   /*
    * @brief C custom defined intrinsic function for M3 and M0 processors
    */
-#if defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY)
+/* #if defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY) */
+#if !defined (ARM_MATH_DSP)
 
   /*
    * @brief C custom defined QADD8 for M3 and M0 processors
    */
-  static __INLINE q31_t __QADD8(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __QADD8(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t sum;
-    q7_t r, s, t, u;
-
-    r = (q7_t) x;
-    s = (q7_t) y;
-
-    r = __SSAT((q31_t) (r + s), 8);
-    s = __SSAT(((q31_t) (((x << 16) >> 24) + ((y << 16) >> 24))), 8);
-    t = __SSAT(((q31_t) (((x << 8) >> 24) + ((y << 8) >> 24))), 8);
-    u = __SSAT(((q31_t) ((x >> 24) + (y >> 24))), 8);
-
-    sum =
-      (((q31_t) u << 24) & 0xFF000000) | (((q31_t) t << 16) & 0x00FF0000) |
-      (((q31_t) s << 8) & 0x0000FF00) | (r & 0x000000FF);
-
-    return sum;
-
+    q31_t r, s, t, u;
+
+    r = __SSAT(((((q31_t)x << 24) >> 24) + (((q31_t)y << 24) >> 24)), 8) & (int32_t)0x000000FF;
+    s = __SSAT(((((q31_t)x << 16) >> 24) + (((q31_t)y << 16) >> 24)), 8) & (int32_t)0x000000FF;
+    t = __SSAT(((((q31_t)x <<  8) >> 24) + (((q31_t)y <<  8) >> 24)), 8) & (int32_t)0x000000FF;
+    u = __SSAT(((((q31_t)x      ) >> 24) + (((q31_t)y      ) >> 24)), 8) & (int32_t)0x000000FF;
+
+    return ((uint32_t)((u << 24) | (t << 16) | (s <<  8) | (r      )));
   }
 
+
   /*
    * @brief C custom defined QSUB8 for M3 and M0 processors
    */
-  static __INLINE q31_t __QSUB8(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __QSUB8(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t sum;
     q31_t r, s, t, u;
 
-    r = (q7_t) x;
-    s = (q7_t) y;
-
-    r = __SSAT((r - s), 8);
-    s = __SSAT(((q31_t) (((x << 16) >> 24) - ((y << 16) >> 24))), 8) << 8;
-    t = __SSAT(((q31_t) (((x << 8) >> 24) - ((y << 8) >> 24))), 8) << 16;
-    u = __SSAT(((q31_t) ((x >> 24) - (y >> 24))), 8) << 24;
-
-    sum =
-      (u & 0xFF000000) | (t & 0x00FF0000) | (s & 0x0000FF00) | (r &
-                                                                0x000000FF);
-
-    return sum;
+    r = __SSAT(((((q31_t)x << 24) >> 24) - (((q31_t)y << 24) >> 24)), 8) & (int32_t)0x000000FF;
+    s = __SSAT(((((q31_t)x << 16) >> 24) - (((q31_t)y << 16) >> 24)), 8) & (int32_t)0x000000FF;
+    t = __SSAT(((((q31_t)x <<  8) >> 24) - (((q31_t)y <<  8) >> 24)), 8) & (int32_t)0x000000FF;
+    u = __SSAT(((((q31_t)x      ) >> 24) - (((q31_t)y      ) >> 24)), 8) & (int32_t)0x000000FF;
+
+    return ((uint32_t)((u << 24) | (t << 16) | (s <<  8) | (r      )));
   }
 
+
   /*
    * @brief C custom defined QADD16 for M3 and M0 processors
    */
-
-  /*
-   * @brief C custom defined QADD16 for M3 and M0 processors
-   */
-  static __INLINE q31_t __QADD16(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __QADD16(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t sum;
-    q31_t r, s;
-
-    r = (q15_t) x;
-    s = (q15_t) y;
-
-    r = __SSAT(r + s, 16);
-    s = __SSAT(((q31_t) ((x >> 16) + (y >> 16))), 16) << 16;
-
-    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);
-
-    return sum;
-
+/*  q31_t r,     s;  without initialisation 'arm_offset_q15 test' fails  but 'intrinsic' tests pass! for armCC */
+    q31_t r = 0, s = 0;
+
+    r = __SSAT(((((q31_t)x << 16) >> 16) + (((q31_t)y << 16) >> 16)), 16) & (int32_t)0x0000FFFF;
+    s = __SSAT(((((q31_t)x      ) >> 16) + (((q31_t)y      ) >> 16)), 16) & (int32_t)0x0000FFFF;
+
+    return ((uint32_t)((s << 16) | (r      )));
   }
 
+
   /*
    * @brief C custom defined SHADD16 for M3 and M0 processors
    */
-  static __INLINE q31_t __SHADD16(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SHADD16(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t sum;
     q31_t r, s;
 
-    r = (q15_t) x;
-    s = (q15_t) y;
-
-    r = ((r >> 1) + (s >> 1));
-    s = ((q31_t) ((x >> 17) + (y >> 17))) << 16;
-
-    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);
-
-    return sum;
-
+    r = (((((q31_t)x << 16) >> 16) + (((q31_t)y << 16) >> 16)) >> 1) & (int32_t)0x0000FFFF;
+    s = (((((q31_t)x      ) >> 16) + (((q31_t)y      ) >> 16)) >> 1) & (int32_t)0x0000FFFF;
+
+    return ((uint32_t)((s << 16) | (r      )));
   }
 
+
   /*
    * @brief C custom defined QSUB16 for M3 and M0 processors
    */
-  static __INLINE q31_t __QSUB16(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __QSUB16(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t sum;
     q31_t r, s;
 
-    r = (q15_t) x;
-    s = (q15_t) y;
-
-    r = __SSAT(r - s, 16);
-    s = __SSAT(((q31_t) ((x >> 16) - (y >> 16))), 16) << 16;
-
-    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);
-
-    return sum;
+    r = __SSAT(((((q31_t)x << 16) >> 16) - (((q31_t)y << 16) >> 16)), 16) & (int32_t)0x0000FFFF;
+    s = __SSAT(((((q31_t)x      ) >> 16) - (((q31_t)y      ) >> 16)), 16) & (int32_t)0x0000FFFF;
+
+    return ((uint32_t)((s << 16) | (r      )));
   }
 
+
   /*
    * @brief C custom defined SHSUB16 for M3 and M0 processors
    */
-  static __INLINE q31_t __SHSUB16(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SHSUB16(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t diff;
     q31_t r, s;
 
-    r = (q15_t) x;
-    s = (q15_t) y;
-
-    r = ((r >> 1) - (s >> 1));
-    s = (((x >> 17) - (y >> 17)) << 16);
-
-    diff = (s & 0xFFFF0000) | (r & 0x0000FFFF);
-
-    return diff;
+    r = (((((q31_t)x << 16) >> 16) - (((q31_t)y << 16) >> 16)) >> 1) & (int32_t)0x0000FFFF;
+    s = (((((q31_t)x      ) >> 16) - (((q31_t)y      ) >> 16)) >> 1) & (int32_t)0x0000FFFF;
+
+    return ((uint32_t)((s << 16) | (r      )));
   }
 
+
   /*
    * @brief C custom defined QASX for M3 and M0 processors
    */
-  static __INLINE q31_t __QASX(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __QASX(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t sum = 0;
-
-    sum =
-      ((sum +
-        clip_q31_to_q15((q31_t) ((q15_t) (x >> 16) + (q15_t) y))) << 16) +
-      clip_q31_to_q15((q31_t) ((q15_t) x - (q15_t) (y >> 16)));
-
-    return sum;
+    q31_t r, s;
+
+    r = __SSAT(((((q31_t)x << 16) >> 16) - (((q31_t)y      ) >> 16)), 16) & (int32_t)0x0000FFFF;
+    s = __SSAT(((((q31_t)x      ) >> 16) + (((q31_t)y << 16) >> 16)), 16) & (int32_t)0x0000FFFF;
+
+    return ((uint32_t)((s << 16) | (r      )));
   }
 
+
   /*
    * @brief C custom defined SHASX for M3 and M0 processors
    */
-  static __INLINE q31_t __SHASX(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SHASX(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t sum;
     q31_t r, s;
 
-    r = (q15_t) x;
-    s = (q15_t) y;
-
-    r = ((r >> 1) - (y >> 17));
-    s = (((x >> 17) + (s >> 1)) << 16);
-
-    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);
-
-    return sum;
+    r = (((((q31_t)x << 16) >> 16) - (((q31_t)y      ) >> 16)) >> 1) & (int32_t)0x0000FFFF;
+    s = (((((q31_t)x      ) >> 16) + (((q31_t)y << 16) >> 16)) >> 1) & (int32_t)0x0000FFFF;
+
+    return ((uint32_t)((s << 16) | (r      )));
   }
 
 
   /*
    * @brief C custom defined QSAX for M3 and M0 processors
    */
-  static __INLINE q31_t __QSAX(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __QSAX(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t sum = 0;
-
-    sum =
-      ((sum +
-        clip_q31_to_q15((q31_t) ((q15_t) (x >> 16) - (q15_t) y))) << 16) +
-      clip_q31_to_q15((q31_t) ((q15_t) x + (q15_t) (y >> 16)));
-
-    return sum;
+    q31_t r, s;
+
+    r = __SSAT(((((q31_t)x << 16) >> 16) + (((q31_t)y      ) >> 16)), 16) & (int32_t)0x0000FFFF;
+    s = __SSAT(((((q31_t)x      ) >> 16) - (((q31_t)y << 16) >> 16)), 16) & (int32_t)0x0000FFFF;
+
+    return ((uint32_t)((s << 16) | (r      )));
   }
 
+
   /*
    * @brief C custom defined SHSAX for M3 and M0 processors
    */
-  static __INLINE q31_t __SHSAX(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SHSAX(
+  uint32_t x,
+  uint32_t y)
   {
-
-    q31_t sum;
     q31_t r, s;
 
-    r = (q15_t) x;
-    s = (q15_t) y;
-
-    r = ((r >> 1) + (y >> 17));
-    s = (((x >> 17) - (s >> 1)) << 16);
-
-    sum = (s & 0xFFFF0000) | (r & 0x0000FFFF);
-
-    return sum;
+    r = (((((q31_t)x << 16) >> 16) + (((q31_t)y      ) >> 16)) >> 1) & (int32_t)0x0000FFFF;
+    s = (((((q31_t)x      ) >> 16) - (((q31_t)y << 16) >> 16)) >> 1) & (int32_t)0x0000FFFF;
+
+    return ((uint32_t)((s << 16) | (r      )));
   }
 
+
   /*
    * @brief C custom defined SMUSDX for M3 and M0 processors
    */
-  static __INLINE q31_t __SMUSDX(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SMUSDX(
+  uint32_t x,
+  uint32_t y)
   {
-
-    return ((q31_t) (((q15_t) x * (q15_t) (y >> 16)) -
-                     ((q15_t) (x >> 16) * (q15_t) y)));
+    return ((uint32_t)(((((q31_t)x << 16) >> 16) * (((q31_t)y      ) >> 16)) -
+                       ((((q31_t)x      ) >> 16) * (((q31_t)y << 16) >> 16))   ));
   }
 
   /*
    * @brief C custom defined SMUADX for M3 and M0 processors
    */
-  static __INLINE q31_t __SMUADX(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SMUADX(
+  uint32_t x,
+  uint32_t y)
   {
-
-    return ((q31_t) (((q15_t) x * (q15_t) (y >> 16)) +
-                     ((q15_t) (x >> 16) * (q15_t) y)));
+    return ((uint32_t)(((((q31_t)x << 16) >> 16) * (((q31_t)y      ) >> 16)) +
+                       ((((q31_t)x      ) >> 16) * (((q31_t)y << 16) >> 16))   ));
   }
 
+
   /*
    * @brief C custom defined QADD for M3 and M0 processors
    */
-  static __INLINE q31_t __QADD(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE int32_t __QADD(
+  int32_t x,
+  int32_t y)
   {
-    return clip_q63_to_q31((q63_t) x + y);
+    return ((int32_t)(clip_q63_to_q31((q63_t)x + (q31_t)y)));
   }
 
+
   /*
    * @brief C custom defined QSUB for M3 and M0 processors
    */
-  static __INLINE q31_t __QSUB(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE int32_t __QSUB(
+  int32_t x,
+  int32_t y)
   {
-    return clip_q63_to_q31((q63_t) x - y);
+    return ((int32_t)(clip_q63_to_q31((q63_t)x - (q31_t)y)));
   }
 
+
   /*
    * @brief C custom defined SMLAD for M3 and M0 processors
    */
-  static __INLINE q31_t __SMLAD(
-  q31_t x,
-  q31_t y,
-  q31_t sum)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SMLAD(
+  uint32_t x,
+  uint32_t y,
+  uint32_t sum)
   {
-
-    return (sum + ((q15_t) (x >> 16) * (q15_t) (y >> 16)) +
-            ((q15_t) x * (q15_t) y));
+    return ((uint32_t)(((((q31_t)x << 16) >> 16) * (((q31_t)y << 16) >> 16)) +
+                       ((((q31_t)x      ) >> 16) * (((q31_t)y      ) >> 16)) +
+                       ( ((q31_t)sum    )                                  )   ));
   }
 
+
   /*
    * @brief C custom defined SMLADX for M3 and M0 processors
    */
-  static __INLINE q31_t __SMLADX(
-  q31_t x,
-  q31_t y,
-  q31_t sum)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SMLADX(
+  uint32_t x,
+  uint32_t y,
+  uint32_t sum)
   {
-
-    return (sum + ((q15_t) (x >> 16) * (q15_t) (y)) +
-            ((q15_t) x * (q15_t) (y >> 16)));
+    return ((uint32_t)(((((q31_t)x << 16) >> 16) * (((q31_t)y      ) >> 16)) +
+                       ((((q31_t)x      ) >> 16) * (((q31_t)y << 16) >> 16)) +
+                       ( ((q31_t)sum    )                                  )   ));
   }
 
+
   /*
    * @brief C custom defined SMLSDX for M3 and M0 processors
    */
-  static __INLINE q31_t __SMLSDX(
-  q31_t x,
-  q31_t y,
-  q31_t sum)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SMLSDX(
+  uint32_t x,
+  uint32_t y,
+  uint32_t sum)
   {
-
-    return (sum - ((q15_t) (x >> 16) * (q15_t) (y)) +
-            ((q15_t) x * (q15_t) (y >> 16)));
+    return ((uint32_t)(((((q31_t)x << 16) >> 16) * (((q31_t)y      ) >> 16)) -
+                       ((((q31_t)x      ) >> 16) * (((q31_t)y << 16) >> 16)) +
+                       ( ((q31_t)sum    )                                  )   ));
   }
 
+
   /*
    * @brief C custom defined SMLALD for M3 and M0 processors
    */
-  static __INLINE q63_t __SMLALD(
-  q31_t x,
-  q31_t y,
-  q63_t sum)
+  CMSIS_INLINE __STATIC_INLINE uint64_t __SMLALD(
+  uint32_t x,
+  uint32_t y,
+  uint64_t sum)
   {
-
-    return (sum + ((q15_t) (x >> 16) * (q15_t) (y >> 16)) +
-            ((q15_t) x * (q15_t) y));
+/*  return (sum + ((q15_t) (x >> 16) * (q15_t) (y >> 16)) + ((q15_t) x * (q15_t) y)); */
+    return ((uint64_t)(((((q31_t)x << 16) >> 16) * (((q31_t)y << 16) >> 16)) +
+                       ((((q31_t)x      ) >> 16) * (((q31_t)y      ) >> 16)) +
+                       ( ((q63_t)sum    )                                  )   ));
   }
 
+
   /*
    * @brief C custom defined SMLALDX for M3 and M0 processors
    */
-  static __INLINE q63_t __SMLALDX(
-  q31_t x,
-  q31_t y,
-  q63_t sum)
+  CMSIS_INLINE __STATIC_INLINE uint64_t __SMLALDX(
+  uint32_t x,
+  uint32_t y,
+  uint64_t sum)
   {
-
-    return (sum + ((q15_t) (x >> 16) * (q15_t) y)) +
-      ((q15_t) x * (q15_t) (y >> 16));
+/*  return (sum + ((q15_t) (x >> 16) * (q15_t) y)) + ((q15_t) x * (q15_t) (y >> 16)); */
+    return ((uint64_t)(((((q31_t)x << 16) >> 16) * (((q31_t)y      ) >> 16)) +
+                       ((((q31_t)x      ) >> 16) * (((q31_t)y << 16) >> 16)) +
+                       ( ((q63_t)sum    )                                  )   ));
   }
 
+
   /*
    * @brief C custom defined SMUAD for M3 and M0 processors
    */
-  static __INLINE q31_t __SMUAD(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SMUAD(
+  uint32_t x,
+  uint32_t y)
   {
-
-    return (((x >> 16) * (y >> 16)) +
-            (((x << 16) >> 16) * ((y << 16) >> 16)));
+    return ((uint32_t)(((((q31_t)x << 16) >> 16) * (((q31_t)y << 16) >> 16)) +
+                       ((((q31_t)x      ) >> 16) * (((q31_t)y      ) >> 16))   ));
   }
 
+
   /*
    * @brief C custom defined SMUSD for M3 and M0 processors
    */
-  static __INLINE q31_t __SMUSD(
-  q31_t x,
-  q31_t y)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SMUSD(
+  uint32_t x,
+  uint32_t y)
   {
-
-    return (-((x >> 16) * (y >> 16)) +
-            (((x << 16) >> 16) * ((y << 16) >> 16)));
+    return ((uint32_t)(((((q31_t)x << 16) >> 16) * (((q31_t)y << 16) >> 16)) -
+                       ((((q31_t)x      ) >> 16) * (((q31_t)y      ) >> 16))   ));
   }
 
 
   /*
    * @brief C custom defined SXTB16 for M3 and M0 processors
    */
-  static __INLINE q31_t __SXTB16(
-  q31_t x)
+  CMSIS_INLINE __STATIC_INLINE uint32_t __SXTB16(
+  uint32_t x)
+  {
+    return ((uint32_t)(((((q31_t)x << 24) >> 24) & (q31_t)0x0000FFFF) |
+                       ((((q31_t)x <<  8) >>  8) & (q31_t)0xFFFF0000)  ));
+  }
+
+  /*
+   * @brief C custom defined SMMLA for M3 and M0 processors
+   */
+  CMSIS_INLINE __STATIC_INLINE int32_t __SMMLA(
+  int32_t x,
+  int32_t y,
+  int32_t sum)
   {
-
-    return ((((x << 24) >> 24) & 0x0000FFFF) |
-            (((x << 8) >> 8) & 0xFFFF0000));
+    return (sum + (int32_t) (((int64_t) x * y) >> 32));
+  }
+
+#if 0
+  /*
+   * @brief C custom defined PKHBT for unavailable DSP extension
+   */
+  CMSIS_INLINE __STATIC_INLINE uint32_t __PKHBT(
+  uint32_t x,
+  uint32_t y,
+  uint32_t leftshift)
+  {
+    return ( ((x             ) & 0x0000FFFFUL) |
+             ((y << leftshift) & 0xFFFF0000UL)  );
   }
 
-
-#endif /* defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY) */
+  /*
+   * @brief C custom defined PKHTB for unavailable DSP extension
+   */
+  CMSIS_INLINE __STATIC_INLINE uint32_t __PKHTB(
+  uint32_t x,
+  uint32_t y,
+  uint32_t rightshift)
+  {
+    return ( ((x              ) & 0xFFFF0000UL) |
+             ((y >> rightshift) & 0x0000FFFFUL)  );
+  }
+#endif
+
+/* #endif // defined (ARM_MATH_CM3) || defined (ARM_MATH_CM0_FAMILY) */
+#endif /* !defined (ARM_MATH_DSP) */
 
 
   /**
@@ -1118,11 +1147,10 @@
 
   /**
    * @brief Processing function for the Q7 FIR filter.
-   * @param[in] *S points to an instance of the Q7 FIR filter structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
+   * @param[in]  S          points to an instance of the Q7 FIR filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
    */
   void arm_fir_q7(
   const arm_fir_instance_q7 * S,
@@ -1133,12 +1161,11 @@
 
   /**
    * @brief  Initialization function for the Q7 FIR filter.
-   * @param[in,out] *S points to an instance of the Q7 FIR structure.
-   * @param[in] numTaps  Number of filter coefficients in the filter.
-   * @param[in] *pCoeffs points to the filter coefficients.
-   * @param[in] *pState points to the state buffer.
-   * @param[in] blockSize number of samples that are processed.
-   * @return none
+   * @param[in,out] S          points to an instance of the Q7 FIR structure.
+   * @param[in]     numTaps    Number of filter coefficients in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of samples that are processed.
    */
   void arm_fir_init_q7(
   arm_fir_instance_q7 * S,
@@ -1150,11 +1177,10 @@
 
   /**
    * @brief Processing function for the Q15 FIR filter.
-   * @param[in] *S points to an instance of the Q15 FIR structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
+   * @param[in]  S          points to an instance of the Q15 FIR structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
    */
   void arm_fir_q15(
   const arm_fir_instance_q15 * S,
@@ -1162,13 +1188,13 @@
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the fast Q15 FIR filter for Cortex-M3 and Cortex-M4.
-   * @param[in] *S points to an instance of the Q15 FIR filter structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
+   * @param[in]  S          points to an instance of the Q15 FIR filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
    */
   void arm_fir_fast_q15(
   const arm_fir_instance_q15 * S,
@@ -1176,17 +1202,17 @@
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the Q15 FIR filter.
-   * @param[in,out] *S points to an instance of the Q15 FIR filter structure.
-   * @param[in] numTaps  Number of filter coefficients in the filter. Must be even and greater than or equal to 4.
-   * @param[in] *pCoeffs points to the filter coefficients.
-   * @param[in] *pState points to the state buffer.
-   * @param[in] blockSize number of samples that are processed at a time.
+   * @param[in,out] S          points to an instance of the Q15 FIR filter structure.
+   * @param[in]     numTaps    Number of filter coefficients in the filter. Must be even and greater than or equal to 4.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of samples that are processed at a time.
    * @return The function returns ARM_MATH_SUCCESS if initialization was successful or ARM_MATH_ARGUMENT_ERROR if
    * <code>numTaps</code> is not a supported value.
    */
-
   arm_status arm_fir_init_q15(
   arm_fir_instance_q15 * S,
   uint16_t numTaps,
@@ -1194,13 +1220,13 @@
   q15_t * pState,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the Q31 FIR filter.
-   * @param[in] *S points to an instance of the Q31 FIR filter structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
+   * @param[in]  S          points to an instance of the Q31 FIR filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
    */
   void arm_fir_q31(
   const arm_fir_instance_q31 * S,
@@ -1208,13 +1234,13 @@
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the fast Q31 FIR filter for Cortex-M3 and Cortex-M4.
-   * @param[in] *S points to an instance of the Q31 FIR structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
+   * @param[in]  S          points to an instance of the Q31 FIR structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
    */
   void arm_fir_fast_q31(
   const arm_fir_instance_q31 * S,
@@ -1222,14 +1248,14 @@
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the Q31 FIR filter.
-   * @param[in,out] *S points to an instance of the Q31 FIR structure.
-   * @param[in] 	numTaps  Number of filter coefficients in the filter.
-   * @param[in] 	*pCoeffs points to the filter coefficients.
-   * @param[in] 	*pState points to the state buffer.
-   * @param[in] 	blockSize number of samples that are processed at a time.
-   * @return 		none.
+   * @param[in,out] S          points to an instance of the Q31 FIR structure.
+   * @param[in]     numTaps    Number of filter coefficients in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of samples that are processed at a time.
    */
   void arm_fir_init_q31(
   arm_fir_instance_q31 * S,
@@ -1238,13 +1264,13 @@
   q31_t * pState,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the floating-point FIR filter.
-   * @param[in] *S points to an instance of the floating-point FIR structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
+   * @param[in]  S          points to an instance of the floating-point FIR structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
    */
   void arm_fir_f32(
   const arm_fir_instance_f32 * S,
@@ -1252,14 +1278,14 @@
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the floating-point FIR filter.
-   * @param[in,out] *S points to an instance of the floating-point FIR filter structure.
-   * @param[in] 	numTaps  Number of filter coefficients in the filter.
-   * @param[in] 	*pCoeffs points to the filter coefficients.
-   * @param[in] 	*pState points to the state buffer.
-   * @param[in] 	blockSize number of samples that are processed at a time.
-   * @return    	none.
+   * @param[in,out] S          points to an instance of the floating-point FIR filter structure.
+   * @param[in]     numTaps    Number of filter coefficients in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of samples that are processed at a time.
    */
   void arm_fir_init_f32(
   arm_fir_instance_f32 * S,
@@ -1274,14 +1300,12 @@
    */
   typedef struct
   {
-    int8_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
-    q15_t *pState;            /**< Points to the array of state coefficients.  The array is of length 4*numStages. */
-    q15_t *pCoeffs;           /**< Points to the array of coefficients.  The array is of length 5*numStages. */
-    int8_t postShift;         /**< Additional shift, in bits, applied to each output sample. */
-
+    int8_t numStages;        /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
+    q15_t *pState;           /**< Points to the array of state coefficients.  The array is of length 4*numStages. */
+    q15_t *pCoeffs;          /**< Points to the array of coefficients.  The array is of length 5*numStages. */
+    int8_t postShift;        /**< Additional shift, in bits, applied to each output sample. */
   } arm_biquad_casd_df1_inst_q15;
 
-
   /**
    * @brief Instance structure for the Q31 Biquad cascade filter.
    */
@@ -1291,7 +1315,6 @@
     q31_t *pState;           /**< Points to the array of state coefficients.  The array is of length 4*numStages. */
     q31_t *pCoeffs;          /**< Points to the array of coefficients.  The array is of length 5*numStages. */
     uint8_t postShift;       /**< Additional shift, in bits, applied to each output sample. */
-
   } arm_biquad_casd_df1_inst_q31;
 
   /**
@@ -1299,40 +1322,34 @@
    */
   typedef struct
   {
-    uint32_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
-    float32_t *pState;          /**< Points to the array of state coefficients.  The array is of length 4*numStages. */
-    float32_t *pCoeffs;         /**< Points to the array of coefficients.  The array is of length 5*numStages. */
-
-
+    uint32_t numStages;      /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
+    float32_t *pState;       /**< Points to the array of state coefficients.  The array is of length 4*numStages. */
+    float32_t *pCoeffs;      /**< Points to the array of coefficients.  The array is of length 5*numStages. */
   } arm_biquad_casd_df1_inst_f32;
 
 
-
   /**
    * @brief Processing function for the Q15 Biquad cascade filter.
-   * @param[in]  *S points to an instance of the Q15 Biquad cascade structure.
-   * @param[in]  *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in]  blockSize number of samples to process.
-   * @return     none.
-   */
-
+   * @param[in]  S          points to an instance of the Q15 Biquad cascade structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_biquad_cascade_df1_q15(
   const arm_biquad_casd_df1_inst_q15 * S,
   q15_t * pSrc,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the Q15 Biquad cascade filter.
-   * @param[in,out] *S           points to an instance of the Q15 Biquad cascade structure.
-   * @param[in]     numStages    number of 2nd order stages in the filter.
-   * @param[in]     *pCoeffs     points to the filter coefficients.
-   * @param[in]     *pState      points to the state buffer.
-   * @param[in]     postShift    Shift to be applied to the output. Varies according to the coefficients format
-   * @return        none
-   */
-
+   * @param[in,out] S          points to an instance of the Q15 Biquad cascade structure.
+   * @param[in]     numStages  number of 2nd order stages in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     postShift  Shift to be applied to the output. Varies according to the coefficients format
+   */
   void arm_biquad_cascade_df1_init_q15(
   arm_biquad_casd_df1_inst_q15 * S,
   uint8_t numStages,
@@ -1343,13 +1360,11 @@
 
   /**
    * @brief Fast but less precise processing function for the Q15 Biquad cascade filter for Cortex-M3 and Cortex-M4.
-   * @param[in]  *S points to an instance of the Q15 Biquad cascade structure.
-   * @param[in]  *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in]  blockSize number of samples to process.
-   * @return     none.
-   */
-
+   * @param[in]  S          points to an instance of the Q15 Biquad cascade structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_biquad_cascade_df1_fast_q15(
   const arm_biquad_casd_df1_inst_q15 * S,
   q15_t * pSrc,
@@ -1359,44 +1374,40 @@
 
