00001 /* ---------------------------------------------------------------------- 00002 * Copyright (C) 2010 ARM Limited. All rights reserved. 00003 * 00004 * $Date: 29. November 2010 00005 * $Revision: V1.0.3 00006 * 00007 * Project: CMSIS DSP Library 00008 * Title: arm_mult_q7.c 00009 * 00010 * Description: Q7 vector multiplication. 00011 * 00012 * Target Processor: Cortex-M4/Cortex-M3 00013 * 00014 * Version 1.0.3 2010/11/29 00015 * Re-organized the CMSIS folders and updated documentation. 00016 * 00017 * Version 1.0.2 2010/11/11 00018 * Documentation updated. 00019 * 00020 * Version 1.0.1 2010/10/05 00021 * Production release and review comments incorporated. 00022 * 00023 * Version 1.0.0 2010/09/20 00024 * Production release and review comments incorporated. 00025 * 00026 * Version 0.0.7 2010/06/10 00027 * Misra-C changes done 00028 * 00029 * Version 0.0.5 2010/04/26 00030 * incorporated review comments and updated with latest CMSIS layer 00031 * 00032 * Version 0.0.3 2010/03/10 DP 00033 * Initial version 00034 * -------------------------------------------------------------------- */ 00035 00036 #include "arm_math.h" 00037 00061 void arm_mult_q7( 00062 q7_t * pSrcA, 00063 q7_t * pSrcB, 00064 q7_t * pDst, 00065 uint32_t blockSize) 00066 { 00067 uint32_t blkCnt; /* loop counters */ 00068 q7_t out1, out2, out3, out4; /* Temporary variables to store the product */ 00069 00070 /* loop Unrolling */ 00071 blkCnt = blockSize >> 2u; 00072 00073 /* First part of the processing with loop unrolling. Compute 4 outputs at a time. 00074 ** a second loop below computes the remaining 1 to 3 samples. */ 00075 while(blkCnt > 0u) 00076 { 00077 /* C = A * B */ 00078 /* Multiply the inputs and store the results in temporary variables */ 00079 out1 = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7); 00080 out2 = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7); 00081 out3 = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7); 00082 out4 = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7); 00083 00084 /* Store the results of 4 inputs in the destination buffer in single cycle by packing */ 00085 *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4); 00086 00087 /* Decrement the blockSize loop counter */ 00088 blkCnt--; 00089 } 00090 00091 /* If the blockSize is not a multiple of 4, compute any remaining output samples here. 00092 ** No loop unrolling is used. */ 00093 blkCnt = blockSize % 0x4u; 00094 00095 while(blkCnt > 0u) 00096 { 00097 /* C = A * B */ 00098 /* Multiply the inputs and store the result in the destination buffer */ 00099 *pDst++ = (q7_t) (((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7); 00100 00101 /* Decrement the blockSize loop counter */ 00102 blkCnt--; 00103 } 00104 } 00105