CMSIS DSP Lib
Fork of mbed-dsp by
cmsis_dsp/MatrixFunctions/arm_mat_scale_f32.c@4:9cee975aadce, 2014-06-23 (annotated)
- Committer:
- mbed_official
- Date:
- Mon Jun 23 09:30:09 2014 +0100
- Revision:
- 4:9cee975aadce
- Parent:
- 3:7a284390b0ce
Synchronized with git revision 6e7c7bcec41226f536474daae3c13d49e4c0e865
Full URL: https://github.com/mbedmicro/mbed/commit/6e7c7bcec41226f536474daae3c13d49e4c0e865/
Fix signed unsigned compare in dsp library
Who changed what in which revision?
User | Revision | Line number | New contents of line |
---|---|---|---|
emilmont | 1:fdd22bb7aa52 | 1 | /* ---------------------------------------------------------------------- |
mbed_official | 3:7a284390b0ce | 2 | * Copyright (C) 2010-2013 ARM Limited. All rights reserved. |
emilmont | 1:fdd22bb7aa52 | 3 | * |
mbed_official | 3:7a284390b0ce | 4 | * $Date: 17. January 2013 |
mbed_official | 3:7a284390b0ce | 5 | * $Revision: V1.4.1 |
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 | * |
mbed_official | 3:7a284390b0ce | 14 | * Redistribution and use in source and binary forms, with or without |
mbed_official | 3:7a284390b0ce | 15 | * modification, are permitted provided that the following conditions |
mbed_official | 3:7a284390b0ce | 16 | * are met: |
mbed_official | 3:7a284390b0ce | 17 | * - Redistributions of source code must retain the above copyright |
mbed_official | 3:7a284390b0ce | 18 | * notice, this list of conditions and the following disclaimer. |
mbed_official | 3:7a284390b0ce | 19 | * - Redistributions in binary form must reproduce the above copyright |
mbed_official | 3:7a284390b0ce | 20 | * notice, this list of conditions and the following disclaimer in |
mbed_official | 3:7a284390b0ce | 21 | * the documentation and/or other materials provided with the |
mbed_official | 3:7a284390b0ce | 22 | * distribution. |
mbed_official | 3:7a284390b0ce | 23 | * - Neither the name of ARM LIMITED nor the names of its contributors |
mbed_official | 3:7a284390b0ce | 24 | * may be used to endorse or promote products derived from this |
mbed_official | 3:7a284390b0ce | 25 | * software without specific prior written permission. |
mbed_official | 3:7a284390b0ce | 26 | * |
mbed_official | 3:7a284390b0ce | 27 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
mbed_official | 3:7a284390b0ce | 28 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
mbed_official | 3:7a284390b0ce | 29 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS |
mbed_official | 3:7a284390b0ce | 30 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
mbed_official | 3:7a284390b0ce | 31 | * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
mbed_official | 3:7a284390b0ce | 32 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, |
mbed_official | 3:7a284390b0ce | 33 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
mbed_official | 3:7a284390b0ce | 34 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
mbed_official | 3:7a284390b0ce | 35 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
mbed_official | 3:7a284390b0ce | 36 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN |
mbed_official | 3:7a284390b0ce | 37 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
mbed_official | 3:7a284390b0ce | 38 | * POSSIBILITY OF SUCH DAMAGE. |
emilmont | 1:fdd22bb7aa52 | 39 | * -------------------------------------------------------------------- */ |
emilmont | 1:fdd22bb7aa52 | 40 | |
