提交 | 用户 | age
|
8b51c7
|
1 |
/* ---------------------------------------------------------------------- |
Q |
2 |
* Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
|
3 |
* |
|
4 |
* $Date: 19. March 2015 |
|
5 |
* $Revision: V.1.4.5 |
|
6 |
* |
|
7 |
* Project: CMSIS DSP Library |
|
8 |
* Title: arm_shift_q7.c |
|
9 |
* |
|
10 |
* Description: Processing function for the Q7 Shifting |
|
11 |
* |
|
12 |
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
|
13 |
* |
|
14 |
* Redistribution and use in source and binary forms, with or without |
|
15 |
* modification, are permitted provided that the following conditions |
|
16 |
* are met: |
|
17 |
* - Redistributions of source code must retain the above copyright |
|
18 |
* notice, this list of conditions and the following disclaimer. |
|
19 |
* - Redistributions in binary form must reproduce the above copyright |
|
20 |
* notice, this list of conditions and the following disclaimer in |
|
21 |
* the documentation and/or other materials provided with the |
|
22 |
* distribution. |
|
23 |
* - Neither the name of ARM LIMITED nor the names of its contributors |
|
24 |
* may be used to endorse or promote products derived from this |
|
25 |
* software without specific prior written permission. |
|
26 |
* |
|
27 |
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
|
28 |
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
|
29 |
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS |
|
30 |
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
|
31 |
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
|
32 |
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, |
|
33 |
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
|
34 |
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
|
35 |
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
|
36 |
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN |
|
37 |
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
|
38 |
* POSSIBILITY OF SUCH DAMAGE. |
|
39 |
* -------------------------------------------------------------------- */ |
|
40 |
|
|
41 |
#include "arm_math.h" |
|
42 |
|
|
43 |
/** |
|
44 |
* @ingroup groupMath |
|
45 |
*/ |
|
46 |
|
|
47 |
/** |
|
48 |
* @addtogroup shift |
|
49 |
* @{ |
|
50 |
*/ |
|
51 |
|
|
52 |
|
|
53 |
/** |
|
54 |
* @brief Shifts the elements of a Q7 vector a specified number of bits. |
|
55 |
* @param[in] *pSrc points to the input vector |
|
56 |
* @param[in] shiftBits number of bits to shift. A positive value shifts left; a negative value shifts right. |
|
57 |
* @param[out] *pDst points to the output vector |
|
58 |
* @param[in] blockSize number of samples in the vector |
|
59 |
* @return none. |
|
60 |
* |
|
61 |
* \par Conditions for optimum performance |
|
62 |
* Input and output buffers should be aligned by 32-bit |
|
63 |
* |
|
64 |
* |
|
65 |
* <b>Scaling and Overflow Behavior:</b> |
|
66 |
* \par |
|
67 |
* The function uses saturating arithmetic. |
|
68 |
* Results outside of the allowable Q7 range [0x8 0x7F] will be saturated. |
|
69 |
*/ |
|
70 |
|
|
71 |
void arm_shift_q7( |
|
72 |
q7_t * pSrc, |
|
73 |
int8_t shiftBits, |
|
74 |
q7_t * pDst, |
|
75 |
uint32_t blockSize) |
|
76 |
{ |
|
77 |
uint32_t blkCnt; /* loop counter */ |
|
78 |
uint8_t sign; /* Sign of shiftBits */ |
|
79 |
|
|
80 |
#ifndef ARM_MATH_CM0_FAMILY |
|
81 |
|
|
82 |
/* Run the below code for Cortex-M4 and Cortex-M3 */ |
|
83 |
q7_t in1; /* Input value1 */ |
|
84 |
q7_t in2; /* Input value2 */ |
|
85 |
q7_t in3; /* Input value3 */ |
|
86 |
q7_t in4; /* Input value4 */ |
|
87 |
|
|
88 |
|
|
89 |
/*loop Unrolling */ |
|
90 |
blkCnt = blockSize >> 2u; |
|
91 |
|
|
92 |
/* Getting the sign of shiftBits */ |
|
93 |
sign = (shiftBits & 0x80); |
|
94 |
|
|
95 |
/* If the shift value is positive then do right shift else left shift */ |
|
96 |
if(sign == 0u) |
|
97 |
{ |
|
98 |
/* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
|
99 |
** a second loop below computes the remaining 1 to 3 samples. */ |
|
100 |
while(blkCnt > 0u) |
|
101 |
{ |
|
102 |
/* C = A << shiftBits */ |
|
103 |
/* Read 4 inputs */ |
|
104 |
in1 = *pSrc; |
|
105 |
in2 = *(pSrc + 1); |
|
106 |
in3 = *(pSrc + 2); |
|
107 |
in4 = *(pSrc + 3); |
|
108 |
|
|
109 |
/* Store the Shifted result in the destination buffer in single cycle by packing the outputs */ |
|
110 |
*__SIMD32(pDst)++ = __PACKq7(__SSAT((in1 << shiftBits), 8), |
|
111 |
__SSAT((in2 << shiftBits), 8), |
|
112 |
__SSAT((in3 << shiftBits), 8), |
|
113 |
__SSAT((in4 << shiftBits), 8)); |
|
114 |
/* Update source pointer to process next sampels */ |
|
115 |
pSrc += 4u; |
|
116 |
|
|
117 |
/* Decrement the loop counter */ |
|
118 |
blkCnt--; |
|
119 |
} |
|
120 |
|
|
121 |
/* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
|
122 |
** No loop unrolling is used. */ |
|
123 |
blkCnt = blockSize % 0x4u; |
|
124 |
|
|
125 |
while(blkCnt > 0u) |
|
126 |
{ |
|
127 |
/* C = A << shiftBits */ |
|
128 |
/* Shift the input and then store the result in the destination buffer. */ |
|
129 |
*pDst++ = (q7_t) __SSAT((*pSrc++ << shiftBits), 8); |
|
130 |
|
|
131 |
/* Decrement the loop counter */ |
|
132 |
blkCnt--; |
|
133 |
} |
|
134 |
} |
|
135 |
else |
|
136 |
{ |
|
137 |
shiftBits = -shiftBits; |
|
138 |
/* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
|
139 |
** a second loop below computes the remaining 1 to 3 samples. */ |
|
140 |
while(blkCnt > 0u) |
|
141 |
{ |
|
142 |
/* C = A >> shiftBits */ |
|
143 |
/* Read 4 inputs */ |
|
144 |
in1 = *pSrc; |
|
145 |
in2 = *(pSrc + 1); |
|
146 |
in3 = *(pSrc + 2); |
|
147 |
in4 = *(pSrc + 3); |
|
148 |
|
|
149 |
/* Store the Shifted result in the destination buffer in single cycle by packing the outputs */ |
|
150 |
*__SIMD32(pDst)++ = __PACKq7((in1 >> shiftBits), (in2 >> shiftBits), |
|
151 |
(in3 >> shiftBits), (in4 >> shiftBits)); |
|
152 |
|
|
153 |
|
|
154 |
pSrc += 4u; |
|
155 |
|
|
156 |
/* Decrement the loop counter */ |
|
157 |
blkCnt--; |
|
158 |
} |
|
159 |
|
|
160 |
/* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
|
161 |
** No loop unrolling is used. */ |
|
162 |
blkCnt = blockSize % 0x4u; |
|
163 |
|
|
164 |
while(blkCnt > 0u) |
|
165 |
{ |
|
166 |
/* C = A >> shiftBits */ |
|
167 |
/* Shift the input and then store the result in the destination buffer. */ |
|
168 |
in1 = *pSrc++; |
|
169 |
*pDst++ = (in1 >> shiftBits); |
|
170 |
|
|
171 |
/* Decrement the loop counter */ |
|
172 |
blkCnt--; |
|
173 |
} |
|
174 |
} |
|
175 |
|
|
176 |
#else |
|
177 |
|
|
178 |
/* Run the below code for Cortex-M0 */ |
|
179 |
|
|
180 |
/* Getting the sign of shiftBits */ |
|
181 |
sign = (shiftBits & 0x80); |
|
182 |
|
|
183 |
/* If the shift value is positive then do right shift else left shift */ |
|
184 |
if(sign == 0u) |
|
185 |
{ |
|
186 |
/* Initialize blkCnt with number of samples */ |
|
187 |
blkCnt = blockSize; |
|
188 |
|
|
189 |
while(blkCnt > 0u) |
|
190 |
{ |
|
191 |
/* C = A << shiftBits */ |
|
192 |
/* Shift the input and then store the result in the destination buffer. */ |
|
193 |
*pDst++ = (q7_t) __SSAT(((q15_t) * pSrc++ << shiftBits), 8); |
|
194 |
|
|
195 |
/* Decrement the loop counter */ |
|
196 |
blkCnt--; |
|
197 |
} |
|
198 |
} |
|
199 |
else |
|
200 |
{ |
|
201 |
/* Initialize blkCnt with number of samples */ |
|
202 |
blkCnt = blockSize; |
|
203 |
|
|
204 |
while(blkCnt > 0u) |
|
205 |
{ |
|
206 |
/* C = A >> shiftBits */ |
|
207 |
/* Shift the input and then store the result in the destination buffer. */ |
|
208 |
*pDst++ = (*pSrc++ >> -shiftBits); |
|
209 |
|
|
210 |
/* Decrement the loop counter */ |
|
211 |
blkCnt--; |
|
212 |
} |
|
213 |
} |
|
214 |
|
|
215 |
#endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
|
216 |
} |
|
217 |
|
|
218 |
/** |
|
219 |
* @} end of shift group |
|
220 |
*/ |