   /**
    * @brief Processing function for the Q31 Biquad cascade filter
-   * @param[in]  *S         points to an instance of the Q31 Biquad cascade structure.
-   * @param[in]  *pSrc      points to the block of input data.
-   * @param[out] *pDst      points to the block of output data.
+   * @param[in]  S          points to an instance of the Q31 Biquad cascade structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
    * @param[in]  blockSize  number of samples to process.
-   * @return     none.
-   */
-
+   */
   void arm_biquad_cascade_df1_q31(
   const arm_biquad_casd_df1_inst_q31 * S,
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Fast but less precise processing function for the Q31 Biquad cascade filter for Cortex-M3 and Cortex-M4.
-   * @param[in]  *S         points to an instance of the Q31 Biquad cascade structure.
-   * @param[in]  *pSrc      points to the block of input data.
-   * @param[out] *pDst      points to the block of output data.
+   * @param[in]  S          points to an instance of the Q31 Biquad cascade structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
    * @param[in]  blockSize  number of samples to process.
-   * @return     none.
-   */
-
+   */
   void arm_biquad_cascade_df1_fast_q31(
   const arm_biquad_casd_df1_inst_q31 * S,
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the Q31 Biquad cascade filter.
-   * @param[in,out] *S           points to an instance of the Q31 Biquad cascade structure.
-   * @param[in]     numStages      number of 2nd order stages in the filter.
-   * @param[in]     *pCoeffs     points to the filter coefficients.
-   * @param[in]     *pState      points to the state buffer.
-   * @param[in]     postShift    Shift to be applied to the output. Varies according to the coefficients format
-   * @return        none
-   */
-
+   * @param[in,out] S          points to an instance of the Q31 Biquad cascade structure.
+   * @param[in]     numStages  number of 2nd order stages in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     postShift  Shift to be applied to the output. Varies according to the coefficients format
+   */
   void arm_biquad_cascade_df1_init_q31(
   arm_biquad_casd_df1_inst_q31 * S,
   uint8_t numStages,
@@ -1404,30 +1415,28 @@
   q31_t * pState,
   int8_t postShift);
 
+
   /**
    * @brief Processing function for the floating-point Biquad cascade filter.
-   * @param[in]  *S         points to an instance of the floating-point Biquad cascade structure.
-   * @param[in]  *pSrc      points to the block of input data.
-   * @param[out] *pDst      points to the block of output data.
+   * @param[in]  S          points to an instance of the floating-point Biquad cascade structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
    * @param[in]  blockSize  number of samples to process.
-   * @return     none.
-   */
-
+   */
   void arm_biquad_cascade_df1_f32(
   const arm_biquad_casd_df1_inst_f32 * S,
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the floating-point Biquad cascade filter.
-   * @param[in,out] *S           points to an instance of the floating-point Biquad cascade structure.
-   * @param[in]     numStages    number of 2nd order stages in the filter.
-   * @param[in]     *pCoeffs     points to the filter coefficients.
-   * @param[in]     *pState      points to the state buffer.
-   * @return        none
-   */
-
+   * @param[in,out] S          points to an instance of the floating-point Biquad cascade structure.
+   * @param[in]     numStages  number of 2nd order stages in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   */
   void arm_biquad_cascade_df1_init_f32(
   arm_biquad_casd_df1_inst_f32 * S,
   uint8_t numStages,
@@ -1438,7 +1447,6 @@
   /**
    * @brief Instance structure for the floating-point matrix structure.
    */
-
   typedef struct
   {
     uint16_t numRows;     /**< number of rows of the matrix.     */
@@ -1450,7 +1458,6 @@
   /**
    * @brief Instance structure for the floating-point matrix structure.
    */
-
   typedef struct
   {
     uint16_t numRows;     /**< number of rows of the matrix.     */
@@ -1461,109 +1468,103 @@
   /**
    * @brief Instance structure for the Q15 matrix structure.
    */
-
   typedef struct
   {
     uint16_t numRows;     /**< number of rows of the matrix.     */
     uint16_t numCols;     /**< number of columns of the matrix.  */
     q15_t *pData;         /**< points to the data of the matrix. */
-
   } arm_matrix_instance_q15;
 
   /**
    * @brief Instance structure for the Q31 matrix structure.
    */
-
   typedef struct
   {
     uint16_t numRows;     /**< number of rows of the matrix.     */
     uint16_t numCols;     /**< number of columns of the matrix.  */
     q31_t *pData;         /**< points to the data of the matrix. */
-
   } arm_matrix_instance_q31;
 
 
-
   /**
    * @brief Floating-point matrix addition.
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_add_f32(
   const arm_matrix_instance_f32 * pSrcA,
   const arm_matrix_instance_f32 * pSrcB,
   arm_matrix_instance_f32 * pDst);
 
+
   /**
    * @brief Q15 matrix addition.
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]   pSrcA  points to the first input matrix structure
+   * @param[in]   pSrcB  points to the second input matrix structure
+   * @param[out]  pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_add_q15(
   const arm_matrix_instance_q15 * pSrcA,
   const arm_matrix_instance_q15 * pSrcB,
   arm_matrix_instance_q15 * pDst);
 
+
   /**
    * @brief Q31 matrix addition.
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_add_q31(
   const arm_matrix_instance_q31 * pSrcA,
   const arm_matrix_instance_q31 * pSrcB,
   arm_matrix_instance_q31 * pDst);
 
+
   /**
    * @brief Floating-point, complex, matrix multiplication.
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_cmplx_mult_f32(
   const arm_matrix_instance_f32 * pSrcA,
   const arm_matrix_instance_f32 * pSrcB,
   arm_matrix_instance_f32 * pDst);
 
+
   /**
    * @brief Q15, complex,  matrix multiplication.
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_cmplx_mult_q15(
   const arm_matrix_instance_q15 * pSrcA,
   const arm_matrix_instance_q15 * pSrcB,
   arm_matrix_instance_q15 * pDst,
   q15_t * pScratch);
 
+
   /**
    * @brief Q31, complex, matrix multiplication.
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_cmplx_mult_q31(
   const arm_matrix_instance_q31 * pSrcA,
   const arm_matrix_instance_q31 * pSrcB,
@@ -1572,12 +1573,11 @@
 
   /**
    * @brief Floating-point matrix transpose.
-   * @param[in]  *pSrc points to the input matrix
-   * @param[out] *pDst points to the output matrix
-   * @return 	The function returns either  <code>ARM_MATH_SIZE_MISMATCH</code>
+   * @param[in]  pSrc  points to the input matrix
+   * @param[out] pDst  points to the output matrix
+   * @return    The function returns either  <code>ARM_MATH_SIZE_MISMATCH</code>
    * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_trans_f32(
   const arm_matrix_instance_f32 * pSrc,
   arm_matrix_instance_f32 * pDst);
@@ -1585,24 +1585,23 @@
 
   /**
    * @brief Q15 matrix transpose.
-   * @param[in]  *pSrc points to the input matrix
-   * @param[out] *pDst points to the output matrix
-   * @return 	The function returns either  <code>ARM_MATH_SIZE_MISMATCH</code>
+   * @param[in]  pSrc  points to the input matrix
+   * @param[out] pDst  points to the output matrix
+   * @return    The function returns either  <code>ARM_MATH_SIZE_MISMATCH</code>
    * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_trans_q15(
   const arm_matrix_instance_q15 * pSrc,
   arm_matrix_instance_q15 * pDst);
 
+
   /**
    * @brief Q31 matrix transpose.
-   * @param[in]  *pSrc points to the input matrix
-   * @param[out] *pDst points to the output matrix
-   * @return 	The function returns either  <code>ARM_MATH_SIZE_MISMATCH</code>
+   * @param[in]  pSrc  points to the input matrix
+   * @param[out] pDst  points to the output matrix
+   * @return    The function returns either  <code>ARM_MATH_SIZE_MISMATCH</code>
    * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_trans_q31(
   const arm_matrix_instance_q31 * pSrc,
   arm_matrix_instance_q31 * pDst);
@@ -1610,73 +1609,72 @@
 
   /**
    * @brief Floating-point matrix multiplication
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_mult_f32(
   const arm_matrix_instance_f32 * pSrcA,
   const arm_matrix_instance_f32 * pSrcB,
   arm_matrix_instance_f32 * pDst);
 
+
   /**
    * @brief Q15 matrix multiplication
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
-   * @param[in]		 *pState points to the array for storing intermediate results
+   * @param[in]  pSrcA   points to the first input matrix structure
+   * @param[in]  pSrcB   points to the second input matrix structure
+   * @param[out] pDst    points to output matrix structure
+   * @param[in]  pState  points to the array for storing intermediate results
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_mult_q15(
   const arm_matrix_instance_q15 * pSrcA,
   const arm_matrix_instance_q15 * pSrcB,
   arm_matrix_instance_q15 * pDst,
   q15_t * pState);
 
+
   /**
    * @brief Q15 matrix multiplication (fast variant) for Cortex-M3 and Cortex-M4
-   * @param[in]       *pSrcA  points to the first input matrix structure
-   * @param[in]       *pSrcB  points to the second input matrix structure
-   * @param[out]      *pDst   points to output matrix structure
-   * @param[in]		  *pState points to the array for storing intermediate results
+   * @param[in]  pSrcA   points to the first input matrix structure
+   * @param[in]  pSrcB   points to the second input matrix structure
+   * @param[out] pDst    points to output matrix structure
+   * @param[in]  pState  points to the array for storing intermediate results
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_mult_fast_q15(
   const arm_matrix_instance_q15 * pSrcA,
   const arm_matrix_instance_q15 * pSrcB,
   arm_matrix_instance_q15 * pDst,
   q15_t * pState);
 
+
   /**
    * @brief Q31 matrix multiplication
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_mult_q31(
   const arm_matrix_instance_q31 * pSrcA,
   const arm_matrix_instance_q31 * pSrcB,
   arm_matrix_instance_q31 * pDst);
 
+
   /**
    * @brief Q31 matrix multiplication (fast variant) for Cortex-M3 and Cortex-M4
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_mult_fast_q31(
   const arm_matrix_instance_q31 * pSrcA,
   const arm_matrix_instance_q31 * pSrcB,
@@ -1685,86 +1683,85 @@
 
   /**
    * @brief Floating-point matrix subtraction
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_sub_f32(
   const arm_matrix_instance_f32 * pSrcA,
   const arm_matrix_instance_f32 * pSrcB,
   arm_matrix_instance_f32 * pDst);
 
+
   /**
    * @brief Q15 matrix subtraction
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_sub_q15(
   const arm_matrix_instance_q15 * pSrcA,
   const arm_matrix_instance_q15 * pSrcB,
   arm_matrix_instance_q15 * pDst);
 
+
   /**
    * @brief Q31 matrix subtraction
-   * @param[in]       *pSrcA points to the first input matrix structure
-   * @param[in]       *pSrcB points to the second input matrix structure
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrcA  points to the first input matrix structure
+   * @param[in]  pSrcB  points to the second input matrix structure
+   * @param[out] pDst   points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_sub_q31(
   const arm_matrix_instance_q31 * pSrcA,
   const arm_matrix_instance_q31 * pSrcB,
   arm_matrix_instance_q31 * pDst);
 
+
   /**
    * @brief Floating-point matrix scaling.
-   * @param[in]  *pSrc points to the input matrix
-   * @param[in]  scale scale factor
-   * @param[out] *pDst points to the output matrix
+   * @param[in]  pSrc   points to the input matrix
+   * @param[in]  scale  scale factor
+   * @param[out] pDst   points to the output matrix
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_scale_f32(
   const arm_matrix_instance_f32 * pSrc,
   float32_t scale,
   arm_matrix_instance_f32 * pDst);
 
+
   /**
    * @brief Q15 matrix scaling.
-   * @param[in]       *pSrc points to input matrix
-   * @param[in]       scaleFract fractional portion of the scale factor
-   * @param[in]       shift number of bits to shift the result by
-   * @param[out]      *pDst points to output matrix
+   * @param[in]  pSrc        points to input matrix
+   * @param[in]  scaleFract  fractional portion of the scale factor
+   * @param[in]  shift       number of bits to shift the result by
+   * @param[out] pDst        points to output matrix
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_scale_q15(
   const arm_matrix_instance_q15 * pSrc,
   q15_t scaleFract,
   int32_t shift,
   arm_matrix_instance_q15 * pDst);
 
+
   /**
    * @brief Q31 matrix scaling.
-   * @param[in]       *pSrc points to input matrix
-   * @param[in]       scaleFract fractional portion of the scale factor
-   * @param[in]       shift number of bits to shift the result by
-   * @param[out]      *pDst points to output matrix structure
+   * @param[in]  pSrc        points to input matrix
+   * @param[in]  scaleFract  fractional portion of the scale factor
+   * @param[in]  shift       number of bits to shift the result by
+   * @param[out] pDst        points to output matrix structure
    * @return     The function returns either
    * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
    */
-
   arm_status arm_mat_scale_q31(
   const arm_matrix_instance_q31 * pSrc,
   q31_t scaleFract,
@@ -1774,43 +1771,39 @@
 
   /**
    * @brief  Q31 matrix initialization.
-   * @param[in,out] *S             points to an instance of the floating-point matrix structure.
-   * @param[in]     nRows          number of rows in the matrix.
-   * @param[in]     nColumns       number of columns in the matrix.
-   * @param[in]     *pData	       points to the matrix data array.
-   * @return        none
-   */
-
+   * @param[in,out] S         points to an instance of the floating-point matrix structure.
+   * @param[in]     nRows     number of rows in the matrix.
+   * @param[in]     nColumns  number of columns in the matrix.
+   * @param[in]     pData     points to the matrix data array.
+   */
   void arm_mat_init_q31(
   arm_matrix_instance_q31 * S,
   uint16_t nRows,
   uint16_t nColumns,
   q31_t * pData);
 
+
   /**
    * @brief  Q15 matrix initialization.
-   * @param[in,out] *S             points to an instance of the floating-point matrix structure.
-   * @param[in]     nRows          number of rows in the matrix.
-   * @param[in]     nColumns       number of columns in the matrix.
-   * @param[in]     *pData	       points to the matrix data array.
-   * @return        none
-   */
-
+   * @param[in,out] S         points to an instance of the floating-point matrix structure.
+   * @param[in]     nRows     number of rows in the matrix.
+   * @param[in]     nColumns  number of columns in the matrix.
+   * @param[in]     pData     points to the matrix data array.
+   */
   void arm_mat_init_q15(
   arm_matrix_instance_q15 * S,
   uint16_t nRows,
   uint16_t nColumns,
   q15_t * pData);
 
+
   /**
    * @brief  Floating-point matrix initialization.
-   * @param[in,out] *S             points to an instance of the floating-point matrix structure.
-   * @param[in]     nRows          number of rows in the matrix.
-   * @param[in]     nColumns       number of columns in the matrix.
-   * @param[in]     *pData	       points to the matrix data array.
-   * @return        none
-   */
-
+   * @param[in,out] S         points to an instance of the floating-point matrix structure.
+   * @param[in]     nRows     number of rows in the matrix.
+   * @param[in]     nColumns  number of columns in the matrix.
+   * @param[in]     pData     points to the matrix data array.
+   */
   void arm_mat_init_f32(
   arm_matrix_instance_f32 * S,
   uint16_t nRows,
@@ -1824,14 +1817,14 @@
    */
   typedef struct
   {
-    q15_t A0;    /**< The derived gain, A0 = Kp + Ki + Kd . */
-#ifdef ARM_MATH_CM0_FAMILY
+    q15_t A0;           /**< The derived gain, A0 = Kp + Ki + Kd . */
+#if !defined (ARM_MATH_DSP)
     q15_t A1;
     q15_t A2;
 #else
     q31_t A1;           /**< The derived gain A1 = -Kp - 2Kd | Kd.*/
 #endif
-    q15_t state[3];       /**< The state array of length 3. */
+    q15_t state[3];     /**< The state array of length 3. */
     q15_t Kp;           /**< The proportional gain. */
     q15_t Ki;           /**< The integral gain. */
     q15_t Kd;           /**< The derivative gain. */
@@ -1849,7 +1842,6 @@
     q31_t Kp;            /**< The proportional gain. */
     q31_t Ki;            /**< The integral gain. */
     q31_t Kd;            /**< The derivative gain. */
-
   } arm_pid_instance_q31;
 
   /**
@@ -1861,27 +1853,26 @@
     float32_t A1;          /**< The derived gain, A1 = -Kp - 2Kd. */
     float32_t A2;          /**< The derived gain, A2 = Kd . */
     float32_t state[3];    /**< The state array of length 3. */
-    float32_t Kp;               /**< The proportional gain. */
-    float32_t Ki;               /**< The integral gain. */
-    float32_t Kd;               /**< The derivative gain. */
+    float32_t Kp;          /**< The proportional gain. */
+    float32_t Ki;          /**< The integral gain. */
+    float32_t Kd;          /**< The derivative gain. */
   } arm_pid_instance_f32;
 
 
 
   /**
    * @brief  Initialization function for the floating-point PID Control.
-   * @param[in,out] *S      points to an instance of the PID structure.
+   * @param[in,out] S               points to an instance of the PID structure.
    * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.
-   * @return none.
    */
   void arm_pid_init_f32(
   arm_pid_instance_f32 * S,
   int32_t resetStateFlag);
 
+
   /**
    * @brief  Reset function for the floating-point PID Control.
-   * @param[in,out] *S is an instance of the floating-point PID Control structure
-   * @return none
+   * @param[in,out] S  is an instance of the floating-point PID Control structure
    */
   void arm_pid_reset_f32(
   arm_pid_instance_f32 * S);
@@ -1889,9 +1880,8 @@
 
   /**
    * @brief  Initialization function for the Q31 PID Control.
-   * @param[in,out] *S points to an instance of the Q15 PID structure.
+   * @param[in,out] S               points to an instance of the Q15 PID structure.
    * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.
-   * @return none.
    */
   void arm_pid_init_q31(
   arm_pid_instance_q31 * S,
@@ -1900,27 +1890,26 @@
 
   /**
    * @brief  Reset function for the Q31 PID Control.
-   * @param[in,out] *S points to an instance of the Q31 PID Control structure
-   * @return none
+   * @param[in,out] S   points to an instance of the Q31 PID Control structure
    */
 
   void arm_pid_reset_q31(
   arm_pid_instance_q31 * S);
 
+
   /**
    * @brief  Initialization function for the Q15 PID Control.
-   * @param[in,out] *S points to an instance of the Q15 PID structure.
-   * @param[in] resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.
-   * @return none.
+   * @param[in,out] S               points to an instance of the Q15 PID structure.
+   * @param[in]     resetStateFlag  flag to reset the state. 0 = no change in state 1 = reset the state.
    */
   void arm_pid_init_q15(
   arm_pid_instance_q15 * S,
   int32_t resetStateFlag);
 
+
   /**
    * @brief  Reset function for the Q15 PID Control.
-   * @param[in,out] *S points to an instance of the q15 PID Control structure
-   * @return none
+   * @param[in,out] S  points to an instance of the q15 PID Control structure
    */
   void arm_pid_reset_q15(
   arm_pid_instance_q15 * S);
@@ -1940,7 +1929,6 @@
   /**
    * @brief Instance structure for the floating-point bilinear interpolation function.
    */
-
   typedef struct
   {
     uint16_t numRows;   /**< number of rows in the data table. */
@@ -1951,7 +1939,6 @@
    /**
    * @brief Instance structure for the Q31 bilinear interpolation function.
    */
-
   typedef struct
   {
     uint16_t numRows;   /**< number of rows in the data table. */
@@ -1962,7 +1949,6 @@
    /**
    * @brief Instance structure for the Q15 bilinear interpolation function.
    */
-
   typedef struct
   {
     uint16_t numRows;   /**< number of rows in the data table. */
@@ -1973,69 +1959,63 @@
    /**
    * @brief Instance structure for the Q15 bilinear interpolation function.
    */
-
   typedef struct
   {
     uint16_t numRows;   /**< number of rows in the data table. */
     uint16_t numCols;   /**< number of columns in the data table. */
-    q7_t *pData;                /**< points to the data table. */
+    q7_t *pData;        /**< points to the data table. */
   } arm_bilinear_interp_instance_q7;
 
 
   /**
    * @brief Q7 vector multiplication.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst  points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_mult_q7(
   q7_t * pSrcA,
   q7_t * pSrcB,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q15 vector multiplication.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst  points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_mult_q15(
   q15_t * pSrcA,
   q15_t * pSrcB,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q31 vector multiplication.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_mult_q31(
   q31_t * pSrcA,
   q31_t * pSrcB,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Floating-point vector multiplication.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_mult_f32(
   float32_t * pSrcA,
   float32_t * pSrcB,
@@ -2043,20 +2023,15 @@
   uint32_t blockSize);
 
 
-
-
-
-
   /**
    * @brief Instance structure for the Q15 CFFT/CIFFT function.
    */
-
   typedef struct
   {
     uint16_t fftLen;                 /**< length of the FFT. */
     uint8_t ifftFlag;                /**< flag that selects forward (ifftFlag=0) or inverse (ifftFlag=1) transform. */
     uint8_t bitReverseFlag;          /**< flag that enables (bitReverseFlag=1) or disables (bitReverseFlag=0) bit reversal of output. */
-    q15_t *pTwiddle;                     /**< points to the Sin twiddle factor table. */
+    q15_t *pTwiddle;                 /**< points to the Sin twiddle factor table. */
     uint16_t *pBitRevTable;          /**< points to the bit reversal table. */
     uint16_t twidCoefModifier;       /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
     uint16_t bitRevFactor;           /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
@@ -2075,11 +2050,9 @@
   q15_t * pSrc);
 
 
-
   /**
    * @brief Instance structure for the Q15 CFFT/CIFFT function.
    */
-
   typedef struct
   {
     uint16_t fftLen;                 /**< length of the FFT. */
@@ -2106,13 +2079,12 @@
   /**
    * @brief Instance structure for the Radix-2 Q31 CFFT/CIFFT function.
    */
-
   typedef struct
   {
     uint16_t fftLen;                 /**< length of the FFT. */
     uint8_t ifftFlag;                /**< flag that selects forward (ifftFlag=0) or inverse (ifftFlag=1) transform. */
     uint8_t bitReverseFlag;          /**< flag that enables (bitReverseFlag=1) or disables (bitReverseFlag=0) bit reversal of output. */
-    q31_t *pTwiddle;                     /**< points to the Twiddle factor table. */
+    q31_t *pTwiddle;                 /**< points to the Twiddle factor table. */
     uint16_t *pBitRevTable;          /**< points to the bit reversal table. */
     uint16_t twidCoefModifier;       /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
     uint16_t bitRevFactor;           /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
@@ -2133,7 +2105,6 @@
   /**
    * @brief Instance structure for the Q31 CFFT/CIFFT function.
    */
-
   typedef struct
   {
     uint16_t fftLen;                 /**< length of the FFT. */
@@ -2160,7 +2131,6 @@
   /**
    * @brief Instance structure for the floating-point CFFT/CIFFT function.
    */
-
   typedef struct
   {
     uint16_t fftLen;                   /**< length of the FFT. */
@@ -2170,7 +2140,7 @@
     uint16_t *pBitRevTable;            /**< points to the bit reversal table. */
     uint16_t twidCoefModifier;         /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
     uint16_t bitRevFactor;             /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
-    float32_t onebyfftLen;                 /**< value of 1/fftLen. */
+    float32_t onebyfftLen;             /**< value of 1/fftLen. */
   } arm_cfft_radix2_instance_f32;
 
 /* Deprecated */
@@ -2188,7 +2158,6 @@
   /**
    * @brief Instance structure for the floating-point CFFT/CIFFT function.
    */
-
   typedef struct
   {
     uint16_t fftLen;                   /**< length of the FFT. */
@@ -2198,7 +2167,7 @@
     uint16_t *pBitRevTable;            /**< points to the bit reversal table. */
     uint16_t twidCoefModifier;         /**< twiddle coefficient modifier that supports different size FFTs with the same twiddle factor table. */
     uint16_t bitRevFactor;             /**< bit reversal modifier that supports different size FFTs with the same bit reversal table. */
-    float32_t onebyfftLen;                 /**< value of 1/fftLen. */
+    float32_t onebyfftLen;             /**< value of 1/fftLen. */
   } arm_cfft_radix4_instance_f32;
 
 /* Deprecated */
@@ -2216,7 +2185,6 @@
   /**
    * @brief Instance structure for the fixed-point CFFT/CIFFT function.
    */
-
   typedef struct
   {
     uint16_t fftLen;                   /**< length of the FFT. */
@@ -2225,16 +2193,15 @@
     uint16_t bitRevLength;             /**< bit reversal table length. */
   } arm_cfft_instance_q15;
 
-void arm_cfft_q15( 
-    const arm_cfft_instance_q15 * S, 
+void arm_cfft_q15(
+    const arm_cfft_instance_q15 * S,
     q15_t * p1,
     uint8_t ifftFlag,
-    uint8_t bitReverseFlag);  
+    uint8_t bitReverseFlag);
 
   /**
    * @brief Instance structure for the fixed-point CFFT/CIFFT function.
    */
-
   typedef struct
   {
     uint16_t fftLen;                   /**< length of the FFT. */
@@ -2243,16 +2210,15 @@
     uint16_t bitRevLength;             /**< bit reversal table length. */
   } arm_cfft_instance_q31;
 
-void arm_cfft_q31( 
-    const arm_cfft_instance_q31 * S, 
+void arm_cfft_q31(
+    const arm_cfft_instance_q31 * S,
     q31_t * p1,
     uint8_t ifftFlag,
-    uint8_t bitReverseFlag);  
-  
+    uint8_t bitReverseFlag);
+
   /**
    * @brief Instance structure for the floating-point CFFT/CIFFT function.
    */
-
   typedef struct
   {
     uint16_t fftLen;                   /**< length of the FFT. */
@@ -2270,7 +2236,6 @@
   /**
    * @brief Instance structure for the Q15 RFFT/RIFFT function.
    */
-
   typedef struct
   {
     uint32_t fftLenReal;                      /**< length of the real FFT. */
@@ -2296,7 +2261,6 @@
   /**
    * @brief Instance structure for the Q31 RFFT/RIFFT function.
    */
-
   typedef struct
   {
     uint32_t fftLenReal;                        /**< length of the real FFT. */
@@ -2322,7 +2286,6 @@
   /**
    * @brief Instance structure for the floating-point RFFT/RIFFT function.
    */
-
   typedef struct
   {
     uint32_t fftLenReal;                        /**< length of the real FFT. */
@@ -2350,17 +2313,16 @@
   /**
    * @brief Instance structure for the floating-point RFFT/RIFFT function.
    */
-
 typedef struct
   {
     arm_cfft_instance_f32 Sint;      /**< Internal CFFT structure. */
-    uint16_t fftLenRFFT;                        /**< length of the real sequence */
-	float32_t * pTwiddleRFFT;					/**< Twiddle factors real stage  */
+    uint16_t fftLenRFFT;             /**< length of the real sequence */
+    float32_t * pTwiddleRFFT;        /**< Twiddle factors real stage  */
   } arm_rfft_fast_instance_f32 ;
 
 arm_status arm_rfft_fast_init_f32 (
-	arm_rfft_fast_instance_f32 * S,
-	uint16_t fftLen);
+   arm_rfft_fast_instance_f32 * S,
+   uint16_t fftLen);
 
 void arm_rfft_fast_f32(
   arm_rfft_fast_instance_f32 * S,
@@ -2370,29 +2332,28 @@
   /**
    * @brief Instance structure for the floating-point DCT4/IDCT4 function.
    */
-
   typedef struct
   {
-    uint16_t N;                         /**< length of the DCT4. */
-    uint16_t Nby2;                      /**< half of the length of the DCT4. */
-    float32_t normalize;                /**< normalizing factor. */
-    float32_t *pTwiddle;                /**< points to the twiddle factor table. */
-    float32_t *pCosFactor;              /**< points to the cosFactor table. */
+    uint16_t N;                          /**< length of the DCT4. */
+    uint16_t Nby2;                       /**< half of the length of the DCT4. */
+    float32_t normalize;                 /**< normalizing factor. */
+    float32_t *pTwiddle;                 /**< points to the twiddle factor table. */
+    float32_t *pCosFactor;               /**< points to the cosFactor table. */
     arm_rfft_instance_f32 *pRfft;        /**< points to the real FFT instance. */
     arm_cfft_radix4_instance_f32 *pCfft; /**< points to the complex FFT instance. */
   } arm_dct4_instance_f32;
 
