summaryrefslogtreecommitdiff
path: root/Blink/Drivers/CMSIS/DSP/Source/BasicMathFunctions/arm_shift_q15.c
blob: 9462ad7803b1fed3481acff2ce06a32cd91296f7 (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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
/* ----------------------------------------------------------------------
 * Project:      CMSIS DSP Library
 * Title:        arm_shift_q15.c
 * Description:  Shifts the elements of a Q15 vector by a specified number of bits
 *
 * $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 shift
 * @{
 */

/**
 * @brief  Shifts the elements of a Q15 vector a specified number of bits.
 * @param[in]  *pSrc points to the input vector
 * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
 * @param[out]  *pDst points to the output vector
 * @param[in]  blockSize number of samples in the 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_shift_q15(
  q15_t * pSrc,
  int8_t shiftBits,
  q15_t * pDst,
  uint32_t blockSize)
{
  uint32_t blkCnt;                               /* loop counter */
  uint8_t sign;                                  /* Sign of shiftBits */

#if defined (ARM_MATH_DSP)

/* Run the below code for Cortex-M4 and Cortex-M3 */

  q15_t in1, in2;                                /* Temporary variables */


  /*loop Unrolling */
  blkCnt = blockSize >> 2U;

  /* Getting the sign of shiftBits */
  sign = (shiftBits & 0x80);

  /* If the shift value is positive then do right shift else left shift */
  if (sign == 0U)
  {
    /* 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)
    {
      /* Read 2 inputs */
      in1 = *pSrc++;
      in2 = *pSrc++;
      /* C = A << shiftBits */
      /* Shift the inputs and then store the results in the destination buffer. */
#ifndef  ARM_MATH_BIG_ENDIAN

      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16),
                                  __SSAT((in2 << shiftBits), 16), 16);

#else

      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16),
                                  __SSAT((in1 << shiftBits), 16), 16);

#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */

      in1 = *pSrc++;
      in2 = *pSrc++;

#ifndef  ARM_MATH_BIG_ENDIAN

      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16),
                                  __SSAT((in2 << shiftBits), 16), 16);

#else

      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16),
                                  __SSAT((in1 << shiftBits), 16), 16);

#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */

      /* 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 << shiftBits */
      /* Shift and then store the results in the destination buffer. */
      *pDst++ = __SSAT((*pSrc++ << shiftBits), 16);

      /* Decrement the loop counter */
      blkCnt--;
    }
  }
  else
  {
    /* 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)
    {
      /* Read 2 inputs */
      in1 = *pSrc++;
      in2 = *pSrc++;

      /* C = A >> shiftBits */
      /* Shift the inputs and then store the results in the destination buffer. */
#ifndef  ARM_MATH_BIG_ENDIAN

      *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits),
                                  (in2 >> -shiftBits), 16);

#else

      *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits),
                                  (in1 >> -shiftBits), 16);

#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */

      in1 = *pSrc++;
      in2 = *pSrc++;

#ifndef  ARM_MATH_BIG_ENDIAN

      *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits),
                                  (in2 >> -shiftBits), 16);

#else

      *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits),
                                  (in1 >> -shiftBits), 16);

#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */

      /* 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 >> shiftBits */
      /* Shift the inputs and then store the results in the destination buffer. */
      *pDst++ = (*pSrc++ >> -shiftBits);

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

#else

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

  /* Getting the sign of shiftBits */
  sign = (shiftBits & 0x80);

  /* If the shift value is positive then do right shift else left shift */
  if (sign == 0U)
  {
    /* Initialize blkCnt with number of samples */
    blkCnt = blockSize;

    while (blkCnt > 0U)
    {
      /* C = A << shiftBits */
      /* Shift and then store the results in the destination buffer. */
      *pDst++ = __SSAT(((q31_t) * pSrc++ << shiftBits), 16);

      /* Decrement the loop counter */
      blkCnt--;
    }
  }
  else
  {
    /* Initialize blkCnt with number of samples */
    blkCnt = blockSize;

    while (blkCnt > 0U)
    {
      /* C = A >> shiftBits */
      /* Shift the inputs and then store the results in the destination buffer. */
      *pDst++ = (*pSrc++ >> -shiftBits);

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

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

}

/**
 * @} end of shift group
 */