Fork of mbed-dsp. CMSIS-DSP library of supporting NEON

Dependents:   mbed-os-example-cmsis_dsp_neon

Fork of mbed-dsp by mbed official

Information

Japanese version is available in lower part of this page.
このページの後半に日本語版が用意されています.

CMSIS-DSP of supporting NEON

What is this ?

A library for CMSIS-DSP of supporting NEON.
We supported the NEON to CMSIS-DSP Ver1.4.3(CMSIS V4.1) that ARM supplied, has achieved the processing speed improvement.
If you use the mbed-dsp library, you can use to replace this library.
CMSIS-DSP of supporting NEON is provied as a library.

Library Creation environment

CMSIS-DSP library of supporting NEON was created by the following environment.

  • Compiler
    ARMCC Version 5.03
  • Compile option switch[C Compiler]
   -DARM_MATH_MATRIX_CHECK -DARM_MATH_ROUNDING -O3 -Otime --cpu=Cortex-A9 --littleend --arm 
   --apcs=/interwork --no_unaligned_access --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp 
   --vectorize --asm
  • Compile option switch[Assembler]
   --cpreproc --cpu=Cortex-A9 --littleend --arm --apcs=/interwork --no_unaligned_access 
   --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp


Effects of NEON support

In the data which passes to each function, large size will be expected more effective than small size.
Also if the data is a multiple of 16, effect will be expected in every function in the CMSIS-DSP.


NEON対応CMSIS-DSP

概要

NEON対応したCMSIS-DSPのライブラリです。
ARM社提供のCMSIS-DSP Ver1.4.3(CMSIS V4.1)をターゲットにNEON対応を行ない、処理速度向上を実現しております。
mbed-dspライブラリを使用している場合は、本ライブラリに置き換えて使用することができます。
NEON対応したCMSIS-DSPはライブラリで提供します。

ライブラリ作成環境

NEON対応CMSIS-DSPライブラリは、以下の環境で作成しています。

  • コンパイラ
    ARMCC Version 5.03
  • コンパイルオプションスイッチ[C Compiler]
   -DARM_MATH_MATRIX_CHECK -DARM_MATH_ROUNDING -O3 -Otime --cpu=Cortex-A9 --littleend --arm 
   --apcs=/interwork --no_unaligned_access --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp 
   --vectorize --asm
  • コンパイルオプションスイッチ[Assembler]
   --cpreproc --cpu=Cortex-A9 --littleend --arm --apcs=/interwork --no_unaligned_access 
   --fpu=vfpv3_fp16 --fpmode=fast --apcs=/hardfp


NEON対応による効果について

CMSIS-DSP内の各関数へ渡すデータは、小さいサイズよりも大きいサイズの方が効果が見込めます。
また、16の倍数のデータであれば、CMSIS-DSP内のどの関数でも効果が見込めます。


Committer:
mbed_official
Date:
Fri Nov 08 13:45:10 2013 +0000
Revision:
3:7a284390b0ce
Parent:
2:da51fb522205
Synchronized with git revision e69956aba2f68a2a26ac26b051f8d349deaa1ce8