+
   /**
    * @brief  Initialization function for the floating-point DCT4/IDCT4.
-   * @param[in,out] *S         points to an instance of floating-point DCT4/IDCT4 structure.
-   * @param[in]     *S_RFFT    points to an instance of floating-point RFFT/RIFFT structure.
-   * @param[in]     *S_CFFT    points to an instance of floating-point CFFT/CIFFT structure.
+   * @param[in,out] S          points to an instance of floating-point DCT4/IDCT4 structure.
+   * @param[in]     S_RFFT     points to an instance of floating-point RFFT/RIFFT structure.
+   * @param[in]     S_CFFT     points to an instance of floating-point CFFT/CIFFT structure.
    * @param[in]     N          length of the DCT4.
    * @param[in]     Nby2       half of the length of the DCT4.
    * @param[in]     normalize  normalizing factor.
-   * @return		arm_status function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_ARGUMENT_ERROR if <code>fftLenReal</code> is not a supported transform length.
-   */
-
+   * @return      arm_status function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_ARGUMENT_ERROR if <code>fftLenReal</code> is not a supported transform length.
+   */
   arm_status arm_dct4_init_f32(
   arm_dct4_instance_f32 * S,
   arm_rfft_instance_f32 * S_RFFT,
@@ -2401,45 +2362,44 @@
   uint16_t Nby2,
   float32_t normalize);
 
+
   /**
    * @brief Processing function for the floating-point DCT4/IDCT4.
-   * @param[in]       *S             points to an instance of the floating-point DCT4/IDCT4 structure.
-   * @param[in]       *pState        points to state buffer.
-   * @param[in,out]   *pInlineBuffer points to the in-place input and output buffer.
-   * @return none.
-   */
-
+   * @param[in]     S              points to an instance of the floating-point DCT4/IDCT4 structure.
+   * @param[in]     pState         points to state buffer.
+   * @param[in,out] pInlineBuffer  points to the in-place input and output buffer.
+   */
   void arm_dct4_f32(
   const arm_dct4_instance_f32 * S,
   float32_t * pState,
   float32_t * pInlineBuffer);
 
+
   /**
    * @brief Instance structure for the Q31 DCT4/IDCT4 function.
    */
-
   typedef struct
   {
-    uint16_t N;                         /**< length of the DCT4. */
-    uint16_t Nby2;                      /**< half of the length of the DCT4. */
-    q31_t normalize;                    /**< normalizing factor. */
-    q31_t *pTwiddle;                    /**< points to the twiddle factor table. */
-    q31_t *pCosFactor;                  /**< points to the cosFactor table. */
+    uint16_t N;                          /**< length of the DCT4. */
+    uint16_t Nby2;                       /**< half of the length of the DCT4. */
+    q31_t normalize;                     /**< normalizing factor. */
+    q31_t *pTwiddle;                     /**< points to the twiddle factor table. */
+    q31_t *pCosFactor;                   /**< points to the cosFactor table. */
     arm_rfft_instance_q31 *pRfft;        /**< points to the real FFT instance. */
     arm_cfft_radix4_instance_q31 *pCfft; /**< points to the complex FFT instance. */
   } arm_dct4_instance_q31;
 
+
   /**
    * @brief  Initialization function for the Q31 DCT4/IDCT4.
-   * @param[in,out] *S         points to an instance of Q31 DCT4/IDCT4 structure.
-   * @param[in]     *S_RFFT    points to an instance of Q31 RFFT/RIFFT structure
-   * @param[in]     *S_CFFT    points to an instance of Q31 CFFT/CIFFT structure
+   * @param[in,out] S          points to an instance of Q31 DCT4/IDCT4 structure.
+   * @param[in]     S_RFFT     points to an instance of Q31 RFFT/RIFFT structure
+   * @param[in]     S_CFFT     points to an instance of Q31 CFFT/CIFFT structure
    * @param[in]     N          length of the DCT4.
    * @param[in]     Nby2       half of the length of the DCT4.
    * @param[in]     normalize  normalizing factor.
-   * @return		arm_status function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_ARGUMENT_ERROR if <code>N</code> is not a supported transform length.
-   */
-
+   * @return      arm_status function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_ARGUMENT_ERROR if <code>N</code> is not a supported transform length.
+   */
   arm_status arm_dct4_init_q31(
   arm_dct4_instance_q31 * S,
   arm_rfft_instance_q31 * S_RFFT,
@@ -2448,45 +2408,44 @@
   uint16_t Nby2,
   q31_t normalize);
 
+
   /**
    * @brief Processing function for the Q31 DCT4/IDCT4.
-   * @param[in]       *S             points to an instance of the Q31 DCT4 structure.
-   * @param[in]       *pState        points to state buffer.
-   * @param[in,out]   *pInlineBuffer points to the in-place input and output buffer.
-   * @return none.
-   */
-
+   * @param[in]     S              points to an instance of the Q31 DCT4 structure.
+   * @param[in]     pState         points to state buffer.
+   * @param[in,out] pInlineBuffer  points to the in-place input and output buffer.
+   */
   void arm_dct4_q31(
   const arm_dct4_instance_q31 * S,
   q31_t * pState,
   q31_t * pInlineBuffer);
 
+
   /**
    * @brief Instance structure for the Q15 DCT4/IDCT4 function.
    */
-
   typedef struct
   {
-    uint16_t N;                         /**< length of the DCT4. */
-    uint16_t Nby2;                      /**< half of the length of the DCT4. */
-    q15_t normalize;                    /**< normalizing factor. */
-    q15_t *pTwiddle;                    /**< points to the twiddle factor table. */
-    q15_t *pCosFactor;                  /**< points to the cosFactor table. */
+    uint16_t N;                          /**< length of the DCT4. */
+    uint16_t Nby2;                       /**< half of the length of the DCT4. */
+    q15_t normalize;                     /**< normalizing factor. */
+    q15_t *pTwiddle;                     /**< points to the twiddle factor table. */
+    q15_t *pCosFactor;                   /**< points to the cosFactor table. */
     arm_rfft_instance_q15 *pRfft;        /**< points to the real FFT instance. */
     arm_cfft_radix4_instance_q15 *pCfft; /**< points to the complex FFT instance. */
   } arm_dct4_instance_q15;
 
+
   /**
    * @brief  Initialization function for the Q15 DCT4/IDCT4.
-   * @param[in,out] *S         points to an instance of Q15 DCT4/IDCT4 structure.
-   * @param[in]     *S_RFFT    points to an instance of Q15 RFFT/RIFFT structure.
-   * @param[in]     *S_CFFT    points to an instance of Q15 CFFT/CIFFT structure.
+   * @param[in,out] S          points to an instance of Q15 DCT4/IDCT4 structure.
+   * @param[in]     S_RFFT     points to an instance of Q15 RFFT/RIFFT structure.
+   * @param[in]     S_CFFT     points to an instance of Q15 CFFT/CIFFT structure.
    * @param[in]     N          length of the DCT4.
    * @param[in]     Nby2       half of the length of the DCT4.
    * @param[in]     normalize  normalizing factor.
-   * @return		arm_status function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_ARGUMENT_ERROR if <code>N</code> is not a supported transform length.
-   */
-
+   * @return      arm_status function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_ARGUMENT_ERROR if <code>N</code> is not a supported transform length.
+   */
   arm_status arm_dct4_init_q15(
   arm_dct4_instance_q15 * S,
   arm_rfft_instance_q15 * S_RFFT,
@@ -2495,164 +2454,153 @@
   uint16_t Nby2,
   q15_t normalize);
 
+
   /**
    * @brief Processing function for the Q15 DCT4/IDCT4.
-   * @param[in]       *S             points to an instance of the Q15 DCT4 structure.
-   * @param[in]       *pState        points to state buffer.
-   * @param[in,out]   *pInlineBuffer points to the in-place input and output buffer.
-   * @return none.
-   */
-
+   * @param[in]     S              points to an instance of the Q15 DCT4 structure.
+   * @param[in]     pState         points to state buffer.
+   * @param[in,out] pInlineBuffer  points to the in-place input and output buffer.
+   */
   void arm_dct4_q15(
   const arm_dct4_instance_q15 * S,
   q15_t * pState,
   q15_t * pInlineBuffer);
 
+
   /**
    * @brief Floating-point vector addition.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_add_f32(
   float32_t * pSrcA,
   float32_t * pSrcB,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q7 vector addition.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_add_q7(
   q7_t * pSrcA,
   q7_t * pSrcB,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q15 vector addition.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_add_q15(
   q15_t * pSrcA,
   q15_t * pSrcB,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q31 vector addition.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_add_q31(
   q31_t * pSrcA,
   q31_t * pSrcB,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Floating-point vector subtraction.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_sub_f32(
   float32_t * pSrcA,
   float32_t * pSrcB,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q7 vector subtraction.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_sub_q7(
   q7_t * pSrcA,
   q7_t * pSrcB,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q15 vector subtraction.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_sub_q15(
   q15_t * pSrcA,
   q15_t * pSrcB,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q31 vector subtraction.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_sub_q31(
   q31_t * pSrcA,
   q31_t * pSrcB,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Multiplies a floating-point vector by a scalar.
-   * @param[in]       *pSrc points to the input vector
-   * @param[in]       scale scale factor to be applied
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[in]  scale      scale factor to be applied
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_scale_f32(
   float32_t * pSrc,
   float32_t scale,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Multiplies a Q7 vector by a scalar.
-   * @param[in]       *pSrc points to the input vector
-   * @param[in]       scaleFract fractional portion of the scale value
-   * @param[in]       shift number of bits to shift the result by
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the input vector
+   * @param[in]  scaleFract  fractional portion of the scale value
+   * @param[in]  shift       number of bits to shift the result by
+   * @param[out] pDst        points to the output vector
+   * @param[in]  blockSize   number of samples in the vector
+   */
   void arm_scale_q7(
   q7_t * pSrc,
   q7_t scaleFract,
@@ -2660,16 +2608,15 @@
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Multiplies a Q15 vector by a scalar.
-   * @param[in]       *pSrc points to the input vector
-   * @param[in]       scaleFract fractional portion of the scale value
-   * @param[in]       shift number of bits to shift the result by
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the input vector
+   * @param[in]  scaleFract  fractional portion of the scale value
+   * @param[in]  shift       number of bits to shift the result by
+   * @param[out] pDst        points to the output vector
+   * @param[in]  blockSize   number of samples in the vector
+   */
   void arm_scale_q15(
   q15_t * pSrc,
   q15_t scaleFract,
@@ -2677,16 +2624,15 @@
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Multiplies a Q31 vector by a scalar.
-   * @param[in]       *pSrc points to the input vector
-   * @param[in]       scaleFract fractional portion of the scale value
-   * @param[in]       shift number of bits to shift the result by
-   * @param[out]      *pDst points to the output vector
-   * @param[in]       blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the input vector
+   * @param[in]  scaleFract  fractional portion of the scale value
+   * @param[in]  shift       number of bits to shift the result by
+   * @param[out] pDst        points to the output vector
+   * @param[in]  blockSize   number of samples in the vector
+   */
   void arm_scale_q31(
   q31_t * pSrc,
   q31_t scaleFract,
@@ -2694,379 +2640,361 @@
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q7 vector absolute value.
-   * @param[in]       *pSrc points to the input buffer
-   * @param[out]      *pDst points to the output buffer
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input buffer
+   * @param[out] pDst       points to the output buffer
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_abs_q7(
   q7_t * pSrc,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Floating-point vector absolute value.
-   * @param[in]       *pSrc points to the input buffer
-   * @param[out]      *pDst points to the output buffer
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input buffer
+   * @param[out] pDst       points to the output buffer
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_abs_f32(
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q15 vector absolute value.
-   * @param[in]       *pSrc points to the input buffer
-   * @param[out]      *pDst points to the output buffer
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input buffer
+   * @param[out] pDst       points to the output buffer
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_abs_q15(
   q15_t * pSrc,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Q31 vector absolute value.
-   * @param[in]       *pSrc points to the input buffer
-   * @param[out]      *pDst points to the output buffer
-   * @param[in]       blockSize number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input buffer
+   * @param[out] pDst       points to the output buffer
+   * @param[in]  blockSize  number of samples in each vector
+   */
   void arm_abs_q31(
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Dot product of floating-point vectors.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[in]       blockSize number of samples in each vector
-   * @param[out]      *result output result returned here
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[in]  blockSize  number of samples in each vector
+   * @param[out] result     output result returned here
+   */
   void arm_dot_prod_f32(
   float32_t * pSrcA,
   float32_t * pSrcB,
   uint32_t blockSize,
   float32_t * result);
 
+
   /**
    * @brief Dot product of Q7 vectors.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[in]       blockSize number of samples in each vector
-   * @param[out]      *result output result returned here
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[in]  blockSize  number of samples in each vector
+   * @param[out] result     output result returned here
+   */
   void arm_dot_prod_q7(
   q7_t * pSrcA,
   q7_t * pSrcB,
   uint32_t blockSize,
   q31_t * result);
 
+
   /**
    * @brief Dot product of Q15 vectors.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[in]       blockSize number of samples in each vector
-   * @param[out]      *result output result returned here
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[in]  blockSize  number of samples in each vector
+   * @param[out] result     output result returned here
+   */
   void arm_dot_prod_q15(
   q15_t * pSrcA,
   q15_t * pSrcB,
   uint32_t blockSize,
   q63_t * result);
 
+
   /**
    * @brief Dot product of Q31 vectors.
-   * @param[in]       *pSrcA points to the first input vector
-   * @param[in]       *pSrcB points to the second input vector
-   * @param[in]       blockSize number of samples in each vector
-   * @param[out]      *result output result returned here
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input vector
+   * @param[in]  pSrcB      points to the second input vector
+   * @param[in]  blockSize  number of samples in each vector
+   * @param[out] result     output result returned here
+   */
   void arm_dot_prod_q31(
   q31_t * pSrcA,
   q31_t * pSrcB,
   uint32_t blockSize,
   q63_t * result);
 
+
   /**
    * @brief  Shifts the elements of a Q7 vector a specified number of bits.
-   * @param[in]  *pSrc points to the input vector
-   * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[in]  shiftBits  number of bits to shift.  A positive value shifts left; a negative value shifts right.
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_shift_q7(
   q7_t * pSrc,
   int8_t shiftBits,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Shifts the elements of a Q15 vector a specified number of bits.
-   * @param[in]  *pSrc points to the input vector
-   * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[in]  shiftBits  number of bits to shift.  A positive value shifts left; a negative value shifts right.
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_shift_q15(
   q15_t * pSrc,
   int8_t shiftBits,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Shifts the elements of a Q31 vector a specified number of bits.
-   * @param[in]  *pSrc points to the input vector
-   * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[in]  shiftBits  number of bits to shift.  A positive value shifts left; a negative value shifts right.
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_shift_q31(
   q31_t * pSrc,
   int8_t shiftBits,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Adds a constant offset to a floating-point vector.
-   * @param[in]  *pSrc points to the input vector
-   * @param[in]  offset is the offset to be added
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[in]  offset     is the offset to be added
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_offset_f32(
   float32_t * pSrc,
   float32_t offset,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Adds a constant offset to a Q7 vector.
-   * @param[in]  *pSrc points to the input vector
-   * @param[in]  offset is the offset to be added
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[in]  offset     is the offset to be added
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_offset_q7(
   q7_t * pSrc,
   q7_t offset,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Adds a constant offset to a Q15 vector.
-   * @param[in]  *pSrc points to the input vector
-   * @param[in]  offset is the offset to be added
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[in]  offset     is the offset to be added
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_offset_q15(
   q15_t * pSrc,
   q15_t offset,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Adds a constant offset to a Q31 vector.
-   * @param[in]  *pSrc points to the input vector
-   * @param[in]  offset is the offset to be added
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[in]  offset     is the offset to be added
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_offset_q31(
   q31_t * pSrc,
   q31_t offset,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Negates the elements of a floating-point vector.
-   * @param[in]  *pSrc points to the input vector
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_negate_f32(
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Negates the elements of a Q7 vector.
-   * @param[in]  *pSrc points to the input vector
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_negate_q7(
   q7_t * pSrc,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Negates the elements of a Q15 vector.
-   * @param[in]  *pSrc points to the input vector
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_negate_q15(
   q15_t * pSrc,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Negates the elements of a Q31 vector.
-   * @param[in]  *pSrc points to the input vector
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  blockSize number of samples in the vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc       points to the input vector
+   * @param[out] pDst       points to the output vector
+   * @param[in]  blockSize  number of samples in the vector
+   */
   void arm_negate_q31(
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t blockSize);
+
+
   /**
    * @brief  Copies the elements of a floating-point vector.
-   * @param[in]  *pSrc input pointer
-   * @param[out]  *pDst output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  pSrc       input pointer
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_copy_f32(
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Copies the elements of a Q7 vector.
-   * @param[in]  *pSrc input pointer
-   * @param[out]  *pDst output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  pSrc       input pointer
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_copy_q7(
   q7_t * pSrc,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Copies the elements of a Q15 vector.
-   * @param[in]  *pSrc input pointer
-   * @param[out]  *pDst output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  pSrc       input pointer
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_copy_q15(
   q15_t * pSrc,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Copies the elements of a Q31 vector.
-   * @param[in]  *pSrc input pointer
-   * @param[out]  *pDst output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  pSrc       input pointer
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_copy_q31(
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t blockSize);
+
+
   /**
    * @brief  Fills a constant value into a floating-point vector.
-   * @param[in]  value input value to be filled
-   * @param[out]  *pDst output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  value      input value to be filled
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_fill_f32(
   float32_t value,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Fills a constant value into a Q7 vector.
-   * @param[in]  value input value to be filled
-   * @param[out]  *pDst output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  value      input value to be filled
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_fill_q7(
   q7_t value,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Fills a constant value into a Q15 vector.
-   * @param[in]  value input value to be filled
-   * @param[out]  *pDst output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  value      input value to be filled
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_fill_q15(
   q15_t value,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Fills a constant value into a Q31 vector.
-   * @param[in]  value input value to be filled
-   * @param[out]  *pDst output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  value      input value to be filled
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_fill_q31(
   q31_t value,
   q31_t * pDst,
   uint32_t blockSize);
 
+
 /**
  * @brief Convolution of floating-point sequences.
- * @param[in] *pSrcA points to the first input sequence.
- * @param[in] srcALen length of the first input sequence.
- * @param[in] *pSrcB points to the second input sequence.
- * @param[in] srcBLen length of the second input sequence.
- * @param[out] *pDst points to the location where the output result is written.  Length srcALen+srcBLen-1.
- * @return none.
+ * @param[in]  pSrcA    points to the first input sequence.
+ * @param[in]  srcALen  length of the first input sequence.
+ * @param[in]  pSrcB    points to the second input sequence.
+ * @param[in]  srcBLen  length of the second input sequence.
+ * @param[out] pDst     points to the location where the output result is written.  Length srcALen+srcBLen-1.
  */
-
   void arm_conv_f32(
   float32_t * pSrcA,
   uint32_t srcALen,
@@ -3077,17 +3005,14 @@
 
   /**
    * @brief Convolution of Q15 sequences.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
-   * @param[in]  *pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
-   * @param[in]  *pScratch2 points to scratch buffer of size min(srcALen, srcBLen).
-   * @return none.
-   */
-
-
+   * @param[in]  pSrcA      points to the first input sequence.
+   * @param[in]  srcALen    length of the first input sequence.
+   * @param[in]  pSrcB      points to the second input sequence.
+   * @param[in]  srcBLen    length of the second input sequence.
+   * @param[out] pDst       points to the block of output data  Length srcALen+srcBLen-1.
+   * @param[in]  pScratch1  points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
+   * @param[in]  pScratch2  points to scratch buffer of size min(srcALen, srcBLen).
+   */
   void arm_conv_opt_q15(
   q15_t * pSrcA,
   uint32_t srcALen,
@@ -3100,14 +3025,12 @@
 
 /**
  * @brief Convolution of Q15 sequences.
- * @param[in] *pSrcA points to the first input sequence.
- * @param[in] srcALen length of the first input sequence.
- * @param[in] *pSrcB points to the second input sequence.
- * @param[in] srcBLen length of the second input sequence.
- * @param[out] *pDst points to the location where the output result is written.  Length srcALen+srcBLen-1.
- * @return none.
+ * @param[in]  pSrcA    points to the first input sequence.
+ * @param[in]  srcALen  length of the first input sequence.
+ * @param[in]  pSrcB    points to the second input sequence.
+ * @param[in]  srcBLen  length of the second input sequence.
+ * @param[out] pDst     points to the location where the output result is written.  Length srcALen+srcBLen-1.
  */
-
   void arm_conv_q15(
   q15_t * pSrcA,
   uint32_t srcALen,
@@ -3115,35 +3038,33 @@
   uint32_t srcBLen,
   q15_t * pDst);
 
-  /**
-   * @brief Convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
-   * @return none.
-   */
-
-  void arm_conv_fast_q15(
-			  q15_t * pSrcA,
-			 uint32_t srcALen,
-			  q15_t * pSrcB,
-			 uint32_t srcBLen,
-			 q15_t * pDst);
 
   /**
    * @brief Convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
-   * @param[in]  *pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
-   * @param[in]  *pScratch2 points to scratch buffer of size min(srcALen, srcBLen).
-   * @return none.
-   */
-
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length srcALen+srcBLen-1.
+   */
+  void arm_conv_fast_q15(
+          q15_t * pSrcA,
+          uint32_t srcALen,
+          q15_t * pSrcB,
+          uint32_t srcBLen,
+          q15_t * pDst);
+
+
+  /**
+   * @brief Convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
+   * @param[in]  pSrcA      points to the first input sequence.
+   * @param[in]  srcALen    length of the first input sequence.
+   * @param[in]  pSrcB      points to the second input sequence.
+   * @param[in]  srcBLen    length of the second input sequence.
+   * @param[out] pDst       points to the block of output data  Length srcALen+srcBLen-1.
+   * @param[in]  pScratch1  points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
+   * @param[in]  pScratch2  points to scratch buffer of size min(srcALen, srcBLen).
+   */
   void arm_conv_fast_opt_q15(
   q15_t * pSrcA,
   uint32_t srcALen,
@@ -3154,17 +3075,14 @@
   q15_t * pScratch2);
 
 
-
   /**
    * @brief Convolution of Q31 sequences.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
-   * @return none.
-   */
-
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length srcALen+srcBLen-1.
+   */
   void arm_conv_q31(
   q31_t * pSrcA,
   uint32_t srcALen,
@@ -3172,16 +3090,15 @@
   uint32_t srcBLen,
   q31_t * pDst);
 
+
   /**
    * @brief Convolution of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
-   * @return none.
-   */
-
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length srcALen+srcBLen-1.
+   */
   void arm_conv_fast_q31(
   q31_t * pSrcA,
   uint32_t srcALen,
@@ -3192,16 +3109,14 @@
 
     /**
    * @brief Convolution of Q7 sequences.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
-   * @param[in]  *pScratch1 points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
-   * @param[in]  *pScratch2 points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input sequence.
+   * @param[in]  srcALen    length of the first input sequence.
+   * @param[in]  pSrcB      points to the second input sequence.
+   * @param[in]  srcBLen    length of the second input sequence.
+   * @param[out] pDst       points to the block of output data  Length srcALen+srcBLen-1.
+   * @param[in]  pScratch1  points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
+   * @param[in]  pScratch2  points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
+   */
   void arm_conv_opt_q7(
   q7_t * pSrcA,
   uint32_t srcALen,
@@ -3212,17 +3127,14 @@
   q15_t * pScratch2);
 
 
-
   /**
    * @brief Convolution of Q7 sequences.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length srcALen+srcBLen-1.
-   * @return none.
-   */
-
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length srcALen+srcBLen-1.
+   */
   void arm_conv_q7(
   q7_t * pSrcA,
   uint32_t srcALen,
@@ -3233,16 +3145,15 @@
 
   /**
    * @brief Partial convolution of floating-point sequences.
-   * @param[in]       *pSrcA points to the first input sequence.
-   * @param[in]       srcALen length of the first input sequence.
-   * @param[in]       *pSrcB points to the second input sequence.
-   * @param[in]       srcBLen length of the second input sequence.
-   * @param[out]      *pDst points to the block of output data
-   * @param[in]       firstIndex is the first output sample to start with.
-   * @param[in]       numPoints is the number of output points to be computed.
+   * @param[in]  pSrcA       points to the first input sequence.
+   * @param[in]  srcALen     length of the first input sequence.
+   * @param[in]  pSrcB       points to the second input sequence.
+   * @param[in]  srcBLen     length of the second input sequence.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  firstIndex  is the first output sample to start with.
+   * @param[in]  numPoints   is the number of output points to be computed.
    * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
    */
-
   arm_status arm_conv_partial_f32(
   float32_t * pSrcA,
   uint32_t srcALen,
@@ -3252,20 +3163,20 @@
   uint32_t firstIndex,
   uint32_t numPoints);
 
-    /**
+
+  /**
    * @brief Partial convolution of Q15 sequences.
-   * @param[in]       *pSrcA points to the first input sequence.
-   * @param[in]       srcALen length of the first input sequence.
-   * @param[in]       *pSrcB points to the second input sequence.
-   * @param[in]       srcBLen length of the second input sequence.
-   * @param[out]      *pDst points to the block of output data
-   * @param[in]       firstIndex is the first output sample to start with.
-   * @param[in]       numPoints is the number of output points to be computed.
-   * @param[in]       * pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
-   * @param[in]       * pScratch2 points to scratch buffer of size min(srcALen, srcBLen).
+   * @param[in]  pSrcA       points to the first input sequence.
+   * @param[in]  srcALen     length of the first input sequence.
+   * @param[in]  pSrcB       points to the second input sequence.
+   * @param[in]  srcBLen     length of the second input sequence.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  firstIndex  is the first output sample to start with.
+   * @param[in]  numPoints   is the number of output points to be computed.
+   * @param[in]  pScratch1   points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
+   * @param[in]  pScratch2   points to scratch buffer of size min(srcALen, srcBLen).
    * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
    */
-
   arm_status arm_conv_partial_opt_q15(
   q15_t * pSrcA,
   uint32_t srcALen,
@@ -3278,18 +3189,17 @@
   q15_t * pScratch2);
 
 
-/**
+  /**
    * @brief Partial convolution of Q15 sequences.
-   * @param[in]       *pSrcA points to the first input sequence.
-   * @param[in]       srcALen length of the first input sequence.
-   * @param[in]       *pSrcB points to the second input sequence.
-   * @param[in]       srcBLen length of the second input sequence.
-   * @param[out]      *pDst points to the block of output data
-   * @param[in]       firstIndex is the first output sample to start with.
-   * @param[in]       numPoints is the number of output points to be computed.
+   * @param[in]  pSrcA       points to the first input sequence.
+   * @param[in]  srcALen     length of the first input sequence.
+   * @param[in]  pSrcB       points to the second input sequence.
+   * @param[in]  srcBLen     length of the second input sequence.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  firstIndex  is the first output sample to start with.
+   * @param[in]  numPoints   is the number of output points to be computed.
    * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
    */
-
   arm_status arm_conv_partial_q15(
   q15_t * pSrcA,
   uint32_t srcALen,
@@ -3299,42 +3209,41 @@
   uint32_t firstIndex,
   uint32_t numPoints);
 
+
   /**
    * @brief Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
-   * @param[in]       *pSrcA points to the first input sequence.
-   * @param[in]       srcALen length of the first input sequence.
-   * @param[in]       *pSrcB points to the second input sequence.
-   * @param[in]       srcBLen length of the second input sequence.
-   * @param[out]      *pDst points to the block of output data
-   * @param[in]       firstIndex is the first output sample to start with.
-   * @param[in]       numPoints is the number of output points to be computed.
+   * @param[in]  pSrcA       points to the first input sequence.
+   * @param[in]  srcALen     length of the first input sequence.
+   * @param[in]  pSrcB       points to the second input sequence.
+   * @param[in]  srcBLen     length of the second input sequence.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  firstIndex  is the first output sample to start with.
+   * @param[in]  numPoints   is the number of output points to be computed.
    * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
    */
-
   arm_status arm_conv_partial_fast_q15(
-				        q15_t * pSrcA,
-				       uint32_t srcALen,
-				        q15_t * pSrcB,
-				       uint32_t srcBLen,
-				       q15_t * pDst,
-				       uint32_t firstIndex,
-				       uint32_t numPoints);
+  q15_t * pSrcA,
+  uint32_t srcALen,
+  q15_t * pSrcB,
+  uint32_t srcBLen,
+  q15_t * pDst,
+  uint32_t firstIndex,
+  uint32_t numPoints);
 
