CMSIS DSP library

Dependents:   KL25Z_FFT_Demo Hat_Board_v5_1 KL25Z_FFT_Demo_tony KL25Z_FFT_Demo_tony ... more

Fork of mbed-dsp by mbed official

Committer:
emilmont
Date:
Thu May 30 17:10:11 2013 +0100
Revision:
2:da51fb522205
Parent:
1:fdd22bb7aa52
Child:
3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source

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 2:da51fb522205 5 * $Revision: V1.1.0
emilmont 1:fdd22bb7aa52 6 *
emilmont 2:da51fb522205 7 * Project: CMSIS DSP Library
emilmont 1:fdd22bb7aa52 8 * Title: arm_mat_scale_f32.c
emilmont 1:fdd22bb7aa52 9 *
emilmont 2:da51fb522205 10 * Description: Multiplies a floating-point 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 * @defgroup MatrixScale Matrix Scale
emilmont 1:fdd22bb7aa52 47 *
emilmont 1:fdd22bb7aa52 48 * Multiplies a matrix by a scalar. This is accomplished by multiplying each element in the
emilmont 1:fdd22bb7aa52 49 * matrix by the scalar. For example:
emilmont 1:fdd22bb7aa52 50 * \image html MatrixScale.gif "Matrix Scaling of a 3 x 3 matrix"
emilmont 1:fdd22bb7aa52 51 *
emilmont 1:fdd22bb7aa52 52 * The function checks to make sure that the input and output matrices are of the same size.
emilmont 1:fdd22bb7aa52 53 *
emilmont 1:fdd22bb7aa52 54 * In the fixed-point Q15 and Q31 functions, <code>scale</code> is represented by
emilmont 1:fdd22bb7aa52 55 * a fractional multiplication <code>scaleFract</code> and an arithmetic shift <code>shift</code>.
emilmont 1:fdd22bb7aa52 56 * The shift allows the gain of the scaling operation to exceed 1.0.
emilmont 1:fdd22bb7aa52 57 * The overall scale factor applied to the fixed-point data is
emilmont 1:fdd22bb7aa52 58 * <pre>
emilmont 1:fdd22bb7aa52 59 * scale = scaleFract * 2^shift.
emilmont 1:fdd22bb7aa52 60 * </pre>
emilmont 1:fdd22bb7aa52 61 */
emilmont 1:fdd22bb7aa52 62
emilmont 1:fdd22bb7aa52 63 /**
emilmont 1:fdd22bb7aa52 64 * @addtogroup MatrixScale
emilmont 1:fdd22bb7aa52 65 * @{
emilmont 1:fdd22bb7aa52 66 */
emilmont 1:fdd22bb7aa52 67
emilmont 1:fdd22bb7aa52 68 /**
emilmont 1:fdd22bb7aa52 69 * @brief Floating-point matrix scaling.
emilmont 1:fdd22bb7aa52 70 * @param[in] *pSrc points to input matrix structure
emilmont 1:fdd22bb7aa52 71 * @param[in] scale scale factor to be applied
emilmont 1:fdd22bb7aa52 72 * @param[out] *pDst points to output matrix structure
emilmont 2:da51fb522205 73 * @return The function returns either <code>ARM_MATH_SIZE_MISMATCH</code>
emilmont 1:fdd22bb7aa52 74 * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
emilmont 1:fdd22bb7aa52 75 *
emilmont 1:fdd22bb7aa52 76 */
emilmont 1:fdd22bb7aa52 77
emilmont 1:fdd22bb7aa52 78 arm_status arm_mat_scale_f32(
emilmont 1:fdd22bb7aa52 79 const arm_matrix_instance_f32 * pSrc,
emilmont 1:fdd22bb7aa52 80 float32_t scale,
emilmont 1:fdd22bb7aa52 81 arm_matrix_instance_f32 * pDst)
emilmont 1:fdd22bb7aa52 82 {
emilmont 1:fdd22bb7aa52 83 float32_t *pIn = pSrc->pData; /* input data matrix pointer */
emilmont 1:fdd22bb7aa52 84 float32_t *pOut = pDst->pData; /* output data matrix pointer */
emilmont 1:fdd22bb7aa52 85 uint32_t numSamples; /* total number of elements in the matrix */
emilmont 1:fdd22bb7aa52 86 uint32_t blkCnt; /* loop counters */
emilmont 1:fdd22bb7aa52 87 arm_status status; /* status of matrix scaling */
emilmont 1:fdd22bb7aa52 88
emilmont 1:fdd22bb7aa52 89 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 90
emilmont 1:fdd22bb7aa52 91 float32_t in1, in2, in3, in4; /* temporary variables */
emilmont 1:fdd22bb7aa52 92 float32_t out1, out2, out3, out4; /* temporary variables */
emilmont 1:fdd22bb7aa52 93
emilmont 1:fdd22bb7aa52 94 #endif // #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 95
emilmont 1:fdd22bb7aa52 96 #ifdef ARM_MATH_MATRIX_CHECK
emilmont 1:fdd22bb7aa52 97 /* Check for matrix mismatch condition */
