1 /* ----------------------------------------------------------------------
2 * Copyright (C) 2010 ARM Limited. All rights reserved.
7 * Project: CMSIS DSP Library
8 * Title: arm_mult_q15.c
10 * Description: Q15 vector multiplication.
12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
14 * Version 1.0.10 2011/7/15
15 * Big Endian support added and Merged M0 and M3/M4 Source code.
17 * Version 1.0.3 2010/11/29
18 * Re-organized the CMSIS folders and updated documentation.
20 * Version 1.0.2 2010/11/11
21 * Documentation updated.
23 * Version 1.0.1 2010/10/05
24 * Production release and review comments incorporated.
26 * Version 1.0.0 2010/09/20
27 * Production release and review comments incorporated.
29 * Version 0.0.5 2010/04/26
30 * incorporated review comments and updated with latest CMSIS layer
32 * Version 0.0.3 2010/03/10
34 * -------------------------------------------------------------------- */
43 * @addtogroup BasicMult
49 * @brief Q15 vector multiplication
50 * @param[in] *pSrcA points to the first input vector
51 * @param[in] *pSrcB points to the second input vector
52 * @param[out] *pDst points to the output vector
53 * @param[in] blockSize number of samples in each vector
56 * <b>Scaling and Overflow Behavior:</b>
58 * The function uses saturating arithmetic.
59 * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
68 uint32_t blkCnt; /* loop counters */
72 /* Run the below code for Cortex-M4 and Cortex-M3 */
75 blkCnt = blockSize >> 2u;
77 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
78 ** a second loop below computes the remaining 1 to 3 samples. */
82 /* Multiply the inputs and store the result in the destination buffer */
83 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
84 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
85 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
86 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
88 /* Decrement the blockSize loop counter */
92 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
93 ** No loop unrolling is used. */
94 blkCnt = blockSize % 0x4u;
98 /* Run the below code for Cortex-M0 */
100 /* Initialize blkCnt with number of samples */
103 #endif /* #ifndef ARM_MATH_CM0 */
109 /* Multiply the inputs and store the result in the destination buffer */
110 *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
112 /* Decrement the blockSize loop counter */
118 * @} end of BasicMult group