V4.0.1 of the ARM CMSIS DSP libraries. Note that arm_bitreversal2.s, arm_cfft_f32.c and arm_rfft_fast_f32.c had to be removed. arm_bitreversal2.s will not assemble with the online tools. So, the fast f32 FFT functions are not yet available. All the other FFT functions are available.
Dependents: MPU9150_Example fir_f32 fir_f32 MPU9150_nucleo_noni2cdev ... more
BasicMathFunctions/arm_dot_prod_q31.c@0:3d9c67d97d6f, 2014-07-28 (annotated)
- Committer:
- emh203
- Date:
- Mon Jul 28 15:03:15 2014 +0000
- Revision:
- 0:3d9c67d97d6f
1st working commit. Had to remove arm_bitreversal2.s arm_cfft_f32.c and arm_rfft_fast_f32.c. The .s will not assemble. For now I removed these functions so we could at least have a library for the other functions.
Who changed what in which revision?
User | Revision | Line number | New contents of line |
---|---|---|---|
emh203 | 0:3d9c67d97d6f | 1 | /* ---------------------------------------------------------------------- |
emh203 | 0:3d9c67d97d6f | 2 | * Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
emh203 | 0:3d9c67d97d6f | 3 | * |
emh203 | 0:3d9c67d97d6f | 4 | * $Date: 12. March 2014 |
emh203 | 0:3d9c67d97d6f | 5 | * $Revision: V1.4.3 |
emh203 | 0:3d9c67d97d6f | 6 | * |
emh203 | 0:3d9c67d97d6f | 7 | * Project: CMSIS DSP Library |
emh203 | 0:3d9c67d97d6f | 8 | * Title: arm_dot_prod_q31.c |
emh203 | 0:3d9c67d97d6f | 9 | * |
emh203 | 0:3d9c67d97d6f | 10 | * Description: Q31 dot product. |
emh203 | 0:3d9c67d97d6f | 11 | * |
emh203 | 0:3d9c67d97d6f | 12 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
emh203 | 0:3d9c67d97d6f | 13 | * |
emh203 | 0:3d9c67d97d6f | 14 | * Redistribution and use in source and binary forms, with or without |
emh203 | 0:3d9c67d97d6f | 15 | * modification, are permitted provided that the following conditions |
emh203 | 0:3d9c67d97d6f | 16 | * are met: |
emh203 | 0:3d9c67d97d6f | 17 | * - Redistributions of source code must retain the above copyright |
emh203 | 0:3d9c67d97d6f | 18 | * notice, this list of conditions and the following disclaimer. |
emh203 | 0:3d9c67d97d6f | 19 | * - Redistributions in binary form must reproduce the above copyright |
emh203 | 0:3d9c67d97d6f | 20 | * notice, this list of conditions and the following disclaimer in |
emh203 | 0:3d9c67d97d6f | 21 | * the documentation and/or other materials provided with the |
emh203 | 0:3d9c67d97d6f | 22 | * distribution. |
emh203 | 0:3d9c67d97d6f | 23 | * - Neither the name of ARM LIMITED nor the names of its contributors |
emh203 | 0:3d9c67d97d6f | 24 | * may be used to endorse or promote products derived from this |
emh203 | 0:3d9c67d97d6f | 25 | * software without specific prior written permission. |
emh203 | 0:3d9c67d97d6f | 26 | * |
emh203 | 0:3d9c67d97d6f | 27 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
emh203 | 0:3d9c67d97d6f | 28 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
emh203 | 0:3d9c67d97d6f | 29 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS |
emh203 | 0:3d9c67d97d6f | 30 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
emh203 | 0:3d9c67d97d6f | 31 | * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
emh203 | 0:3d9c67d97d6f | 32 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, |
emh203 | 0:3d9c67d97d6f | 33 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