 
   /**
    * @brief Partial convolution of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4
-   * @param[in]       *pSrcA points to the first input sequence.
-   * @param[in]       srcALen length of the first input sequence.
-   * @param[in]       *pSrcB points to the second input sequence.
-   * @param[in]       srcBLen length of the second input sequence.
-   * @param[out]      *pDst points to the block of output data
-   * @param[in]       firstIndex is the first output sample to start with.
-   * @param[in]       numPoints is the number of output points to be computed.
-   * @param[in]       * pScratch1 points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
-   * @param[in]       * pScratch2 points to scratch buffer of size min(srcALen, srcBLen).
+   * @param[in]  pSrcA       points to the first input sequence.
+   * @param[in]  srcALen     length of the first input sequence.
+   * @param[in]  pSrcB       points to the second input sequence.
+   * @param[in]  srcBLen     length of the second input sequence.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  firstIndex  is the first output sample to start with.
+   * @param[in]  numPoints   is the number of output points to be computed.
+   * @param[in]  pScratch1   points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
+   * @param[in]  pScratch2   points to scratch buffer of size min(srcALen, srcBLen).
    * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
    */
-
   arm_status arm_conv_partial_fast_opt_q15(
   q15_t * pSrcA,
   uint32_t srcALen,
@@ -3349,16 +3258,15 @@
 
   /**
    * @brief Partial convolution of Q31 sequences.
-   * @param[in]       *pSrcA points to the first input sequence.
-   * @param[in]       srcALen length of the first input sequence.
-   * @param[in]       *pSrcB points to the second input sequence.
-   * @param[in]       srcBLen length of the second input sequence.
-   * @param[out]      *pDst points to the block of output data
-   * @param[in]       firstIndex is the first output sample to start with.
-   * @param[in]       numPoints is the number of output points to be computed.
+   * @param[in]  pSrcA       points to the first input sequence.
+   * @param[in]  srcALen     length of the first input sequence.
+   * @param[in]  pSrcB       points to the second input sequence.
+   * @param[in]  srcBLen     length of the second input sequence.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  firstIndex  is the first output sample to start with.
+   * @param[in]  numPoints   is the number of output points to be computed.
    * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
    */
-
   arm_status arm_conv_partial_q31(
   q31_t * pSrcA,
   uint32_t srcALen,
@@ -3371,16 +3279,15 @@
 
   /**
    * @brief Partial convolution of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4
-   * @param[in]       *pSrcA points to the first input sequence.
-   * @param[in]       srcALen length of the first input sequence.
-   * @param[in]       *pSrcB points to the second input sequence.
-   * @param[in]       srcBLen length of the second input sequence.
-   * @param[out]      *pDst points to the block of output data
-   * @param[in]       firstIndex is the first output sample to start with.
-   * @param[in]       numPoints is the number of output points to be computed.
+   * @param[in]  pSrcA       points to the first input sequence.
+   * @param[in]  srcALen     length of the first input sequence.
+   * @param[in]  pSrcB       points to the second input sequence.
+   * @param[in]  srcBLen     length of the second input sequence.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  firstIndex  is the first output sample to start with.
+   * @param[in]  numPoints   is the number of output points to be computed.
    * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
    */
-
   arm_status arm_conv_partial_fast_q31(
   q31_t * pSrcA,
   uint32_t srcALen,
@@ -3393,18 +3300,17 @@
 
   /**
    * @brief Partial convolution of Q7 sequences
-   * @param[in]       *pSrcA points to the first input sequence.
-   * @param[in]       srcALen length of the first input sequence.
-   * @param[in]       *pSrcB points to the second input sequence.
-   * @param[in]       srcBLen length of the second input sequence.
-   * @param[out]      *pDst points to the block of output data
-   * @param[in]       firstIndex is the first output sample to start with.
-   * @param[in]       numPoints is the number of output points to be computed.
-   * @param[in]  *pScratch1 points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
-   * @param[in]  *pScratch2 points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
+   * @param[in]  pSrcA       points to the first input sequence.
+   * @param[in]  srcALen     length of the first input sequence.
+   * @param[in]  pSrcB       points to the second input sequence.
+   * @param[in]  srcBLen     length of the second input sequence.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  firstIndex  is the first output sample to start with.
+   * @param[in]  numPoints   is the number of output points to be computed.
+   * @param[in]  pScratch1   points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
+   * @param[in]  pScratch2   points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
    * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
    */
-
   arm_status arm_conv_partial_opt_q7(
   q7_t * pSrcA,
   uint32_t srcALen,
@@ -3419,16 +3325,15 @@
 
 /**
    * @brief Partial convolution of Q7 sequences.
-   * @param[in]       *pSrcA points to the first input sequence.
-   * @param[in]       srcALen length of the first input sequence.
-   * @param[in]       *pSrcB points to the second input sequence.
-   * @param[in]       srcBLen length of the second input sequence.
-   * @param[out]      *pDst points to the block of output data
-   * @param[in]       firstIndex is the first output sample to start with.
-   * @param[in]       numPoints is the number of output points to be computed.
+   * @param[in]  pSrcA       points to the first input sequence.
+   * @param[in]  srcALen     length of the first input sequence.
+   * @param[in]  pSrcB       points to the second input sequence.
+   * @param[in]  srcBLen     length of the second input sequence.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  firstIndex  is the first output sample to start with.
+   * @param[in]  numPoints   is the number of output points to be computed.
    * @return  Returns either ARM_MATH_SUCCESS if the function completed correctly or ARM_MATH_ARGUMENT_ERROR if the requested subset is not in the range [0 srcALen+srcBLen-2].
    */
-
   arm_status arm_conv_partial_q7(
   q7_t * pSrcA,
   uint32_t srcALen,
@@ -3439,56 +3344,47 @@
   uint32_t numPoints);
 
 
-
   /**
    * @brief Instance structure for the Q15 FIR decimator.
    */
-
   typedef struct
   {
-    uint8_t M;                      /**< decimation factor. */
-    uint16_t numTaps;               /**< number of coefficients in the filter. */
-    q15_t *pCoeffs;                  /**< points to the coefficient array. The array is of length numTaps.*/
-    q15_t *pState;                   /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
+    uint8_t M;                  /**< decimation factor. */
+    uint16_t numTaps;           /**< number of coefficients in the filter. */
+    q15_t *pCoeffs;             /**< points to the coefficient array. The array is of length numTaps.*/
+    q15_t *pState;              /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
   } arm_fir_decimate_instance_q15;
 
   /**
    * @brief Instance structure for the Q31 FIR decimator.
    */
-
   typedef struct
   {
     uint8_t M;                  /**< decimation factor. */
     uint16_t numTaps;           /**< number of coefficients in the filter. */
-    q31_t *pCoeffs;              /**< points to the coefficient array. The array is of length numTaps.*/
-    q31_t *pState;               /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
-
+    q31_t *pCoeffs;             /**< points to the coefficient array. The array is of length numTaps.*/
+    q31_t *pState;              /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
   } arm_fir_decimate_instance_q31;
 
   /**
    * @brief Instance structure for the floating-point FIR decimator.
    */
-
   typedef struct
   {
-    uint8_t M;                          /**< decimation factor. */
-    uint16_t numTaps;                   /**< number of coefficients in the filter. */
-    float32_t *pCoeffs;                  /**< points to the coefficient array. The array is of length numTaps.*/
-    float32_t *pState;                   /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
-
+    uint8_t M;                  /**< decimation factor. */
+    uint16_t numTaps;           /**< number of coefficients in the filter. */
+    float32_t *pCoeffs;         /**< points to the coefficient array. The array is of length numTaps.*/
+    float32_t *pState;          /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
   } arm_fir_decimate_instance_f32;
 
 
-
   /**
    * @brief Processing function for the floating-point FIR decimator.
-   * @param[in] *S points to an instance of the floating-point FIR decimator structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data
-   * @param[in] blockSize number of input samples to process per call.
-   * @return none
-   */
-
+   * @param[in]  S          points to an instance of the floating-point FIR decimator structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of input samples to process per call.
+   */
   void arm_fir_decimate_f32(
   const arm_fir_decimate_instance_f32 * S,
   float32_t * pSrc,
@@ -3498,16 +3394,15 @@
 
   /**
    * @brief  Initialization function for the floating-point FIR decimator.
-   * @param[in,out] *S points to an instance of the floating-point FIR decimator structure.
-   * @param[in] numTaps  number of coefficients in the filter.
-   * @param[in] M  decimation factor.
-   * @param[in] *pCoeffs points to the filter coefficients.
-   * @param[in] *pState points to the state buffer.
-   * @param[in] blockSize number of input samples to process per call.
+   * @param[in,out] S          points to an instance of the floating-point FIR decimator structure.
+   * @param[in]     numTaps    number of coefficients in the filter.
+   * @param[in]     M          decimation factor.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of input samples to process per call.
    * @return    The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
    * <code>blockSize</code> is not a multiple of <code>M</code>.
    */
-
   arm_status arm_fir_decimate_init_f32(
   arm_fir_decimate_instance_f32 * S,
   uint16_t numTaps,
@@ -3516,30 +3411,28 @@
   float32_t * pState,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the Q15 FIR decimator.
-   * @param[in] *S points to an instance of the Q15 FIR decimator structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data
-   * @param[in] blockSize number of input samples to process per call.
-   * @return none
-   */
-
+   * @param[in]  S          points to an instance of the Q15 FIR decimator structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of input samples to process per call.
+   */
   void arm_fir_decimate_q15(
   const arm_fir_decimate_instance_q15 * S,
   q15_t * pSrc,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the Q15 FIR decimator (fast variant) for Cortex-M3 and Cortex-M4.
-   * @param[in] *S points to an instance of the Q15 FIR decimator structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data
-   * @param[in] blockSize number of input samples to process per call.
-   * @return none
-   */
-
+   * @param[in]  S          points to an instance of the Q15 FIR decimator structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of input samples to process per call.
+   */
   void arm_fir_decimate_fast_q15(
   const arm_fir_decimate_instance_q15 * S,
   q15_t * pSrc,
@@ -3547,19 +3440,17 @@
   uint32_t blockSize);
 
 
-
   /**
    * @brief  Initialization function for the Q15 FIR decimator.
-   * @param[in,out] *S points to an instance of the Q15 FIR decimator structure.
-   * @param[in] numTaps  number of coefficients in the filter.
-   * @param[in] M  decimation factor.
-   * @param[in] *pCoeffs points to the filter coefficients.
-   * @param[in] *pState points to the state buffer.
-   * @param[in] blockSize number of input samples to process per call.
+   * @param[in,out] S          points to an instance of the Q15 FIR decimator structure.
+   * @param[in]     numTaps    number of coefficients in the filter.
+   * @param[in]     M          decimation factor.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of input samples to process per call.
    * @return    The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
    * <code>blockSize</code> is not a multiple of <code>M</code>.
    */
-
   arm_status arm_fir_decimate_init_q15(
   arm_fir_decimate_instance_q15 * S,
   uint16_t numTaps,
@@ -3568,15 +3459,14 @@
   q15_t * pState,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the Q31 FIR decimator.
-   * @param[in] *S points to an instance of the Q31 FIR decimator structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data
+   * @param[in]  S     points to an instance of the Q31 FIR decimator structure.
+   * @param[in]  pSrc  points to the block of input data.
+   * @param[out] pDst  points to the block of output data
    * @param[in] blockSize number of input samples to process per call.
-   * @return none
-   */
-
+   */
   void arm_fir_decimate_q31(
   const arm_fir_decimate_instance_q31 * S,
   q31_t * pSrc,
@@ -3585,13 +3475,11 @@
 
   /**
    * @brief Processing function for the Q31 FIR decimator (fast variant) for Cortex-M3 and Cortex-M4.
-   * @param[in] *S points to an instance of the Q31 FIR decimator structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data
-   * @param[in] blockSize number of input samples to process per call.
-   * @return none
-   */
-
+   * @param[in]  S          points to an instance of the Q31 FIR decimator structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of input samples to process per call.
+   */
   void arm_fir_decimate_fast_q31(
   arm_fir_decimate_instance_q31 * S,
   q31_t * pSrc,
@@ -3601,16 +3489,15 @@
 
   /**
    * @brief  Initialization function for the Q31 FIR decimator.
-   * @param[in,out] *S points to an instance of the Q31 FIR decimator structure.
-   * @param[in] numTaps  number of coefficients in the filter.
-   * @param[in] M  decimation factor.
-   * @param[in] *pCoeffs points to the filter coefficients.
-   * @param[in] *pState points to the state buffer.
-   * @param[in] blockSize number of input samples to process per call.
+   * @param[in,out] S          points to an instance of the Q31 FIR decimator structure.
+   * @param[in]     numTaps    number of coefficients in the filter.
+   * @param[in]     M          decimation factor.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of input samples to process per call.
    * @return    The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
    * <code>blockSize</code> is not a multiple of <code>M</code>.
    */
-
   arm_status arm_fir_decimate_init_q31(
   arm_fir_decimate_instance_q31 * S,
   uint16_t numTaps,
@@ -3620,11 +3507,9 @@
   uint32_t blockSize);
 
 
-
   /**
    * @brief Instance structure for the Q15 FIR interpolator.
    */
-
   typedef struct
   {
     uint8_t L;                      /**< upsample factor. */
@@ -3636,37 +3521,33 @@
   /**
    * @brief Instance structure for the Q31 FIR interpolator.
    */
-
   typedef struct
   {
     uint8_t L;                      /**< upsample factor. */
     uint16_t phaseLength;           /**< length of each polyphase filter component. */
-    q31_t *pCoeffs;                  /**< points to the coefficient array. The array is of length L*phaseLength. */
-    q31_t *pState;                   /**< points to the state variable array. The array is of length blockSize+phaseLength-1. */
+    q31_t *pCoeffs;                 /**< points to the coefficient array. The array is of length L*phaseLength. */
+    q31_t *pState;                  /**< points to the state variable array. The array is of length blockSize+phaseLength-1. */
   } arm_fir_interpolate_instance_q31;
 
   /**
    * @brief Instance structure for the floating-point FIR interpolator.
    */
-
   typedef struct
   {
     uint8_t L;                     /**< upsample factor. */
     uint16_t phaseLength;          /**< length of each polyphase filter component. */
-    float32_t *pCoeffs;             /**< points to the coefficient array. The array is of length L*phaseLength. */
-    float32_t *pState;              /**< points to the state variable array. The array is of length phaseLength+numTaps-1. */
+    float32_t *pCoeffs;            /**< points to the coefficient array. The array is of length L*phaseLength. */
+    float32_t *pState;             /**< points to the state variable array. The array is of length phaseLength+numTaps-1. */
   } arm_fir_interpolate_instance_f32;
 
 
   /**
    * @brief Processing function for the Q15 FIR interpolator.
-   * @param[in] *S        points to an instance of the Q15 FIR interpolator structure.
-   * @param[in] *pSrc     points to the block of input data.
-   * @param[out] *pDst    points to the block of output data.
-   * @param[in] blockSize number of input samples to process per call.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the Q15 FIR interpolator structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of input samples to process per call.
+   */
   void arm_fir_interpolate_q15(
   const arm_fir_interpolate_instance_q15 * S,
   q15_t * pSrc,
@@ -3676,16 +3557,15 @@
 
   /**
    * @brief  Initialization function for the Q15 FIR interpolator.
-   * @param[in,out] *S        points to an instance of the Q15 FIR interpolator structure.
-   * @param[in]     L         upsample factor.
-   * @param[in]     numTaps   number of filter coefficients in the filter.
-   * @param[in]     *pCoeffs  points to the filter coefficient buffer.
-   * @param[in]     *pState   points to the state buffer.
-   * @param[in]     blockSize number of input samples to process per call.
+   * @param[in,out] S          points to an instance of the Q15 FIR interpolator structure.
+   * @param[in]     L          upsample factor.
+   * @param[in]     numTaps    number of filter coefficients in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficient buffer.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of input samples to process per call.
    * @return        The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
    * the filter length <code>numTaps</code> is not a multiple of the interpolation factor <code>L</code>.
    */
-
   arm_status arm_fir_interpolate_init_q15(
   arm_fir_interpolate_instance_q15 * S,
   uint8_t L,
@@ -3694,33 +3574,32 @@
   q15_t * pState,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the Q31 FIR interpolator.
-   * @param[in] *S        points to an instance of the Q15 FIR interpolator structure.
-   * @param[in] *pSrc     points to the block of input data.
-   * @param[out] *pDst    points to the block of output data.
-   * @param[in] blockSize number of input samples to process per call.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the Q15 FIR interpolator structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of input samples to process per call.
+   */
   void arm_fir_interpolate_q31(
   const arm_fir_interpolate_instance_q31 * S,
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the Q31 FIR interpolator.
-   * @param[in,out] *S        points to an instance of the Q31 FIR interpolator structure.
-   * @param[in]     L         upsample factor.
-   * @param[in]     numTaps   number of filter coefficients in the filter.
-   * @param[in]     *pCoeffs  points to the filter coefficient buffer.
-   * @param[in]     *pState   points to the state buffer.
-   * @param[in]     blockSize number of input samples to process per call.
+   * @param[in,out] S          points to an instance of the Q31 FIR interpolator structure.
+   * @param[in]     L          upsample factor.
+   * @param[in]     numTaps    number of filter coefficients in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficient buffer.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of input samples to process per call.
    * @return        The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
    * the filter length <code>numTaps</code> is not a multiple of the interpolation factor <code>L</code>.
    */
-
   arm_status arm_fir_interpolate_init_q31(
   arm_fir_interpolate_instance_q31 * S,
   uint8_t L,
@@ -3732,31 +3611,29 @@
 
   /**
    * @brief Processing function for the floating-point FIR interpolator.
-   * @param[in] *S        points to an instance of the floating-point FIR interpolator structure.
-   * @param[in] *pSrc     points to the block of input data.
-   * @param[out] *pDst    points to the block of output data.
-   * @param[in] blockSize number of input samples to process per call.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the floating-point FIR interpolator structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of input samples to process per call.
+   */
   void arm_fir_interpolate_f32(
   const arm_fir_interpolate_instance_f32 * S,
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the floating-point FIR interpolator.
-   * @param[in,out] *S        points to an instance of the floating-point FIR interpolator structure.
-   * @param[in]     L         upsample factor.
-   * @param[in]     numTaps   number of filter coefficients in the filter.
-   * @param[in]     *pCoeffs  points to the filter coefficient buffer.
-   * @param[in]     *pState   points to the state buffer.
-   * @param[in]     blockSize number of input samples to process per call.
+   * @param[in,out] S          points to an instance of the floating-point FIR interpolator structure.
+   * @param[in]     L          upsample factor.
+   * @param[in]     numTaps    number of filter coefficients in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficient buffer.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     blockSize  number of input samples to process per call.
    * @return        The function returns ARM_MATH_SUCCESS if initialization is successful or ARM_MATH_LENGTH_ERROR if
    * the filter length <code>numTaps</code> is not a multiple of the interpolation factor <code>L</code>.
    */
-
   arm_status arm_fir_interpolate_init_f32(
   arm_fir_interpolate_instance_f32 * S,
   uint8_t L,
@@ -3765,28 +3642,25 @@
   float32_t * pState,
   uint32_t blockSize);
 
+
   /**
    * @brief Instance structure for the high precision Q31 Biquad cascade filter.
    */
-
   typedef struct
   {
     uint8_t numStages;       /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
     q63_t *pState;           /**< points to the array of state coefficients.  The array is of length 4*numStages. */
     q31_t *pCoeffs;          /**< points to the array of coefficients.  The array is of length 5*numStages. */
     uint8_t postShift;       /**< additional shift, in bits, applied to each output sample. */
-
   } arm_biquad_cas_df1_32x64_ins_q31;
 
 
   /**
-   * @param[in]  *S        points to an instance of the high precision Q31 Biquad cascade filter structure.
-   * @param[in]  *pSrc     points to the block of input data.
-   * @param[out] *pDst     points to the block of output data
-   * @param[in]  blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the high precision Q31 Biquad cascade filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_biquad_cas_df1_32x64_q31(
   const arm_biquad_cas_df1_32x64_ins_q31 * S,
   q31_t * pSrc,
@@ -3795,14 +3669,12 @@
 
 
   /**
-   * @param[in,out] *S           points to an instance of the high precision Q31 Biquad cascade filter structure.
-   * @param[in]     numStages    number of 2nd order stages in the filter.
-   * @param[in]     *pCoeffs     points to the filter coefficients.
-   * @param[in]     *pState      points to the state buffer.
-   * @param[in]     postShift    shift to be applied to the output. Varies according to the coefficients format
-   * @return        none
-   */
-
+   * @param[in,out] S          points to an instance of the high precision Q31 Biquad cascade filter structure.
+   * @param[in]     numStages  number of 2nd order stages in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     postShift  shift to be applied to the output. Varies according to the coefficients format
+   */
   void arm_biquad_cas_df1_32x64_init_q31(
   arm_biquad_cas_df1_32x64_ins_q31 * S,
   uint8_t numStages,
@@ -3811,11 +3683,9 @@
   uint8_t postShift);
 
 
-
   /**
    * @brief Instance structure for the floating-point transposed direct form II Biquad cascade filter.
    */
-
   typedef struct
   {
     uint8_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
@@ -3823,12 +3693,9 @@
     float32_t *pCoeffs;        /**< points to the array of coefficients.  The array is of length 5*numStages. */
   } arm_biquad_cascade_df2T_instance_f32;
 
-
-
   /**
    * @brief Instance structure for the floating-point transposed direct form II Biquad cascade filter.
    */
-
   typedef struct
   {
     uint8_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
@@ -3836,12 +3703,9 @@
     float32_t *pCoeffs;        /**< points to the array of coefficients.  The array is of length 5*numStages. */
   } arm_biquad_cascade_stereo_df2T_instance_f32;
 
-
-
   /**
    * @brief Instance structure for the floating-point transposed direct form II Biquad cascade filter.
    */
-
   typedef struct
   {
     uint8_t numStages;         /**< number of 2nd order stages in the filter.  Overall order is 2*numStages. */
@@ -3852,13 +3716,11 @@
 
   /**
    * @brief Processing function for the floating-point transposed direct form II Biquad cascade filter.
-   * @param[in]  *S        points to an instance of the filter data structure.
-   * @param[in]  *pSrc     points to the block of input data.
-   * @param[out] *pDst     points to the block of output data
-   * @param[in]  blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the filter data structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_biquad_cascade_df2T_f32(
   const arm_biquad_cascade_df2T_instance_f32 * S,
   float32_t * pSrc,
@@ -3868,28 +3730,25 @@
 
   /**
    * @brief Processing function for the floating-point transposed direct form II Biquad cascade filter. 2 channels
-   * @param[in]  *S        points to an instance of the filter data structure.
-   * @param[in]  *pSrc     points to the block of input data.
-   * @param[out] *pDst     points to the block of output data
-   * @param[in]  blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the filter data structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_biquad_cascade_stereo_df2T_f32(
   const arm_biquad_cascade_stereo_df2T_instance_f32 * S,
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the floating-point transposed direct form II Biquad cascade filter.
-   * @param[in]  *S        points to an instance of the filter data structure.
-   * @param[in]  *pSrc     points to the block of input data.
-   * @param[out] *pDst     points to the block of output data
-   * @param[in]  blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the filter data structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_biquad_cascade_df2T_f64(
   const arm_biquad_cascade_df2T_instance_f64 * S,
   float64_t * pSrc,
@@ -3899,13 +3758,11 @@
 
   /**
    * @brief  Initialization function for the floating-point transposed direct form II Biquad cascade filter.
-   * @param[in,out] *S           points to an instance of the filter data structure.
-   * @param[in]     numStages    number of 2nd order stages in the filter.
-   * @param[in]     *pCoeffs     points to the filter coefficients.
-   * @param[in]     *pState      points to the state buffer.
-   * @return        none
-   */
-
+   * @param[in,out] S          points to an instance of the filter data structure.
+   * @param[in]     numStages  number of 2nd order stages in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   */
   void arm_biquad_cascade_df2T_init_f32(
   arm_biquad_cascade_df2T_instance_f32 * S,
   uint8_t numStages,
@@ -3915,13 +3772,11 @@
 
   /**
    * @brief  Initialization function for the floating-point transposed direct form II Biquad cascade filter.
-   * @param[in,out] *S           points to an instance of the filter data structure.
-   * @param[in]     numStages    number of 2nd order stages in the filter.
-   * @param[in]     *pCoeffs     points to the filter coefficients.
-   * @param[in]     *pState      points to the state buffer.
-   * @return        none
-   */
-
+   * @param[in,out] S          points to an instance of the filter data structure.
+   * @param[in]     numStages  number of 2nd order stages in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   */
   void arm_biquad_cascade_stereo_df2T_init_f32(
   arm_biquad_cascade_stereo_df2T_instance_f32 * S,
   uint8_t numStages,
@@ -3931,13 +3786,11 @@
 
   /**
    * @brief  Initialization function for the floating-point transposed direct form II Biquad cascade filter.
-   * @param[in,out] *S           points to an instance of the filter data structure.
-   * @param[in]     numStages    number of 2nd order stages in the filter.
-   * @param[in]     *pCoeffs     points to the filter coefficients.
-   * @param[in]     *pState      points to the state buffer.
-   * @return        none
-   */
-
+   * @param[in,out] S          points to an instance of the filter data structure.
+   * @param[in]     numStages  number of 2nd order stages in the filter.
+   * @param[in]     pCoeffs    points to the filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   */
   void arm_biquad_cascade_df2T_init_f64(
   arm_biquad_cascade_df2T_instance_f64 * S,
   uint8_t numStages,
@@ -3945,33 +3798,29 @@
   float64_t * pState);
 
 
-
   /**
    * @brief Instance structure for the Q15 FIR lattice filter.
    */
-
   typedef struct
   {
-    uint16_t numStages;                          /**< number of filter stages. */
-    q15_t *pState;                               /**< points to the state variable array. The array is of length numStages. */
-    q15_t *pCoeffs;                              /**< points to the coefficient array. The array is of length numStages. */
+    uint16_t numStages;                  /**< number of filter stages. */
+    q15_t *pState;                       /**< points to the state variable array. The array is of length numStages. */
+    q15_t *pCoeffs;                      /**< points to the coefficient array. The array is of length numStages. */
   } arm_fir_lattice_instance_q15;
 
   /**
    * @brief Instance structure for the Q31 FIR lattice filter.
    */
-
   typedef struct
   {
-    uint16_t numStages;                          /**< number of filter stages. */
-    q31_t *pState;                               /**< points to the state variable array. The array is of length numStages. */
-    q31_t *pCoeffs;                              /**< points to the coefficient array. The array is of length numStages. */
+    uint16_t numStages;                  /**< number of filter stages. */
+    q31_t *pState;                       /**< points to the state variable array. The array is of length numStages. */
+    q31_t *pCoeffs;                      /**< points to the coefficient array. The array is of length numStages. */
   } arm_fir_lattice_instance_q31;
 
   /**
    * @brief Instance structure for the floating-point FIR lattice filter.
    */
-
   typedef struct
   {
     uint16_t numStages;                  /**< number of filter stages. */
@@ -3979,15 +3828,14 @@
     float32_t *pCoeffs;                  /**< points to the coefficient array. The array is of length numStages. */
   } arm_fir_lattice_instance_f32;
 
+
   /**
    * @brief Initialization function for the Q15 FIR lattice filter.
-   * @param[in] *S points to an instance of the Q15 FIR lattice structure.
+   * @param[in] S          points to an instance of the Q15 FIR lattice structure.
    * @param[in] numStages  number of filter stages.
-   * @param[in] *pCoeffs points to the coefficient buffer.  The array is of length numStages.
-   * @param[in] *pState points to the state buffer.  The array is of length numStages.
-   * @return none.
-   */
-
+   * @param[in] pCoeffs    points to the coefficient buffer.  The array is of length numStages.
+   * @param[in] pState     points to the state buffer.  The array is of length numStages.
+   */
   void arm_fir_lattice_init_q15(
   arm_fir_lattice_instance_q15 * S,
   uint16_t numStages,
@@ -3997,11 +3845,10 @@
 
   /**
    * @brief Processing function for the Q15 FIR lattice filter.
-   * @param[in] *S points to an instance of the Q15 FIR lattice structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
+   * @param[in]  S          points to an instance of the Q15 FIR lattice structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
    */
   void arm_fir_lattice_q15(
   const arm_fir_lattice_instance_q15 * S,
@@ -4009,15 +3856,14 @@
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Initialization function for the Q31 FIR lattice filter.
-   * @param[in] *S points to an instance of the Q31 FIR lattice structure.
+   * @param[in] S          points to an instance of the Q31 FIR lattice structure.
    * @param[in] numStages  number of filter stages.
-   * @param[in] *pCoeffs points to the coefficient buffer.  The array is of length numStages.
-   * @param[in] *pState points to the state buffer.   The array is of length numStages.
-   * @return none.
-   */
-
+   * @param[in] pCoeffs    points to the coefficient buffer.  The array is of length numStages.
+   * @param[in] pState     points to the state buffer.   The array is of length numStages.
+   */
   void arm_fir_lattice_init_q31(
   arm_fir_lattice_instance_q31 * S,
   uint16_t numStages,
@@ -4027,58 +3873,55 @@
 
