summaryrefslogtreecommitdiff
path: root/Drivers/CMSIS/DSP/Source/ComplexMathFunctions/arm_cmplx_mult_real_f32.c
blob: 2b7d087c3f9e4816eff91b0d6649fefd09a63131 (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
164
165
166
167
168
169
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_cmplx_mult_real_f32.c
 * Description:  Floating-point complex by real multiplication
 *
 * $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 groupCmplxMath
 */

/**
  @defgroup CmplxByRealMult Complex-by-Real Multiplication

  Multiplies a complex vector by a real vector and generates a complex result.
  The data in the complex arrays is stored in an interleaved fashion
  (real, imag, real, imag, ...).
  The parameter <code>numSamples</code> represents the number of complex
  samples processed.  The complex arrays have a total of <code>2*numSamples</code>
  real values while the real array has a total of <code>numSamples</code>
  real values.

  The underlying algorithm is used:

  <pre>
  for (n = 0; n < numSamples; n++) {
      pCmplxDst[(2*n)+0] = pSrcCmplx[(2*n)+0] * pSrcReal[n];
      pCmplxDst[(2*n)+1] = pSrcCmplx[(2*n)+1] * pSrcReal[n];
  }
  </pre>

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

/**
  @addtogroup CmplxByRealMult
  @{
 */

/**
  @brief         Floating-point complex-by-real multiplication.
  @param[in]     pSrcCmplx   points to complex input vector
  @param[in]     pSrcReal    points to real input vector
  @param[out]    pCmplxDst   points to complex output vector
  @param[in]     numSamples  number of samples in each vector
  @return        none
 */

void arm_cmplx_mult_real_f32(
  const float32_t * pSrcCmplx,
  const float32_t * pSrcReal,
        float32_t * pCmplxDst,
        uint32_t numSamples)
{
        uint32_t blkCnt;                               /* Loop counter */
        float32_t in;                                  /* Temporary variable */

#if defined(ARM_MATH_NEON)
    float32x4_t r;
    float32x4x2_t ab,outCplx;

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

    while (blkCnt > 0U)
    {
        ab = vld2q_f32(pSrcCmplx);  // load & separate real/imag pSrcA (de-interleave 2)
        r = vld1q_f32(pSrcReal);  // load & separate real/imag pSrcB

	/* Increment pointers */
        pSrcCmplx += 8;
        pSrcReal += 4;

        outCplx.val[0] = vmulq_f32(ab.val[0], r);
        outCplx.val[1] = vmulq_f32(ab.val[1], r);

        vst2q_f32(pCmplxDst, outCplx);
        pCmplxDst += 8;

        blkCnt--;
    }

    /* Tail */
    blkCnt = numSamples & 3;
#else
#if defined (ARM_MATH_LOOPUNROLL)

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

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

    in = *pSrcReal++;
    /* store result in destination buffer. */
    *pCmplxDst++ = *pSrcCmplx++ * in;
    *pCmplxDst++ = *pSrcCmplx++ * in;

    in = *pSrcReal++;
    *pCmplxDst++ = *pSrcCmplx++ * in;
    *pCmplxDst++ = *pSrcCmplx++ * in;

    in = *pSrcReal++;
    *pCmplxDst++ = *pSrcCmplx++ * in;
    *pCmplxDst++ = *pSrcCmplx++ * in;

    in = *pSrcReal++;
    *pCmplxDst++ = *pSrcCmplx++* in;
    *pCmplxDst++ = *pSrcCmplx++ * in;

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

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

#else

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

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

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

    in = *pSrcReal++;
    /* store result in destination buffer. */
    *pCmplxDst++ = *pSrcCmplx++ * in;
    *pCmplxDst++ = *pSrcCmplx++ * in;

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

}

/**
  @} end of CmplxByRealMult group
 */