Michele Riccio / mbed-dsp_F767ZI

mbed-os 6.10 versione

cmsis_dsp/BasicMathFunctions/arm_abs_q7.c@1:fdd22bb7aa52, 2012-11-28 (annotated)

Committer:
emilmont
Date:
Wed Nov 28 12:30:09 2012 +0000
Revision:
1:fdd22bb7aa52
Child:
2:da51fb522205
DSP library code

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
emilmont 1:fdd22bb7aa52 2 * Copyright (C) 2010 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
emilmont 1:fdd22bb7aa52 4 * $Date: 15. February 2012
emilmont 1:fdd22bb7aa52 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 1:fdd22bb7aa52 7 * Project: CMSIS DSP Library
emilmont 1:fdd22bb7aa52 8 * Title: arm_abs_q7.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Q7 vector absolute value.
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 13 *
emilmont 1:fdd22bb7aa52 14 * Version 1.1.0 2012/02/15
emilmont 1:fdd22bb7aa52 15 * Updated with more optimizations, bug fixes and minor API changes.
emilmont 1:fdd22bb7aa52 16 *
emilmont 1:fdd22bb7aa52 17 * Version 1.0.10 2011/7/15
emilmont 1:fdd22bb7aa52 18 * Big Endian support added and Merged M0 and M3/M4 Source code.
emilmont 1:fdd22bb7aa52 19 *
emilmont 1:fdd22bb7aa52 20 * Version 1.0.3 2010/11/29
emilmont 1:fdd22bb7aa52 21 * Re-organized the CMSIS folders and updated documentation.
emilmont 1:fdd22bb7aa52 22 *
emilmont 1:fdd22bb7aa52 23 * Version 1.0.2 2010/11/11
emilmont 1:fdd22bb7aa52 24 * Documentation updated.
emilmont 1:fdd22bb7aa52 25 *
emilmont 1:fdd22bb7aa52 26 * Version 1.0.1 2010/10/05
emilmont 1:fdd22bb7aa52 27 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 28 *
emilmont 1:fdd22bb7aa52 29 * Version 1.0.0 2010/09/20
emilmont 1:fdd22bb7aa52 30 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 31 *
emilmont 1:fdd22bb7aa52 32 * Version 0.0.7 2010/06/10
emilmont 1:fdd22bb7aa52 33 * Misra-C changes done
emilmont 1:fdd22bb7aa52 34 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 35
emilmont 1:fdd22bb7aa52 36 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 37
emilmont 1:fdd22bb7aa52 38 /**
emilmont 1:fdd22bb7aa52 39 * @ingroup groupMath
emilmont 1:fdd22bb7aa52 40 */
emilmont 1:fdd22bb7aa52 41
emilmont 1:fdd22bb7aa52 42 /**
emilmont 1:fdd22bb7aa52 43 * @addtogroup BasicAbs
emilmont 1:fdd22bb7aa52 44 * @{
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @brief Q7 vector absolute value.
emilmont 1:fdd22bb7aa52 49 * @param[in] *pSrc points to the input buffer
emilmont 1:fdd22bb7aa52 50 * @param[out] *pDst points to the output buffer
emilmont 1:fdd22bb7aa52 51 * @param[in] blockSize number of samples in each vector
emilmont 1:fdd22bb7aa52 52 * @return none.
emilmont 1:fdd22bb7aa52 53 *
emilmont 1:fdd22bb7aa52 54 * \par Conditions for optimum performance
emilmont 1:fdd22bb7aa52 55 * Input and output buffers should be aligned by 32-bit
emilmont 1:fdd22bb7aa52 56 *
emilmont 1:fdd22bb7aa52 57 *
emilmont 1:fdd22bb7aa52 58 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 59 * \par
emilmont 1:fdd22bb7aa52 60 * The function uses saturating arithmetic.
emilmont 1:fdd22bb7aa52 61 * The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F.
emilmont 1:fdd22bb7aa52 62 */
emilmont 1:fdd22bb7aa52 63
emilmont 1:fdd22bb7aa52 64 void arm_abs_q7(
emilmont 1:fdd22bb7aa52 65 q7_t * pSrc,
emilmont 1:fdd22bb7aa52 66 q7_t * pDst,
emilmont 1:fdd22bb7aa52 67 uint32_t blockSize)
emilmont 1:fdd22bb7aa52 68 {
emilmont 1:fdd22bb7aa52 69 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 70 q7_t in; /* Input value1 */
