Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/BasicMathFunctions/arm_scale_q7.c@1:fdd22bb7aa52, 2012-11-28 (annotated)

Committer:
emilmont
Date:
Wed Nov 28 12:30:09 2012 +0000
Revision:
1:fdd22bb7aa52
Child:
2:da51fb522205
DSP library code

Who changed what in which revision?

UserRevisionLine numberNew contents of line
emilmont 1:fdd22bb7aa52 1 /* ----------------------------------------------------------------------
emilmont 1:fdd22bb7aa52 2 * Copyright (C) 2010 ARM Limited. All rights reserved.
emilmont 1:fdd22bb7aa52 3 *
emilmont 1:fdd22bb7aa52 4 * $Date: 15. February 2012
emilmont 1:fdd22bb7aa52 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 1:fdd22bb7aa52 7 * Project: CMSIS DSP Library
emilmont 1:fdd22bb7aa52 8 * Title: arm_scale_q7.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Multiplies a Q7 vector by a scalar.
emilmont 1:fdd22bb7aa52 11 *
emilmont 1:fdd22bb7aa52 12 * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
emilmont 1:fdd22bb7aa52 13 *
emilmont 1:fdd22bb7aa52 14 * Version 1.1.0 2012/02/15
emilmont 1:fdd22bb7aa52 15 * Updated with more optimizations, bug fixes and minor API changes.
emilmont 1:fdd22bb7aa52 16 *
emilmont 1:fdd22bb7aa52 17 * Version 1.0.10 2011/7/15
emilmont 1:fdd22bb7aa52 18 * Big Endian support added and Merged M0 and M3/M4 Source code.
emilmont 1:fdd22bb7aa52 19 *
emilmont 1:fdd22bb7aa52 20 * Version 1.0.3 2010/11/29
emilmont 1:fdd22bb7aa52 21 * Re-organized the CMSIS folders and updated documentation.
emilmont 1:fdd22bb7aa52 22 *
emilmont 1:fdd22bb7aa52 23 * Version 1.0.2 2010/11/11
emilmont 1:fdd22bb7aa52 24 * Documentation updated.
emilmont 1:fdd22bb7aa52 25 *
emilmont 1:fdd22bb7aa52 26 * Version 1.0.1 2010/10/05
emilmont 1:fdd22bb7aa52 27 * Production release and review comments incorporated.
emilmont 1:fdd22bb7aa52 28 *
emilmont 1:fdd22bb7aa52 29 * Version 1.0.0 2010/09/20
emilmont 1:fdd22bb7aa52 30 * Production release and review comments incorporated
emilmont 1:fdd22bb7aa52 31 *
emilmont 1:fdd22bb7aa52 32 * Version 0.0.7 2010/06/10
emilmont 1:fdd22bb7aa52 33 * Misra-C changes done
emilmont 1:fdd22bb7aa52 34 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 35
emilmont 1:fdd22bb7aa52 36 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 37
emilmont 1:fdd22bb7aa52 38 /**
emilmont 1:fdd22bb7aa52 39 * @ingroup groupMath
emilmont 1:fdd22bb7aa52 40 */
emilmont 1:fdd22bb7aa52 41
emilmont 1:fdd22bb7aa52 42 /**
emilmont 1:fdd22bb7aa52 43 * @addtogroup scale
emilmont 1:fdd22bb7aa52 44 * @{
emilmont 1:fdd22bb7aa52 45 */
emilmont 1:fdd22bb7aa52 46
emilmont 1:fdd22bb7aa52 47 /**
emilmont 1:fdd22bb7aa52 48 * @brief Multiplies a Q7 vector by a scalar.
emilmont 1:fdd22bb7aa52 49 * @param[in] *pSrc points to the input vector
emilmont 1:fdd22bb7aa52 50 * @param[in] scaleFract fractional portion of the scale value
emilmont 1:fdd22bb7aa52 51 * @param[in] shift number of bits to shift the result by
emilmont 1:fdd22bb7aa52 52 * @param[out] *pDst points to the output vector
emilmont 1:fdd22bb7aa52 53 * @param[in] blockSize number of samples in the vector
emilmont 1:fdd22bb7aa52 54 * @return none.
emilmont 1:fdd22bb7aa52 55 *
emilmont 1:fdd22bb7aa52 56 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 57 * \par
emilmont 1:fdd22bb7aa52 58 * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.7 format.
emilmont 1:fdd22bb7aa52 59 * These are multiplied to yield a 2.14 intermediate result and this is shifted with saturation to 1.7 format.
emilmont 1:fdd22bb7aa52 60 */
emilmont 1:fdd22bb7aa52 61
emilmont 1:fdd22bb7aa52 62 void arm_scale_q7(
emilmont 1:fdd22bb7aa52 63 q7_t * pSrc,
emilmont 1:fdd22bb7aa52 64 q7_t scaleFract,
emilmont 1:fdd22bb7aa52 65 int8_t shift,
emilmont 1:fdd22bb7aa52 66 q7_t * pDst,
emilmont 1:fdd22bb7aa52 67 uint32_t blockSize)
