Laxmi Kant Tiwari / mbed-dsp

CMSIS DSP Lib

Fork of mbed-dsp by mbed official

cmsis_dsp/MatrixFunctions/arm_mat_scale_q15.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_mat_scale_q15.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 1:fdd22bb7aa52 10 * Description: Multiplies a Q15 matrix 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 0.0.5 2010/04/26
emilmont 1:fdd22bb7aa52 33 * incorporated review comments and updated with latest CMSIS layer
emilmont 1:fdd22bb7aa52 34 *
emilmont 1:fdd22bb7aa52 35 * Version 0.0.3 2010/03/10
emilmont 1:fdd22bb7aa52 36 * Initial version
emilmont 1:fdd22bb7aa52 37 * -------------------------------------------------------------------- */
emilmont 1:fdd22bb7aa52 38
emilmont 1:fdd22bb7aa52 39 #include "arm_math.h"
emilmont 1:fdd22bb7aa52 40
emilmont 1:fdd22bb7aa52 41 /**
emilmont 1:fdd22bb7aa52 42 * @ingroup groupMatrix
emilmont 1:fdd22bb7aa52 43 */
emilmont 1:fdd22bb7aa52 44
emilmont 1:fdd22bb7aa52 45 /**
emilmont 1:fdd22bb7aa52 46 * @addtogroup MatrixScale
emilmont 1:fdd22bb7aa52 47 * @{
emilmont 1:fdd22bb7aa52 48 */
emilmont 1:fdd22bb7aa52 49
emilmont 1:fdd22bb7aa52 50 /**
emilmont 1:fdd22bb7aa52 51 * @brief Q15 matrix scaling.
emilmont 1:fdd22bb7aa52 52 * @param[in] *pSrc points to input matrix
emilmont 1:fdd22bb7aa52 53 * @param[in] scaleFract fractional portion of the scale factor
emilmont 1:fdd22bb7aa52 54 * @param[in] shift number of bits to shift the result by
emilmont 1:fdd22bb7aa52 55 * @param[out] *pDst points to output matrix structure
emilmont 1:fdd22bb7aa52 56 * @return The function returns either
emilmont 1:fdd22bb7aa52 57 * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 58 *
emilmont 1:fdd22bb7aa52 59 * @details
emilmont 1:fdd22bb7aa52 60 * <b>Scaling and Overflow Behavior:</b>
emilmont 1:fdd22bb7aa52 61 * \par
emilmont 1:fdd22bb7aa52 62 * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.15 format.
emilmont 1:fdd22bb7aa52 63 * These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format.
emilmont 1:fdd22bb7aa52 64 */
emilmont 1:fdd22bb7aa52 65
emilmont 1:fdd22bb7aa52 66 arm_status arm_mat_scale_q15(
emilmont 1:fdd22bb7aa52 67 const arm_matrix_instance_q15 * pSrc,
emilmont 1:fdd22bb7aa52 68 q15_t scaleFract,
emilmont 1:fdd22bb7aa52 69 int32_t shift,
emilmont 1:fdd22bb7aa52 70 arm_matrix_instance_q15 * pDst)
emilmont 1:fdd22bb7aa52 71 {
emilmont 1:fdd22bb7aa52 72 q15_t *pIn = pSrc->pData; /* input data matrix pointer */
emilmont 1:fdd22bb7aa52 73 q15_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 74 uint32_t numSamples; /* total number of elements in the matrix */
emilmont 1:fdd22bb7aa52 75 int32_t totShift = 15 - shift; /* total shift to apply after scaling */
emilmont 1:fdd22bb7aa52 76 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 77 arm_status status; /* status of matrix scaling */
emilmont 1:fdd22bb7aa52 78
emilmont 1:fdd22bb7aa52 79 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 80
emilmont 1:fdd22bb7aa52 81 q15_t in1, in2, in3, in4;
emilmont 1:fdd22bb7aa52 82 q31_t out1, out2, out3, out4;
emilmont 1:fdd22bb7aa52 83 q31_t inA1, inA2;
emilmont 1:fdd22bb7aa52 84
emilmont 1:fdd22bb7aa52 85 #endif // #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 86
emilmont 1:fdd22bb7aa52 87 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 88 /* Check for matrix mismatch */
emilmont 1:fdd22bb7aa52 89 if((pSrc->numRows != pDst->numRows) || (pSrc->numCols != pDst->numCols))
emilmont 1:fdd22bb7aa52 90 {
emilmont 1:fdd22bb7aa52 91 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 92 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 93 }
emilmont 1:fdd22bb7aa52 94 else
emilmont 1:fdd22bb7aa52 95 #endif // #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 96 {
emilmont 1:fdd22bb7aa52 97 /* Total number of samples in the input matrix */
emilmont 1:fdd22bb7aa52 98 numSamples = (uint32_t) pSrc->numRows * pSrc->numCols;
emilmont 1:fdd22bb7aa52 99