emilmont 1:fdd22bb7aa52 98 if((pSrc->numRows != pDst->numRows) || (pSrc->numCols != pDst->numCols))
emilmont 1:fdd22bb7aa52 99 {
emilmont 1:fdd22bb7aa52 100 /* Set status as ARM_MATH_SIZE_MISMATCH */
emilmont 1:fdd22bb7aa52 101 status = ARM_MATH_SIZE_MISMATCH;
emilmont 1:fdd22bb7aa52 102 }
emilmont 1:fdd22bb7aa52 103 else
emilmont 1:fdd22bb7aa52 104 #endif /* #ifdef ARM_MATH_MATRIX_CHECK */
emilmont 1:fdd22bb7aa52 105 {
emilmont 1:fdd22bb7aa52 106 /* Total number of samples in the input matrix */
emilmont 1:fdd22bb7aa52 107 numSamples = (uint32_t) pSrc->numRows * pSrc->numCols;
emilmont 1:fdd22bb7aa52 108
emilmont 1:fdd22bb7aa52 109 #ifndef ARM_MATH_CM0
emilmont 1:fdd22bb7aa52 110
emilmont 1:fdd22bb7aa52 111 /* Run the below code for Cortex-M4 and Cortex-M3 */
emilmont 1:fdd22bb7aa52 112
emilmont 1:fdd22bb7aa52 113 /* Loop Unrolling */
emilmont 1:fdd22bb7aa52 114 blkCnt = numSamples >> 2;
emilmont 1:fdd22bb7aa52 115
emilmont 1:fdd22bb7aa52 116 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emilmont 1:fdd22bb7aa52 117 ** a second loop below computes the remaining 1 to 3 samples. */
emilmont 1:fdd22bb7aa52 118 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 119 {
emilmont 1:fdd22bb7aa52 120 /* C(m,n) = A(m,n) * scale */
emilmont 1:fdd22bb7aa52 121 /* Scaling and results are stored in the destination buffer. */
emilmont 1:fdd22bb7aa52 122 in1 = pIn[0];
emilmont 1:fdd22bb7aa52 123 in2 = pIn[1];
emilmont 1:fdd22bb7aa52 124 in3 = pIn[2];
emilmont 1:fdd22bb7aa52 125 in4 = pIn[3];
emilmont 1:fdd22bb7aa52 126
emilmont 1:fdd22bb7aa52 127 out1 = in1 * scale;
emilmont 1:fdd22bb7aa52 128 out2 = in2 * scale;
emilmont 1:fdd22bb7aa52 129 out3 = in3 * scale;
emilmont 1:fdd22bb7aa52 130 out4 = in4 * scale;
emilmont 1:fdd22bb7aa52 131
emilmont 1:fdd22bb7aa52 132
emilmont 1:fdd22bb7aa52 133 pOut[0] = out1;
emilmont 1:fdd22bb7aa52 134 pOut[1] = out2;
emilmont 1:fdd22bb7aa52 135 pOut[2] = out3;
emilmont 1:fdd22bb7aa52 136 pOut[3] = out4;
emilmont 1:fdd22bb7aa52 137
emilmont 1:fdd22bb7aa52 138 /* update pointers to process next sampels */
emilmont 1:fdd22bb7aa52 139 pIn += 4u;
emilmont 1:fdd22bb7aa52 140 pOut += 4u;
emilmont 1:fdd22bb7aa52 141
emilmont 1:fdd22bb7aa52 142 /* Decrement the numSamples loop counter */
emilmont 1:fdd22bb7aa52 143 blkCnt--;
emilmont 1:fdd22bb7aa52 144 }
emilmont 1:fdd22bb7aa52 145
emilmont 1:fdd22bb7aa52 146 /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
emilmont 1:fdd22bb7aa52 147 ** No loop unrolling is used. */
emilmont 1:fdd22bb7aa52 148 blkCnt = numSamples % 0x4u;
emilmont 1:fdd22bb7aa52 149
emilmont 1:fdd22bb7aa52 150 #else
emilmont 1:fdd22bb7aa52 151
emilmont 1:fdd22bb7aa52 152 /* Run the below code for Cortex-M0 */
emilmont 1:fdd22bb7aa52 153
emilmont 1:fdd22bb7aa52 154 /* Initialize blkCnt with number of samples */
emilmont 1:fdd22bb7aa52 155 blkCnt = numSamples;
emilmont 1:fdd22bb7aa52 156
emilmont 1:fdd22bb7aa52 157 #endif /* #ifndef ARM_MATH_CM0 */
emilmont 1:fdd22bb7aa52 158
emilmont 1:fdd22bb7aa52 159 while(blkCnt > 0u)
emilmont 1:fdd22bb7aa52 160 {
emilmont 1:fdd22bb7aa52 161 /* C(m,n) = A(m,n) * scale */
emilmont 1:fdd22bb7aa52 162 /* The results are stored in the destination buffer. */
emilmont 1:fdd22bb7aa52 163 *pOut++ = (*pIn++) * scale;
emilmont 1:fdd22bb7aa52 164
emilmont 1:fdd22bb7aa52 165 /* Decrement the loop counter */
emilmont 1:fdd22bb7aa52 166 blkCnt--;
emilmont 1:fdd22bb7aa52 167 }
emilmont 1:fdd22bb7aa52 168
emilmont 1:fdd22bb7aa52 169 /* Set status as ARM_MATH_SUCCESS */
emilmont 1:fdd22bb7aa52 170 status = ARM_MATH_SUCCESS;
emilmont 1:fdd22bb7aa52 171 }
emilmont 1:fdd22bb7aa52 172
emilmont 1:fdd22bb7aa52 173 /* Return to application */
emilmont 1:fdd22bb7aa52 174 return (status);
emilmont 1:fdd22bb7aa52 175 }
emilmont 1:fdd22bb7aa52 176
emilmont 1:fdd22bb7aa52 177 /**
emilmont 1:fdd22bb7aa52 178 * @} end of MatrixScale group
emilmont 1:fdd22bb7aa52 179 */