summaryrefslogtreecommitdiff
path: root/hid-dials/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_add_q15.c
blob: 2a14c2919feb689400609fe3530d4c03873f858c (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
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_add_q15.c
 * Description:  Q15 vector addition
 *
 * $Date:        27. January 2017
 * $Revision:    V.1.5.1
 *
 * Target Processor: Cortex-M cores
 * -------------------------------------------------------------------- */
/*
 * Copyright (C) 2010-2017 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 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.
 *
 * <b>Scaling and Overflow Behavior:</b>
 * \par
 * The function uses saturating arithmetic.
 * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
 */

void arm_add_q15(
  q15_t * pSrcA,
  q15_t * pSrcB,
  q15_t * pDst,
  uint32_t blockSize)
{
  uint32_t blkCnt;                               /* loop counter */

#if defined (ARM_MATH_DSP)

/* Run the below code for Cortex-M4 and Cortex-M3 */
  q31_t inA1, inA2, inB1, inB2;

  /*loop Unrolling */
  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 + B */
    /* Add and then store the results in the destination buffer. */
    inA1 = *__SIMD32(pSrcA)++;
    inA2 = *__SIMD32(pSrcA)++;
    inB1 = *__SIMD32(pSrcB)++;
    inB2 = *__SIMD32(pSrcB)++;

    *__SIMD32(pDst)++ = __QADD16(inA1, inB1);
    *__SIMD32(pDst)++ = __QADD16(inA2, inB2);

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

  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
   ** No loop unrolling is used. */
  blkCnt = blockSize % 0x4U;

  while (blkCnt > 0U)
  {
    /* C = A + B */
    /* Add and then store the results in the destination buffer. */
    *pDst++ = (q15_t) __QADD16(*pSrcA++, *pSrcB++);

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

#else

  /* Run the below code for Cortex-M0 */



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

  while (blkCnt > 0U)
  {
    /* C = A + B */
    /* Add and then store the results in the destination buffer. */
    *pDst++ = (q15_t) __SSAT(((q31_t) * pSrcA++ + *pSrcB++), 16);

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

#endif /* #if defined (ARM_MATH_DSP) */


}

/**
 * @} end of BasicAdd group
 */