mbed official / mbed-dsp

CMSIS DSP library

Dependents:   KL25Z_FFT_Demo Hat_Board_v5_1 KL25Z_FFT_Demo_tony KL25Z_FFT_Demo_tony ... more

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_mult_q31.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?

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 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_mult_q31.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q31 vector multiplication.
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 0.0.5 2010/04/26
emilmont 1:fdd22bb7aa52 33 * incorporated review comments and updated with latest CMSIS layer
emilmont 1:fdd22bb7aa52 34 *
emilmont 1:fdd22bb7aa52 35 * Version 0.0.3 2010/03/10
emilmont 1:fdd22bb7aa52 36 * Initial version
emilmont 1:fdd22bb7aa52 37 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 38
emilmont 1:fdd22bb7aa52 39 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 40
emilmont 1:fdd22bb7aa52 41 /**
emilmont 1:fdd22bb7aa52 42 * @ingroup groupMath
emilmont 1:fdd22bb7aa52 43 */
emilmont 1:fdd22bb7aa52 44
emilmont 1:fdd22bb7aa52 45 /**
emilmont 1:fdd22bb7aa52 46 * @addtogroup BasicMult
emilmont 1:fdd22bb7aa52 47 * @{
emilmont 1:fdd22bb7aa52 48 */
emilmont 1:fdd22bb7aa52 49
emilmont 1:fdd22bb7aa52 50 /**
emilmont 1:fdd22bb7aa52 51 * @brief Q31 vector multiplication.
emilmont 1:fdd22bb7aa52 52 * @param[in] *pSrcA points to the first input vector
emilmont 1:fdd22bb7aa52 53 * @param[in] *pSrcB points to the second input vector
emilmont 1:fdd22bb7aa52 54 * @param[out] *pDst points to the output vector
emilmont 1:fdd22bb7aa52 55 * @param[in] blockSize number of samples in each vector
emilmont 1:fdd22bb7aa52 56 * @return none.
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 * Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] will be saturated.
emilmont 1:fdd22bb7aa52 62 */
emilmont 1:fdd22bb7aa52 63
emilmont 1:fdd22bb7aa52 64 void arm_mult_q31(
emilmont 1:fdd22bb7aa52 65 q31_t * pSrcA,
emilmont 1:fdd22bb7aa52 66 q31_t * pSrcB,
emilmont 1:fdd22bb7aa52 67 q31_t * pDst,
emilmont 1:fdd22bb7aa52 68 uint32_t blockSize)
emilmont 1:fdd22bb7aa52 69 {
emilmont 1:fdd22bb7aa52 70 uint32_t blkCnt; /* loop counters */
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 inA1, inA2, inA3, inA4; /* temporary input variables */
emilmont 1:fdd22bb7aa52 76 q31_t inB1, inB2, inB3, inB4; /* temporary input variables */
emilmont 1:fdd22bb7aa52 77 q31_t out1, out2, out3, out4; /* temporary output variables */
emilmont 1:fdd22bb7aa52 78
emilmont 1:fdd22bb7aa52 79 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 80 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 81
emilmont 1:fdd22bb7aa52 82 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 83 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 84 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 85 {
emilmont 1:fdd22bb7aa52 86 /* C = A * B */
emilmont 1:fdd22bb7aa52 87 /* Multiply the inputs and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 88 inA1 = *pSrcA++;
emilmont 1:fdd22bb7aa52 89 inA2 = *pSrcA++;
emilmont 1:fdd22bb7aa52 90 inA3 = *pSrcA++;
emilmont 1:fdd22bb7aa52 91 inA4 = *pSrcA++;
emilmont 1:fdd22bb7aa52 92 inB1 = *pSrcB++;
emilmont 1:fdd22bb7aa52 93 inB2 = *pSrcB++;
emilmont 1:fdd22bb7aa52 94 inB3 = *pSrcB++;
emilmont 1:fdd22bb7aa52 95 inB4 = *pSrcB++;
emilmont 1:fdd22bb7aa52 96
emilmont 1:fdd22bb7aa52 97 out1 = ((q63_t) inA1 * inB1) >> 32;
emilmont 1:fdd22bb7aa52 98 out2 = ((q63_t) inA2 * inB2) >> 32;
emilmont 1:fdd22bb7aa52 99 out3 = ((q63_t) inA3 * inB3) >> 32;
emilmont 1:fdd22bb7aa52 100 out4 = ((q63_t) inA4 * inB4) >> 32;
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 out1 = __SSAT(out1, 31);
emilmont 1:fdd22bb7aa52 103 out2 = __SSAT(out2, 31);
emilmont 1:fdd22bb7aa52 104 out3 = __SSAT(out3, 31);
emilmont 1:fdd22bb7aa52 105 out4 = __SSAT(out4, 31);
emilmont 1:fdd22bb7aa52 106
emilmont 1:fdd22bb7aa52 107 *pDst++ = out1 << 1u;
emilmont 1:fdd22bb7aa52 108 *pDst++ = out2 << 1u;
emilmont 1:fdd22bb7aa52 109 *pDst++ = out3 << 1u;
emilmont 1:fdd22bb7aa52 110 *pDst++ = out4 << 1u;
emilmont 1:fdd22bb7aa52 111
emilmont 1:fdd22bb7aa52 112 /* Decrement the blockSize loop counter */
emilmont 1:fdd22bb7aa52 113 blkCnt--;
emilmont 1:fdd22bb7aa52 114 }
emilmont 1:fdd22bb7aa52 115
emilmont 1:fdd22bb7aa52 116 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 117 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 118 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 119
emilmont 1:fdd22bb7aa52 120 #else
emilmont 1:fdd22bb7aa52 121
emilmont 1:fdd22bb7aa52 122 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 123
emilmont 1:fdd22bb7aa52 124 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 125 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 126
emilmont 1:fdd22bb7aa52 127 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 130 {
emilmont 1:fdd22bb7aa52 131 /* C = A * B */
emilmont 1:fdd22bb7aa52 132 /* Multiply the inputs and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 133 *pDst++ =
emilmont 1:fdd22bb7aa52 134 (q31_t) clip_q63_to_q31(((q63_t) (*pSrcA++) * (*pSrcB++)) >> 31);
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 /* Decrement the blockSize loop counter */
emilmont 1:fdd22bb7aa52 137 blkCnt--;
emilmont 1:fdd22bb7aa52 138 }
emilmont 1:fdd22bb7aa52 139 }
emilmont 1:fdd22bb7aa52 140
emilmont 1:fdd22bb7aa52 141 /**
emilmont 1:fdd22bb7aa52 142 * @} end of BasicMult group
emilmont 1:fdd22bb7aa52 143 */