1 /* ----------------------------------------------------------------------
2 * Copyright (C) 2010 ARM Limited. All rights reserved.
7 * Project: CMSIS DSP Library
10 * Description: Q7 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 0.0.7 2010/06/10
30 * Misra-C changes done
32 * Version 0.0.5 2010/04/26
33 * incorporated review comments and updated with latest CMSIS layer
35 * Version 0.0.3 2010/03/10 DP
37 * -------------------------------------------------------------------- */
46 * @addtogroup BasicMult
51 * @brief Q7 vector multiplication
52 * @param[in] *pSrcA points to the first input vector
53 * @param[in] *pSrcB points to the second input vector
54 * @param[out] *pDst points to the output vector
55 * @param[in] blockSize number of samples in each vector
58 * <b>Scaling and Overflow Behavior:</b>
60 * The function uses saturating arithmetic.
61 * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.
70 uint32_t blkCnt; /* loop counters */
74 /* Run the below code for Cortex-M4 and Cortex-M3 */
75 q7_t out1, out2, out3, out4; /* Temporary variables to store the product */
78 blkCnt = blockSize >> 2u;
80 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
81 ** a second loop below computes the remaining 1 to 3 samples. */
85 /* Multiply the inputs and store the results in temporary variables */
86 out1 = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7);
87 out2 = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7);
88 out3 = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7);
89 out4 = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7);
91 /* Store the results of 4 inputs in the destination buffer in single cycle by packing */
92 *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
94 /* Decrement the blockSize loop counter */
98 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
99 ** No loop unrolling is used. */
100 blkCnt = blockSize % 0x4u;
104 /* Run the below code for Cortex-M0 */
106 /* Initialize blkCnt with number of samples */
109 #endif /* #ifndef ARM_MATH_CM0 */
115 /* Multiply the inputs and store the result in the destination buffer */
116 *pDst++ = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7);
118 /* Decrement the blockSize loop counter */
124 * @} end of BasicMult group