emilmont | 1:fdd22bb7aa52 | 41 | #include "arm_math.h" |
emilmont | 1:fdd22bb7aa52 | 42 | |
emilmont | 1:fdd22bb7aa52 | 43 | /** |
emilmont | 1:fdd22bb7aa52 | 44 | * @ingroup groupMatrix |
emilmont | 1:fdd22bb7aa52 | 45 | */ |
emilmont | 1:fdd22bb7aa52 | 46 | |
emilmont | 1:fdd22bb7aa52 | 47 | /** |
emilmont | 1:fdd22bb7aa52 | 48 | * @defgroup MatrixScale Matrix Scale |
emilmont | 1:fdd22bb7aa52 | 49 | * |
emilmont | 1:fdd22bb7aa52 | 50 | * Multiplies a matrix by a scalar. This is accomplished by multiplying each element in the |
emilmont | 1:fdd22bb7aa52 | 51 | * matrix by the scalar. For example: |
emilmont | 1:fdd22bb7aa52 | 52 | * \image html MatrixScale.gif "Matrix Scaling of a 3 x 3 matrix" |
emilmont | 1:fdd22bb7aa52 | 53 | * |
emilmont | 1:fdd22bb7aa52 | 54 | * The function checks to make sure that the input and output matrices are of the same size. |
emilmont | 1:fdd22bb7aa52 | 55 | * |
emilmont | 1:fdd22bb7aa52 | 56 | * In the fixed-point Q15 and Q31 functions, <code>scale</code> is represented by |
emilmont | 1:fdd22bb7aa52 | 57 | * a fractional multiplication <code>scaleFract</code> and an arithmetic shift <code>shift</code>. |
emilmont | 1:fdd22bb7aa52 | 58 | * The shift allows the gain of the scaling operation to exceed 1.0. |
emilmont | 1:fdd22bb7aa52 | 59 | * The overall scale factor applied to the fixed-point data is |
emilmont | 1:fdd22bb7aa52 | 60 | * <pre> |
emilmont | 1:fdd22bb7aa52 | 61 | * scale = scaleFract * 2^shift. |
emilmont | 1:fdd22bb7aa52 | 62 | * </pre> |
emilmont | 1:fdd22bb7aa52 | 63 | */ |
emilmont | 1:fdd22bb7aa52 | 64 | |
emilmont | 1:fdd22bb7aa52 | 65 | /** |
emilmont | 1:fdd22bb7aa52 | 66 | * @addtogroup MatrixScale |
emilmont | 1:fdd22bb7aa52 | 67 | * @{ |
emilmont | 1:fdd22bb7aa52 | 68 | */ |
emilmont | 1:fdd22bb7aa52 | 69 | |
emilmont | 1:fdd22bb7aa52 | 70 | /** |
emilmont | 1:fdd22bb7aa52 | 71 | * @brief Floating-point matrix scaling. |
emilmont | 1:fdd22bb7aa52 | 72 | * @param[in] *pSrc points to input matrix structure |
emilmont | 1:fdd22bb7aa52 | 73 | * @param[in] scale scale factor to be applied |
emilmont | 1:fdd22bb7aa52 | 74 | * @param[out] *pDst points to output matrix structure |
emilmont | 2:da51fb522205 | 75 | * @return The function returns either <code>ARM_MATH_SIZE_MISMATCH</code> |
emilmont | 1:fdd22bb7aa52 | 76 | * or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking. |
emilmont | 1:fdd22bb7aa52 | 77 | * |
emilmont | 1:fdd22bb7aa52 | 78 | */ |
emilmont | 1:fdd22bb7aa52 | 79 | |
emilmont | 1:fdd22bb7aa52 | 80 | arm_status arm_mat_scale_f32( |
emilmont | 1:fdd22bb7aa52 | 81 | const arm_matrix_instance_f32 * pSrc, |
emilmont | 1:fdd22bb7aa52 | 82 | float32_t scale, |
emilmont | 1:fdd22bb7aa52 | 83 | arm_matrix_instance_f32 * pDst) |
emilmont | 1:fdd22bb7aa52 | 84 | { |
emilmont | 1:fdd22bb7aa52 | 85 | float32_t *pIn = pSrc->pData; /* input data matrix pointer */ |
emilmont | 1:fdd22bb7aa52 | 86 | float32_t *pOut = pDst->pData; /* output data matrix pointer */ |
emilmont | 1:fdd22bb7aa52 | 87 | uint32_t numSamples; /* total number of elements in the matrix */ |
emilmont | 1:fdd22bb7aa52 | 88 | uint32_t blkCnt; /* loop counters */ |
emilmont | 1:fdd22bb7aa52 | 89 | arm_status status; /* status of matrix scaling */ |
emilmont | 1:fdd22bb7aa52 | 90 | |
mbed_official | 3:7a284390b0ce | 91 | #ifndef ARM_MATH_CM0_FAMILY |
emilmont | 1:fdd22bb7aa52 | 92 | |
emilmont | 1:fdd22bb7aa52 | 93 | float32_t in1, in2, in3, in4; /* temporary variables */ |
