mbed-os 6.10 versione
cmsis_dsp/BasicMathFunctions/arm_abs_q15.c@2:da51fb522205, 2013-05-30 (annotated)
- Committer:
- emilmont
- Date:
- Thu May 30 17:10:11 2013 +0100
- Revision:
- 2:da51fb522205
- Parent:
- 1:fdd22bb7aa52
- Child:
- 3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source
Who changed what in which revision?
User | Revision | Line number | New 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 | 2:da51fb522205 | 5 | * $Revision: V1.1.0 |
emilmont | 1:fdd22bb7aa52 | 6 | * |
emilmont | 2:da51fb522205 | 7 | * Project: CMSIS DSP Library |
emilmont | 2:da51fb522205 | 8 | * Title: arm_abs_q15.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 2:da51fb522205 | 10 | * Description: Q15 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 Q15 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 | * <b>Scaling and Overflow Behavior:</b> |
emilmont | 1:fdd22bb7aa52 | 55 | * \par |
emilmont | 1:fdd22bb7aa52 | 56 | * The function uses saturating arithmetic. |
emilmont | 1:fdd22bb7aa52 | 57 | * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF. |
emilmont | 1:fdd22bb7aa52 | 58 | */ |
emilmont | 1:fdd22bb7aa52 | 59 | |
emilmont | 1:fdd22bb7aa52 | 60 | void arm_abs_q15( |
emilmont | 1:fdd22bb7aa52 | 61 | q15_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 62 | q15_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 63 | uint32_t blockSize) |
emilmont | 1:fdd22bb7aa52 | 64 | { |
emilmont | 1:fdd22bb7aa52 | 65 | uint32_t blkCnt; /* loop counter */ |
emilmont | 1:fdd22bb7aa52 | 66 | |
emilmont | 1:fdd22bb7aa52 | 67 | #ifndef ARM_MATH_CM0 |
emilmont | 1:fdd22bb7aa52 | 68 | |
emilmont | 1:fdd22bb7aa52 | 69 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emilmont | 1:fdd22bb7aa52 | 70 | |
emilmont | 1:fdd22bb7aa52 | 71 | q15_t in1; /* Input value1 */ |
emilmont | 1:fdd22bb7aa52 | 72 | q15_t in2; /* Input value2 */ |
emilmont | 1:fdd22bb7aa52 | 73 | |
emilmont | 1:fdd22bb7aa52 | 74 | |
emilmont | 1:fdd22bb7aa52 | 75 | /*loop Unrolling */ |
emilmont | 1:fdd22bb7aa52 | 76 | blkCnt = blockSize >> 2u; |
emilmont | 1:fdd22bb7aa52 | 77 | |
emilmont | 1:fdd22bb7aa52 | 78 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 79 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 80 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 81 | { |
emilmont | 1:fdd22bb7aa52 | 82 | /* C = |A| */ |
emilmont | 1:fdd22bb7aa52 | 83 | /* Read two inputs */ |
emilmont | 1:fdd22bb7aa52 | 84 | in1 = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 85 | in2 = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 86 | |
emilmont | 1:fdd22bb7aa52 | 87 | |
emilmont | 1:fdd22bb7aa52 | 88 | /* Store the Absolute result in the destination buffer by packing the two values, in a single cycle */ |
emilmont | 1:fdd22bb7aa52 | 89 | |
emilmont | 1:fdd22bb7aa52 | 90 | #ifndef ARM_MATH_BIG_ENDIAN |
emilmont | 1:fdd22bb7aa52 | 91 | |
emilmont | 1:fdd22bb7aa52 | 92 | *__SIMD32(pDst)++ = |
emilmont | 1:fdd22bb7aa52 | 93 | __PKHBT(((in1 > 0) ? in1 : __QSUB16(0, in1)), |
emilmont | 1:fdd22bb7aa52 | 94 | ((in2 > 0) ? in2 : __QSUB16(0, in2)), 16); |
emilmont | 1:fdd22bb7aa52 | 95 | |
emilmont | 1:fdd22bb7aa52 | 96 | #else |
emilmont | 1:fdd22bb7aa52 | 97 | |
emilmont | 1:fdd22bb7aa52 | 98 | |
emilmont | 1:fdd22bb7aa52 | 99 | *__SIMD32(pDst)++ = |
emilmont | 1:fdd22bb7aa52 | 100 | __PKHBT(((in2 > 0) ? in2 : __QSUB16(0, in2)), |
emilmont | 1:fdd22bb7aa52 | 101 | ((in1 > 0) ? in1 : __QSUB16(0, in1)), 16); |
emilmont | 1:fdd22bb7aa52 | 102 | |
emilmont | 1:fdd22bb7aa52 | 103 | #endif /* #ifndef ARM_MATH_BIG_ENDIAN */ |
emilmont | 1:fdd22bb7aa52 | 104 | |
emilmont | 1:fdd22bb7aa52 | 105 | in1 = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 106 | in2 = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 107 | |
