summaryrefslogtreecommitdiff
path: root/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_scale_q15.c
blob: fc3f2ee1d764db5b7c23f4f05720b48be345c6d4 (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
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_scale_q15.c
 * Description:  Multiplies a Q15 vector by a scalar
 *
 * $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 BasicScale
  @{
 */

/**
  @brief         Multiplies a Q15 vector by a scalar.
  @param[in]     pSrc       points to the input vector
  @param[in]     scaleFract fractional portion of the scale value
  @param[in]     shift      number of bits to shift the result by
  @param[out]    pDst       points to the output vector
  @param[in]     blockSize  number of samples in each vector
  @return        none

  @par           Scaling and Overflow Behavior
                   The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.15 format.
                   These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format.
 */

void arm_scale_q15(
  const q15_t *pSrc,
        q15_t scaleFract,
        int8_t shift,
        q15_t *pDst,
        uint32_t blockSize)
{
        uint32_t blkCnt;                               /* Loop counter */
        int8_t kShift = 15 - shift;                    /* Shift to apply after scaling */

#if defined (ARM_MATH_LOOPUNROLL)
#if defined (ARM_MATH_DSP)
  q31_t inA1, inA2;
  q31_t out1, out2, out3, out4;                  /* Temporary output variables */
  q15_t in1, in2, in3, in4;                      /* Temporary input variables */
#endif
#endif

#if defined (ARM_MATH_LOOPUNROLL)

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

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

#if defined (ARM_MATH_DSP)
    /* read 2 times 2 samples at a time from source */
    inA1 = read_q15x2_ia ((q15_t **) &pSrc);
    inA2 = read_q15x2_ia ((q15_t **) &pSrc);

    /* Scale inputs and store result in temporary variables
     * in single cycle by packing the outputs */
    out1 = (q31_t) ((q15_t) (inA1 >> 16) * scaleFract);
    out2 = (q31_t) ((q15_t) (inA1      ) * scaleFract);
    out3 = (q31_t) ((q15_t) (inA2 >> 16) * scaleFract);
    out4 = (q31_t) ((q15_t) (inA2      ) * scaleFract);

    /* apply shifting */
    out1 = out1 >> kShift;
    out2 = out2 >> kShift;
    out3 = out3 >> kShift;
    out4 = out4 >> kShift;

    /* saturate the output */
    in1 = (q15_t) (__SSAT(out1, 16));
    in2 = (q15_t) (__SSAT(out2, 16));
    in3 = (q15_t) (__SSAT(out3, 16));
    in4 = (q15_t) (__SSAT(out4, 16));

    /* store result to destination */
    write_q15x2_ia (&pDst, __PKHBT(in2, in1, 16));
    write_q15x2_ia (&pDst, __PKHBT(in4, in3, 16));
#else
    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 16));
    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 16));
    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 16));
    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 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 * scale */

    /* Scale input and store result in destination buffer. */
    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 16));

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

}

/**
  @} end of BasicScale group
 */