emh203 | 0:3d9c67d97d6f | 34 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
emh203 | 0:3d9c67d97d6f | 35 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
emh203 | 0:3d9c67d97d6f | 36 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN |
emh203 | 0:3d9c67d97d6f | 37 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
emh203 | 0:3d9c67d97d6f | 38 | * POSSIBILITY OF SUCH DAMAGE. |
emh203 | 0:3d9c67d97d6f | 39 | * -------------------------------------------------------------------- */ |
emh203 | 0:3d9c67d97d6f | 40 | |
emh203 | 0:3d9c67d97d6f | 41 | #include "arm_math.h" |
emh203 | 0:3d9c67d97d6f | 42 | |
emh203 | 0:3d9c67d97d6f | 43 | /** |
emh203 | 0:3d9c67d97d6f | 44 | * @ingroup groupMath |
emh203 | 0:3d9c67d97d6f | 45 | */ |
emh203 | 0:3d9c67d97d6f | 46 | |
emh203 | 0:3d9c67d97d6f | 47 | /** |
emh203 | 0:3d9c67d97d6f | 48 | * @addtogroup dot_prod |
emh203 | 0:3d9c67d97d6f | 49 | * @{ |
emh203 | 0:3d9c67d97d6f | 50 | */ |
emh203 | 0:3d9c67d97d6f | 51 | |
emh203 | 0:3d9c67d97d6f | 52 | /** |
emh203 | 0:3d9c67d97d6f | 53 | * @brief Dot product of Q31 vectors. |
emh203 | 0:3d9c67d97d6f | 54 | * @param[in] *pSrcA points to the first input vector |
emh203 | 0:3d9c67d97d6f | 55 | * @param[in] *pSrcB points to the second input vector |
emh203 | 0:3d9c67d97d6f | 56 | * @param[in] blockSize number of samples in each vector |
emh203 | 0:3d9c67d97d6f | 57 | * @param[out] *result output result returned here |
emh203 | 0:3d9c67d97d6f | 58 | * @return none. |
emh203 | 0:3d9c67d97d6f | 59 | * |
emh203 | 0:3d9c67d97d6f | 60 | * <b>Scaling and Overflow Behavior:</b> |
emh203 | 0:3d9c67d97d6f | 61 | * \par |
emh203 | 0:3d9c67d97d6f | 62 | * The intermediate multiplications are in 1.31 x 1.31 = 2.62 format and these |
emh203 | 0:3d9c67d97d6f | 63 | * are truncated to 2.48 format by discarding the lower 14 bits. |
emh203 | 0:3d9c67d97d6f | 64 | * The 2.48 result is then added without saturation to a 64-bit accumulator in 16.48 format. |
emh203 | 0:3d9c67d97d6f | 65 | * There are 15 guard bits in the accumulator and there is no risk of overflow as long as |
emh203 | 0:3d9c67d97d6f | 66 | * the length of the vectors is less than 2^16 elements. |
emh203 | 0:3d9c67d97d6f | 67 | * The return result is in 16.48 format. |
emh203 | 0:3d9c67d97d6f | 68 | */ |
emh203 | 0:3d9c67d97d6f | 69 | |
emh203 | 0:3d9c67d97d6f | 70 | void arm_dot_prod_q31( |
emh203 | 0:3d9c67d97d6f | 71 | q31_t * pSrcA, |
emh203 | 0:3d9c67d97d6f | 72 | q31_t * pSrcB, |
emh203 | 0:3d9c67d97d6f | 73 | uint32_t blockSize, |
emh203 | 0:3d9c67d97d6f | 74 | q63_t * result) |
emh203 | 0:3d9c67d97d6f | 75 | { |
emh203 | 0:3d9c67d97d6f | 76 | q63_t sum = 0; /* Temporary result storage */ |
emh203 | 0:3d9c67d97d6f | 77 | uint32_t blkCnt; /* loop counter */ |
emh203 | 0:3d9c67d97d6f | 78 | |
emh203 | 0:3d9c67d97d6f | 79 | |
emh203 | 0:3d9c67d97d6f | 80 | #ifndef ARM_MATH_CM0_FAMILY |
emh203 | 0:3d9c67d97d6f | 81 | |
emh203 | 0:3d9c67d97d6f | 82 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emh203 | 0:3d9c67d97d6f | 83 | q31_t inA1, inA2, inA3, inA4; |
emh203 | 0:3d9c67d97d6f | 84 | q31_t inB1, inB2, inB3, inB4; |
emh203 | 0:3d9c67d97d6f | 85 | |
emh203 | 0:3d9c67d97d6f | 86 | /*loop Unrolling */ |
