| 1 | /* ----------------------------------------------------------------------
|
|---|
| 2 | * Project: CMSIS DSP Library
|
|---|
| 3 | * Title: arm_add_f32.c
|
|---|
| 4 | * Description: Floating-point vector addition
|
|---|
| 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 groupMath
|
|---|
| 33 | */
|
|---|
| 34 |
|
|---|
| 35 | /**
|
|---|
| 36 | * @defgroup BasicAdd Vector Addition
|
|---|
| 37 | *
|
|---|
| 38 | * Element-by-element addition of two vectors.
|
|---|
| 39 | *
|
|---|
| 40 | * <pre>
|
|---|
| 41 | * pDst[n] = pSrcA[n] + pSrcB[n], 0 <= n < blockSize.
|
|---|
| 42 | * </pre>
|
|---|
| 43 | *
|
|---|
| 44 | * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
|
|---|
| 45 | */
|
|---|
| 46 |
|
|---|
| 47 | /**
|
|---|
| 48 | * @addtogroup BasicAdd
|
|---|
| 49 | * @{
|
|---|
| 50 | */
|
|---|
| 51 |
|
|---|
| 52 | /**
|
|---|
| 53 | * @brief Floating-point vector addition.
|
|---|
| 54 | * @param[in] *pSrcA points to the first input vector
|
|---|
| 55 | * @param[in] *pSrcB points to the second input vector
|
|---|
| 56 | * @param[out] *pDst points to the output vector
|
|---|
| 57 | * @param[in] blockSize number of samples in each vector
|
|---|
| 58 | * @return none.
|
|---|
| 59 | */
|
|---|
| 60 |
|
|---|
| 61 | void arm_add_f32(
|
|---|
| 62 | float32_t * pSrcA,
|
|---|
| 63 | float32_t * pSrcB,
|
|---|
| 64 | float32_t * pDst,
|
|---|
| 65 | uint32_t blockSize)
|
|---|
| 66 | {
|
|---|
| 67 | uint32_t blkCnt; /* loop counter */
|
|---|
| 68 |
|
|---|
| 69 | #if defined (ARM_MATH_DSP)
|
|---|
| 70 |
|
|---|
| 71 | /* Run the below code for Cortex-M4 and Cortex-M3 */
|
|---|
| 72 | float32_t inA1, inA2, inA3, inA4; /* temporary input variabels */
|
|---|
| 73 | float32_t inB1, inB2, inB3, inB4; /* temporary input variables */
|
|---|
| 74 |
|
|---|
| 75 | /*loop Unrolling */
|
|---|
| 76 | blkCnt = blockSize >> 2U;
|
|---|
| 77 |
|
|---|
| 78 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
|
|---|
| 79 | ** a second loop below computes the remaining 1 to 3 samples. */
|
|---|
| 80 | while (blkCnt > 0U)
|
|---|
| 81 | {
|
|---|
| 82 | /* C = A + B */
|
|---|
| 83 | /* Add and then store the results in the destination buffer. */
|
|---|
| 84 |
|
|---|
| 85 | /* read four inputs from sourceA and four inputs from sourceB */
|
|---|
| 86 | inA1 = *pSrcA;
|
|---|
| 87 | inB1 = *pSrcB;
|
|---|
| 88 | inA2 = *(pSrcA + 1);
|
|---|
| 89 | inB2 = *(pSrcB + 1);
|
|---|
| 90 | inA3 = *(pSrcA + 2);
|
|---|
| 91 | inB3 = *(pSrcB + 2);
|
|---|
| 92 | inA4 = *(pSrcA + 3);
|
|---|
| 93 | inB4 = *(pSrcB + 3);
|
|---|
| 94 |
|
|---|
| 95 | /* C = A + B */
|
|---|
| 96 | /* add and store result to destination */
|
|---|
| 97 | *pDst = inA1 + inB1;
|
|---|
| 98 | *(pDst + 1) = inA2 + inB2;
|
|---|
| 99 | *(pDst + 2) = inA3 + inB3;
|
|---|
| 100 | *(pDst + 3) = inA4 + inB4;
|
|---|
| 101 |
|
|---|
| 102 | /* update pointers to process next samples */
|
|---|
| 103 | pSrcA += 4U;
|
|---|
| 104 | pSrcB += 4U;
|
|---|
| 105 | pDst += 4U;
|
|---|
| 106 |
|
|---|
| 107 |
|
|---|
| 108 | /* Decrement the loop counter */
|
|---|
| 109 | blkCnt--;
|
|---|
| 110 | }
|
|---|
| 111 |
|
|---|
| 112 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
|
|---|
| 113 | ** No loop unrolling is used. */
|
|---|
| 114 | blkCnt = blockSize % 0x4U;
|
|---|
| 115 |
|
|---|
| 116 | #else
|
|---|
| 117 |
|
|---|
| 118 | /* Run the below code for Cortex-M0 */
|
|---|
| 119 |
|
|---|
| 120 | /* Initialize blkCnt with number of samples */
|
|---|
| 121 | blkCnt = blockSize;
|
|---|
| 122 |
|
|---|
| 123 | #endif /* #if defined (ARM_MATH_DSP) */
|
|---|
| 124 |
|
|---|
| 125 | while (blkCnt > 0U)
|
|---|
| 126 | {
|
|---|
| 127 | /* C = A + B */
|
|---|
| 128 | /* Add and then store the results in the destination buffer. */
|
|---|
| 129 | *pDst++ = (*pSrcA++) + (*pSrcB++);
|
|---|
| 130 |
|
|---|
| 131 | /* Decrement the loop counter */
|
|---|
| 132 | blkCnt--;
|
|---|
| 133 | }
|
|---|
| 134 | }
|
|---|
| 135 |
|
|---|
| 136 | /**
|
|---|
| 137 | * @} end of BasicAdd group
|
|---|
| 138 | */
|
|---|