emilmont 1:fdd22bb7aa52 71
emilmont 1:fdd22bb7aa52 72 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 75 q31_t in1, in2, in3, in4; /* temporary input variables */
emilmont 1:fdd22bb7aa52 76 q31_t out1, out2, out3, out4; /* temporary output variables */
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 79 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 82 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 83 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 84 {
emilmont 1:fdd22bb7aa52 85 /* C = |A| */
emilmont 1:fdd22bb7aa52 86 /* Read inputs */
emilmont 1:fdd22bb7aa52 87 in1 = (q31_t) * pSrc;
emilmont 1:fdd22bb7aa52 88 in2 = (q31_t) * (pSrc + 1);
emilmont 1:fdd22bb7aa52 89 in3 = (q31_t) * (pSrc + 2);
emilmont 1:fdd22bb7aa52 90
emilmont 1:fdd22bb7aa52 91 /* find absolute value */
emilmont 1:fdd22bb7aa52 92 out1 = (in1 > 0) ? in1 : __QSUB8(0, in1);
emilmont 1:fdd22bb7aa52 93
emilmont 1:fdd22bb7aa52 94 /* read input */
emilmont 1:fdd22bb7aa52 95 in4 = (q31_t) * (pSrc + 3);
emilmont 1:fdd22bb7aa52 96
emilmont 1:fdd22bb7aa52 97 /* find absolute value */
emilmont 1:fdd22bb7aa52 98 out2 = (in2 > 0) ? in2 : __QSUB8(0, in2);
emilmont 1:fdd22bb7aa52 99
emilmont 1:fdd22bb7aa52 100 /* store result to destination */
emilmont 1:fdd22bb7aa52 101 *pDst = (q7_t) out1;
emilmont 1:fdd22bb7aa52 102
emilmont 1:fdd22bb7aa52 103 /* find absolute value */
emilmont 1:fdd22bb7aa52 104 out3 = (in3 > 0) ? in3 : __QSUB8(0, in3);
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* find absolute value */
emilmont 1:fdd22bb7aa52 107 out4 = (in4 > 0) ? in4 : __QSUB8(0, in4);
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 /* store result to destination */
emilmont 1:fdd22bb7aa52 110 *(pDst + 1) = (q7_t) out2;
emilmont 1:fdd22bb7aa52 111
emilmont 1:fdd22bb7aa52 112 /* store result to destination */
emilmont 1:fdd22bb7aa52 113 *(pDst + 2) = (q7_t) out3;
emilmont 1:fdd22bb7aa52 114
emilmont 1:fdd22bb7aa52 115 /* store result to destination */
emilmont 1:fdd22bb7aa52 116 *(pDst + 3) = (q7_t) out4;
emilmont 1:fdd22bb7aa52 117
emilmont 1:fdd22bb7aa52 118 /* update pointers to process next samples */
emilmont 1:fdd22bb7aa52 119 pSrc += 4u;
emilmont 1:fdd22bb7aa52 120 pDst += 4u;
emilmont 1:fdd22bb7aa52 121
emilmont 1:fdd22bb7aa52 122 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 123 blkCnt--;
emilmont 1:fdd22bb7aa52 124 }
emilmont 1:fdd22bb7aa52 125
emilmont 1:fdd22bb7aa52 126 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 127 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 128 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 129 #else
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 132 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 133
emilmont 1:fdd22bb7aa52 134 #endif // #define ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 137 {
emilmont 1:fdd22bb7aa52 138 /* C = |A| */
emilmont 1:fdd22bb7aa52 139 /* Read the input */
emilmont 1:fdd22bb7aa52 140 in = *pSrc++;
emilmont 1:fdd22bb7aa52 141
emilmont 1:fdd22bb7aa52 142 /* Store the Absolute result in the destination buffer */
emilmont 1:fdd22bb7aa52 143 *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? 0x7f : -in);
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 146 blkCnt--;
emilmont 1:fdd22bb7aa52 147 }
emilmont 1:fdd22bb7aa52 148 }
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 /**
emilmont 1:fdd22bb7aa52 151 * @} end of BasicAbs group
emilmont 1:fdd22bb7aa52 152 */