   /**
    * @brief Processing function for the Q31 FIR lattice filter.
-   * @param[in]  *S        points to an instance of the Q31 FIR lattice structure.
-   * @param[in]  *pSrc     points to the block of input data.
-   * @param[out] *pDst     points to the block of output data
-   * @param[in]  blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the Q31 FIR lattice structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_fir_lattice_q31(
   const arm_fir_lattice_instance_q31 * S,
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t blockSize);
 
+
 /**
  * @brief Initialization function for the floating-point FIR lattice filter.
- * @param[in] *S points to an instance of the floating-point FIR lattice structure.
+ * @param[in] S          points to an instance of the floating-point FIR lattice structure.
  * @param[in] numStages  number of filter stages.
- * @param[in] *pCoeffs points to the coefficient buffer.  The array is of length numStages.
- * @param[in] *pState points to the state buffer.  The array is of length numStages.
- * @return none.
+ * @param[in] pCoeffs    points to the coefficient buffer.  The array is of length numStages.
+ * @param[in] pState     points to the state buffer.  The array is of length numStages.
  */
-
   void arm_fir_lattice_init_f32(
   arm_fir_lattice_instance_f32 * S,
   uint16_t numStages,
   float32_t * pCoeffs,
   float32_t * pState);
 
+
   /**
    * @brief Processing function for the floating-point FIR lattice filter.
-   * @param[in]  *S        points to an instance of the floating-point FIR lattice structure.
-   * @param[in]  *pSrc     points to the block of input data.
-   * @param[out] *pDst     points to the block of output data
-   * @param[in]  blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the floating-point FIR lattice structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_fir_lattice_f32(
   const arm_fir_lattice_instance_f32 * S,
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Instance structure for the Q15 IIR lattice filter.
    */
   typedef struct
   {
-    uint16_t numStages;                         /**< number of stages in the filter. */
-    q15_t *pState;                              /**< points to the state variable array. The array is of length numStages+blockSize. */
-    q15_t *pkCoeffs;                            /**< points to the reflection coefficient array. The array is of length numStages. */
-    q15_t *pvCoeffs;                            /**< points to the ladder coefficient array. The array is of length numStages+1. */
+    uint16_t numStages;                  /**< number of stages in the filter. */
+    q15_t *pState;                       /**< points to the state variable array. The array is of length numStages+blockSize. */
+    q15_t *pkCoeffs;                     /**< points to the reflection coefficient array. The array is of length numStages. */
+    q15_t *pvCoeffs;                     /**< points to the ladder coefficient array. The array is of length numStages+1. */
   } arm_iir_lattice_instance_q15;
 
   /**
@@ -4086,10 +3929,10 @@
    */
   typedef struct
   {
-    uint16_t numStages;                         /**< number of stages in the filter. */
-    q31_t *pState;                              /**< points to the state variable array. The array is of length numStages+blockSize. */
-    q31_t *pkCoeffs;                            /**< points to the reflection coefficient array. The array is of length numStages. */
-    q31_t *pvCoeffs;                            /**< points to the ladder coefficient array. The array is of length numStages+1. */
+    uint16_t numStages;                  /**< number of stages in the filter. */
+    q31_t *pState;                       /**< points to the state variable array. The array is of length numStages+blockSize. */
+    q31_t *pkCoeffs;                     /**< points to the reflection coefficient array. The array is of length numStages. */
+    q31_t *pvCoeffs;                     /**< points to the ladder coefficient array. The array is of length numStages+1. */
   } arm_iir_lattice_instance_q31;
 
   /**
@@ -4097,38 +3940,36 @@
    */
   typedef struct
   {
-    uint16_t numStages;                         /**< number of stages in the filter. */
-    float32_t *pState;                          /**< points to the state variable array. The array is of length numStages+blockSize. */
-    float32_t *pkCoeffs;                        /**< points to the reflection coefficient array. The array is of length numStages. */
-    float32_t *pvCoeffs;                        /**< points to the ladder coefficient array. The array is of length numStages+1. */
+    uint16_t numStages;                  /**< number of stages in the filter. */
+    float32_t *pState;                   /**< points to the state variable array. The array is of length numStages+blockSize. */
+    float32_t *pkCoeffs;                 /**< points to the reflection coefficient array. The array is of length numStages. */
+    float32_t *pvCoeffs;                 /**< points to the ladder coefficient array. The array is of length numStages+1. */
   } arm_iir_lattice_instance_f32;
 
+
   /**
    * @brief Processing function for the floating-point IIR lattice filter.
-   * @param[in] *S points to an instance of the floating-point IIR lattice structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the floating-point IIR lattice structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_iir_lattice_f32(
   const arm_iir_lattice_instance_f32 * S,
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Initialization function for the floating-point IIR lattice filter.
-   * @param[in] *S points to an instance of the floating-point IIR lattice structure.
-   * @param[in] numStages number of stages in the filter.
-   * @param[in] *pkCoeffs points to the reflection coefficient buffer.  The array is of length numStages.
-   * @param[in] *pvCoeffs points to the ladder coefficient buffer.  The array is of length numStages+1.
-   * @param[in] *pState points to the state buffer.  The array is of length numStages+blockSize-1.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in] S          points to an instance of the floating-point IIR lattice structure.
+   * @param[in] numStages  number of stages in the filter.
+   * @param[in] pkCoeffs   points to the reflection coefficient buffer.  The array is of length numStages.
+   * @param[in] pvCoeffs   points to the ladder coefficient buffer.  The array is of length numStages+1.
+   * @param[in] pState     points to the state buffer.  The array is of length numStages+blockSize-1.
+   * @param[in] blockSize  number of samples to process.
+   */
   void arm_iir_lattice_init_f32(
   arm_iir_lattice_instance_f32 * S,
   uint16_t numStages,
@@ -4140,13 +3981,11 @@
 
   /**
    * @brief Processing function for the Q31 IIR lattice filter.
-   * @param[in] *S points to an instance of the Q31 IIR lattice structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the Q31 IIR lattice structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_iir_lattice_q31(
   const arm_iir_lattice_instance_q31 * S,
   q31_t * pSrc,
@@ -4156,15 +3995,13 @@
 
   /**
    * @brief Initialization function for the Q31 IIR lattice filter.
-   * @param[in] *S points to an instance of the Q31 IIR lattice structure.
-   * @param[in] numStages number of stages in the filter.
-   * @param[in] *pkCoeffs points to the reflection coefficient buffer.  The array is of length numStages.
-   * @param[in] *pvCoeffs points to the ladder coefficient buffer.  The array is of length numStages+1.
-   * @param[in] *pState points to the state buffer.  The array is of length numStages+blockSize.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in] S          points to an instance of the Q31 IIR lattice structure.
+   * @param[in] numStages  number of stages in the filter.
+   * @param[in] pkCoeffs   points to the reflection coefficient buffer.  The array is of length numStages.
+   * @param[in] pvCoeffs   points to the ladder coefficient buffer.  The array is of length numStages+1.
+   * @param[in] pState     points to the state buffer.  The array is of length numStages+blockSize.
+   * @param[in] blockSize  number of samples to process.
+   */
   void arm_iir_lattice_init_q31(
   arm_iir_lattice_instance_q31 * S,
   uint16_t numStages,
@@ -4176,13 +4013,11 @@
 
   /**
    * @brief Processing function for the Q15 IIR lattice filter.
-   * @param[in] *S points to an instance of the Q15 IIR lattice structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[out] *pDst points to the block of output data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the Q15 IIR lattice structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[out] pDst       points to the block of output data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_iir_lattice_q15(
   const arm_iir_lattice_instance_q15 * S,
   q15_t * pSrc,
@@ -4192,15 +4027,13 @@
 
 /**
  * @brief Initialization function for the Q15 IIR lattice filter.
- * @param[in] *S points to an instance of the fixed-point Q15 IIR lattice structure.
+ * @param[in] S          points to an instance of the fixed-point Q15 IIR lattice structure.
  * @param[in] numStages  number of stages in the filter.
- * @param[in] *pkCoeffs points to reflection coefficient buffer.  The array is of length numStages.
- * @param[in] *pvCoeffs points to ladder coefficient buffer.  The array is of length numStages+1.
- * @param[in] *pState points to state buffer.  The array is of length numStages+blockSize.
- * @param[in] blockSize number of samples to process per call.
- * @return none.
+ * @param[in] pkCoeffs   points to reflection coefficient buffer.  The array is of length numStages.
+ * @param[in] pvCoeffs   points to ladder coefficient buffer.  The array is of length numStages+1.
+ * @param[in] pState     points to state buffer.  The array is of length numStages+blockSize.
+ * @param[in] blockSize  number of samples to process per call.
  */
-
   void arm_iir_lattice_init_q15(
   arm_iir_lattice_instance_q15 * S,
   uint16_t numStages,
@@ -4209,10 +4042,10 @@
   q15_t * pState,
   uint32_t blockSize);
 
+
   /**
    * @brief Instance structure for the floating-point LMS filter.
    */
-
   typedef struct
   {
     uint16_t numTaps;    /**< number of coefficients in the filter. */
@@ -4221,17 +4054,16 @@
     float32_t mu;        /**< step size that controls filter coefficient updates. */
   } arm_lms_instance_f32;
 
+
   /**
    * @brief Processing function for floating-point LMS filter.
-   * @param[in]  *S points to an instance of the floating-point LMS filter structure.
-   * @param[in]  *pSrc points to the block of input data.
-   * @param[in]  *pRef points to the block of reference data.
-   * @param[out] *pOut points to the block of output data.
-   * @param[out] *pErr points to the block of error data.
-   * @param[in]  blockSize number of samples to process.
-   * @return     none.
-   */
-
+   * @param[in]  S          points to an instance of the floating-point LMS filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[in]  pRef       points to the block of reference data.
+   * @param[out] pOut       points to the block of output data.
+   * @param[out] pErr       points to the block of error data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_lms_f32(
   const arm_lms_instance_f32 * S,
   float32_t * pSrc,
@@ -4240,17 +4072,16 @@
   float32_t * pErr,
   uint32_t blockSize);
 
+
   /**
    * @brief Initialization function for floating-point LMS filter.
-   * @param[in] *S points to an instance of the floating-point LMS filter structure.
-   * @param[in] numTaps  number of filter coefficients.
-   * @param[in] *pCoeffs points to the coefficient buffer.
-   * @param[in] *pState points to state buffer.
-   * @param[in] mu step size that controls filter coefficient updates.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in] S          points to an instance of the floating-point LMS filter structure.
+   * @param[in] numTaps    number of filter coefficients.
+   * @param[in] pCoeffs    points to the coefficient buffer.
+   * @param[in] pState     points to state buffer.
+   * @param[in] mu         step size that controls filter coefficient updates.
+   * @param[in] blockSize  number of samples to process.
+   */
   void arm_lms_init_f32(
   arm_lms_instance_f32 * S,
   uint16_t numTaps,
@@ -4259,10 +4090,10 @@
   float32_t mu,
   uint32_t blockSize);
 
+
   /**
    * @brief Instance structure for the Q15 LMS filter.
    */
-
   typedef struct
   {
     uint16_t numTaps;    /**< number of coefficients in the filter. */
@@ -4275,16 +4106,14 @@
 
   /**
    * @brief Initialization function for the Q15 LMS filter.
-   * @param[in] *S points to an instance of the Q15 LMS filter structure.
-   * @param[in] numTaps  number of filter coefficients.
-   * @param[in] *pCoeffs points to the coefficient buffer.
-   * @param[in] *pState points to the state buffer.
-   * @param[in] mu step size that controls filter coefficient updates.
-   * @param[in] blockSize number of samples to process.
-   * @param[in] postShift bit shift applied to coefficients.
-   * @return    none.
-   */
-
+   * @param[in] S          points to an instance of the Q15 LMS filter structure.
+   * @param[in] numTaps    number of filter coefficients.
+   * @param[in] pCoeffs    points to the coefficient buffer.
+   * @param[in] pState     points to the state buffer.
+   * @param[in] mu         step size that controls filter coefficient updates.
+   * @param[in] blockSize  number of samples to process.
+   * @param[in] postShift  bit shift applied to coefficients.
+   */
   void arm_lms_init_q15(
   arm_lms_instance_q15 * S,
   uint16_t numTaps,
@@ -4294,17 +4123,16 @@
   uint32_t blockSize,
   uint32_t postShift);
 
+
   /**
    * @brief Processing function for Q15 LMS filter.
-   * @param[in] *S points to an instance of the Q15 LMS filter structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[in] *pRef points to the block of reference data.
-   * @param[out] *pOut points to the block of output data.
-   * @param[out] *pErr points to the block of error data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the Q15 LMS filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[in]  pRef       points to the block of reference data.
+   * @param[out] pOut       points to the block of output data.
+   * @param[out] pErr       points to the block of error data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_lms_q15(
   const arm_lms_instance_q15 * S,
   q15_t * pSrc,
@@ -4317,7 +4145,6 @@
   /**
    * @brief Instance structure for the Q31 LMS filter.
    */
-
   typedef struct
   {
     uint16_t numTaps;    /**< number of coefficients in the filter. */
@@ -4325,20 +4152,18 @@
     q31_t *pCoeffs;      /**< points to the coefficient array. The array is of length numTaps. */
     q31_t mu;            /**< step size that controls filter coefficient updates. */
     uint32_t postShift;  /**< bit shift applied to coefficients. */
-
   } arm_lms_instance_q31;
 
+
   /**
    * @brief Processing function for Q31 LMS filter.
-   * @param[in]  *S points to an instance of the Q15 LMS filter structure.
-   * @param[in]  *pSrc points to the block of input data.
-   * @param[in]  *pRef points to the block of reference data.
-   * @param[out] *pOut points to the block of output data.
-   * @param[out] *pErr points to the block of error data.
-   * @param[in]  blockSize number of samples to process.
-   * @return     none.
-   */
-
+   * @param[in]  S          points to an instance of the Q15 LMS filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[in]  pRef       points to the block of reference data.
+   * @param[out] pOut       points to the block of output data.
+   * @param[out] pErr       points to the block of error data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_lms_q31(
   const arm_lms_instance_q31 * S,
   q31_t * pSrc,
@@ -4347,18 +4172,17 @@
   q31_t * pErr,
   uint32_t blockSize);
 
+
   /**
    * @brief Initialization function for Q31 LMS filter.
-   * @param[in] *S points to an instance of the Q31 LMS filter structure.
-   * @param[in] numTaps  number of filter coefficients.
-   * @param[in] *pCoeffs points to coefficient buffer.
-   * @param[in] *pState points to state buffer.
-   * @param[in] mu step size that controls filter coefficient updates.
-   * @param[in] blockSize number of samples to process.
-   * @param[in] postShift bit shift applied to coefficients.
-   * @return none.
-   */
-
+   * @param[in] S          points to an instance of the Q31 LMS filter structure.
+   * @param[in] numTaps    number of filter coefficients.
+   * @param[in] pCoeffs    points to coefficient buffer.
+   * @param[in] pState     points to state buffer.
+   * @param[in] mu         step size that controls filter coefficient updates.
+   * @param[in] blockSize  number of samples to process.
+   * @param[in] postShift  bit shift applied to coefficients.
+   */
   void arm_lms_init_q31(
   arm_lms_instance_q31 * S,
   uint16_t numTaps,
@@ -4368,31 +4192,30 @@
   uint32_t blockSize,
   uint32_t postShift);
 
+
   /**
    * @brief Instance structure for the floating-point normalized LMS filter.
    */
-
   typedef struct
   {
     uint16_t numTaps;     /**< number of coefficients in the filter. */
     float32_t *pState;    /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
     float32_t *pCoeffs;   /**< points to the coefficient array. The array is of length numTaps. */
-    float32_t mu;        /**< step size that control filter coefficient updates. */
-    float32_t energy;    /**< saves previous frame energy. */
-    float32_t x0;        /**< saves previous input sample. */
+    float32_t mu;         /**< step size that control filter coefficient updates. */
+    float32_t energy;     /**< saves previous frame energy. */
+    float32_t x0;         /**< saves previous input sample. */
   } arm_lms_norm_instance_f32;
 
+
   /**
    * @brief Processing function for floating-point normalized LMS filter.
-   * @param[in] *S points to an instance of the floating-point normalized LMS filter structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[in] *pRef points to the block of reference data.
-   * @param[out] *pOut points to the block of output data.
-   * @param[out] *pErr points to the block of error data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the floating-point normalized LMS filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[in]  pRef       points to the block of reference data.
+   * @param[out] pOut       points to the block of output data.
+   * @param[out] pErr       points to the block of error data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_lms_norm_f32(
   arm_lms_norm_instance_f32 * S,
   float32_t * pSrc,
@@ -4401,17 +4224,16 @@
   float32_t * pErr,
   uint32_t blockSize);
 
+
   /**
    * @brief Initialization function for floating-point normalized LMS filter.
-   * @param[in] *S points to an instance of the floating-point LMS filter structure.
-   * @param[in] numTaps  number of filter coefficients.
-   * @param[in] *pCoeffs points to coefficient buffer.
-   * @param[in] *pState points to state buffer.
-   * @param[in] mu step size that controls filter coefficient updates.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in] S          points to an instance of the floating-point LMS filter structure.
+   * @param[in] numTaps    number of filter coefficients.
+   * @param[in] pCoeffs    points to coefficient buffer.
+   * @param[in] pState     points to state buffer.
+   * @param[in] mu         step size that controls filter coefficient updates.
+   * @param[in] blockSize  number of samples to process.
+   */
   void arm_lms_norm_init_f32(
   arm_lms_norm_instance_f32 * S,
   uint16_t numTaps,
@@ -4436,17 +4258,16 @@
     q31_t x0;             /**< saves previous input sample. */
   } arm_lms_norm_instance_q31;
 
+
   /**
    * @brief Processing function for Q31 normalized LMS filter.
-   * @param[in] *S points to an instance of the Q31 normalized LMS filter structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[in] *pRef points to the block of reference data.
-   * @param[out] *pOut points to the block of output data.
-   * @param[out] *pErr points to the block of error data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the Q31 normalized LMS filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[in]  pRef       points to the block of reference data.
+   * @param[out] pOut       points to the block of output data.
+   * @param[out] pErr       points to the block of error data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_lms_norm_q31(
   arm_lms_norm_instance_q31 * S,
   q31_t * pSrc,
@@ -4455,18 +4276,17 @@
   q31_t * pErr,
   uint32_t blockSize);
 
+
   /**
    * @brief Initialization function for Q31 normalized LMS filter.
-   * @param[in] *S points to an instance of the Q31 normalized LMS filter structure.
-   * @param[in] numTaps  number of filter coefficients.
-   * @param[in] *pCoeffs points to coefficient buffer.
-   * @param[in] *pState points to state buffer.
-   * @param[in] mu step size that controls filter coefficient updates.
-   * @param[in] blockSize number of samples to process.
-   * @param[in] postShift bit shift applied to coefficients.
-   * @return none.
-   */
-
+   * @param[in] S          points to an instance of the Q31 normalized LMS filter structure.
+   * @param[in] numTaps    number of filter coefficients.
+   * @param[in] pCoeffs    points to coefficient buffer.
+   * @param[in] pState     points to state buffer.
+   * @param[in] mu         step size that controls filter coefficient updates.
+   * @param[in] blockSize  number of samples to process.
+   * @param[in] postShift  bit shift applied to coefficients.
+   */
   void arm_lms_norm_init_q31(
   arm_lms_norm_instance_q31 * S,
   uint16_t numTaps,
@@ -4476,33 +4296,32 @@
   uint32_t blockSize,
   uint8_t postShift);
 
+
   /**
    * @brief Instance structure for the Q15 normalized LMS filter.
    */
-
   typedef struct
   {
-    uint16_t numTaps;    /**< Number of coefficients in the filter. */
+    uint16_t numTaps;     /**< Number of coefficients in the filter. */
     q15_t *pState;        /**< points to the state variable array. The array is of length numTaps+blockSize-1. */
     q15_t *pCoeffs;       /**< points to the coefficient array. The array is of length numTaps. */
-    q15_t mu;            /**< step size that controls filter coefficient updates. */
-    uint8_t postShift;   /**< bit shift applied to coefficients. */
-    q15_t *recipTable;   /**< Points to the reciprocal initial value table. */
-    q15_t energy;        /**< saves previous frame energy. */
-    q15_t x0;            /**< saves previous input sample. */
+    q15_t mu;             /**< step size that controls filter coefficient updates. */
+    uint8_t postShift;    /**< bit shift applied to coefficients. */
+    q15_t *recipTable;    /**< Points to the reciprocal initial value table. */
+    q15_t energy;         /**< saves previous frame energy. */
+    q15_t x0;             /**< saves previous input sample. */
   } arm_lms_norm_instance_q15;
 
+
   /**
    * @brief Processing function for Q15 normalized LMS filter.
-   * @param[in] *S points to an instance of the Q15 normalized LMS filter structure.
-   * @param[in] *pSrc points to the block of input data.
-   * @param[in] *pRef points to the block of reference data.
-   * @param[out] *pOut points to the block of output data.
-   * @param[out] *pErr points to the block of error data.
-   * @param[in] blockSize number of samples to process.
-   * @return none.
-   */
-
+   * @param[in]  S          points to an instance of the Q15 normalized LMS filter structure.
+   * @param[in]  pSrc       points to the block of input data.
+   * @param[in]  pRef       points to the block of reference data.
+   * @param[out] pOut       points to the block of output data.
+   * @param[out] pErr       points to the block of error data.
+   * @param[in]  blockSize  number of samples to process.
+   */
   void arm_lms_norm_q15(
   arm_lms_norm_instance_q15 * S,
   q15_t * pSrc,
@@ -4514,16 +4333,14 @@
 
   /**
    * @brief Initialization function for Q15 normalized LMS filter.
-   * @param[in] *S points to an instance of the Q15 normalized LMS filter structure.
-   * @param[in] numTaps  number of filter coefficients.
-   * @param[in] *pCoeffs points to coefficient buffer.
-   * @param[in] *pState points to state buffer.
-   * @param[in] mu step size that controls filter coefficient updates.
-   * @param[in] blockSize number of samples to process.
-   * @param[in] postShift bit shift applied to coefficients.
-   * @return none.
-   */
-
+   * @param[in] S          points to an instance of the Q15 normalized LMS filter structure.
+   * @param[in] numTaps    number of filter coefficients.
+   * @param[in] pCoeffs    points to coefficient buffer.
+   * @param[in] pState     points to state buffer.
+   * @param[in] mu         step size that controls filter coefficient updates.
+   * @param[in] blockSize  number of samples to process.
+   * @param[in] postShift  bit shift applied to coefficients.
+   */
   void arm_lms_norm_init_q15(
   arm_lms_norm_instance_q15 * S,
   uint16_t numTaps,
@@ -4533,16 +4350,15 @@
   uint32_t blockSize,
   uint8_t postShift);
 
+
   /**
    * @brief Correlation of floating-point sequences.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
-   * @return none.
-   */
-
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
+   */
   void arm_correlate_f32(
   float32_t * pSrcA,
   uint32_t srcALen,
@@ -4553,13 +4369,12 @@
 
    /**
    * @brief Correlation of Q15 sequences
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
-   * @param[in]  *pScratch points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
-   * @return none.
+   * @param[in]  pSrcA     points to the first input sequence.
+   * @param[in]  srcALen   length of the first input sequence.
+   * @param[in]  pSrcB     points to the second input sequence.
+   * @param[in]  srcBLen   length of the second input sequence.
+   * @param[out] pDst      points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
+   * @param[in]  pScratch  points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
    */
   void arm_correlate_opt_q15(
   q15_t * pSrcA,
@@ -4572,12 +4387,11 @@
 
   /**
    * @brief Correlation of Q15 sequences.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
-   * @return none.
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
    */
 
   void arm_correlate_q15(
@@ -4587,36 +4401,33 @@
   uint32_t srcBLen,
   q15_t * pDst);
 
+
   /**
    * @brief Correlation of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
-   * @return none.
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
    */
 
   void arm_correlate_fast_q15(
-			       q15_t * pSrcA,
-			      uint32_t srcALen,
-			       q15_t * pSrcB,
-			      uint32_t srcBLen,
-			      q15_t * pDst);
-
+  q15_t * pSrcA,
+  uint32_t srcALen,
+  q15_t * pSrcB,
+  uint32_t srcBLen,
+  q15_t * pDst);
 
 
   /**
    * @brief Correlation of Q15 sequences (fast version) for Cortex-M3 and Cortex-M4.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
-   * @param[in]  *pScratch points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
-   * @return none.
-   */
-
+   * @param[in]  pSrcA     points to the first input sequence.
+   * @param[in]  srcALen   length of the first input sequence.
+   * @param[in]  pSrcB     points to the second input sequence.
+   * @param[in]  srcBLen   length of the second input sequence.
+   * @param[out] pDst      points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
+   * @param[in]  pScratch  points to scratch buffer of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
+   */
   void arm_correlate_fast_opt_q15(
   q15_t * pSrcA,
   uint32_t srcALen,
@@ -4625,16 +4436,15 @@
   q15_t * pDst,
   q15_t * pScratch);
 
+
   /**
    * @brief Correlation of Q31 sequences.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
-   * @return none.
-   */
-
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
+   */
   void arm_correlate_q31(
   q31_t * pSrcA,
   uint32_t srcALen,
@@ -4642,16 +4452,15 @@
   uint32_t srcBLen,
   q31_t * pDst);
 
+
   /**
    * @brief Correlation of Q31 sequences (fast version) for Cortex-M3 and Cortex-M4
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
-   * @return none.
-   */
-
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
+   */
   void arm_correlate_fast_q31(
   q31_t * pSrcA,
   uint32_t srcALen,
@@ -4660,19 +4469,16 @@
   q31_t * pDst);
 
 
-
  /**
    * @brief Correlation of Q7 sequences.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
-   * @param[in]  *pScratch1 points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
-   * @param[in]  *pScratch2 points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
-   * @return none.
-   */
-
+   * @param[in]  pSrcA      points to the first input sequence.
+   * @param[in]  srcALen    length of the first input sequence.
+   * @param[in]  pSrcB      points to the second input sequence.
+   * @param[in]  srcBLen    length of the second input sequence.
+   * @param[out] pDst       points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
+   * @param[in]  pScratch1  points to scratch buffer(of type q15_t) of size max(srcALen, srcBLen) + 2*min(srcALen, srcBLen) - 2.
+   * @param[in]  pScratch2  points to scratch buffer (of type q15_t) of size min(srcALen, srcBLen).
+   */
   void arm_correlate_opt_q7(
   q7_t * pSrcA,
   uint32_t srcALen,
@@ -4685,14 +4491,12 @@
 
   /**
    * @brief Correlation of Q7 sequences.
-   * @param[in] *pSrcA points to the first input sequence.
-   * @param[in] srcALen length of the first input sequence.
-   * @param[in] *pSrcB points to the second input sequence.
-   * @param[in] srcBLen length of the second input sequence.
-   * @param[out] *pDst points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
-   * @return none.
-   */
-
+   * @param[in]  pSrcA    points to the first input sequence.
+   * @param[in]  srcALen  length of the first input sequence.
+   * @param[in]  pSrcB    points to the second input sequence.
+   * @param[in]  srcBLen  length of the second input sequence.
+   * @param[out] pDst     points to the block of output data  Length 2 * max(srcALen, srcBLen) - 1.
+   */
   void arm_correlate_q7(
   q7_t * pSrcA,
   uint32_t srcALen,
@@ -4717,7 +4521,6 @@
   /**
    * @brief Instance structure for the Q31 sparse FIR filter.
    */
-
   typedef struct
   {
     uint16_t numTaps;             /**< number of coefficients in the filter. */
@@ -4731,7 +4534,6 @@
   /**
    * @brief Instance structure for the Q15 sparse FIR filter.
    */
-
   typedef struct
   {
     uint16_t numTaps;             /**< number of coefficients in the filter. */
@@ -4745,7 +4547,6 @@
   /**
    * @brief Instance structure for the Q7 sparse FIR filter.
    */
-
   typedef struct
   {
     uint16_t numTaps;             /**< number of coefficients in the filter. */
@@ -4756,16 +4557,15 @@
     int32_t *pTapDelay;           /**< points to the array of delay values.  The array is of length numTaps. */
   } arm_fir_sparse_instance_q7;
 
