Rev 2 | Details | Compare with Previous | Last modification | View Log | RSS feed
| Rev | Author | Line No. | Line |
|---|---|---|---|
| 2 | mjames | 1 | /* ---------------------------------------------------------------------- |
| 2 | * Project: CMSIS DSP Library |
||
| 3 | * Title: arm_power_f32.c |
||
| 4 | * Description: Sum of the squares of the elements of a floating-point vector |
||
| 5 | * |
||
| 6 | * $Date: 27. January 2017 |
||
| 7 | * $Revision: V.1.5.1 |
||
| 8 | * |
||
| 9 | * Target Processor: Cortex-M cores |
||
| 10 | * -------------------------------------------------------------------- */ |
||
| 11 | /* |
||
| 12 | * Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved. |
||
| 13 | * |
||
| 14 | * SPDX-License-Identifier: Apache-2.0 |
||
| 15 | * |
||
| 16 | * Licensed under the Apache License, Version 2.0 (the License); you may |
||
| 17 | * not use this file except in compliance with the License. |
||
| 18 | * You may obtain a copy of the License at |
||
| 19 | * |
||
| 20 | * www.apache.org/licenses/LICENSE-2.0 |
||
| 21 | * |
||
| 22 | * Unless required by applicable law or agreed to in writing, software |
||
| 23 | * distributed under the License is distributed on an AS IS BASIS, WITHOUT |
||
| 24 | * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
||
| 25 | * See the License for the specific language governing permissions and |
||
| 26 | * limitations under the License. |
||
| 27 | */ |
||
| 28 | |||
| 29 | #include "arm_math.h" |
||
| 30 | |||
| 31 | /** |
||
| 32 | * @ingroup groupStats |
||
| 33 | */ |
||
| 34 | |||
| 35 | /** |
||
| 36 | * @defgroup power Power |
||
| 37 | * |
||
| 38 | * Calculates the sum of the squares of the elements in the input vector. |
||
| 39 | * The underlying algorithm is used: |
||
| 40 | * |
||
| 41 | * <pre> |
||
| 42 | * Result = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + pSrc[2] * pSrc[2] + ... + pSrc[blockSize-1] * pSrc[blockSize-1]; |
||
| 43 | * </pre> |
||
| 44 | * |
||
| 45 | * There are separate functions for floating point, Q31, Q15, and Q7 data types. |
||
| 46 | */ |
||
| 47 | |||
| 48 | /** |
||
| 49 | * @addtogroup power |
||
| 50 | * @{ |
||
| 51 | */ |
||
| 52 | |||
| 53 | |||
| 54 | /** |
||
| 55 | * @brief Sum of the squares of the elements of a floating-point vector. |
||
| 56 | * @param[in] *pSrc points to the input vector |
||
| 57 | * @param[in] blockSize length of the input vector |
||
| 58 | * @param[out] *pResult sum of the squares value returned here |
||
| 59 | * @return none. |
||
| 60 | * |
||
| 61 | */ |
||
| 62 | |||
| 63 | |||
| 64 | void arm_power_f32( |
||
| 65 | float32_t * pSrc, |
||
| 66 | uint32_t blockSize, |
||
| 67 | float32_t * pResult) |
||
| 68 | { |
||
| 69 | float32_t sum = 0.0f; /* accumulator */ |
||
| 70 | float32_t in; /* Temporary variable to store input value */ |
||
| 71 | uint32_t blkCnt; /* loop counter */ |
||
| 72 | |||
| 73 | #if defined (ARM_MATH_DSP) |
||
| 74 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
||
| 75 | |||
| 76 | /*loop Unrolling */ |
||
| 77 | blkCnt = blockSize >> 2U; |
||
| 78 | |||
| 79 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
||
| 80 | ** a second loop below computes the remaining 1 to 3 samples. */ |
||
| 81 | while (blkCnt > 0U) |
||
| 82 | { |
||
| 83 | /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ |
||
| 84 | /* Compute Power and then store the result in a temporary variable, sum. */ |
||
| 85 | in = *pSrc++; |
||
| 86 | sum += in * in; |
||
| 87 | in = *pSrc++; |
||
| 88 | sum += in * in; |
||
| 89 | in = *pSrc++; |
||
| 90 | sum += in * in; |
||
| 91 | in = *pSrc++; |
||
| 92 | sum += in * in; |
||
| 93 | |||
| 94 | /* Decrement the loop counter */ |
||
| 95 | blkCnt--; |
||
| 96 | } |
||
| 97 | |||
| 98 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
||
| 99 | ** No loop unrolling is used. */ |
||
| 100 | blkCnt = blockSize % 0x4U; |
||
| 101 | |||
| 102 | |||
| 103 | #else |
||
| 104 | /* Run the below code for Cortex-M0 */ |
||
| 105 | |||
| 106 | /* Loop over blockSize number of values */ |
||
| 107 | blkCnt = blockSize; |
||
| 108 | |||
| 109 | #endif /* #if defined (ARM_MATH_DSP) */ |
||
| 110 | |||
| 111 | |||
| 112 | while (blkCnt > 0U) |
||
| 113 | { |
||
| 114 | /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ |
||
| 115 | /* compute power and then store the result in a temporary variable, sum. */ |
||
| 116 | in = *pSrc++; |
||
| 117 | sum += in * in; |
||
| 118 | |||
| 119 | /* Decrement the loop counter */ |
||
| 120 | blkCnt--; |
||
| 121 | } |
||
| 122 | |||
| 123 | /* Store the result to the destination */ |
||
| 124 | *pResult = sum; |
||
| 125 | } |
||
| 126 | |||
| 127 | /** |
||
| 128 | * @} end of power group |
||
| 129 | */ |