emilmont | 1:fdd22bb7aa52 | 94 | float32_t out1, out2, out3, out4; /* temporary variables */ |
emilmont | 1:fdd22bb7aa52 | 95 | |
mbed_official | 3:7a284390b0ce | 96 | #endif // #ifndef ARM_MATH_CM0_FAMILY |
emilmont | 1:fdd22bb7aa52 | 97 | |
emilmont | 1:fdd22bb7aa52 | 98 | #ifdef ARM_MATH_MATRIX_CHECK |
emilmont | 1:fdd22bb7aa52 | 99 | /* Check for matrix mismatch condition */ |
emilmont | 1:fdd22bb7aa52 | 100 | if((pSrc->numRows != pDst->numRows) || (pSrc->numCols != pDst->numCols)) |
emilmont | 1:fdd22bb7aa52 | 101 | { |
emilmont | 1:fdd22bb7aa52 | 102 | /* Set status as ARM_MATH_SIZE_MISMATCH */ |
emilmont | 1:fdd22bb7aa52 | 103 | status = ARM_MATH_SIZE_MISMATCH; |
emilmont | 1:fdd22bb7aa52 | 104 | } |
emilmont | 1:fdd22bb7aa52 | 105 | else |
emilmont | 1:fdd22bb7aa52 | 106 | #endif /* #ifdef ARM_MATH_MATRIX_CHECK */ |
emilmont | 1:fdd22bb7aa52 | 107 | { |
emilmont | 1:fdd22bb7aa52 | 108 | /* Total number of samples in the input matrix */ |
emilmont | 1:fdd22bb7aa52 | 109 | numSamples = (uint32_t) pSrc->numRows * pSrc->numCols; |
emilmont | 1:fdd22bb7aa52 | 110 | |
mbed_official | 3:7a284390b0ce | 111 | #ifndef ARM_MATH_CM0_FAMILY |
emilmont | 1:fdd22bb7aa52 | 112 | |
emilmont | 1:fdd22bb7aa52 | 113 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emilmont | 1:fdd22bb7aa52 | 114 | |
emilmont | 1:fdd22bb7aa52 | 115 | /* Loop Unrolling */ |
emilmont | 1:fdd22bb7aa52 | 116 | blkCnt = numSamples >> 2; |
emilmont | 1:fdd22bb7aa52 | 117 | |
emilmont | 1:fdd22bb7aa52 | 118 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 119 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 120 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 121 | { |
emilmont | 1:fdd22bb7aa52 | 122 | /* C(m,n) = A(m,n) * scale */ |
emilmont | 1:fdd22bb7aa52 | 123 | /* Scaling and results are stored in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 124 | in1 = pIn[0]; |
emilmont | 1:fdd22bb7aa52 | 125 | in2 = pIn[1]; |
emilmont | 1:fdd22bb7aa52 | 126 | in3 = pIn[2]; |
emilmont | 1:fdd22bb7aa52 | 127 | in4 = pIn[3]; |
emilmont | 1:fdd22bb7aa52 | 128 | |
emilmont | 1:fdd22bb7aa52 | 129 | out1 = in1 * scale; |
emilmont | 1:fdd22bb7aa52 | 130 | out2 = in2 * scale; |
emilmont | 1:fdd22bb7aa52 | 131 | out3 = in3 * scale; |
emilmont | 1:fdd22bb7aa52 | 132 | out4 = in4 * scale; |
emilmont | 1:fdd22bb7aa52 | 133 | |
emilmont | 1:fdd22bb7aa52 | 134 | |
emilmont | 1:fdd22bb7aa52 | 135 | pOut[0] = out1; |
emilmont | 1:fdd22bb7aa52 | 136 | pOut[1] = out2; |
emilmont | 1:fdd22bb7aa52 | 137 | pOut[2] = out3; |
emilmont | 1:fdd22bb7aa52 | 138 | pOut[3] = out4; |
emilmont | 1:fdd22bb7aa52 | 139 | |
emilmont | 1:fdd22bb7aa52 | 140 | /* update pointers to process next sampels */ |
emilmont | 1:fdd22bb7aa52 | 141 | pIn += 4u; |
emilmont | 1:fdd22bb7aa52 | 142 | pOut += 4u; |
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 | |
mbed_official | 3:7a284390b0ce | 159 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
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) * scale */ |
emilmont | 1:fdd22bb7aa52 | 164 | /* The results are stored in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 165 | *pOut++ = (*pIn++) * scale; |
emilmont | 1:fdd22bb7aa52 | 166 | |
emilmont | 1:fdd22bb7aa52 | 167 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 168 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 169 | } |
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 | */ |