CMSIS DSP Library from CMSIS 2.0. See http://www.onarm.com/cmsis/ for full details

Dependents:   K22F_DSP_Matrix_least_square BNO055-ELEC3810 1BNO055 ECE4180Project--Slave2 ... more

Committer:
simon
Date:
Thu Mar 10 15:07:50 2011 +0000
Revision:
0:1014af42efd9

        

Who changed what in which revision?

UserRevisionLine numberNew contents of line
simon 0:1014af42efd9 1 /* ----------------------------------------------------------------------
simon 0:1014af42efd9 2 * Copyright (C) 2010 ARM Limited. All rights reserved.
simon 0:1014af42efd9 3 *
simon 0:1014af42efd9 4 * $Date: 29. November 2010
simon 0:1014af42efd9 5 * $Revision: V1.0.3
simon 0:1014af42efd9 6 *
simon 0:1014af42efd9 7 * Project: CMSIS DSP Library
simon 0:1014af42efd9 8 * Title: arm_mult_q15.c
simon 0:1014af42efd9 9 *
simon 0:1014af42efd9 10 * Description: Q15 vector multiplication.
simon 0:1014af42efd9 11 *
simon 0:1014af42efd9 12 * Target Processor: Cortex-M4/Cortex-M3
simon 0:1014af42efd9 13 *
simon 0:1014af42efd9 14 * Version 1.0.3 2010/11/29
simon 0:1014af42efd9 15 * Re-organized the CMSIS folders and updated documentation.
simon 0:1014af42efd9 16 *
simon 0:1014af42efd9 17 * Version 1.0.2 2010/11/11
simon 0:1014af42efd9 18 * Documentation updated.
simon 0:1014af42efd9 19 *
simon 0:1014af42efd9 20 * Version 1.0.1 2010/10/05
simon 0:1014af42efd9 21 * Production release and review comments incorporated.
simon 0:1014af42efd9 22 *
simon 0:1014af42efd9 23 * Version 1.0.0 2010/09/20
simon 0:1014af42efd9 24 * Production release and review comments incorporated.
simon 0:1014af42efd9 25 *
simon 0:1014af42efd9 26 * Version 0.0.5 2010/04/26
simon 0:1014af42efd9 27 * incorporated review comments and updated with latest CMSIS layer
simon 0:1014af42efd9 28 *
simon 0:1014af42efd9 29 * Version 0.0.3 2010/03/10
simon 0:1014af42efd9 30 * Initial version
simon 0:1014af42efd9 31 * -------------------------------------------------------------------- */
simon 0:1014af42efd9 32
simon 0:1014af42efd9 33 #include "arm_math.h"
simon 0:1014af42efd9 34
simon 0:1014af42efd9 35 /**
simon 0:1014af42efd9 36 * @ingroup groupMath
simon 0:1014af42efd9 37 */
simon 0:1014af42efd9 38
simon 0:1014af42efd9 39 /**
simon 0:1014af42efd9 40 * @addtogroup BasicMult
simon 0:1014af42efd9 41 * @{
simon 0:1014af42efd9 42 */
simon 0:1014af42efd9 43
simon 0:1014af42efd9 44
simon 0:1014af42efd9 45 /**
simon 0:1014af42efd9 46 * @brief Q15 vector multiplication
simon 0:1014af42efd9 47 * @param[in] *pSrcA points to the first input vector
simon 0:1014af42efd9 48 * @param[in] *pSrcB points to the second input vector
simon 0:1014af42efd9 49 * @param[out] *pDst points to the output vector
simon 0:1014af42efd9 50 * @param[in] blockSize number of samples in each vector
simon 0:1014af42efd9 51 * @return none.
simon 0:1014af42efd9 52 *
simon 0:1014af42efd9 53 * <b>Scaling and Overflow Behavior:</b>
simon 0:1014af42efd9 54 * \par
simon 0:1014af42efd9 55 * The function uses saturating arithmetic.
simon 0:1014af42efd9 56 * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
simon 0:1014af42efd9 57 */
simon 0:1014af42efd9 58
simon 0:1014af42efd9 59 void arm_mult_q15(
simon 0:1014af42efd9 60 q15_t * pSrcA,
simon 0:1014af42efd9 61 q15_t * pSrcB,
simon 0:1014af42efd9 62 q15_t * pDst,
simon 0:1014af42efd9 63 uint32_t blockSize)
simon 0:1014af42efd9 64 {
simon 0:1014af42efd9 65 uint32_t blkCnt; /* loop counters */
simon 0:1014af42efd9 66
simon 0:1014af42efd9 67 /* loop Unrolling */
simon 0:1014af42efd9 68 blkCnt = blockSize >> 2u;
simon 0:1014af42efd9 69
simon 0:1014af42efd9 70 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
simon 0:1014af42efd9 71 ** a second loop below computes the remaining 1 to 3 samples. */
simon 0:1014af42efd9 72 while(blkCnt > 0u)
simon 0:1014af42efd9 73 {
simon 0:1014af42efd9 74 /* C = A * B */
simon 0:1014af42efd9 75 /* Multiply the inputs and store the result in the destination buffer */
simon 0:1014af42efd9 76 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
simon 0:1014af42efd9 77 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
simon 0:1014af42efd9 78 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
simon 0:1014af42efd9 79 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
simon 0:1014af42efd9 80
simon 0:1014af42efd9 81 /* Decrement the blockSize loop counter */
simon 0:1014af42efd9 82 blkCnt--;
simon 0:1014af42efd9 83 }
simon 0:1014af42efd9 84
simon 0:1014af42efd9 85 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
simon 0:1014af42efd9 86 ** No loop unrolling is used. */
simon 0:1014af42efd9 87 blkCnt = blockSize % 0x4u;
simon 0:1014af42efd9 88
simon 0:1014af42efd9 89 while(blkCnt > 0u)
simon 0:1014af42efd9 90 {
simon 0:1014af42efd9 91 /* C = A * B */
simon 0:1014af42efd9 92 /* Multiply the inputs and store the result in the destination buffer */
simon 0:1014af42efd9 93 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
simon 0:1014af42efd9 94
simon 0:1014af42efd9 95 /* Decrement the blockSize loop counter */
simon 0:1014af42efd9 96 blkCnt--;
simon 0:1014af42efd9 97 }
simon 0:1014af42efd9 98 }
simon 0:1014af42efd9 99
simon 0:1014af42efd9 100 /**
simon 0:1014af42efd9 101 * @} end of BasicMult group
simon 0:1014af42efd9 102 */