emilmont 1:fdd22bb7aa52 68 {
emilmont 1:fdd22bb7aa52 69 int8_t kShift = 7 - shift; /* shift to apply after scaling */
emilmont 1:fdd22bb7aa52 70 uint32_t blkCnt; /* loop counter */
emilmont 1:fdd22bb7aa52 71
emilmont 1:fdd22bb7aa52 72 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 73
emilmont 1:fdd22bb7aa52 74 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 75 q7_t in1, in2, in3, in4, out1, out2, out3, out4; /* Temporary variables to store input & output */
emilmont 1:fdd22bb7aa52 76
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 /*loop Unrolling */
emilmont 1:fdd22bb7aa52 79 blkCnt = blockSize >> 2u;
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81
emilmont 1:fdd22bb7aa52 82 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 83 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 84 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 85 {
emilmont 1:fdd22bb7aa52 86 /* Reading 4 inputs from memory */
emilmont 1:fdd22bb7aa52 87 in1 = *pSrc++;
emilmont 1:fdd22bb7aa52 88 in2 = *pSrc++;
emilmont 1:fdd22bb7aa52 89 in3 = *pSrc++;
emilmont 1:fdd22bb7aa52 90 in4 = *pSrc++;
emilmont 1:fdd22bb7aa52 91
emilmont 1:fdd22bb7aa52 92 /* C = A * scale */
emilmont 1:fdd22bb7aa52 93 /* Scale the inputs and then store the results in the temporary variables. */
emilmont 1:fdd22bb7aa52 94 out1 = (q7_t) (__SSAT(((in1) * scaleFract) >> kShift, 8));
emilmont 1:fdd22bb7aa52 95 out2 = (q7_t) (__SSAT(((in2) * scaleFract) >> kShift, 8));
emilmont 1:fdd22bb7aa52 96 out3 = (q7_t) (__SSAT(((in3) * scaleFract) >> kShift, 8));
emilmont 1:fdd22bb7aa52 97 out4 = (q7_t) (__SSAT(((in4) * scaleFract) >> kShift, 8));
emilmont 1:fdd22bb7aa52 98
emilmont 1:fdd22bb7aa52 99 /* Packing the individual outputs into 32bit and storing in
emilmont 1:fdd22bb7aa52 100 * destination buffer in single write */
emilmont 1:fdd22bb7aa52 101 *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
emilmont 1:fdd22bb7aa52 102
emilmont 1:fdd22bb7aa52 103 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 104 blkCnt--;
emilmont 1:fdd22bb7aa52 105 }
emilmont 1:fdd22bb7aa52 106
emilmont 1:fdd22bb7aa52 107 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 108 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 109 blkCnt = blockSize % 0x4u;
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 112 {
emilmont 1:fdd22bb7aa52 113 /* C = A * scale */
emilmont 1:fdd22bb7aa52 114 /* Scale the input and then store the result in the destination buffer. */
emilmont 1:fdd22bb7aa52 115 *pDst++ = (q7_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 8));
emilmont 1:fdd22bb7aa52 116
emilmont 1:fdd22bb7aa52 117 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 118 blkCnt--;
emilmont 1:fdd22bb7aa52 119 }
emilmont 1:fdd22bb7aa52 120
emilmont 1:fdd22bb7aa52 121 #else
emilmont 1:fdd22bb7aa52 122
emilmont 1:fdd22bb7aa52 123 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 124
emilmont 1:fdd22bb7aa52 125 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 126 blkCnt = blockSize;
emilmont 1:fdd22bb7aa52 127
emilmont 1:fdd22bb7aa52 128 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 129 {
emilmont 1:fdd22bb7aa52 130 /* C = A * scale */
emilmont 1:fdd22bb7aa52 131 /* Scale the input and then store the result in the destination buffer. */
emilmont 1:fdd22bb7aa52 132 *pDst++ = (q7_t) (__SSAT((((q15_t) * pSrc++ * scaleFract) >> kShift), 8));
emilmont 1:fdd22bb7aa52 133
emilmont 1:fdd22bb7aa52 134 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 135 blkCnt--;
emilmont 1:fdd22bb7aa52 136 }
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 139
emilmont 1:fdd22bb7aa52 140 }
emilmont 1:fdd22bb7aa52 141
emilmont 1:fdd22bb7aa52 142 /**
emilmont 1:fdd22bb7aa52 143 * @} end of scale group
emilmont 1:fdd22bb7aa52 144 */