summaryrefslogtreecommitdiff
path: root/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_mult_q15.c
blob: 270dc730b768015c83636fe733cb1c694d207c7b (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
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_mult_q15.c
 * Description:  Q15 vector 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 groupMath
 */

/**
  @addtogroup BasicMult
  @{
 */

/**
  @brief         Q15 vector multiplication
  @param[in]     pSrcA      points to first input vector
  @param[in]     pSrcB      points to second input vector
  @param[out]    pDst       points to output vector
  @param[in]     blockSize  number of samples in each vector
  @return        none

  @par           Scaling and Overflow Behavior
                   The function uses saturating arithmetic.
                   Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.
 */

void arm_mult_q15(
  const q15_t * pSrcA,
  const q15_t * pSrcB,
        q15_t * pDst,
        uint32_t blockSize)
{
        uint32_t blkCnt;                               /* Loop counter */

#if defined (ARM_MATH_LOOPUNROLL)

#if defined (ARM_MATH_DSP)
  q31_t inA1, inA2, inB1, inB2;                  /* Temporary input variables */
  q15_t out1, out2, out3, out4;                  /* Temporary output variables */
  q31_t mul1, mul2, mul3, mul4;                  /* Temporary variables */
#endif

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

  while (blkCnt > 0U)
  {
    /* C = A * B */

#if defined (ARM_MATH_DSP)
    /* read 2 samples at a time from sourceA */
    inA1 = read_q15x2_ia ((q15_t **) &pSrcA);
    /* read 2 samples at a time from sourceB */
    inB1 = read_q15x2_ia ((q15_t **) &pSrcB);
    /* read 2 samples at a time from sourceA */
    inA2 = read_q15x2_ia ((q15_t **) &pSrcA);
    /* read 2 samples at a time from sourceB */
    inB2 = read_q15x2_ia ((q15_t **) &pSrcB);

    /* multiply mul = sourceA * sourceB */
    mul1 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
    mul2 = (q31_t) ((q15_t) (inA1      ) * (q15_t) (inB1      ));
    mul3 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB2 >> 16));
    mul4 = (q31_t) ((q15_t) (inA2      ) * (q15_t) (inB2      ));

    /* saturate result to 16 bit */
    out1 = (q15_t) __SSAT(mul1 >> 15, 16);
    out2 = (q15_t) __SSAT(mul2 >> 15, 16);
    out3 = (q15_t) __SSAT(mul3 >> 15, 16);
    out4 = (q15_t) __SSAT(mul4 >> 15, 16);

    /* store result to destination */
#ifndef ARM_MATH_BIG_ENDIAN
    write_q15x2_ia (&pDst, __PKHBT(out2, out1, 16));
    write_q15x2_ia (&pDst, __PKHBT(out4, out3, 16));
#else
    write_q15x2_ia (&pDst, __PKHBT(out1, out2, 16));
    write_q15x2_ia (&pDst, __PKHBT(out3, out4, 16));
#endif /* #ifndef ARM_MATH_BIG_ENDIAN */

#else
    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
#endif

    /* 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) */

  while (blkCnt > 0U)
  {
    /* C = A * B */

    /* Multiply inputs and store result in destination buffer. */
    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);

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

}

/**
  @} end of BasicMult group
 */