summaryrefslogtreecommitdiffstats
path: root/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_add_q15.c
blob: 0bf9d06ad5d92cb11266e6cf7fdc04d29e761364 (plain)
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
170
171
172
173
174
175
176
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_add_q15.c
 * Description:  Q15 vector addition
 *
 * $Date:        23 April 2021
 * $Revision:    V1.9.0
 *
 * Target Processor: Cortex-M and Cortex-A cores
 * -------------------------------------------------------------------- */
/*
 * Copyright (C) 2010-2021 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 "dsp/basic_math_functions.h"

/**
  @ingroup groupMath
 */

/**
  @addtogroup BasicAdd
  @{
 */

/**
  @brief         Q15 vector addition.
  @param[in]     pSrcA      points to the first input vector
  @param[in]     pSrcB      points to the second input vector
  @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 function uses saturating arithmetic.
                   Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.
 */

#if defined(ARM_MATH_MVEI) && !defined(ARM_MATH_AUTOVECTORIZE)

#include "arm_helium_utils.h"

void arm_add_q15(
    const q15_t * pSrcA,
    const q15_t * pSrcB,
    q15_t * pDst,
    uint32_t blockSize)
{
    uint32_t  blkCnt;           /* loop counters */
    q15x8_t vecA;
    q15x8_t vecB;

    /* Compute 8 outputs at a time */
    blkCnt = blockSize >> 3;
    while (blkCnt > 0U)
    {
        /*
         * C = A + B
         * Add and then store the results in the destination buffer.
         */
        vecA = vld1q(pSrcA);
        vecB = vld1q(pSrcB);
        vst1q(pDst, vqaddq(vecA, vecB));
        /*
         * Decrement the blockSize loop counter
         */
        blkCnt--;
        /*
         * advance vector source and destination pointers
         */
        pSrcA  += 8;
        pSrcB  += 8;
        pDst   += 8;
    }
    /*
     * tail
     */
    blkCnt = blockSize & 7;
    if (blkCnt > 0U)
    {
        mve_pred16_t p0 = vctp16q(blkCnt);
        vecA = vld1q(pSrcA);
        vecB = vld1q(pSrcB);
        vstrhq_p(pDst, vqaddq(vecA, vecB), p0);
    }
}

#else
void arm_add_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;
  q31_t inB1, inB2;
#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 times 2 samples at a time from sourceA */
    inA1 = read_q15x2_ia (&pSrcA);
    inA2 = read_q15x2_ia (&pSrcA);
    /* read 2 times 2 samples at a time from sourceB */
    inB1 = read_q15x2_ia (&pSrcB);
    inB2 = read_q15x2_ia (&pSrcB);

    /* Add and store 2 times 2 samples at a time */
    write_q15x2_ia (&pDst, __QADD16(inA1, inB1));
    write_q15x2_ia (&pDst, __QADD16(inA2, inB2));
#else
    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 16);
    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 16);
    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 16);
    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 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 */

    /* Add and store result in destination buffer. */
#if defined (ARM_MATH_DSP)
    *pDst++ = (q15_t) __QADD16(*pSrcA++, *pSrcB++);
#else
    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 16);
#endif

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

}
#endif /* defined(ARM_MATH_MVEI) */
/**
  @} end of BasicAdd group
 */