Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_mult_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?

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_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Q15 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 /**
emilmont 1:fdd22bb7aa52 52 * @brief Q15 vector multiplication
emilmont 1:fdd22bb7aa52 53 * @param[in] *pSrcA points to the first input vector
emilmont 1:fdd22bb7aa52 54 * @param[in] *pSrcB points to the second input vector
emilmont 1:fdd22bb7aa52 55 * @param[out] *pDst points to the output vector
emilmont 1:fdd22bb7aa52 56 * @param[in] blockSize number of samples in each vector
emilmont 1:fdd22bb7aa52 57 * @return none.
emilmont 1:fdd22bb7aa52 58 *
emilmont 1:fdd22bb7aa52 59 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 60 * \par
emilmont 1:fdd22bb7aa52 61 * The function uses saturating arithmetic.
emilmont 1:fdd22bb7aa52 62 * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
emilmont 1:fdd22bb7aa52 63 */
emilmont 1:fdd22bb7aa52 64
emilmont 1:fdd22bb7aa52 65 void arm_mult_q15(
emilmont 1:fdd22bb7aa52 66 q15_t * pSrcA,
emilmont 1:fdd22bb7aa52 67 q15_t * pSrcB,
emilmont 1:fdd22bb7aa52 68 q15_t * pDst,
emilmont 1:fdd22bb7aa52 69 uint32_t blockSize)
emilmont 1:fdd22bb7aa52 70 {
emilmont 1:fdd22bb7aa52 71 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 72
emilmont 1:fdd22bb7aa52 73 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 74
emilmont 1:fdd22bb7aa52 75 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 76 q31_t inA1, inA2, inB1, inB2; /* temporary input variables */
emilmont 1:fdd22bb7aa52 77 q15_t out1, out2, out3, out4; /* temporary output variables */
emilmont 1:fdd22bb7aa52 78 q31_t mul1, mul2, mul3, mul4; /* temporary variables */
emilmont 1:fdd22bb7aa52 79
emilmont 1:fdd22bb7aa52 80 /* loop Unrolling */
emilmont 1:fdd22bb7aa52 81 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 82
emilmont 1:fdd22bb7aa52 83 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 84 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 85 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 86 {
emilmont 1:fdd22bb7aa52 87 /* read two samples at a time from sourceA */
emilmont 1:fdd22bb7aa52 88 inA1 = *__SIMD32(pSrcA)++;
emilmont 1:fdd22bb7aa52 89 /* read two samples at a time from sourceB */
emilmont 1:fdd22bb7aa52 90 inB1 = *__SIMD32(pSrcB)++;
emilmont 1:fdd22bb7aa52 91 /* read two samples at a time from sourceA */
emilmont 1:fdd22bb7aa52 92 inA2 = *__SIMD32(pSrcA)++;
emilmont 1:fdd22bb7aa52 93 /* read two samples at a time from sourceB */
emilmont 1:fdd22bb7aa52 94 inB2 = *__SIMD32(pSrcB)++;
emilmont 1:fdd22bb7aa52 95
emilmont 1:fdd22bb7aa52 96 /* multiply mul = sourceA * sourceB */
emilmont 1:fdd22bb7aa52 97 mul1 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
emilmont 1:fdd22bb7aa52 98 mul2 = (q31_t) ((q15_t) inA1 * (q15_t) inB1);
emilmont 1:fdd22bb7aa52 99 mul3 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB2 >> 16));
emilmont 1:fdd22bb7aa52 100 mul4 = (q31_t) ((q15_t) inA2 * (q15_t) inB2);
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /* saturate result to 16 bit */
emilmont 1:fdd22bb7aa52 103 out1 = (q15_t) __SSAT(mul1 >> 15, 16);
emilmont 1:fdd22bb7aa52 104 out2 = (q15_t) __SSAT(mul2 >> 15, 16);
emilmont 1:fdd22bb7aa52 105 out3 = (q15_t) __SSAT(mul3 >> 15, 16);
emilmont 1:fdd22bb7aa52 106 out4 = (q15_t) __SSAT(mul4 >> 15, 16);
emilmont 1:fdd22bb7aa52 107
emilmont 1:fdd22bb7aa52 108 /* store the result */
emilmont 1:fdd22bb7aa52 109 #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 *__SIMD32(pDst)++ = __PKHBT(out2, out1, 16);
emilmont 1:fdd22bb7aa52 112 *__SIMD32(pDst)++ = __PKHBT(out4, out3, 16);
emilmont 1:fdd22bb7aa52 113
emilmont 1:fdd22bb7aa52 114 #else
emilmont 1:fdd22bb7aa52 115
emilmont 1:fdd22bb7aa52 116 *__SIMD32(pDst)++ = __PKHBT(out2, out1, 16);
emilmont 1:fdd22bb7aa52 117 *__SIMD32(pDst)++ = __PKHBT(out4, out3, 16);
emilmont 1:fdd22bb7aa52 118
emilmont 1:fdd22bb7aa52 119 #endif // #ifndef ARM_MATH_BIG_ENDIAN
emilmont 1:fdd22bb7aa52 120
emilmont 1:fdd22bb7aa52 121 /* Decrement the blockSize loop counter */
emilmont 1:fdd22bb7aa52 122 blkCnt--;
emilmont 1:fdd22bb7aa52 123 }
emilmont 1:fdd22bb7aa52 124
emilmont 1:fdd22bb7aa52 125 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 126 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 127 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 128
emilmont 1:fdd22bb7aa52 129 #else
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 134 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 140 {
emilmont 1:fdd22bb7aa52 141 /* C = A * B */
emilmont 1:fdd22bb7aa52 142 /* Multiply the inputs and store the result in the destination buffer */
emilmont 1:fdd22bb7aa52 143 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
emilmont 1:fdd22bb7aa52 144
emilmont 1:fdd22bb7aa52 145 /* Decrement the blockSize 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 BasicMult group
emilmont 1:fdd22bb7aa52 152 */