emilmont | 1:fdd22bb7aa52 | 108 | |
emilmont | 1:fdd22bb7aa52 | 109 | #ifndef ARM_MATH_BIG_ENDIAN |
emilmont | 1:fdd22bb7aa52 | 110 | |
emilmont | 1:fdd22bb7aa52 | 111 | *__SIMD32(pDst)++ = |
emilmont | 1:fdd22bb7aa52 | 112 | __PKHBT(((in1 > 0) ? in1 : __QSUB16(0, in1)), |
emilmont | 1:fdd22bb7aa52 | 113 | ((in2 > 0) ? in2 : __QSUB16(0, in2)), 16); |
emilmont | 1:fdd22bb7aa52 | 114 | |
emilmont | 1:fdd22bb7aa52 | 115 | #else |
emilmont | 1:fdd22bb7aa52 | 116 | |
emilmont | 1:fdd22bb7aa52 | 117 | |
emilmont | 1:fdd22bb7aa52 | 118 | *__SIMD32(pDst)++ = |
emilmont | 1:fdd22bb7aa52 | 119 | __PKHBT(((in2 > 0) ? in2 : __QSUB16(0, in2)), |
emilmont | 1:fdd22bb7aa52 | 120 | ((in1 > 0) ? in1 : __QSUB16(0, in1)), 16); |
emilmont | 1:fdd22bb7aa52 | 121 | |
emilmont | 1:fdd22bb7aa52 | 122 | #endif /* #ifndef ARM_MATH_BIG_ENDIAN */ |
emilmont | 1:fdd22bb7aa52 | 123 | |
emilmont | 1:fdd22bb7aa52 | 124 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 125 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 126 | } |
emilmont | 1:fdd22bb7aa52 | 127 | |
emilmont | 1:fdd22bb7aa52 | 128 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
emilmont | 1:fdd22bb7aa52 | 129 | ** No loop unrolling is used. */ |
emilmont | 1:fdd22bb7aa52 | 130 | blkCnt = blockSize % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 131 | |
emilmont | 1:fdd22bb7aa52 | 132 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 133 | { |
emilmont | 1:fdd22bb7aa52 | 134 | /* C = |A| */ |
emilmont | 1:fdd22bb7aa52 | 135 | /* Read the input */ |
emilmont | 1:fdd22bb7aa52 | 136 | in1 = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 137 | |
emilmont | 1:fdd22bb7aa52 | 138 | /* Calculate absolute value of input and then store the result in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 139 | *pDst++ = (in1 > 0) ? in1 : __QSUB16(0, in1); |
emilmont | 1:fdd22bb7aa52 | 140 | |
emilmont | 1:fdd22bb7aa52 | 141 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 142 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 143 | } |
emilmont | 1:fdd22bb7aa52 | 144 | |
emilmont | 1:fdd22bb7aa52 | 145 | #else |
emilmont | 1:fdd22bb7aa52 | 146 | |
emilmont | 1:fdd22bb7aa52 | 147 | /* Run the below code for Cortex-M0 */ |
emilmont | 1:fdd22bb7aa52 | 148 | |
emilmont | 1:fdd22bb7aa52 | 149 | q15_t in; /* Temporary input variable */ |
emilmont | 1:fdd22bb7aa52 | 150 | |
emilmont | 1:fdd22bb7aa52 | 151 | /* Initialize blkCnt with number of samples */ |
emilmont | 1:fdd22bb7aa52 | 152 | blkCnt = blockSize; |
emilmont | 1:fdd22bb7aa52 | 153 | |
emilmont | 1:fdd22bb7aa52 | 154 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 155 | { |
emilmont | 1:fdd22bb7aa52 | 156 | /* C = |A| */ |
emilmont | 1:fdd22bb7aa52 | 157 | /* Read the input */ |
emilmont | 1:fdd22bb7aa52 | 158 | in = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 159 | |
emilmont | 1:fdd22bb7aa52 | 160 | /* Calculate absolute value of input and then store the result in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 161 | *pDst++ = (in > 0) ? in : ((in == (q15_t) 0x8000) ? 0x7fff : -in); |
emilmont | 1:fdd22bb7aa52 | 162 | |
emilmont | 1:fdd22bb7aa52 | 163 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 164 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 165 | } |
emilmont | 1:fdd22bb7aa52 | 166 | |
emilmont | 1:fdd22bb7aa52 | 167 | #endif /* #ifndef ARM_MATH_CM0 */ |
emilmont | 1:fdd22bb7aa52 | 168 | |
emilmont | 1:fdd22bb7aa52 | 169 | } |
emilmont | 1:fdd22bb7aa52 | 170 | |
emilmont | 1:fdd22bb7aa52 | 171 | /** |
emilmont | 1:fdd22bb7aa52 | 172 | * @} end of BasicAbs group |
emilmont | 1:fdd22bb7aa52 | 173 | */ |