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------------
mbed_official 3:7a284390b0ce 2 * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
mbed_official 3:7a284390b0ce 4 * $Date: 17. January 2013
mbed_official 3:7a284390b0ce 5 * $Revision: V1.4.1
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 1:fdd22bb7aa52 8 * Title: arm_mat_add_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Floating-point matrix addition
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 13 *
mbed_official 3:7a284390b0ce 14 * Redistribution and use in source and binary forms, with or without
mbed_official 3:7a284390b0ce 15 * modification, are permitted provided that the following conditions
mbed_official 3:7a284390b0ce 16 * are met:
mbed_official 3:7a284390b0ce 17 * - Redistributions of source code must retain the above copyright
mbed_official 3:7a284390b0ce 18 * notice, this list of conditions and the following disclaimer.
mbed_official 3:7a284390b0ce 19 * - Redistributions in binary form must reproduce the above copyright
mbed_official 3:7a284390b0ce 20 * notice, this list of conditions and the following disclaimer in
mbed_official 3:7a284390b0ce 21 * the documentation and/or other materials provided with the
mbed_official 3:7a284390b0ce 22 * distribution.
mbed_official 3:7a284390b0ce 23 * - Neither the name of ARM LIMITED nor the names of its contributors
mbed_official 3:7a284390b0ce 24 * may be used to endorse or promote products derived from this
mbed_official 3:7a284390b0ce 25 * software without specific prior written permission.
mbed_official 3:7a284390b0ce 26 *
mbed_official 3:7a284390b0ce 27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
mbed_official 3:7a284390b0ce 28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
mbed_official 3:7a284390b0ce 29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
mbed_official 3:7a284390b0ce 30 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
mbed_official 3:7a284390b0ce 31 * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
mbed_official 3:7a284390b0ce 32 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
mbed_official 3:7a284390b0ce 33 * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
mbed_official 3:7a284390b0ce 34 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
mbed_official 3:7a284390b0ce 35 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
mbed_official 3:7a284390b0ce 36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
mbed_official 3:7a284390b0ce 37 * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
mbed_official 3:7a284390b0ce 38 * POSSIBILITY OF SUCH DAMAGE.
emilmont 1:fdd22bb7aa52 39 * -------------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 40
emilmont 1:fdd22bb7aa52 41 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 42
emilmont 1:fdd22bb7aa52 43 /**
emilmont 1:fdd22bb7aa52 44 * @ingroup groupMatrix
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @defgroup MatrixAdd Matrix Addition
emilmont 1:fdd22bb7aa52 49 *
emilmont 1:fdd22bb7aa52 50 * Adds two matrices.
emilmont 1:fdd22bb7aa52 51 * \image html MatrixAddition.gif "Addition of two 3 x 3 matrices"
emilmont 1:fdd22bb7aa52 52 *
emilmont 1:fdd22bb7aa52 53 * The functions check to make sure that
emilmont 1:fdd22bb7aa52 54 * <code>pSrcA</code>, <code>pSrcB</code>, and <code>pDst</code> have the same
emilmont 1:fdd22bb7aa52 55 * number of rows and columns.
emilmont 1:fdd22bb7aa52 56 */
emilmont 1:fdd22bb7aa52 57
emilmont 1:fdd22bb7aa52 58 /**
emilmont 1:fdd22bb7aa52 59 * @addtogroup MatrixAdd
emilmont 1:fdd22bb7aa52 60 * @{
emilmont 1:fdd22bb7aa52 61 */
emilmont 1:fdd22bb7aa52 62
emilmont 1:fdd22bb7aa52 63
emilmont 1:fdd22bb7aa52 64 /**
emilmont 1:fdd22bb7aa52 65 * @brief Floating-point matrix addition.
emilmont 1:fdd22bb7aa52 66 * @param[in] *pSrcA points to the first input matrix structure
emilmont 1:fdd22bb7aa52 67 * @param[in] *pSrcB points to the second input matrix structure
emilmont 1:fdd22bb7aa52 68 * @param[out] *pDst points to output matrix structure
emilmont 2:da51fb522205 69 * @return The function returns either
emilmont 1:fdd22bb7aa52 70 * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 71 */
emilmont 1:fdd22bb7aa52 72
emilmont 1:fdd22bb7aa52 73 arm_status arm_mat_add_f32(
emilmont 1:fdd22bb7aa52 74 const arm_matrix_instance_f32 * pSrcA,
emilmont 1:fdd22bb7aa52 75 const arm_matrix_instance_f32 * pSrcB,
emilmont 1:fdd22bb7aa52 76 arm_matrix_instance_f32 * pDst)
emilmont 1:fdd22bb7aa52 77 {
emilmont 1:fdd22bb7aa52 78 float32_t *pIn1 = pSrcA->pData; /* input data matrix pointer A */
emilmont 1:fdd22bb7aa52 79 float32_t *pIn2 = pSrcB->pData; /* input data matrix pointer B */
emilmont 1:fdd22bb7aa52 80 float32_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 81
mbed_official 3:7a284390b0ce 82 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 83
emilmont 1:fdd22bb7aa52 84 float32_t inA1, inA2, inB1, inB2, out1, out2; /* temporary variables */
emilmont 1:fdd22bb7aa52 85
mbed_official 3:7a284390b0ce 86 #endif // #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 87
emilmont 1:fdd22bb7aa52 88 uint32_t numSamples; /* total number of elements in the matrix */
emilmont 1:fdd22bb7aa52 89 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 90 arm_status status; /* status of matrix addition */
emilmont 1:fdd22bb7aa52 91