+
   /**
    * @brief Processing function for the floating-point sparse FIR filter.
-   * @param[in]  *S          points to an instance of the floating-point sparse FIR structure.
-   * @param[in]  *pSrc       points to the block of input data.
-   * @param[out] *pDst       points to the block of output data
-   * @param[in]  *pScratchIn points to a temporary buffer of size blockSize.
+   * @param[in]  S           points to an instance of the floating-point sparse FIR structure.
+   * @param[in]  pSrc        points to the block of input data.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  pScratchIn  points to a temporary buffer of size blockSize.
    * @param[in]  blockSize   number of input samples to process per call.
-   * @return none.
-   */
-
+   */
   void arm_fir_sparse_f32(
   arm_fir_sparse_instance_f32 * S,
   float32_t * pSrc,
@@ -4773,18 +4573,17 @@
   float32_t * pScratchIn,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the floating-point sparse FIR filter.
-   * @param[in,out] *S         points to an instance of the floating-point sparse FIR structure.
+   * @param[in,out] S          points to an instance of the floating-point sparse FIR structure.
    * @param[in]     numTaps    number of nonzero coefficients in the filter.
-   * @param[in]     *pCoeffs   points to the array of filter coefficients.
-   * @param[in]     *pState    points to the state buffer.
-   * @param[in]     *pTapDelay points to the array of offset times.
+   * @param[in]     pCoeffs    points to the array of filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     pTapDelay  points to the array of offset times.
    * @param[in]     maxDelay   maximum offset time supported.
    * @param[in]     blockSize  number of samples that will be processed per block.
-   * @return none
-   */
-
+   */
   void arm_fir_sparse_init_f32(
   arm_fir_sparse_instance_f32 * S,
   uint16_t numTaps,
@@ -4794,16 +4593,15 @@
   uint16_t maxDelay,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the Q31 sparse FIR filter.
-   * @param[in]  *S          points to an instance of the Q31 sparse FIR structure.
-   * @param[in]  *pSrc       points to the block of input data.
-   * @param[out] *pDst       points to the block of output data
-   * @param[in]  *pScratchIn points to a temporary buffer of size blockSize.
+   * @param[in]  S           points to an instance of the Q31 sparse FIR structure.
+   * @param[in]  pSrc        points to the block of input data.
+   * @param[out] pDst        points to the block of output data
+   * @param[in]  pScratchIn  points to a temporary buffer of size blockSize.
    * @param[in]  blockSize   number of input samples to process per call.
-   * @return none.
-   */
-
+   */
   void arm_fir_sparse_q31(
   arm_fir_sparse_instance_q31 * S,
   q31_t * pSrc,
@@ -4811,18 +4609,17 @@
   q31_t * pScratchIn,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the Q31 sparse FIR filter.
-   * @param[in,out] *S         points to an instance of the Q31 sparse FIR structure.
+   * @param[in,out] S          points to an instance of the Q31 sparse FIR structure.
    * @param[in]     numTaps    number of nonzero coefficients in the filter.
-   * @param[in]     *pCoeffs   points to the array of filter coefficients.
-   * @param[in]     *pState    points to the state buffer.
-   * @param[in]     *pTapDelay points to the array of offset times.
+   * @param[in]     pCoeffs    points to the array of filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     pTapDelay  points to the array of offset times.
    * @param[in]     maxDelay   maximum offset time supported.
    * @param[in]     blockSize  number of samples that will be processed per block.
-   * @return none
-   */
-
+   */
   void arm_fir_sparse_init_q31(
   arm_fir_sparse_instance_q31 * S,
   uint16_t numTaps,
@@ -4832,17 +4629,16 @@
   uint16_t maxDelay,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the Q15 sparse FIR filter.
-   * @param[in]  *S           points to an instance of the Q15 sparse FIR structure.
-   * @param[in]  *pSrc        points to the block of input data.
-   * @param[out] *pDst        points to the block of output data
-   * @param[in]  *pScratchIn  points to a temporary buffer of size blockSize.
-   * @param[in]  *pScratchOut points to a temporary buffer of size blockSize.
+   * @param[in]  S            points to an instance of the Q15 sparse FIR structure.
+   * @param[in]  pSrc         points to the block of input data.
+   * @param[out] pDst         points to the block of output data
+   * @param[in]  pScratchIn   points to a temporary buffer of size blockSize.
+   * @param[in]  pScratchOut  points to a temporary buffer of size blockSize.
    * @param[in]  blockSize    number of input samples to process per call.
-   * @return none.
-   */
-
+   */
   void arm_fir_sparse_q15(
   arm_fir_sparse_instance_q15 * S,
   q15_t * pSrc,
@@ -4854,16 +4650,14 @@
 
   /**
    * @brief  Initialization function for the Q15 sparse FIR filter.
-   * @param[in,out] *S         points to an instance of the Q15 sparse FIR structure.
+   * @param[in,out] S          points to an instance of the Q15 sparse FIR structure.
    * @param[in]     numTaps    number of nonzero coefficients in the filter.
-   * @param[in]     *pCoeffs   points to the array of filter coefficients.
-   * @param[in]     *pState    points to the state buffer.
-   * @param[in]     *pTapDelay points to the array of offset times.
+   * @param[in]     pCoeffs    points to the array of filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     pTapDelay  points to the array of offset times.
    * @param[in]     maxDelay   maximum offset time supported.
    * @param[in]     blockSize  number of samples that will be processed per block.
-   * @return none
-   */
-
+   */
   void arm_fir_sparse_init_q15(
   arm_fir_sparse_instance_q15 * S,
   uint16_t numTaps,
@@ -4873,17 +4667,16 @@
   uint16_t maxDelay,
   uint32_t blockSize);
 
+
   /**
    * @brief Processing function for the Q7 sparse FIR filter.
-   * @param[in]  *S           points to an instance of the Q7 sparse FIR structure.
-   * @param[in]  *pSrc        points to the block of input data.
-   * @param[out] *pDst        points to the block of output data
-   * @param[in]  *pScratchIn  points to a temporary buffer of size blockSize.
-   * @param[in]  *pScratchOut points to a temporary buffer of size blockSize.
+   * @param[in]  S            points to an instance of the Q7 sparse FIR structure.
+   * @param[in]  pSrc         points to the block of input data.
+   * @param[out] pDst         points to the block of output data
+   * @param[in]  pScratchIn   points to a temporary buffer of size blockSize.
+   * @param[in]  pScratchOut  points to a temporary buffer of size blockSize.
    * @param[in]  blockSize    number of input samples to process per call.
-   * @return none.
-   */
-
+   */
   void arm_fir_sparse_q7(
   arm_fir_sparse_instance_q7 * S,
   q7_t * pSrc,
@@ -4892,18 +4685,17 @@
   q31_t * pScratchOut,
   uint32_t blockSize);
 
+
   /**
    * @brief  Initialization function for the Q7 sparse FIR filter.
-   * @param[in,out] *S         points to an instance of the Q7 sparse FIR structure.
+   * @param[in,out] S          points to an instance of the Q7 sparse FIR structure.
    * @param[in]     numTaps    number of nonzero coefficients in the filter.
-   * @param[in]     *pCoeffs   points to the array of filter coefficients.
-   * @param[in]     *pState    points to the state buffer.
-   * @param[in]     *pTapDelay points to the array of offset times.
+   * @param[in]     pCoeffs    points to the array of filter coefficients.
+   * @param[in]     pState     points to the state buffer.
+   * @param[in]     pTapDelay  points to the array of offset times.
    * @param[in]     maxDelay   maximum offset time supported.
    * @param[in]     blockSize  number of samples that will be processed per block.
-   * @return none
-   */
-
+   */
   void arm_fir_sparse_init_q7(
   arm_fir_sparse_instance_q7 * S,
   uint16_t numTaps,
@@ -4914,27 +4706,24 @@
   uint32_t blockSize);
 
 
-  /*
+  /**
    * @brief  Floating-point sin_cos function.
-   * @param[in]  theta    input value in degrees
-   * @param[out] *pSinVal points to the processed sine output.
-   * @param[out] *pCosVal points to the processed cos output.
-   * @return none.
-   */
-
+   * @param[in]  theta   input value in degrees
+   * @param[out] pSinVal  points to the processed sine output.
+   * @param[out] pCosVal  points to the processed cos output.
+   */
   void arm_sin_cos_f32(
   float32_t theta,
   float32_t * pSinVal,
-  float32_t * pCcosVal);
-
-  /*
+  float32_t * pCosVal);
+
+
+  /**
    * @brief  Q31 sin_cos function.
    * @param[in]  theta    scaled input value in degrees
-   * @param[out] *pSinVal points to the processed sine output.
-   * @param[out] *pCosVal points to the processed cosine output.
-   * @return none.
-   */
-
+   * @param[out] pSinVal  points to the processed sine output.
+   * @param[out] pCosVal  points to the processed cosine output.
+   */
   void arm_sin_cos_q31(
   q31_t theta,
   q31_t * pSinVal,
@@ -4943,12 +4732,10 @@
 
   /**
    * @brief  Floating-point complex conjugate.
-   * @param[in]  *pSrc points to the input vector
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  numSamples number of complex samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the input vector
+   * @param[out] pDst        points to the output vector
+   * @param[in]  numSamples  number of complex samples in each vector
+   */
   void arm_cmplx_conj_f32(
   float32_t * pSrc,
   float32_t * pDst,
@@ -4956,66 +4743,58 @@
 
   /**
    * @brief  Q31 complex conjugate.
-   * @param[in]  *pSrc points to the input vector
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  numSamples number of complex samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the input vector
+   * @param[out] pDst        points to the output vector
+   * @param[in]  numSamples  number of complex samples in each vector
+   */
   void arm_cmplx_conj_q31(
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Q15 complex conjugate.
-   * @param[in]  *pSrc points to the input vector
-   * @param[out]  *pDst points to the output vector
-   * @param[in]  numSamples number of complex samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the input vector
+   * @param[out] pDst        points to the output vector
+   * @param[in]  numSamples  number of complex samples in each vector
+   */
   void arm_cmplx_conj_q15(
   q15_t * pSrc,
   q15_t * pDst,
   uint32_t numSamples);
 
 
-
   /**
    * @brief  Floating-point complex magnitude squared
-   * @param[in]  *pSrc points to the complex input vector
-   * @param[out]  *pDst points to the real output vector
-   * @param[in]  numSamples number of complex samples in the input vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the complex input vector
+   * @param[out] pDst        points to the real output vector
+   * @param[in]  numSamples  number of complex samples in the input vector
+   */
   void arm_cmplx_mag_squared_f32(
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Q31 complex magnitude squared
-   * @param[in]  *pSrc points to the complex input vector
-   * @param[out]  *pDst points to the real output vector
-   * @param[in]  numSamples number of complex samples in the input vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the complex input vector
+   * @param[out] pDst        points to the real output vector
+   * @param[in]  numSamples  number of complex samples in the input vector
+   */
   void arm_cmplx_mag_squared_q31(
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Q15 complex magnitude squared
-   * @param[in]  *pSrc points to the complex input vector
-   * @param[out]  *pDst points to the real output vector
-   * @param[in]  numSamples number of complex samples in the input vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the complex input vector
+   * @param[out] pDst        points to the real output vector
+   * @param[in]  numSamples  number of complex samples in the input vector
+   */
   void arm_cmplx_mag_squared_q15(
   q15_t * pSrc,
   q15_t * pDst,
@@ -5090,13 +4869,11 @@
 
   /**
    * @brief  Process function for the floating-point PID Control.
-   * @param[in,out] *S is an instance of the floating-point PID Control structure
-   * @param[in] in input sample to process
+   * @param[in,out] S   is an instance of the floating-point PID Control structure
+   * @param[in]     in  input sample to process
    * @return out processed output sample.
    */
-
-
-  static __INLINE float32_t arm_pid_f32(
+  CMSIS_INLINE __STATIC_INLINE float32_t arm_pid_f32(
   arm_pid_instance_f32 * S,
   float32_t in)
   {
@@ -5118,8 +4895,8 @@
 
   /**
    * @brief  Process function for the Q31 PID Control.
-   * @param[in,out] *S points to an instance of the Q31 PID Control structure
-   * @param[in] in input sample to process
+   * @param[in,out] S  points to an instance of the Q31 PID Control structure
+   * @param[in]     in  input sample to process
    * @return out processed output sample.
    *
    * <b>Scaling and Overflow Behavior:</b>
@@ -5130,8 +4907,7 @@
    * In order to avoid overflows completely the input signal must be scaled down by 2 bits as there are four additions.
    * After all multiply-accumulates are performed, the 2.62 accumulator is truncated to 1.32 format and then saturated to 1.31 format.
    */
-
-  static __INLINE q31_t arm_pid_q31(
+  CMSIS_INLINE __STATIC_INLINE q31_t arm_pid_q31(
   arm_pid_instance_q31 * S,
   q31_t in)
   {
@@ -5160,13 +4936,13 @@
 
     /* return to application */
     return (out);
-
   }
 
+
   /**
    * @brief  Process function for the Q15 PID Control.
-   * @param[in,out] *S points to an instance of the Q15 PID Control structure
-   * @param[in] in input sample to process
+   * @param[in,out] S   points to an instance of the Q15 PID Control structure
+   * @param[in]     in  input sample to process
    * @return out processed output sample.
    *
    * <b>Scaling and Overflow Behavior:</b>
@@ -5178,26 +4954,24 @@
    * After all additions have been performed, the accumulator is truncated to 34.15 format by discarding low 15 bits.
    * Lastly, the accumulator is saturated to yield a result in 1.15 format.
    */
-
-  static __INLINE q15_t arm_pid_q15(
+  CMSIS_INLINE __STATIC_INLINE q15_t arm_pid_q15(
   arm_pid_instance_q15 * S,
   q15_t in)
   {
     q63_t acc;
     q15_t out;
 
-#ifndef ARM_MATH_CM0_FAMILY
+#if defined (ARM_MATH_DSP)
     __SIMD32_TYPE *vstate;
 
     /* Implementation of PID controller */
 
     /* acc = A0 * x[n]  */
-    acc = (q31_t) __SMUAD(S->A0, in);
+    acc = (q31_t) __SMUAD((uint32_t)S->A0, (uint32_t)in);
 
     /* acc += A1 * x[n-1] + A2 * x[n-2]  */
     vstate = __SIMD32_CONST(S->state);
-    acc = __SMLALD(S->A1, (q31_t) *vstate, acc);
-
+    acc = (q63_t)__SMLALD((uint32_t)S->A1, (uint32_t)*vstate, (uint64_t)acc);
 #else
     /* acc = A0 * x[n]  */
     acc = ((q31_t) S->A0) * in;
@@ -5205,7 +4979,6 @@
     /* acc += A1 * x[n-1] + A2 * x[n-2]  */
     acc += (q31_t) S->A1 * S->state[0];
     acc += (q31_t) S->A2 * S->state[1];
-
 #endif
 
     /* acc += y[n-1] */
@@ -5221,7 +4994,6 @@
 
     /* return to application */
     return (out);
-
   }
 
   /**
@@ -5231,12 +5003,11 @@
 
   /**
    * @brief Floating-point matrix inverse.
-   * @param[in]  *src points to the instance of the input floating-point matrix structure.
-   * @param[out] *dst points to the instance of the output floating-point matrix structure.
+   * @param[in]  src   points to the instance of the input floating-point matrix structure.
+   * @param[out] dst   points to the instance of the output floating-point matrix structure.
    * @return The function returns ARM_MATH_SIZE_MISMATCH, if the dimensions do not match.
    * If the input matrix is singular (does not have an inverse), then the algorithm terminates and returns error status ARM_MATH_SINGULAR.
    */
-
   arm_status arm_mat_inverse_f32(
   const arm_matrix_instance_f32 * src,
   arm_matrix_instance_f32 * dst);
@@ -5244,12 +5015,11 @@
 
   /**
    * @brief Floating-point matrix inverse.
-   * @param[in]  *src points to the instance of the input floating-point matrix structure.
-   * @param[out] *dst points to the instance of the output floating-point matrix structure.
+   * @param[in]  src   points to the instance of the input floating-point matrix structure.
+   * @param[out] dst   points to the instance of the output floating-point matrix structure.
    * @return The function returns ARM_MATH_SIZE_MISMATCH, if the dimensions do not match.
    * If the input matrix is singular (does not have an inverse), then the algorithm terminates and returns error status ARM_MATH_SINGULAR.
    */
-
   arm_status arm_mat_inverse_f64(
   const arm_matrix_instance_f64 * src,
   arm_matrix_instance_f64 * dst);
@@ -5260,7 +5030,6 @@
    * @ingroup groupController
    */
 
-
   /**
    * @defgroup clarke Vector Clarke Transform
    * Forward Clarke transform converts the instantaneous stator phases into a two-coordinate time invariant vector.
@@ -5291,14 +5060,12 @@
   /**
    *
    * @brief  Floating-point Clarke transform
-   * @param[in]       Ia       input three-phase coordinate <code>a</code>
-   * @param[in]       Ib       input three-phase coordinate <code>b</code>
-   * @param[out]      *pIalpha points to output two-phase orthogonal vector axis alpha
-   * @param[out]      *pIbeta  points to output two-phase orthogonal vector axis beta
-   * @return none.
-   */
-
-  static __INLINE void arm_clarke_f32(
+   * @param[in]  Ia       input three-phase coordinate <code>a</code>
+   * @param[in]  Ib       input three-phase coordinate <code>b</code>
+   * @param[out] pIalpha  points to output two-phase orthogonal vector axis alpha
+   * @param[out] pIbeta   points to output two-phase orthogonal vector axis beta
+   */
+  CMSIS_INLINE __STATIC_INLINE void arm_clarke_f32(
   float32_t Ia,
   float32_t Ib,
   float32_t * pIalpha,
@@ -5308,18 +5075,16 @@
     *pIalpha = Ia;
 
     /* Calculate pIbeta using the equation, pIbeta = (1/sqrt(3)) * Ia + (2/sqrt(3)) * Ib */
-    *pIbeta =
-      ((float32_t) 0.57735026919 * Ia + (float32_t) 1.15470053838 * Ib);
-
+    *pIbeta = ((float32_t) 0.57735026919 * Ia + (float32_t) 1.15470053838 * Ib);
   }
 
+
   /**
    * @brief  Clarke transform for Q31 version
-   * @param[in]       Ia       input three-phase coordinate <code>a</code>
-   * @param[in]       Ib       input three-phase coordinate <code>b</code>
-   * @param[out]      *pIalpha points to output two-phase orthogonal vector axis alpha
-   * @param[out]      *pIbeta  points to output two-phase orthogonal vector axis beta
-   * @return none.
+   * @param[in]  Ia       input three-phase coordinate <code>a</code>
+   * @param[in]  Ib       input three-phase coordinate <code>b</code>
+   * @param[out] pIalpha  points to output two-phase orthogonal vector axis alpha
+   * @param[out] pIbeta   points to output two-phase orthogonal vector axis beta
    *
    * <b>Scaling and Overflow Behavior:</b>
    * \par
@@ -5327,8 +5092,7 @@
    * The accumulator maintains 1.31 format by truncating lower 31 bits of the intermediate multiplication in 2.62 format.
    * There is saturation on the addition, hence there is no risk of overflow.
    */
-
-  static __INLINE void arm_clarke_q31(
+  CMSIS_INLINE __STATIC_INLINE void arm_clarke_q31(
   q31_t Ia,
   q31_t Ib,
   q31_t * pIalpha,
@@ -5355,10 +5119,9 @@
 
   /**
    * @brief  Converts the elements of the Q7 vector to Q31 vector.
-   * @param[in]  *pSrc     input pointer
-   * @param[out]  *pDst    output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  pSrc       input pointer
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_q7_to_q31(
   q7_t * pSrc,
@@ -5367,7 +5130,6 @@
 
 
 
-
   /**
    * @ingroup groupController
    */
@@ -5395,15 +5157,12 @@
 
    /**
    * @brief  Floating-point Inverse Clarke transform
-   * @param[in]       Ialpha  input two-phase orthogonal vector axis alpha
-   * @param[in]       Ibeta   input two-phase orthogonal vector axis beta
-   * @param[out]      *pIa    points to output three-phase coordinate <code>a</code>
-   * @param[out]      *pIb    points to output three-phase coordinate <code>b</code>
-   * @return none.
-   */
-
-
-  static __INLINE void arm_inv_clarke_f32(
+   * @param[in]  Ialpha  input two-phase orthogonal vector axis alpha
+   * @param[in]  Ibeta   input two-phase orthogonal vector axis beta
+   * @param[out] pIa     points to output three-phase coordinate <code>a</code>
+   * @param[out] pIb     points to output three-phase coordinate <code>b</code>
+   */
+  CMSIS_INLINE __STATIC_INLINE void arm_inv_clarke_f32(
   float32_t Ialpha,
   float32_t Ibeta,
   float32_t * pIa,
@@ -5413,17 +5172,16 @@
     *pIa = Ialpha;
 
     /* Calculating pIb from Ialpha and Ibeta by equation pIb = -(1/2) * Ialpha + (sqrt(3)/2) * Ibeta */
-    *pIb = -0.5 * Ialpha + (float32_t) 0.8660254039 *Ibeta;
-
+    *pIb = -0.5f * Ialpha + 0.8660254039f * Ibeta;
   }
 
+
   /**
    * @brief  Inverse Clarke transform for Q31 version
-   * @param[in]       Ialpha  input two-phase orthogonal vector axis alpha
-   * @param[in]       Ibeta   input two-phase orthogonal vector axis beta
-   * @param[out]      *pIa    points to output three-phase coordinate <code>a</code>
-   * @param[out]      *pIb    points to output three-phase coordinate <code>b</code>
-   * @return none.
+   * @param[in]  Ialpha  input two-phase orthogonal vector axis alpha
+   * @param[in]  Ibeta   input two-phase orthogonal vector axis beta
+   * @param[out] pIa     points to output three-phase coordinate <code>a</code>
+   * @param[out] pIb     points to output three-phase coordinate <code>b</code>
    *
    * <b>Scaling and Overflow Behavior:</b>
    * \par
@@ -5431,8 +5189,7 @@
    * The accumulator maintains 1.31 format by truncating lower 31 bits of the intermediate multiplication in 2.62 format.
    * There is saturation on the subtraction, hence there is no risk of overflow.
    */
-
-  static __INLINE void arm_inv_clarke_q31(
+  CMSIS_INLINE __STATIC_INLINE void arm_inv_clarke_q31(
   q31_t Ialpha,
   q31_t Ibeta,
   q31_t * pIa,
@@ -5451,7 +5208,6 @@
 
     /* pIb is calculated by subtracting the products */
     *pIb = __QSUB(product2, product1);
-
   }
 
   /**
@@ -5460,10 +5216,9 @@
 
   /**
    * @brief  Converts the elements of the Q7 vector to Q15 vector.
-   * @param[in]  *pSrc     input pointer
-   * @param[out] *pDst     output pointer
-   * @param[in]  blockSize number of samples to process
-   * @return none.
+   * @param[in]  pSrc       input pointer
+   * @param[out] pDst       output pointer
+   * @param[in]  blockSize  number of samples to process
    */
   void arm_q7_to_q15(
   q7_t * pSrc,
@@ -5507,19 +5262,17 @@
 
   /**
    * @brief Floating-point Park transform
-   * @param[in]       Ialpha input two-phase vector coordinate alpha
-   * @param[in]       Ibeta  input two-phase vector coordinate beta
-   * @param[out]      *pId   points to output	rotor reference frame d
-   * @param[out]      *pIq   points to output	rotor reference frame q
-   * @param[in]       sinVal sine value of rotation angle theta
-   * @param[in]       cosVal cosine value of rotation angle theta
-   * @return none.
+   * @param[in]  Ialpha  input two-phase vector coordinate alpha
+   * @param[in]  Ibeta   input two-phase vector coordinate beta
+   * @param[out] pId     points to output   rotor reference frame d
+   * @param[out] pIq     points to output   rotor reference frame q
+   * @param[in]  sinVal  sine value of rotation angle theta
+   * @param[in]  cosVal  cosine value of rotation angle theta
    *
    * The function implements the forward Park transform.
    *
    */
-
-  static __INLINE void arm_park_f32(
+  CMSIS_INLINE __STATIC_INLINE void arm_park_f32(
   float32_t Ialpha,
   float32_t Ibeta,
   float32_t * pId,
@@ -5532,18 +5285,17 @@
 
     /* Calculate pIq using the equation, pIq = - Ialpha * sinVal + Ibeta * cosVal */
     *pIq = -Ialpha * sinVal + Ibeta * cosVal;
-
   }
 
+
   /**
    * @brief  Park transform for Q31 version
-   * @param[in]       Ialpha input two-phase vector coordinate alpha
-   * @param[in]       Ibeta  input two-phase vector coordinate beta
-   * @param[out]      *pId   points to output rotor reference frame d
-   * @param[out]      *pIq   points to output rotor reference frame q
-   * @param[in]       sinVal sine value of rotation angle theta
-   * @param[in]       cosVal cosine value of rotation angle theta
-   * @return none.
+   * @param[in]  Ialpha  input two-phase vector coordinate alpha
+   * @param[in]  Ibeta   input two-phase vector coordinate beta
+   * @param[out] pId     points to output rotor reference frame d
+   * @param[out] pIq     points to output rotor reference frame q
+   * @param[in]  sinVal  sine value of rotation angle theta
+   * @param[in]  cosVal  cosine value of rotation angle theta
    *
    * <b>Scaling and Overflow Behavior:</b>
    * \par
@@ -5551,9 +5303,7 @@
    * The accumulator maintains 1.31 format by truncating lower 31 bits of the intermediate multiplication in 2.62 format.
    * There is saturation on the addition and subtraction, hence there is no risk of overflow.
    */
-
-
-  static __INLINE void arm_park_q31(
+  CMSIS_INLINE __STATIC_INLINE void arm_park_q31(
   q31_t Ialpha,
   q31_t Ibeta,
   q31_t * pId,
@@ -5590,10 +5340,9 @@
 
   /**
    * @brief  Converts the elements of the Q7 vector to floating-point vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[out]  *pDst is output pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[out] pDst       is output pointer
+   * @param[in]  blockSize  is the number of samples to process
    */
   void arm_q7_to_float(
   q7_t * pSrc,
@@ -5629,16 +5378,14 @@
 
    /**
    * @brief  Floating-point Inverse Park transform
-   * @param[in]       Id        input coordinate of rotor reference frame d
-   * @param[in]       Iq        input coordinate of rotor reference frame q
-   * @param[out]      *pIalpha  points to output two-phase orthogonal vector axis alpha
-   * @param[out]      *pIbeta   points to output two-phase orthogonal vector axis beta
-   * @param[in]       sinVal    sine value of rotation angle theta
-   * @param[in]       cosVal    cosine value of rotation angle theta
-   * @return none.
-   */
-
-  static __INLINE void arm_inv_park_f32(
+   * @param[in]  Id       input coordinate of rotor reference frame d
+   * @param[in]  Iq       input coordinate of rotor reference frame q
+   * @param[out] pIalpha  points to output two-phase orthogonal vector axis alpha
+   * @param[out] pIbeta   points to output two-phase orthogonal vector axis beta
+   * @param[in]  sinVal   sine value of rotation angle theta
+   * @param[in]  cosVal   cosine value of rotation angle theta
+   */
+  CMSIS_INLINE __STATIC_INLINE void arm_inv_park_f32(
   float32_t Id,
   float32_t Iq,
   float32_t * pIalpha,
@@ -5651,19 +5398,17 @@
 
     /* Calculate pIbeta using the equation, pIbeta = Id * sinVal + Iq * cosVal */
     *pIbeta = Id * sinVal + Iq * cosVal;
-
   }
 