emilmont 1:fdd22bb7aa52 100 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 101
emilmont 1:fdd22bb7aa52 102 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 103 /* Loop Unrolling */
emilmont 1:fdd22bb7aa52 104 blkCnt = numSamples >> 2;
emilmont 1:fdd22bb7aa52 105
emilmont 1:fdd22bb7aa52 106 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 107 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 108 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 109 {
emilmont 1:fdd22bb7aa52 110 /* C(m,n) = A(m,n) * k */
emilmont 1:fdd22bb7aa52 111 /* Scale, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 112 /* Reading 2 inputs from memory */
emilmont 1:fdd22bb7aa52 113 inA1 = _SIMD32_OFFSET(pIn);
emilmont 1:fdd22bb7aa52 114 inA2 = _SIMD32_OFFSET(pIn + 2);
emilmont 1:fdd22bb7aa52 115
emilmont 1:fdd22bb7aa52 116 /* C = A * scale */
emilmont 1:fdd22bb7aa52 117 /* Scale the inputs and then store the 2 results in the destination buffer
emilmont 1:fdd22bb7aa52 118 * in single cycle by packing the outputs */
emilmont 1:fdd22bb7aa52 119 out1 = (q31_t) ((q15_t) (inA1 >> 16) * scaleFract);
emilmont 1:fdd22bb7aa52 120 out2 = (q31_t) ((q15_t) inA1 * scaleFract);
emilmont 1:fdd22bb7aa52 121 out3 = (q31_t) ((q15_t) (inA2 >> 16) * scaleFract);
emilmont 1:fdd22bb7aa52 122 out4 = (q31_t) ((q15_t) inA2 * scaleFract);
emilmont 1:fdd22bb7aa52 123
emilmont 1:fdd22bb7aa52 124 out1 = out1 >> totShift;
emilmont 1:fdd22bb7aa52 125 inA1 = _SIMD32_OFFSET(pIn + 4);
emilmont 1:fdd22bb7aa52 126 out2 = out2 >> totShift;
emilmont 1:fdd22bb7aa52 127 inA2 = _SIMD32_OFFSET(pIn + 6);
emilmont 1:fdd22bb7aa52 128 out3 = out3 >> totShift;
emilmont 1:fdd22bb7aa52 129 out4 = out4 >> totShift;
emilmont 1:fdd22bb7aa52 130
emilmont 1:fdd22bb7aa52 131 in1 = (q15_t) (__SSAT(out1, 16));
emilmont 1:fdd22bb7aa52 132 in2 = (q15_t) (__SSAT(out2, 16));
emilmont 1:fdd22bb7aa52 133 in3 = (q15_t) (__SSAT(out3, 16));
emilmont 1:fdd22bb7aa52 134 in4 = (q15_t) (__SSAT(out4, 16));
emilmont 1:fdd22bb7aa52 135
emilmont 1:fdd22bb7aa52 136 _SIMD32_OFFSET(pOut) = __PKHBT(in2, in1, 16);
emilmont 1:fdd22bb7aa52 137 _SIMD32_OFFSET(pOut + 2) = __PKHBT(in4, in3, 16);
emilmont 1:fdd22bb7aa52 138
emilmont 1:fdd22bb7aa52 139 /* update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 140 pIn += 4u;
emilmont 1:fdd22bb7aa52 141 pOut += 4u;
emilmont 1:fdd22bb7aa52 142
emilmont 1:fdd22bb7aa52 143
emilmont 1:fdd22bb7aa52 144 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 145 blkCnt--;
emilmont 1:fdd22bb7aa52 146 }
emilmont 1:fdd22bb7aa52 147
emilmont 1:fdd22bb7aa52 148 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 149 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 150 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 #else
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 155
emilmont 1:fdd22bb7aa52 156 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 157 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 160
emilmont 1:fdd22bb7aa52 161 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 162 {
emilmont 1:fdd22bb7aa52 163 /* C(m,n) = A(m,n) * k */
emilmont 1:fdd22bb7aa52 164 /* Scale, saturate and then store the results in the destination buffer. */
emilmont 1:fdd22bb7aa52 165 *pOut++ =
emilmont 1:fdd22bb7aa52 166 (q15_t) (__SSAT(((q31_t) (*pIn++) * scaleFract) >> totShift, 16));
emilmont 1:fdd22bb7aa52 167
emilmont 1:fdd22bb7aa52 168 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 169 blkCnt--;
emilmont 1:fdd22bb7aa52 170 }
emilmont 1:fdd22bb7aa52 171 /* Set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 172 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 173 }
emilmont 1:fdd22bb7aa52 174
emilmont 1:fdd22bb7aa52 175 /* Return to application */
emilmont 1:fdd22bb7aa52 176 return (status);
emilmont 1:fdd22bb7aa52 177 }
emilmont 1:fdd22bb7aa52 178
emilmont 1:fdd22bb7aa52 179 /**
emilmont 1:fdd22bb7aa52 180 * @} end of MatrixScale group
emilmont 1:fdd22bb7aa52 181 */