00001 /* ---------------------------------------------------------------------- 00002 * Copyright (C) 2010 ARM Limited. All rights reserved. 00003 * 00004 * $Date: 15. July 2011 00005 * $Revision: V1.0.10 00006 * 00007 * Project: CMSIS DSP Library 00008 * Title: arm_scale_f32.c 00009 * 00010 * Description: Multiplies a floating-point vector by a scalar. 00011 * 00012 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 00013 * 00014 * Version 1.0.10 2011/7/15 00015 * Big Endian support added and Merged M0 and M3/M4 Source code. 00016 * 00017 * Version 1.0.3 2010/11/29 00018 * Re-organized the CMSIS folders and updated documentation. 00019 * 00020 * Version 1.0.2 2010/11/11 00021 * Documentation updated. 00022 * 00023 * Version 1.0.1 2010/10/05 00024 * Production release and review comments incorporated. 00025 * 00026 * Version 1.0.0 2010/09/20 00027 * Production release and review comments incorporated 00028 * 00029 * Version 0.0.7 2010/06/10 00030 * Misra-C changes done 00031 * ---------------------------------------------------------------------------- */ 00032 00033 #include "arm_math.h" 00034 00078 void arm_scale_f32( 00079 float32_t * pSrc, 00080 float32_t scale, 00081 float32_t * pDst, 00082 uint32_t blockSize) 00083 { 00084 uint32_t blkCnt; /* loop counter */ 00085 00086 #ifndef ARM_MATH_CM0 00087 00088 /* Run the below code for Cortex-M4 and Cortex-M3 */ 00089 /*loop Unrolling */ 00090 blkCnt = blockSize >> 2u; 00091 00092 /* First part of the processing with loop unrolling. Compute 4 outputs at a time. 00093 ** a second loop below computes the remaining 1 to 3 samples. */ 00094 while(blkCnt > 0u) 00095 { 00096 /* C = A * scale */ 00097 /* Scale the input and then store the results in the destination buffer. */ 00098 *pDst++ = (*pSrc++) * scale; 00099 *pDst++ = (*pSrc++) * scale; 00100 *pDst++ = (*pSrc++) * scale; 00101 *pDst++ = (*pSrc++) * scale; 00102 00103 /* Decrement the loop counter */ 00104 blkCnt--; 00105 } 00106 00107 /* If the blockSize is not a multiple of 4, compute any remaining output samples here. 00108 ** No loop unrolling is used. */ 00109 blkCnt = blockSize % 0x4u; 00110 00111 #else 00112 00113 /* Run the below code for Cortex-M0 */ 00114 00115 /* Initialize blkCnt with number of samples */ 00116 blkCnt = blockSize; 00117 00118 #endif /* #ifndef ARM_MATH_CM0 */ 00119 00120 while(blkCnt > 0u) 00121 { 00122 /* C = A * scale */ 00123 /* Scale the input and then store the result in the destination buffer. */ 00124 *pDst++ = (*pSrc++) * scale; 00125 00126 /* Decrement the loop counter */ 00127 blkCnt--; 00128 } 00129 } 00130