 
   /**
-   * @brief  Inverse Park transform for	Q31 version
-   * @param[in]       Id        input coordinate of rotor reference frame d
-   * @param[in]       Iq        input coordinate of rotor reference frame q
-   * @param[out]      *pIalpha  points to output two-phase orthogonal vector axis alpha
-   * @param[out]      *pIbeta   points to output two-phase orthogonal vector axis beta
-   * @param[in]       sinVal    sine value of rotation angle theta
-   * @param[in]       cosVal    cosine value of rotation angle theta
-   * @return none.
+   * @brief  Inverse Park transform for   Q31 version
+   * @param[in]  Id       input coordinate of rotor reference frame d
+   * @param[in]  Iq       input coordinate of rotor reference frame q
+   * @param[out] pIalpha  points to output two-phase orthogonal vector axis alpha
+   * @param[out] pIbeta   points to output two-phase orthogonal vector axis beta
+   * @param[in]  sinVal   sine value of rotation angle theta
+   * @param[in]  cosVal   cosine value of rotation angle theta
    *
    * <b>Scaling and Overflow Behavior:</b>
    * \par
@@ -5671,9 +5416,7 @@
    * The accumulator maintains 1.31 format by truncating lower 31 bits of the intermediate multiplication in 2.62 format.
    * There is saturation on the addition, hence there is no risk of overflow.
    */
-
-
-  static __INLINE void arm_inv_park_q31(
+  CMSIS_INLINE __STATIC_INLINE void arm_inv_park_q31(
   q31_t Id,
   q31_t Iq,
   q31_t * pIalpha,
@@ -5702,7 +5445,6 @@
 
     /* Calculate pIbeta by using the two intermediate products 3 and 4 */
     *pIbeta = __QADD(product4, product3);
-
   }
 
   /**
@@ -5712,10 +5454,9 @@
 
   /**
    * @brief  Converts the elements of the Q31 vector to floating-point vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[out]  *pDst is output pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[out] pDst       is output pointer
+   * @param[in]  blockSize  is the number of samples to process
    */
   void arm_q31_to_float(
   q31_t * pSrc,
@@ -5765,17 +5506,15 @@
 
   /**
    * @brief  Process function for the floating-point Linear Interpolation Function.
-   * @param[in,out] *S is an instance of the floating-point Linear Interpolation structure
-   * @param[in] x input sample to process
+   * @param[in,out] S  is an instance of the floating-point Linear Interpolation structure
+   * @param[in]     x  input sample to process
    * @return y processed output sample.
    *
    */
-
-  static __INLINE float32_t arm_linear_interp_f32(
+  CMSIS_INLINE __STATIC_INLINE float32_t arm_linear_interp_f32(
   arm_linear_interp_instance_f32 * S,
   float32_t x)
   {
-
     float32_t y;
     float32_t x0, x1;                            /* Nearest input values */
     float32_t y0, y1;                            /* Nearest output values */
@@ -5786,12 +5525,12 @@
     /* Calculation of index */
     i = (int32_t) ((x - S->x1) / xSpacing);
 
-    if(i < 0)
+    if (i < 0)
     {
       /* Iniatilize output for below specified range as least output value of table */
       y = pYData[0];
     }
-    else if((uint32_t)i >= S->nValues)
+    else if ((uint32_t)i >= S->nValues)
     {
       /* Iniatilize output for above specified range as last output value of table */
       y = pYData[S->nValues - 1];
@@ -5799,7 +5538,7 @@
     else
     {
       /* Calculation of nearest input values */
-      x0 = S->x1 + i * xSpacing;
+      x0 = S->x1 +  i      * xSpacing;
       x1 = S->x1 + (i + 1) * xSpacing;
 
       /* Read of nearest output values */
@@ -5815,12 +5554,13 @@
     return (y);
   }
 
+
    /**
    *
    * @brief  Process function for the Q31 Linear Interpolation Function.
-   * @param[in] *pYData  pointer to Q31 Linear Interpolation table
-   * @param[in] x input sample to process
-   * @param[in] nValues number of table values
+   * @param[in] pYData   pointer to Q31 Linear Interpolation table
+   * @param[in] x        input sample to process
+   * @param[in] nValues  number of table values
    * @return y processed output sample.
    *
    * \par
@@ -5828,9 +5568,7 @@
    * This function can support maximum of table size 2^12.
    *
    */
-
-
-  static __INLINE q31_t arm_linear_interp_q31(
+  CMSIS_INLINE __STATIC_INLINE q31_t arm_linear_interp_q31(
   q31_t * pYData,
   q31_t x,
   uint32_t nValues)
@@ -5843,26 +5581,25 @@
     /* Input is in 12.20 format */
     /* 12 bits for the table index */
     /* Index value calculation */
-    index = ((x & 0xFFF00000) >> 20);
-
-    if(index >= (int32_t)(nValues - 1))
+    index = ((x & (q31_t)0xFFF00000) >> 20);
+
+    if (index >= (int32_t)(nValues - 1))
     {
       return (pYData[nValues - 1]);
     }
-    else if(index < 0)
+    else if (index < 0)
     {
       return (pYData[0]);
     }
     else
     {
-
       /* 20 bits for the fractional part */
       /* shift left by 11 to keep fract in 1.31 format */
       fract = (x & 0x000FFFFF) << 11;
 
       /* Read two nearest output values from the index in 1.31(q31) format */
       y0 = pYData[index];
-      y1 = pYData[index + 1u];
+      y1 = pYData[index + 1];
 
       /* Calculation of y0 * (1-fract) and y is in 2.30 format */
       y = ((q31_t) ((q63_t) y0 * (0x7FFFFFFF - fract) >> 32));
@@ -5872,17 +5609,16 @@
 
       /* Convert y to 1.31 format */
       return (y << 1u);
-
     }
-
   }
 
+
   /**
    *
    * @brief  Process function for the Q15 Linear Interpolation Function.
-   * @param[in] *pYData  pointer to Q15 Linear Interpolation table
-   * @param[in] x input sample to process
-   * @param[in] nValues number of table values
+   * @param[in] pYData   pointer to Q15 Linear Interpolation table
+   * @param[in] x        input sample to process
+   * @param[in] nValues  number of table values
    * @return y processed output sample.
    *
    * \par
@@ -5890,9 +5626,7 @@
    * This function can support maximum of table size 2^12.
    *
    */
-
-
-  static __INLINE q15_t arm_linear_interp_q15(
+  CMSIS_INLINE __STATIC_INLINE q15_t arm_linear_interp_q15(
   q15_t * pYData,
   q31_t x,
   uint32_t nValues)
@@ -5905,13 +5639,13 @@
     /* Input is in 12.20 format */
     /* 12 bits for the table index */
     /* Index value calculation */
-    index = ((x & 0xFFF00000) >> 20u);
-
-    if(index >= (int32_t)(nValues - 1))
+    index = ((x & (int32_t)0xFFF00000) >> 20);
+
+    if (index >= (int32_t)(nValues - 1))
     {
       return (pYData[nValues - 1]);
     }
-    else if(index < 0)
+    else if (index < 0)
     {
       return (pYData[0]);
     }
@@ -5923,7 +5657,7 @@
 
       /* Read two nearest output values from the index */
       y0 = pYData[index];
-      y1 = pYData[index + 1u];
+      y1 = pYData[index + 1];
 
       /* Calculation of y0 * (1-fract) and y is in 13.35 format */
       y = ((q63_t) y0 * (0xFFFFF - fract));
@@ -5932,27 +5666,24 @@
       y += ((q63_t) y1 * (fract));
 
       /* convert y to 1.15 format */
-      return (y >> 20);
+      return (q15_t) (y >> 20);
     }
-
-
   }
 
+
   /**
    *
    * @brief  Process function for the Q7 Linear Interpolation Function.
-   * @param[in] *pYData  pointer to Q7 Linear Interpolation table
-   * @param[in] x input sample to process
-   * @param[in] nValues number of table values
+   * @param[in] pYData   pointer to Q7 Linear Interpolation table
+   * @param[in] x        input sample to process
+   * @param[in] nValues  number of table values
    * @return y processed output sample.
    *
    * \par
    * Input sample <code>x</code> is in 12.20 format which contains 12 bits for table index and 20 bits for fractional part.
    * This function can support maximum of table size 2^12.
    */
-
-
-  static __INLINE q7_t arm_linear_interp_q7(
+  CMSIS_INLINE __STATIC_INLINE q7_t arm_linear_interp_q7(
   q7_t * pYData,
   q31_t x,
   uint32_t nValues)
@@ -5971,21 +5702,19 @@
     }
     index = (x >> 20) & 0xfff;
 
-
-    if(index >= (nValues - 1))
+    if (index >= (nValues - 1))
     {
       return (pYData[nValues - 1]);
     }
     else
     {
-
       /* 20 bits for the fractional part */
       /* fract is in 12.20 format */
       fract = (x & 0x000FFFFF);
 
       /* Read two nearest output values from the index and are in 1.7(q7) format */
       y0 = pYData[index];
-      y1 = pYData[index + 1u];
+      y1 = pYData[index + 1];
 
       /* Calculation of y0 * (1-fract ) and y is in 13.27(q27) format */
       y = ((y0 * (0xFFFFF - fract)));
@@ -5994,66 +5723,64 @@
       y += (y1 * fract);
 
       /* convert y to 1.7(q7) format */
-      return (y >> 20u);
-
-    }
-
+      return (q7_t) (y >> 20);
+     }
   }
+
   /**
    * @} end of LinearInterpolate group
    */
 
   /**
    * @brief  Fast approximation to the trigonometric sine function for floating-point data.
-   * @param[in] x input value in radians.
+   * @param[in] x  input value in radians.
    * @return  sin(x).
    */
-
   float32_t arm_sin_f32(
   float32_t x);
 
+
   /**
    * @brief  Fast approximation to the trigonometric sine function for Q31 data.
-   * @param[in] x Scaled input value in radians.
+   * @param[in] x  Scaled input value in radians.
    * @return  sin(x).
    */
-
   q31_t arm_sin_q31(
   q31_t x);
 
+
   /**
    * @brief  Fast approximation to the trigonometric sine function for Q15 data.
-   * @param[in] x Scaled input value in radians.
+   * @param[in] x  Scaled input value in radians.
    * @return  sin(x).
    */
-
   q15_t arm_sin_q15(
   q15_t x);
 
+
   /**
    * @brief  Fast approximation to the trigonometric cosine function for floating-point data.
-   * @param[in] x input value in radians.
+   * @param[in] x  input value in radians.
    * @return  cos(x).
    */
-
   float32_t arm_cos_f32(
   float32_t x);
 
+
   /**
    * @brief Fast approximation to the trigonometric cosine function for Q31 data.
-   * @param[in] x Scaled input value in radians.
+   * @param[in] x  Scaled input value in radians.
    * @return  cos(x).
    */
-
   q31_t arm_cos_q31(
   q31_t x);
 
+
   /**
    * @brief  Fast approximation to the trigonometric cosine function for Q15 data.
-   * @param[in] x Scaled input value in radians.
+   * @param[in] x  Scaled input value in radians.
    * @return  cos(x).
    */
-
   q15_t arm_cos_q15(
   q15_t x);
 
@@ -6091,22 +5818,26 @@
 
   /**
    * @brief  Floating-point square root function.
-   * @param[in]  in     input value.
-   * @param[out] *pOut  square root of input value.
+   * @param[in]  in    input value.
+   * @param[out] pOut  square root of input value.
    * @return The function returns ARM_MATH_SUCCESS if input value is positive value or ARM_MATH_ARGUMENT_ERROR if
    * <code>in</code> is negative value and returns zero output for negative values.
    */
-
-  static __INLINE arm_status arm_sqrt_f32(
+  CMSIS_INLINE __STATIC_INLINE arm_status arm_sqrt_f32(
   float32_t in,
   float32_t * pOut)
   {
-    if(in >= 0.0f)
+    if (in >= 0.0f)
     {
 
-//      #if __FPU_USED
-#if (__FPU_USED == 1) && defined ( __CC_ARM   )
+#if   (__FPU_USED == 1) && defined ( __CC_ARM   )
       *pOut = __sqrtf(in);
+#elif (__FPU_USED == 1) && (defined(__ARMCC_VERSION) && (__ARMCC_VERSION >= 6010050))
+      *pOut = __builtin_sqrtf(in);
+#elif (__FPU_USED == 1) && defined(__GNUC__)
+      *pOut = __builtin_sqrtf(in);
+#elif (__FPU_USED == 1) && defined ( __ICCARM__ ) && (__VER__ >= 6040000)
+      __ASM("VSQRT.F32 %0,%1" : "=t"(*pOut) : "t"(in));
 #else
       *pOut = sqrtf(in);
 #endif
@@ -6118,14 +5849,13 @@
       *pOut = 0.0f;
       return (ARM_MATH_ARGUMENT_ERROR);
     }
-
   }
 
 
   /**
    * @brief Q31 square root function.
-   * @param[in]   in    input value.  The range of the input value is [0 +1) or 0x00000000 to 0x7FFFFFFF.
-   * @param[out]  *pOut square root of input value.
+   * @param[in]  in    input value.  The range of the input value is [0 +1) or 0x00000000 to 0x7FFFFFFF.
+   * @param[out] pOut  square root of input value.
    * @return The function returns ARM_MATH_SUCCESS if input value is positive value or ARM_MATH_ARGUMENT_ERROR if
    * <code>in</code> is negative value and returns zero output for negative values.
    */
@@ -6133,10 +5863,11 @@
   q31_t in,
   q31_t * pOut);
 
+
   /**
    * @brief  Q15 square root function.
-   * @param[in]   in     input value.  The range of the input value is [0 +1) or 0x0000 to 0x7FFF.
-   * @param[out]  *pOut  square root of input value.
+   * @param[in]  in    input value.  The range of the input value is [0 +1) or 0x0000 to 0x7FFF.
+   * @param[out] pOut  square root of input value.
    * @return The function returns ARM_MATH_SUCCESS if input value is positive value or ARM_MATH_ARGUMENT_ERROR if
    * <code>in</code> is negative value and returns zero output for negative values.
    */
@@ -6149,15 +5880,10 @@
    */
 
 
-
-
-
-
   /**
    * @brief floating-point Circular write function.
    */
-
-  static __INLINE void arm_circularWrite_f32(
+  CMSIS_INLINE __STATIC_INLINE void arm_circularWrite_f32(
   int32_t * circBuffer,
   int32_t L,
   uint16_t * writeOffset,
@@ -6176,7 +5902,7 @@
     /* Loop over the blockSize */
     i = blockSize;
 
-    while(i > 0u)
+    while (i > 0u)
     {
       /* copy the input sample to the circular buffer */
       circBuffer[wOffset] = *src;
@@ -6186,7 +5912,7 @@
 
       /* Circularly update wOffset.  Watch out for positive and negative value */
       wOffset += bufferInc;
-      if(wOffset >= L)
+      if (wOffset >= L)
         wOffset -= L;
 
       /* Decrement the loop counter */
@@ -6194,7 +5920,7 @@
     }
 
     /* Update the index pointer */
-    *writeOffset = wOffset;
+    *writeOffset = (uint16_t)wOffset;
   }
 
 
@@ -6202,7 +5928,7 @@
   /**
    * @brief floating-point Circular Read function.
    */
-  static __INLINE void arm_circularRead_f32(
+  CMSIS_INLINE __STATIC_INLINE void arm_circularRead_f32(
   int32_t * circBuffer,
   int32_t L,
   int32_t * readOffset,
@@ -6224,7 +5950,7 @@
     /* Loop over the blockSize */
     i = blockSize;
 
-    while(i > 0u)
+    while (i > 0u)
     {
       /* copy the sample from the circular buffer to the destination buffer */
       *dst = circBuffer[rOffset];
@@ -6232,7 +5958,7 @@
       /* Update the input pointer */
       dst += dstInc;
 
-      if(dst == (int32_t *) dst_end)
+      if (dst == (int32_t *) dst_end)
       {
         dst = dst_base;
       }
@@ -6240,7 +5966,7 @@
       /* Circularly update rOffset.  Watch out for positive and negative value  */
       rOffset += bufferInc;
 
-      if(rOffset >= L)
+      if (rOffset >= L)
       {
         rOffset -= L;
       }
@@ -6253,11 +5979,11 @@
     *readOffset = rOffset;
   }
 
+
   /**
    * @brief Q15 Circular write function.
    */
-
-  static __INLINE void arm_circularWrite_q15(
+  CMSIS_INLINE __STATIC_INLINE void arm_circularWrite_q15(
   q15_t * circBuffer,
   int32_t L,
   uint16_t * writeOffset,
@@ -6276,7 +6002,7 @@
     /* Loop over the blockSize */
     i = blockSize;
 
-    while(i > 0u)
+    while (i > 0u)
     {
       /* copy the input sample to the circular buffer */
       circBuffer[wOffset] = *src;
@@ -6286,7 +6012,7 @@
 
       /* Circularly update wOffset.  Watch out for positive and negative value */
       wOffset += bufferInc;
-      if(wOffset >= L)
+      if (wOffset >= L)
         wOffset -= L;
 
       /* Decrement the loop counter */
@@ -6294,15 +6020,14 @@
     }
 
     /* Update the index pointer */
-    *writeOffset = wOffset;
+    *writeOffset = (uint16_t)wOffset;
   }
 
 
-
   /**
    * @brief Q15 Circular Read function.
    */
-  static __INLINE void arm_circularRead_q15(
+  CMSIS_INLINE __STATIC_INLINE void arm_circularRead_q15(
   q15_t * circBuffer,
   int32_t L,
   int32_t * readOffset,
@@ -6325,7 +6050,7 @@
     /* Loop over the blockSize */
     i = blockSize;
 
-    while(i > 0u)
+    while (i > 0u)
     {
       /* copy the sample from the circular buffer to the destination buffer */
       *dst = circBuffer[rOffset];
@@ -6333,7 +6058,7 @@
       /* Update the input pointer */
       dst += dstInc;
 
-      if(dst == (q15_t *) dst_end)
+      if (dst == (q15_t *) dst_end)
       {
         dst = dst_base;
       }
@@ -6341,7 +6066,7 @@
       /* Circularly update wOffset.  Watch out for positive and negative value */
       rOffset += bufferInc;
 
-      if(rOffset >= L)
+      if (rOffset >= L)
       {
         rOffset -= L;
       }
@@ -6358,8 +6083,7 @@
   /**
    * @brief Q7 Circular write function.
    */
-
-  static __INLINE void arm_circularWrite_q7(
+  CMSIS_INLINE __STATIC_INLINE void arm_circularWrite_q7(
   q7_t * circBuffer,
   int32_t L,
   uint16_t * writeOffset,
@@ -6378,7 +6102,7 @@
     /* Loop over the blockSize */
     i = blockSize;
 
-    while(i > 0u)
+    while (i > 0u)
     {
       /* copy the input sample to the circular buffer */
       circBuffer[wOffset] = *src;
@@ -6388,7 +6112,7 @@
 
       /* Circularly update wOffset.  Watch out for positive and negative value */
       wOffset += bufferInc;
-      if(wOffset >= L)
+      if (wOffset >= L)
         wOffset -= L;
 
       /* Decrement the loop counter */
@@ -6396,15 +6120,14 @@
     }
 
     /* Update the index pointer */
-    *writeOffset = wOffset;
+    *writeOffset = (uint16_t)wOffset;
   }
 
 
-
   /**
    * @brief Q7 Circular Read function.
    */
-  static __INLINE void arm_circularRead_q7(
+  CMSIS_INLINE __STATIC_INLINE void arm_circularRead_q7(
   q7_t * circBuffer,
   int32_t L,
   int32_t * readOffset,
@@ -6427,7 +6150,7 @@
     /* Loop over the blockSize */
     i = blockSize;
 
-    while(i > 0u)
+    while (i > 0u)
     {
       /* copy the sample from the circular buffer to the destination buffer */
       *dst = circBuffer[rOffset];
@@ -6435,7 +6158,7 @@
       /* Update the input pointer */
       dst += dstInc;
 
-      if(dst == (q7_t *) dst_end)
+      if (dst == (q7_t *) dst_end)
       {
         dst = dst_base;
       }
@@ -6443,7 +6166,7 @@
       /* Circularly update rOffset.  Watch out for positive and negative value */
       rOffset += bufferInc;
 
-      if(rOffset >= L)
+      if (rOffset >= L)
       {
         rOffset -= L;
       }
@@ -6459,271 +6182,252 @@
 
   /**
    * @brief  Sum of the squares of the elements of a Q31 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_power_q31(
   q31_t * pSrc,
   uint32_t blockSize,
   q63_t * pResult);
 
+
   /**
    * @brief  Sum of the squares of the elements of a floating-point vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_power_f32(
   float32_t * pSrc,
   uint32_t blockSize,
   float32_t * pResult);
 
+
   /**
    * @brief  Sum of the squares of the elements of a Q15 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_power_q15(
   q15_t * pSrc,
   uint32_t blockSize,
   q63_t * pResult);
 
+
   /**
    * @brief  Sum of the squares of the elements of a Q7 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_power_q7(
   q7_t * pSrc,
   uint32_t blockSize,
   q31_t * pResult);
 
+
   /**
    * @brief  Mean value of a Q7 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_mean_q7(
   q7_t * pSrc,
   uint32_t blockSize,
   q7_t * pResult);
 
+
   /**
    * @brief  Mean value of a Q15 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
    */
   void arm_mean_q15(
   q15_t * pSrc,
   uint32_t blockSize,
   q15_t * pResult);
 
+
   /**
    * @brief  Mean value of a Q31 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
    */
   void arm_mean_q31(
   q31_t * pSrc,
   uint32_t blockSize,
   q31_t * pResult);
 
+
   /**
    * @brief  Mean value of a floating-point vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
    */
   void arm_mean_f32(
   float32_t * pSrc,
   uint32_t blockSize,
   float32_t * pResult);
 
+
   /**
    * @brief  Variance of the elements of a floating-point vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_var_f32(
   float32_t * pSrc,
   uint32_t blockSize,
   float32_t * pResult);
 
+
   /**
    * @brief  Variance of the elements of a Q31 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_var_q31(
   q31_t * pSrc,
   uint32_t blockSize,
   q31_t * pResult);
 
+
   /**
    * @brief  Variance of the elements of a Q15 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_var_q15(
   q15_t * pSrc,
   uint32_t blockSize,
   q15_t * pResult);
 
+
   /**
    * @brief  Root Mean Square of the elements of a floating-point vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_rms_f32(
   float32_t * pSrc,
   uint32_t blockSize,
   float32_t * pResult);
 
+
   /**
    * @brief  Root Mean Square of the elements of a Q31 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_rms_q31(
   q31_t * pSrc,
   uint32_t blockSize,
   q31_t * pResult);
 
+
   /**
    * @brief  Root Mean Square of the elements of a Q15 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_rms_q15(
   q15_t * pSrc,
   uint32_t blockSize,
   q15_t * pResult);
 
+
   /**
    * @brief  Standard deviation of the elements of a floating-point vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_std_f32(
   float32_t * pSrc,
   uint32_t blockSize,
   float32_t * pResult);
 
+
   /**
    * @brief  Standard deviation of the elements of a Q31 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_std_q31(
   q31_t * pSrc,
   uint32_t blockSize,
   q31_t * pResult);
 
+
   /**
    * @brief  Standard deviation of the elements of a Q15 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output value.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output value.
+   */
   void arm_std_q15(
   q15_t * pSrc,
   uint32_t blockSize,
   q15_t * pResult);
 
+
   /**
    * @brief  Floating-point complex magnitude
-   * @param[in]  *pSrc points to the complex input vector
-   * @param[out]  *pDst points to the real output vector
-   * @param[in]  numSamples number of complex samples in the input vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the complex input vector
+   * @param[out] pDst        points to the real output vector
+   * @param[in]  numSamples  number of complex samples in the input vector
+   */
   void arm_cmplx_mag_f32(
   float32_t * pSrc,
   float32_t * pDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Q31 complex magnitude
-   * @param[in]  *pSrc points to the complex input vector
-   * @param[out]  *pDst points to the real output vector
-   * @param[in]  numSamples number of complex samples in the input vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the complex input vector
+   * @param[out] pDst        points to the real output vector
+   * @param[in]  numSamples  number of complex samples in the input vector
+   */
   void arm_cmplx_mag_q31(
   q31_t * pSrc,
   q31_t * pDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Q15 complex magnitude
-   * @param[in]  *pSrc points to the complex input vector
-   * @param[out]  *pDst points to the real output vector
-   * @param[in]  numSamples number of complex samples in the input vector
-   * @return none.
-   */
-
+   * @param[in]  pSrc        points to the complex input vector
+   * @param[out] pDst        points to the real output vector
+   * @param[in]  numSamples  number of complex samples in the input vector
+   */
   void arm_cmplx_mag_q15(
   q15_t * pSrc,
   q15_t * pDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Q15 complex dot product
-   * @param[in]  *pSrcA points to the first input vector
-   * @param[in]  *pSrcB points to the second input vector
-   * @param[in]  numSamples number of complex samples in each vector
-   * @param[out]  *realResult real part of the result returned here
-   * @param[out]  *imagResult imaginary part of the result returned here
-   * @return none.
-   */
-
+   * @param[in]  pSrcA       points to the first input vector
+   * @param[in]  pSrcB       points to the second input vector
+   * @param[in]  numSamples  number of complex samples in each vector
+   * @param[out] realResult  real part of the result returned here
+   * @param[out] imagResult  imaginary part of the result returned here
+   */
   void arm_cmplx_dot_prod_q15(
   q15_t * pSrcA,
   q15_t * pSrcB,
@@ -6731,16 +6435,15 @@
   q31_t * realResult,
   q31_t * imagResult);
 
+
   /**
    * @brief  Q31 complex dot product
-   * @param[in]  *pSrcA points to the first input vector
-   * @param[in]  *pSrcB points to the second input vector
-   * @param[in]  numSamples number of complex samples in each vector
-   * @param[out]  *realResult real part of the result returned here
-   * @param[out]  *imagResult imaginary part of the result returned here
-   * @return none.
-   */
-
+   * @param[in]  pSrcA       points to the first input vector
+   * @param[in]  pSrcB       points to the second input vector
+   * @param[in]  numSamples  number of complex samples in each vector
+   * @param[out] realResult  real part of the result returned here
+   * @param[out] imagResult  imaginary part of the result returned here
+   */
   void arm_cmplx_dot_prod_q31(
   q31_t * pSrcA,
   q31_t * pSrcB,
@@ -6748,16 +6451,15 @@
   q63_t * realResult,
   q63_t * imagResult);
 
+
   /**
    * @brief  Floating-point complex dot product
-   * @param[in]  *pSrcA points to the first input vector
-   * @param[in]  *pSrcB points to the second input vector
-   * @param[in]  numSamples number of complex samples in each vector
-   * @param[out]  *realResult real part of the result returned here
-   * @param[out]  *imagResult imaginary part of the result returned here
-   * @return none.
-   */
-
+   * @param[in]  pSrcA       points to the first input vector
+   * @param[in]  pSrcB       points to the second input vector
+   * @param[in]  numSamples  number of complex samples in each vector
+   * @param[out] realResult  real part of the result returned here
+   * @param[out] imagResult  imaginary part of the result returned here
+   */
   void arm_cmplx_dot_prod_f32(
   float32_t * pSrcA,
   float32_t * pSrcB,
@@ -6765,88 +6467,83 @@
   float32_t * realResult,
   float32_t * imagResult);
 
+
   /**
    * @brief  Q15 complex-by-real multiplication
-   * @param[in]  *pSrcCmplx points to the complex input vector
-   * @param[in]  *pSrcReal points to the real input vector
-   * @param[out]  *pCmplxDst points to the complex output vector
-   * @param[in]  numSamples number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcCmplx   points to the complex input vector
+   * @param[in]  pSrcReal    points to the real input vector
+   * @param[out] pCmplxDst   points to the complex output vector
+   * @param[in]  numSamples  number of samples in each vector
+   */
   void arm_cmplx_mult_real_q15(
   q15_t * pSrcCmplx,
   q15_t * pSrcReal,
   q15_t * pCmplxDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Q31 complex-by-real multiplication
-   * @param[in]  *pSrcCmplx points to the complex input vector
-   * @param[in]  *pSrcReal points to the real input vector
-   * @param[out]  *pCmplxDst points to the complex output vector
-   * @param[in]  numSamples number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcCmplx   points to the complex input vector
+   * @param[in]  pSrcReal    points to the real input vector
+   * @param[out] pCmplxDst   points to the complex output vector
+   * @param[in]  numSamples  number of samples in each vector
+   */
   void arm_cmplx_mult_real_q31(
   q31_t * pSrcCmplx,
   q31_t * pSrcReal,
   q31_t * pCmplxDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Floating-point complex-by-real multiplication
-   * @param[in]  *pSrcCmplx points to the complex input vector
-   * @param[in]  *pSrcReal points to the real input vector
-   * @param[out]  *pCmplxDst points to the complex output vector
-   * @param[in]  numSamples number of samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcCmplx   points to the complex input vector
+   * @param[in]  pSrcReal    points to the real input vector
+   * @param[out] pCmplxDst   points to the complex output vector
+   * @param[in]  numSamples  number of samples in each vector
+   */
   void arm_cmplx_mult_real_f32(
   float32_t * pSrcCmplx,
   float32_t * pSrcReal,
   float32_t * pCmplxDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Minimum value of a Q7 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *result is output pointer
-   * @param[in]  index is the array index of the minimum value in the input buffer.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] result     is output pointer
+   * @param[in]  index      is the array index of the minimum value in the input buffer.
+   */
   void arm_min_q7(
   q7_t * pSrc,
   uint32_t blockSize,
   q7_t * result,
   uint32_t * index);
 
