CMSIS DSP Lib
Fork of mbed-dsp by
cmsis_dsp/StatisticsFunctions/arm_power_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 | 2:da51fb522205 | 8 | * Title: arm_power_f32.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 2:da51fb522205 | 10 | * Description: Sum of the squares of the elements of a floating-point vector. |
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 groupStats |
emilmont | 1:fdd22bb7aa52 | 45 | */ |
emilmont | 1:fdd22bb7aa52 | 46 | |
emilmont | 1:fdd22bb7aa52 | 47 | /** |
emilmont | 1:fdd22bb7aa52 | 48 | * @defgroup power Power |
emilmont | 1:fdd22bb7aa52 | 49 | * |
emilmont | 1:fdd22bb7aa52 | 50 | * Calculates the sum of the squares of the elements in the input vector. |
emilmont | 1:fdd22bb7aa52 | 51 | * The underlying algorithm is used: |
emilmont | 1:fdd22bb7aa52 | 52 | * |
emilmont | 1:fdd22bb7aa52 | 53 | * <pre> |
emilmont | 2:da51fb522205 | 54 | * Result = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + pSrc[2] * pSrc[2] + ... + pSrc[blockSize-1] * pSrc[blockSize-1]; |
emilmont | 1:fdd22bb7aa52 | 55 | * </pre> |
emilmont | 1:fdd22bb7aa52 | 56 | * |
emilmont | 1:fdd22bb7aa52 | 57 | * There are separate functions for floating point, Q31, Q15, and Q7 data types. |
emilmont | 1:fdd22bb7aa52 | 58 | */ |
emilmont | 1:fdd22bb7aa52 | 59 | |
emilmont | 1:fdd22bb7aa52 | 60 | /** |
emilmont | 1:fdd22bb7aa52 | 61 | * @addtogroup power |
emilmont | 1:fdd22bb7aa52 | 62 | * @{ |
emilmont | 1:fdd22bb7aa52 | 63 | */ |
emilmont | 1:fdd22bb7aa52 | 64 | |
emilmont | 1:fdd22bb7aa52 | 65 | |
emilmont | 1:fdd22bb7aa52 | 66 | /** |
emilmont | 1:fdd22bb7aa52 | 67 | * @brief Sum of the squares of the elements of a floating-point vector. |
emilmont | 1:fdd22bb7aa52 | 68 | * @param[in] *pSrc points to the input vector |
emilmont | 1:fdd22bb7aa52 | 69 | * @param[in] blockSize length of the input vector |
emilmont | 1:fdd22bb7aa52 | 70 | * @param[out] *pResult sum of the squares value returned here |
emilmont | 1:fdd22bb7aa52 | 71 | * @return none. |
emilmont | 1:fdd22bb7aa52 | 72 | * |
emilmont | 1:fdd22bb7aa52 | 73 | */ |
emilmont | 1:fdd22bb7aa52 | 74 | |
emilmont | 1:fdd22bb7aa52 | 75 | |
emilmont | 1:fdd22bb7aa52 | 76 | void arm_power_f32( |
emilmont | 1:fdd22bb7aa52 | 77 | float32_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 78 | uint32_t blockSize, |
emilmont | 1:fdd22bb7aa52 | 79 | float32_t * pResult) |
emilmont | 1:fdd22bb7aa52 | 80 | { |
emilmont | 1:fdd22bb7aa52 | 81 | float32_t sum = 0.0f; /* accumulator */ |
emilmont | 1:fdd22bb7aa52 | 82 | float32_t in; /* Temporary variable to store input value */ |
emilmont | 1:fdd22bb7aa52 | 83 | uint32_t blkCnt; /* loop counter */ |
emilmont | 1:fdd22bb7aa52 | 84 | |
mbed_official | 3:7a284390b0ce | 85 | #ifndef ARM_MATH_CM0_FAMILY |
emilmont | 1:fdd22bb7aa52 | 86 | |
emilmont | 1:fdd22bb7aa52 | 87 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emilmont | 1:fdd22bb7aa52 | 88 | |
emilmont | 1:fdd22bb7aa52 | 89 | /*loop Unrolling */ |
emilmont | 1:fdd22bb7aa52 | 90 | blkCnt = blockSize >> 2u; |
emilmont | 1:fdd22bb7aa52 | 91 | |
emilmont | 1:fdd22bb7aa52 | 92 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emilmont | 1:fdd22bb7aa52 | 93 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emilmont | 1:fdd22bb7aa52 | 94 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 95 | { |
emilmont | 1:fdd22bb7aa52 | 96 | /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ |
emilmont | 1:fdd22bb7aa52 | 97 | /* Compute Power and then store the result in a temporary variable, sum. */ |
emilmont | 1:fdd22bb7aa52 | 98 | in = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 99 | sum += in * in; |
emilmont | 1:fdd22bb7aa52 | 100 | in = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 101 | sum += in * in; |
emilmont | 1:fdd22bb7aa52 | 102 | in = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 103 | sum += in * in; |
emilmont | 1:fdd22bb7aa52 | 104 | in = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 105 | sum += in * in; |
emilmont | 1:fdd22bb7aa52 | 106 | |
emilmont | 1:fdd22bb7aa52 | 107 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 108 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 109 | } |
emilmont | 1:fdd22bb7aa52 | 110 | |
emilmont | 1:fdd22bb7aa52 | 111 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
emilmont | 1:fdd22bb7aa52 | 112 | ** No loop unrolling is used. */ |
emilmont | 1:fdd22bb7aa52 | 113 | blkCnt = blockSize % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 114 | |
emilmont | 1:fdd22bb7aa52 | 115 | |
emilmont | 1:fdd22bb7aa52 | 116 | #else |
emilmont | 1:fdd22bb7aa52 | 117 | |
emilmont | 1:fdd22bb7aa52 | 118 | /* Run the below code for Cortex-M0 */ |
emilmont | 1:fdd22bb7aa52 | 119 | |
emilmont | 1:fdd22bb7aa52 | 120 | /* Loop over blockSize number of values */ |
emilmont | 1:fdd22bb7aa52 | 121 | blkCnt = blockSize; |
emilmont | 1:fdd22bb7aa52 | 122 | |
mbed_official | 3:7a284390b0ce | 123 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
emilmont | 1:fdd22bb7aa52 | 124 | |
emilmont | 1:fdd22bb7aa52 | 125 | |
emilmont | 1:fdd22bb7aa52 | 126 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 127 | { |
emilmont | 1:fdd22bb7aa52 | 128 | /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ |
emilmont | 1:fdd22bb7aa52 | 129 | /* compute power and then store the result in a temporary variable, sum. */ |
emilmont | 1:fdd22bb7aa52 | 130 | in = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 131 | sum += in * in; |
emilmont | 1:fdd22bb7aa52 | 132 | |
emilmont | 1:fdd22bb7aa52 | 133 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 134 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 135 | } |
emilmont | 1:fdd22bb7aa52 | 136 | |
emilmont | 1:fdd22bb7aa52 | 137 | /* Store the result to the destination */ |
emilmont | 1:fdd22bb7aa52 | 138 | *pResult = sum; |
emilmont | 1:fdd22bb7aa52 | 139 | } |
emilmont | 1:fdd22bb7aa52 | 140 | |
emilmont | 1:fdd22bb7aa52 | 141 | /** |
emilmont | 1:fdd22bb7aa52 | 142 | * @} end of power group |
emilmont | 1:fdd22bb7aa52 | 143 | */ |