emh203 | 0:3d9c67d97d6f | 87 | blkCnt = blockSize >> 2u; |
emh203 | 0:3d9c67d97d6f | 88 | |
emh203 | 0:3d9c67d97d6f | 89 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emh203 | 0:3d9c67d97d6f | 90 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emh203 | 0:3d9c67d97d6f | 91 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 92 | { |
emh203 | 0:3d9c67d97d6f | 93 | /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */ |
emh203 | 0:3d9c67d97d6f | 94 | /* Calculate dot product and then store the result in a temporary buffer. */ |
emh203 | 0:3d9c67d97d6f | 95 | inA1 = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 96 | inA2 = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 97 | inA3 = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 98 | inA4 = *pSrcA++; |
emh203 | 0:3d9c67d97d6f | 99 | inB1 = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 100 | inB2 = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 101 | inB3 = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 102 | inB4 = *pSrcB++; |
emh203 | 0:3d9c67d97d6f | 103 | |
emh203 | 0:3d9c67d97d6f | 104 | sum += ((q63_t) inA1 * inB1) >> 14u; |
emh203 | 0:3d9c67d97d6f | 105 | sum += ((q63_t) inA2 * inB2) >> 14u; |
emh203 | 0:3d9c67d97d6f | 106 | sum += ((q63_t) inA3 * inB3) >> 14u; |
emh203 | 0:3d9c67d97d6f | 107 | sum += ((q63_t) inA4 * inB4) >> 14u; |
emh203 | 0:3d9c67d97d6f | 108 | |
emh203 | 0:3d9c67d97d6f | 109 | /* Decrement the loop counter */ |
emh203 | 0:3d9c67d97d6f | 110 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 111 | } |
emh203 | 0:3d9c67d97d6f | 112 | |
emh203 | 0:3d9c67d97d6f | 113 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
emh203 | 0:3d9c67d97d6f | 114 | ** No loop unrolling is used. */ |
emh203 | 0:3d9c67d97d6f | 115 | blkCnt = blockSize % 0x4u; |
emh203 | 0:3d9c67d97d6f | 116 | |
emh203 | 0:3d9c67d97d6f | 117 | #else |
emh203 | 0:3d9c67d97d6f | 118 | |
emh203 | 0:3d9c67d97d6f | 119 | /* Run the below code for Cortex-M0 */ |
emh203 | 0:3d9c67d97d6f | 120 | |
emh203 | 0:3d9c67d97d6f | 121 | /* Initialize blkCnt with number of samples */ |
emh203 | 0:3d9c67d97d6f | 122 | blkCnt = blockSize; |
emh203 | 0:3d9c67d97d6f | 123 | |
emh203 | 0:3d9c67d97d6f | 124 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
emh203 | 0:3d9c67d97d6f | 125 | |
emh203 | 0:3d9c67d97d6f | 126 | |
emh203 | 0:3d9c67d97d6f | 127 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 128 | { |
emh203 | 0:3d9c67d97d6f | 129 | /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */ |
emh203 | 0:3d9c67d97d6f | 130 | /* Calculate dot product and then store the result in a temporary buffer. */ |
emh203 | 0:3d9c67d97d6f | 131 | sum += ((q63_t) * pSrcA++ * *pSrcB++) >> 14u; |
emh203 | 0:3d9c67d97d6f | 132 | |
emh203 | 0:3d9c67d97d6f | 133 | /* Decrement the loop counter */ |
emh203 | 0:3d9c67d97d6f | 134 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 135 | } |
emh203 | 0:3d9c67d97d6f | 136 | |
emh203 | 0:3d9c67d97d6f | 137 | /* Store the result in the destination buffer in 16.48 format */ |
emh203 | 0:3d9c67d97d6f | 138 | *result = sum; |
emh203 | 0:3d9c67d97d6f | 139 | } |
emh203 | 0:3d9c67d97d6f | 140 | |
emh203 | 0:3d9c67d97d6f | 141 | /** |
emh203 | 0:3d9c67d97d6f | 142 | * @} end of dot_prod group |
emh203 | 0:3d9c67d97d6f | 143 | */ |