+
   /**
    * @brief  Minimum value of a Q15 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output pointer
-   * @param[in]  *pIndex is the array index of the minimum value in the input buffer.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output pointer
+   * @param[in]  pIndex     is the array index of the minimum value in the input buffer.
+   */
   void arm_min_q15(
   q15_t * pSrc,
   uint32_t blockSize,
   q15_t * pResult,
   uint32_t * pIndex);
 
+
   /**
    * @brief  Minimum value of a Q31 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output pointer
-   * @param[out]  *pIndex is the array index of the minimum value in the input buffer.
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output pointer
+   * @param[out] pIndex     is the array index of the minimum value in the input buffer.
    */
   void arm_min_q31(
   q31_t * pSrc,
@@ -6854,156 +6551,148 @@
   q31_t * pResult,
   uint32_t * pIndex);
 
+
   /**
    * @brief  Minimum value of a floating-point vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @param[out]  *pResult is output pointer
-   * @param[out]  *pIndex is the array index of the minimum value in the input buffer.
-   * @return none.
-   */
-
+   * @param[in]  pSrc       is input pointer
+   * @param[in]  blockSize  is the number of samples to process
+   * @param[out] pResult    is output pointer
+   * @param[out] pIndex     is the array index of the minimum value in the input buffer.
+   */
   void arm_min_f32(
   float32_t * pSrc,
   uint32_t blockSize,
   float32_t * pResult,
   uint32_t * pIndex);
 
+
 /**
  * @brief Maximum value of a Q7 vector.
- * @param[in]       *pSrc points to the input buffer
- * @param[in]       blockSize length of the input vector
- * @param[out]      *pResult maximum value returned here
- * @param[out]      *pIndex index of maximum value returned here
- * @return none.
+ * @param[in]  pSrc       points to the input buffer
+ * @param[in]  blockSize  length of the input vector
+ * @param[out] pResult    maximum value returned here
+ * @param[out] pIndex     index of maximum value returned here
  */
-
   void arm_max_q7(
   q7_t * pSrc,
   uint32_t blockSize,
   q7_t * pResult,
   uint32_t * pIndex);
 
+
 /**
  * @brief Maximum value of a Q15 vector.
- * @param[in]       *pSrc points to the input buffer
- * @param[in]       blockSize length of the input vector
- * @param[out]      *pResult maximum value returned here
- * @param[out]      *pIndex index of maximum value returned here
- * @return none.
+ * @param[in]  pSrc       points to the input buffer
+ * @param[in]  blockSize  length of the input vector
+ * @param[out] pResult    maximum value returned here
+ * @param[out] pIndex     index of maximum value returned here
  */
-
   void arm_max_q15(
   q15_t * pSrc,
   uint32_t blockSize,
   q15_t * pResult,
   uint32_t * pIndex);
 
+
 /**
  * @brief Maximum value of a Q31 vector.
- * @param[in]       *pSrc points to the input buffer
- * @param[in]       blockSize length of the input vector
- * @param[out]      *pResult maximum value returned here
- * @param[out]      *pIndex index of maximum value returned here
- * @return none.
+ * @param[in]  pSrc       points to the input buffer
+ * @param[in]  blockSize  length of the input vector
+ * @param[out] pResult    maximum value returned here
+ * @param[out] pIndex     index of maximum value returned here
  */
-
   void arm_max_q31(
   q31_t * pSrc,
   uint32_t blockSize,
   q31_t * pResult,
   uint32_t * pIndex);
 
+
 /**
  * @brief Maximum value of a floating-point vector.
- * @param[in]       *pSrc points to the input buffer
- * @param[in]       blockSize length of the input vector
- * @param[out]      *pResult maximum value returned here
- * @param[out]      *pIndex index of maximum value returned here
- * @return none.
+ * @param[in]  pSrc       points to the input buffer
+ * @param[in]  blockSize  length of the input vector
+ * @param[out] pResult    maximum value returned here
+ * @param[out] pIndex     index of maximum value returned here
  */
-
   void arm_max_f32(
   float32_t * pSrc,
   uint32_t blockSize,
   float32_t * pResult,
   uint32_t * pIndex);
 
+
   /**
    * @brief  Q15 complex-by-complex multiplication
-   * @param[in]  *pSrcA points to the first input vector
-   * @param[in]  *pSrcB points to the second input vector
-   * @param[out]  *pDst  points to the output vector
-   * @param[in]  numSamples number of complex samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA       points to the first input vector
+   * @param[in]  pSrcB       points to the second input vector
+   * @param[out] pDst        points to the output vector
+   * @param[in]  numSamples  number of complex samples in each vector
+   */
   void arm_cmplx_mult_cmplx_q15(
   q15_t * pSrcA,
   q15_t * pSrcB,
   q15_t * pDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Q31 complex-by-complex multiplication
-   * @param[in]  *pSrcA points to the first input vector
-   * @param[in]  *pSrcB points to the second input vector
-   * @param[out]  *pDst  points to the output vector
-   * @param[in]  numSamples number of complex samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA       points to the first input vector
+   * @param[in]  pSrcB       points to the second input vector
+   * @param[out] pDst        points to the output vector
+   * @param[in]  numSamples  number of complex samples in each vector
+   */
   void arm_cmplx_mult_cmplx_q31(
   q31_t * pSrcA,
   q31_t * pSrcB,
   q31_t * pDst,
   uint32_t numSamples);
 
+
   /**
    * @brief  Floating-point complex-by-complex multiplication
-   * @param[in]  *pSrcA points to the first input vector
-   * @param[in]  *pSrcB points to the second input vector
-   * @param[out]  *pDst  points to the output vector
-   * @param[in]  numSamples number of complex samples in each vector
-   * @return none.
-   */
-
+   * @param[in]  pSrcA       points to the first input vector
+   * @param[in]  pSrcB       points to the second input vector
+   * @param[out] pDst        points to the output vector
+   * @param[in]  numSamples  number of complex samples in each vector
+   */
   void arm_cmplx_mult_cmplx_f32(
   float32_t * pSrcA,
   float32_t * pSrcB,
   float32_t * pDst,
   uint32_t numSamples);
 
+
   /**
    * @brief Converts the elements of the floating-point vector to Q31 vector.
-   * @param[in]       *pSrc points to the floating-point input vector
-   * @param[out]      *pDst points to the Q31 output vector
-   * @param[in]       blockSize length of the input vector
-   * @return none.
+   * @param[in]  pSrc       points to the floating-point input vector
+   * @param[out] pDst       points to the Q31 output vector
+   * @param[in]  blockSize  length of the input vector
    */
   void arm_float_to_q31(
   float32_t * pSrc,
   q31_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Converts the elements of the floating-point vector to Q15 vector.
-   * @param[in]       *pSrc points to the floating-point input vector
-   * @param[out]      *pDst points to the Q15 output vector
-   * @param[in]       blockSize length of the input vector
-   * @return          none
+   * @param[in]  pSrc       points to the floating-point input vector
+   * @param[out] pDst       points to the Q15 output vector
+   * @param[in]  blockSize  length of the input vector
    */
   void arm_float_to_q15(
   float32_t * pSrc,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief Converts the elements of the floating-point vector to Q7 vector.
-   * @param[in]       *pSrc points to the floating-point input vector
-   * @param[out]      *pDst points to the Q7 output vector
-   * @param[in]       blockSize length of the input vector
-   * @return          none
+   * @param[in]  pSrc       points to the floating-point input vector
+   * @param[out] pDst       points to the Q7 output vector
+   * @param[in]  blockSize  length of the input vector
    */
   void arm_float_to_q7(
   float32_t * pSrc,
@@ -7013,34 +6702,33 @@
 
   /**
    * @brief  Converts the elements of the Q31 vector to Q15 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[out]  *pDst is output pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[out] pDst       is output pointer
+   * @param[in]  blockSize  is the number of samples to process
    */
   void arm_q31_to_q15(
   q31_t * pSrc,
   q15_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Converts the elements of the Q31 vector to Q7 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[out]  *pDst is output pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[out] pDst       is output pointer
+   * @param[in]  blockSize  is the number of samples to process
    */
   void arm_q31_to_q7(
   q31_t * pSrc,
   q7_t * pDst,
   uint32_t blockSize);
 
+
   /**
    * @brief  Converts the elements of the Q15 vector to floating-point vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[out]  *pDst is output pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[out] pDst       is output pointer
+   * @param[in]  blockSize  is the number of samples to process
    */
   void arm_q15_to_float(
   q15_t * pSrc,
@@ -7050,10 +6738,9 @@
 
   /**
    * @brief  Converts the elements of the Q15 vector to Q31 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[out]  *pDst is output pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[out] pDst       is output pointer
+   * @param[in]  blockSize  is the number of samples to process
    */
   void arm_q15_to_q31(
   q15_t * pSrc,
@@ -7063,10 +6750,9 @@
 
   /**
    * @brief  Converts the elements of the Q15 vector to Q7 vector.
-   * @param[in]  *pSrc is input pointer
-   * @param[out]  *pDst is output pointer
-   * @param[in]  blockSize is the number of samples to process
-   * @return none.
+   * @param[in]  pSrc       is input pointer
+   * @param[out] pDst       is output pointer
+   * @param[in]  blockSize  is the number of samples to process
    */
   void arm_q15_to_q7(
   q15_t * pSrc,
@@ -7135,17 +6821,16 @@
    * @{
    */
 
+
   /**
   *
   * @brief  Floating-point bilinear interpolation.
-  * @param[in,out] *S points to an instance of the interpolation structure.
-  * @param[in] X interpolation coordinate.
-  * @param[in] Y interpolation coordinate.
+  * @param[in,out] S  points to an instance of the interpolation structure.
+  * @param[in]     X  interpolation coordinate.
+  * @param[in]     Y  interpolation coordinate.
   * @return out interpolated value.
   */
-
-
-  static __INLINE float32_t arm_bilinear_interp_f32(
+  CMSIS_INLINE __STATIC_INLINE float32_t arm_bilinear_interp_f32(
   const arm_bilinear_interp_instance_f32 * S,
   float32_t X,
   float32_t Y)
@@ -7162,8 +6847,7 @@
 
     /* Care taken for table outside boundary */
     /* Returns zero output when values are outside table boundary */
-    if(xIndex < 0 || xIndex > (S->numRows - 1) || yIndex < 0
-       || yIndex > (S->numCols - 1))
+    if (xIndex < 0 || xIndex > (S->numRows - 1) || yIndex < 0 || yIndex > (S->numCols - 1))
     {
       return (0);
     }
@@ -7201,19 +6885,18 @@
 
     /* return to application */
     return (out);
-
   }
 
+
   /**
   *
   * @brief  Q31 bilinear interpolation.
-  * @param[in,out] *S points to an instance of the interpolation structure.
-  * @param[in] X interpolation coordinate in 12.20 format.
-  * @param[in] Y interpolation coordinate in 12.20 format.
+  * @param[in,out] S  points to an instance of the interpolation structure.
+  * @param[in]     X  interpolation coordinate in 12.20 format.
+  * @param[in]     Y  interpolation coordinate in 12.20 format.
   * @return out interpolated value.
   */
-
-  static __INLINE q31_t arm_bilinear_interp_q31(
+  CMSIS_INLINE __STATIC_INLINE q31_t arm_bilinear_interp_q31(
   arm_bilinear_interp_instance_q31 * S,
   q31_t X,
   q31_t Y)
@@ -7226,20 +6909,19 @@
     q31_t *pYData = S->pData;                    /* pointer to output table values */
     uint32_t nCols = S->numCols;                 /* num of rows */
 
+    /* Input is in 12.20 format */
+    /* 12 bits for the table index */
+    /* Index value calculation */
+    rI = ((X & (q31_t)0xFFF00000) >> 20);
 
     /* Input is in 12.20 format */
     /* 12 bits for the table index */
     /* Index value calculation */
-    rI = ((X & 0xFFF00000) >> 20u);
-
-    /* Input is in 12.20 format */
-    /* 12 bits for the table index */
-    /* Index value calculation */
-    cI = ((Y & 0xFFF00000) >> 20u);
+    cI = ((Y & (q31_t)0xFFF00000) >> 20);
 
     /* Care taken for table outside boundary */
     /* Returns zero output when values are outside table boundary */
-    if(rI < 0 || rI > (S->numRows - 1) || cI < 0 || cI > (S->numCols - 1))
+    if (rI < 0 || rI > (S->numRows - 1) || cI < 0 || cI > (S->numCols - 1))
     {
       return (0);
     }
@@ -7249,19 +6931,19 @@
     xfract = (X & 0x000FFFFF) << 11u;
 
     /* Read two nearest output values from the index */
-    x1 = pYData[(rI) + nCols * (cI)];
-    x2 = pYData[(rI) + nCols * (cI) + 1u];
+    x1 = pYData[(rI) + (int32_t)nCols * (cI)    ];
+    x2 = pYData[(rI) + (int32_t)nCols * (cI) + 1];
 
     /* 20 bits for the fractional part */
     /* shift left yfract by 11 to keep 1.31 format */
     yfract = (Y & 0x000FFFFF) << 11u;
 
     /* Read two nearest output values from the index */
-    y1 = pYData[(rI) + nCols * (cI + 1)];
-    y2 = pYData[(rI) + nCols * (cI + 1) + 1u];
+    y1 = pYData[(rI) + (int32_t)nCols * (cI + 1)    ];
+    y2 = pYData[(rI) + (int32_t)nCols * (cI + 1) + 1];
 
     /* Calculation of x1 * (1-xfract ) * (1-yfract) and acc is in 3.29(q29) format */
-    out = ((q31_t) (((q63_t) x1 * (0x7FFFFFFF - xfract)) >> 32));
+    out = ((q31_t) (((q63_t) x1  * (0x7FFFFFFF - xfract)) >> 32));
     acc = ((q31_t) (((q63_t) out * (0x7FFFFFFF - yfract)) >> 32));
 
     /* x2 * (xfract) * (1-yfract)  in 3.29(q29) and adding to acc */
@@ -7277,19 +6959,18 @@
     acc += ((q31_t) ((q63_t) out * (yfract) >> 32));
 
     /* Convert acc to 1.31(q31) format */
-    return (acc << 2u);
-
+    return ((q31_t)(acc << 2));
   }
 
+
   /**
   * @brief  Q15 bilinear interpolation.
-  * @param[in,out] *S points to an instance of the interpolation structure.
-  * @param[in] X interpolation coordinate in 12.20 format.
-  * @param[in] Y interpolation coordinate in 12.20 format.
+  * @param[in,out] S  points to an instance of the interpolation structure.
+  * @param[in]     X  interpolation coordinate in 12.20 format.
+  * @param[in]     Y  interpolation coordinate in 12.20 format.
   * @return out interpolated value.
   */
-
-  static __INLINE q15_t arm_bilinear_interp_q15(
+  CMSIS_INLINE __STATIC_INLINE q15_t arm_bilinear_interp_q15(
   arm_bilinear_interp_instance_q15 * S,
   q31_t X,
   q31_t Y)
@@ -7305,16 +6986,16 @@
     /* Input is in 12.20 format */
     /* 12 bits for the table index */
     /* Index value calculation */
-    rI = ((X & 0xFFF00000) >> 20);
+    rI = ((X & (q31_t)0xFFF00000) >> 20);
 
     /* Input is in 12.20 format */
     /* 12 bits for the table index */
     /* Index value calculation */
-    cI = ((Y & 0xFFF00000) >> 20);
+    cI = ((Y & (q31_t)0xFFF00000) >> 20);
 
     /* Care taken for table outside boundary */
     /* Returns zero output when values are outside table boundary */
-    if(rI < 0 || rI > (S->numRows - 1) || cI < 0 || cI > (S->numCols - 1))
+    if (rI < 0 || rI > (S->numRows - 1) || cI < 0 || cI > (S->numCols - 1))
     {
       return (0);
     }
@@ -7324,17 +7005,16 @@
     xfract = (X & 0x000FFFFF);
 
     /* Read two nearest output values from the index */
-    x1 = pYData[(rI) + nCols * (cI)];
-    x2 = pYData[(rI) + nCols * (cI) + 1u];
-
+    x1 = pYData[((uint32_t)rI) + nCols * ((uint32_t)cI)    ];
+    x2 = pYData[((uint32_t)rI) + nCols * ((uint32_t)cI) + 1];
 
     /* 20 bits for the fractional part */
     /* yfract should be in 12.20 format */
     yfract = (Y & 0x000FFFFF);
 
     /* Read two nearest output values from the index */
-    y1 = pYData[(rI) + nCols * (cI + 1)];
-    y2 = pYData[(rI) + nCols * (cI + 1) + 1u];
+    y1 = pYData[((uint32_t)rI) + nCols * ((uint32_t)cI + 1)    ];
+    y2 = pYData[((uint32_t)rI) + nCols * ((uint32_t)cI + 1) + 1];
 
     /* Calculation of x1 * (1-xfract ) * (1-yfract) and acc is in 13.51 format */
 
@@ -7357,19 +7037,18 @@
 
     /* acc is in 13.51 format and down shift acc by 36 times */
     /* Convert out to 1.15 format */
-    return (acc >> 36);
-
+    return ((q15_t)(acc >> 36));
   }
 
+
   /**
   * @brief  Q7 bilinear interpolation.
-  * @param[in,out] *S points to an instance of the interpolation structure.
-  * @param[in] X interpolation coordinate in 12.20 format.
-  * @param[in] Y interpolation coordinate in 12.20 format.
+  * @param[in,out] S  points to an instance of the interpolation structure.
+  * @param[in]     X  interpolation coordinate in 12.20 format.
+  * @param[in]     Y  interpolation coordinate in 12.20 format.
   * @return out interpolated value.
   */
-
-  static __INLINE q7_t arm_bilinear_interp_q7(
+  CMSIS_INLINE __STATIC_INLINE q7_t arm_bilinear_interp_q7(
   arm_bilinear_interp_instance_q7 * S,
   q31_t X,
   q31_t Y)
@@ -7385,36 +7064,35 @@
     /* Input is in 12.20 format */
     /* 12 bits for the table index */
     /* Index value calculation */
-    rI = ((X & 0xFFF00000) >> 20);
+    rI = ((X & (q31_t)0xFFF00000) >> 20);
 
     /* Input is in 12.20 format */
     /* 12 bits for the table index */
     /* Index value calculation */
-    cI = ((Y & 0xFFF00000) >> 20);
+    cI = ((Y & (q31_t)0xFFF00000) >> 20);
 
     /* Care taken for table outside boundary */
     /* Returns zero output when values are outside table boundary */
-    if(rI < 0 || rI > (S->numRows - 1) || cI < 0 || cI > (S->numCols - 1))
+    if (rI < 0 || rI > (S->numRows - 1) || cI < 0 || cI > (S->numCols - 1))
     {
       return (0);
     }
 
     /* 20 bits for the fractional part */
     /* xfract should be in 12.20 format */
-    xfract = (X & 0x000FFFFF);
+    xfract = (X & (q31_t)0x000FFFFF);
 
     /* Read two nearest output values from the index */
-    x1 = pYData[(rI) + nCols * (cI)];
-    x2 = pYData[(rI) + nCols * (cI) + 1u];
-
+    x1 = pYData[((uint32_t)rI) + nCols * ((uint32_t)cI)    ];
+    x2 = pYData[((uint32_t)rI) + nCols * ((uint32_t)cI) + 1];
 
     /* 20 bits for the fractional part */
     /* yfract should be in 12.20 format */
-    yfract = (Y & 0x000FFFFF);
+    yfract = (Y & (q31_t)0x000FFFFF);
 
     /* Read two nearest output values from the index */
-    y1 = pYData[(rI) + nCols * (cI + 1)];
-    y2 = pYData[(rI) + nCols * (cI + 1) + 1u];
+    y1 = pYData[((uint32_t)rI) + nCols * ((uint32_t)cI + 1)    ];
+    y2 = pYData[((uint32_t)rI) + nCols * ((uint32_t)cI + 1) + 1];
 
     /* Calculation of x1 * (1-xfract ) * (1-yfract) and acc is in 16.47 format */
     out = ((x1 * (0xFFFFF - xfract)));
@@ -7433,120 +7111,143 @@
     acc += (((q63_t) out * (xfract)));
 
     /* acc in 16.47 format and down shift by 40 to convert to 1.7 format */
-    return (acc >> 40);
-
+    return ((q7_t)(acc >> 40));
   }
 
   /**
    * @} end of BilinearInterpolate group
    */
-   
-
-//SMMLAR
+
+
+/* SMMLAR */
 #define multAcc_32x32_keep32_R(a, x, y) \
     a = (q31_t) (((((q63_t) a) << 32) + ((q63_t) x * y) + 0x80000000LL ) >> 32)
 
-//SMMLSR
+/* SMMLSR */
 #define multSub_32x32_keep32_R(a, x, y) \
     a = (q31_t) (((((q63_t) a) << 32) - ((q63_t) x * y) + 0x80000000LL ) >> 32)
 
-//SMMULR
+/* SMMULR */
 #define mult_32x32_keep32_R(a, x, y) \
     a = (q31_t) (((q63_t) x * y + 0x80000000LL ) >> 32)
 
-//SMMLA
+/* SMMLA */
 #define multAcc_32x32_keep32(a, x, y) \
     a += (q31_t) (((q63_t) x * y) >> 32)
 
-//SMMLS
+/* SMMLS */
 #define multSub_32x32_keep32(a, x, y) \
     a -= (q31_t) (((q63_t) x * y) >> 32)
 
-//SMMUL
+/* SMMUL */
 #define mult_32x32_keep32(a, x, y) \
     a = (q31_t) (((q63_t) x * y ) >> 32)
 
 
-#if defined ( __CC_ARM ) //Keil
-
-//Enter low optimization region - place directly above function definition
-    #ifdef ARM_MATH_CM4
-      #define LOW_OPTIMIZATION_ENTER \
-         _Pragma ("push")         \
-         _Pragma ("O1")
-    #else
-      #define LOW_OPTIMIZATION_ENTER 
-    #endif
-
-//Exit low optimization region - place directly after end of function definition
-    #ifdef ARM_MATH_CM4
-      #define LOW_OPTIMIZATION_EXIT \
-         _Pragma ("pop")
-    #else
-      #define LOW_OPTIMIZATION_EXIT  
-    #endif
-
-//Enter low optimization region - place directly above function definition
+#if   defined ( __CC_ARM )
+  /* Enter low optimization region - place directly above function definition */
+  #if defined( ARM_MATH_CM4 ) || defined( ARM_MATH_CM7)
+    #define LOW_OPTIMIZATION_ENTER \
+       _Pragma ("push")         \
+       _Pragma ("O1")
+  #else
+    #define LOW_OPTIMIZATION_ENTER
+  #endif
+
+  /* Exit low optimization region - place directly after end of function definition */
+  #if defined ( ARM_MATH_CM4 ) || defined ( ARM_MATH_CM7 )
+    #define LOW_OPTIMIZATION_EXIT \
+       _Pragma ("pop")
+  #else
+    #define LOW_OPTIMIZATION_EXIT
+  #endif
+
+  /* Enter low optimization region - place directly above function definition */
   #define IAR_ONLY_LOW_OPTIMIZATION_ENTER
 
-//Exit low optimization region - place directly after end of function definition
+  /* Exit low optimization region - place directly after end of function definition */
+  #define IAR_ONLY_LOW_OPTIMIZATION_EXIT
+
+#elif defined (__ARMCC_VERSION ) && ( __ARMCC_VERSION >= 6010050 )
+  #define LOW_OPTIMIZATION_ENTER
+  #define LOW_OPTIMIZATION_EXIT
+  #define IAR_ONLY_LOW_OPTIMIZATION_ENTER
+  #define IAR_ONLY_LOW_OPTIMIZATION_EXIT
+
+#elif defined ( __GNUC__ )
+  #define LOW_OPTIMIZATION_ENTER \
+       __attribute__(( optimize("-O1") ))
+  #define LOW_OPTIMIZATION_EXIT
+  #define IAR_ONLY_LOW_OPTIMIZATION_ENTER
   #define IAR_ONLY_LOW_OPTIMIZATION_EXIT
 
-#elif defined(__ICCARM__) //IAR
-
-//Enter low optimization region - place directly above function definition
-    #ifdef ARM_MATH_CM4
-      #define LOW_OPTIMIZATION_ENTER \
-         _Pragma ("optimize=low")
-    #else
-      #define LOW_OPTIMIZATION_ENTER   
-    #endif
-
-//Exit low optimization region - place directly after end of function definition
+#elif defined ( __ICCARM__ )
+  /* Enter low optimization region - place directly above function definition */
+  #if defined ( ARM_MATH_CM4 ) || defined ( ARM_MATH_CM7 )
+    #define LOW_OPTIMIZATION_ENTER \
+       _Pragma ("optimize=low")
+  #else
+    #define LOW_OPTIMIZATION_ENTER
+  #endif
+
+  /* Exit low optimization region - place directly after end of function definition */
   #define LOW_OPTIMIZATION_EXIT
 
-//Enter low optimization region - place directly above function definition
-    #ifdef ARM_MATH_CM4
-      #define IAR_ONLY_LOW_OPTIMIZATION_ENTER \
-         _Pragma ("optimize=low")
-    #else
-      #define IAR_ONLY_LOW_OPTIMIZATION_ENTER   
-    #endif
-
-//Exit low optimization region - place directly after end of function definition
+  /* Enter low optimization region - place directly above function definition */
+  #if defined ( ARM_MATH_CM4 ) || defined ( ARM_MATH_CM7 )
+    #define IAR_ONLY_LOW_OPTIMIZATION_ENTER \
+       _Pragma ("optimize=low")
+  #else
+    #define IAR_ONLY_LOW_OPTIMIZATION_ENTER
+  #endif
+
+  /* Exit low optimization region - place directly after end of function definition */
   #define IAR_ONLY_LOW_OPTIMIZATION_EXIT
 
-#elif defined(__GNUC__)
-
-  #define LOW_OPTIMIZATION_ENTER __attribute__(( optimize("-O1") ))
-
+#elif defined ( __TI_ARM__ )
+  #define LOW_OPTIMIZATION_ENTER
   #define LOW_OPTIMIZATION_EXIT
-
   #define IAR_ONLY_LOW_OPTIMIZATION_ENTER
-
   #define IAR_ONLY_LOW_OPTIMIZATION_EXIT
 
-#elif defined(__CSMC__)		// Cosmic
-
-#define LOW_OPTIMIZATION_ENTER
-#define LOW_OPTIMIZATION_EXIT
-#define IAR_ONLY_LOW_OPTIMIZATION_ENTER
-#define IAR_ONLY_LOW_OPTIMIZATION_EXIT
-
-#elif defined(__TASKING__)		// TASKING
-
-#define LOW_OPTIMIZATION_ENTER
-#define LOW_OPTIMIZATION_EXIT
-#define IAR_ONLY_LOW_OPTIMIZATION_ENTER
-#define IAR_ONLY_LOW_OPTIMIZATION_EXIT
+#elif defined ( __CSMC__ )
+  #define LOW_OPTIMIZATION_ENTER
+  #define LOW_OPTIMIZATION_EXIT
+  #define IAR_ONLY_LOW_OPTIMIZATION_ENTER
+  #define IAR_ONLY_LOW_OPTIMIZATION_EXIT
+
+#elif defined ( __TASKING__ )
+  #define LOW_OPTIMIZATION_ENTER
+  #define LOW_OPTIMIZATION_EXIT
+  #define IAR_ONLY_LOW_OPTIMIZATION_ENTER
+  #define IAR_ONLY_LOW_OPTIMIZATION_EXIT
 
 #endif
 
 
-#ifdef	__cplusplus
+#ifdef   __cplusplus
 }
 #endif
 
+/* Compiler specific diagnostic adjustment */
+#if   defined ( __CC_ARM )
+
+#elif defined ( __ARMCC_VERSION ) && ( __ARMCC_VERSION >= 6010050 )
+
+#elif defined ( __GNUC__ )
+#pragma GCC diagnostic pop
+
+#elif defined ( __ICCARM__ )
+
+#elif defined ( __TI_ARM__ )
+
+#elif defined ( __CSMC__ )
+
+#elif defined ( __TASKING__ )
+
+#else
+  #error Unknown compiler
+#endif
 
 #endif /* _ARM_MATH_H */