summaryrefslogtreecommitdiff
path: root/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_dot_prod_f32.c
blob: 41ec12e25878cb8414a8732be20e92c465405adc (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_dot_prod_f32.c
 * Description:  Floating-point dot product
 *
 * $Date:        18. March 2019
 * $Revision:    V1.6.0
 *
 * Target Processor: Cortex-M cores
 * -------------------------------------------------------------------- */
/*
 * Copyright (C) 2010-2019 ARM Limited or its affiliates. All rights reserved.
 *
 * SPDX-License-Identifier: Apache-2.0
 *
 * Licensed under the Apache License, Version 2.0 (the License); you may
 * not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 * www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an AS IS BASIS, WITHOUT
 * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#include "arm_math.h"

/**
  @ingroup groupMath
 */

/**
  @defgroup BasicDotProd Vector Dot Product

  Computes the dot product of two vectors.
  The vectors are multiplied element-by-element and then summed.

  <pre>
      sum = pSrcA[0]*pSrcB[0] + pSrcA[1]*pSrcB[1] + ... + pSrcA[blockSize-1]*pSrcB[blockSize-1]
  </pre>

  There are separate functions for floating-point, Q7, Q15, and Q31 data types.
 */

/**
  @addtogroup BasicDotProd
  @{
 */

/**
  @brief         Dot product of floating-point vectors.
  @param[in]     pSrcA      points to the first input vector.
  @param[in]     pSrcB      points to the second input vector.
  @param[in]     blockSize  number of samples in each vector.
  @param[out]    result     output result returned here.
  @return        none
 */

void arm_dot_prod_f32(
  const float32_t * pSrcA,
  const float32_t * pSrcB,
        uint32_t blockSize,
        float32_t * result)
{
        uint32_t blkCnt;                               /* Loop counter */
        float32_t sum = 0.0f;                          /* Temporary return variable */

#if defined(ARM_MATH_NEON)
    float32x4_t vec1;
    float32x4_t vec2;
    float32x4_t res;
    float32x4_t accum = vdupq_n_f32(0);    

    /* Compute 4 outputs at a time */
    blkCnt = blockSize >> 2U;

    vec1 = vld1q_f32(pSrcA);
    vec2 = vld1q_f32(pSrcB);

    while (blkCnt > 0U)
    {
        /* C = A[0]*B[0] + A[1]*B[1] + A[2]*B[2] + ... + A[blockSize-1]*B[blockSize-1] */
        /* Calculate dot product and then store the result in a temporary buffer. */
        
	accum = vmlaq_f32(accum, vec1, vec2);
	
        /* Increment pointers */
        pSrcA += 4;
        pSrcB += 4; 

        vec1 = vld1q_f32(pSrcA);
        vec2 = vld1q_f32(pSrcB);
        
        /* Decrement the loop counter */
        blkCnt--;
    }
    
#if __aarch64__
    sum = vpadds_f32(vpadd_f32(vget_low_f32(accum), vget_high_f32(accum)));
#else
    sum = (vpadd_f32(vget_low_f32(accum), vget_high_f32(accum)))[0] + (vpadd_f32(vget_low_f32(accum), vget_high_f32(accum)))[1];
#endif    

    /* Tail */
    blkCnt = blockSize & 0x3;

#else
#if defined (ARM_MATH_LOOPUNROLL)

  /* Loop unrolling: Compute 4 outputs at a time */
  blkCnt = blockSize >> 2U;

  /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
   ** a second loop below computes the remaining 1 to 3 samples. */
  while (blkCnt > 0U)
  {
    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */

    /* Calculate dot product and store result in a temporary buffer. */
    sum += (*pSrcA++) * (*pSrcB++);

    sum += (*pSrcA++) * (*pSrcB++);

    sum += (*pSrcA++) * (*pSrcB++);

    sum += (*pSrcA++) * (*pSrcB++);

    /* Decrement loop counter */
    blkCnt--;
  }

  /* Loop unrolling: Compute remaining outputs */
  blkCnt = blockSize % 0x4U;

#else

  /* Initialize blkCnt with number of samples */
  blkCnt = blockSize;

#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
#endif /* #if defined(ARM_MATH_NEON) */

  while (blkCnt > 0U)
  {
    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */

    /* Calculate dot product and store result in a temporary buffer. */
    sum += (*pSrcA++) * (*pSrcB++);

    /* Decrement loop counter */
    blkCnt--;
  }

  /* Store result in destination buffer */
  *result = sum;
}

/**
  @} end of BasicDotProd group
 */