emilmont 1:fdd22bb7aa52 92 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 93 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 94 if((pSrcA->numRows != pSrcB->numRows) ||
emilmont 1:fdd22bb7aa52 95 (pSrcA->numCols != pSrcB->numCols) ||
emilmont 1:fdd22bb7aa52 96 (pSrcA->numRows != pDst->numRows) || (pSrcA->numCols != pDst->numCols))
emilmont 1:fdd22bb7aa52 97 {
emilmont 1:fdd22bb7aa52 98 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 99 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 100 }
emilmont 1:fdd22bb7aa52 101 else
emilmont 1:fdd22bb7aa52 102 #endif
emilmont 1:fdd22bb7aa52 103 {
emilmont 1:fdd22bb7aa52 104
emilmont 1:fdd22bb7aa52 105 /* Total number of samples in the input matrix */
emilmont 1:fdd22bb7aa52 106 numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols;
emilmont 1:fdd22bb7aa52 107
mbed_official 3:7a284390b0ce 108 #ifndef ARM_MATH_CM0_FAMILY
emilmont 1:fdd22bb7aa52 109
emilmont 1:fdd22bb7aa52 110 /* Loop unrolling */
emilmont 1:fdd22bb7aa52 111 blkCnt = numSamples >> 2u;
emilmont 1:fdd22bb7aa52 112
emilmont 1:fdd22bb7aa52 113 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 114 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 115 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 116 {
emilmont 1:fdd22bb7aa52 117 /* C(m,n) = A(m,n) + B(m,n) */
emilmont 1:fdd22bb7aa52 118 /* Add and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 119 /* Read values from source A */
emilmont 1:fdd22bb7aa52 120 inA1 = pIn1[0];
emilmont 1:fdd22bb7aa52 121
emilmont 1:fdd22bb7aa52 122 /* Read values from source B */
emilmont 1:fdd22bb7aa52 123 inB1 = pIn2[0];
emilmont 1:fdd22bb7aa52 124
emilmont 1:fdd22bb7aa52 125 /* Read values from source A */
emilmont 1:fdd22bb7aa52 126 inA2 = pIn1[1];
emilmont 1:fdd22bb7aa52 127
emilmont 1:fdd22bb7aa52 128 /* out = sourceA + sourceB */
emilmont 1:fdd22bb7aa52 129 out1 = inA1 + inB1;
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 /* Read values from source B */
emilmont 1:fdd22bb7aa52 132 inB2 = pIn2[1];
emilmont 1:fdd22bb7aa52 133
emilmont 1:fdd22bb7aa52 134 /* Read values from source A */
emilmont 1:fdd22bb7aa52 135 inA1 = pIn1[2];
emilmont 1:fdd22bb7aa52 136
emilmont 1:fdd22bb7aa52 137 /* out = sourceA + sourceB */
emilmont 1:fdd22bb7aa52 138 out2 = inA2 + inB2;
emilmont 1:fdd22bb7aa52 139
emilmont 1:fdd22bb7aa52 140 /* Read values from source B */
emilmont 1:fdd22bb7aa52 141 inB1 = pIn2[2];
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143 /* Store result in destination */
emilmont 1:fdd22bb7aa52 144 pOut[0] = out1;
emilmont 1:fdd22bb7aa52 145 pOut[1] = out2;
emilmont 1:fdd22bb7aa52 146
emilmont 1:fdd22bb7aa52 147 /* Read values from source A */
emilmont 1:fdd22bb7aa52 148 inA2 = pIn1[3];
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 /* Read values from source B */
emilmont 1:fdd22bb7aa52 151 inB2 = pIn2[3];
emilmont 1:fdd22bb7aa52 152
emilmont 1:fdd22bb7aa52 153 /* out = sourceA + sourceB */
emilmont 1:fdd22bb7aa52 154 out1 = inA1 + inB1;
emilmont 1:fdd22bb7aa52 155
emilmont 1:fdd22bb7aa52 156 /* out = sourceA + sourceB */
emilmont 1:fdd22bb7aa52 157 out2 = inA2 + inB2;
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 /* Store result in destination */
emilmont 1:fdd22bb7aa52 160 pOut[2] = out1;
emilmont 1:fdd22bb7aa52 161
emilmont 1:fdd22bb7aa52 162 /* Store result in destination */
emilmont 1:fdd22bb7aa52 163 pOut[3] = out2;
emilmont 1:fdd22bb7aa52 164
emilmont 1:fdd22bb7aa52 165
emilmont 1:fdd22bb7aa52 166 /* update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 167 pIn1 += 4u;
emilmont 1:fdd22bb7aa52 168 pIn2 += 4u;
emilmont 1:fdd22bb7aa52 169 pOut += 4u;
emilmont 1:fdd22bb7aa52 170 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 171 blkCnt--;
emilmont 1:fdd22bb7aa52 172 }
emilmont 1:fdd22bb7aa52 173
emilmont 1:fdd22bb7aa52 174 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 175 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 176 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 177
emilmont 1:fdd22bb7aa52 178 #else
emilmont 1:fdd22bb7aa52 179
emilmont 1:fdd22bb7aa52 180 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 181
emilmont 1:fdd22bb7aa52 182 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 183 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 184
mbed_official 3:7a284390b0ce 185 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emilmont 1:fdd22bb7aa52 186
emilmont 1:fdd22bb7aa52 187 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 188 {
emilmont 1:fdd22bb7aa52 189 /* C(m,n) = A(m,n) + B(m,n) */
emilmont 1:fdd22bb7aa52 190 /* Add and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 191 *pOut++ = (*pIn1++) + (*pIn2++);
emilmont 1:fdd22bb7aa52 192
emilmont 1:fdd22bb7aa52 193 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 194 blkCnt--;
emilmont 1:fdd22bb7aa52 195 }
emilmont 1:fdd22bb7aa52 196
emilmont 1:fdd22bb7aa52 197 /* set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 198 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 199
emilmont 1:fdd22bb7aa52 200 }
emilmont 1:fdd22bb7aa52 201
emilmont 1:fdd22bb7aa52 202 /* Return to application */
emilmont 1:fdd22bb7aa52 203 return (status);
emilmont 1:fdd22bb7aa52 204 }
emilmont 1:fdd22bb7aa52 205
emilmont 1:fdd22bb7aa52 206 /**
emilmont 1:fdd22bb7aa52 207 * @} end of MatrixAdd group
emilmont 1:fdd22bb7aa52 208 */