2
|
1 /* ----------------------------------------------------------------------
|
|
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_abs_q7.c
|
|
9 *
|
|
10 * Description: Q7 vector absolute value.
|
|
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 BasicAbs
|
|
49 * @{
|
|
50 */
|
|
51
|
|
52 /**
|
|
53 * @brief Q7 vector absolute value.
|
|
54 * @param[in] *pSrc points to the input buffer
|
|
55 * @param[out] *pDst points to the output buffer
|
|
56 * @param[in] blockSize number of samples in each vector
|
|
57 * @return none.
|
|
58 *
|
|
59 * \par Conditions for optimum performance
|
|
60 * Input and output buffers should be aligned by 32-bit
|
|
61 *
|
|
62 *
|
|
63 * <b>Scaling and Overflow Behavior:</b>
|
|
64 * \par
|
|
65 * The function uses saturating arithmetic.
|
|
66 * The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F.
|
|
67 */
|
|
68
|
|
69 void arm_abs_q7(
|
|
70 q7_t * pSrc,
|
|
71 q7_t * pDst,
|
|
72 uint32_t blockSize)
|
|
73 {
|
|
74 uint32_t blkCnt; /* loop counter */
|
|
75 q7_t in; /* Input value1 */
|
|
76
|
|
77 #ifndef ARM_MATH_CM0_FAMILY
|
|
78
|
|
79 /* Run the below code for Cortex-M4 and Cortex-M3 */
|
|
80 q31_t in1, in2, in3, in4; /* temporary input variables */
|
|
81 q31_t out1, out2, out3, out4; /* temporary output variables */
|
|
82
|
|
83 /*loop Unrolling */
|
|
84 blkCnt = blockSize >> 2u;
|
|
85
|
|
86 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
|
|
87 ** a second loop below computes the remaining 1 to 3 samples. */
|
|
88 while(blkCnt > 0u)
|
|
89 {
|
|
90 /* C = |A| */
|
|
91 /* Read inputs */
|
|
92 in1 = (q31_t) * pSrc;
|
|
93 in2 = (q31_t) * (pSrc + 1);
|
|
94 in3 = (q31_t) * (pSrc + 2);
|
|
95
|
|
96 /* find absolute value */
|
|
97 out1 = (in1 > 0) ? in1 : (q31_t)__QSUB8(0, in1);
|
|
98
|
|
99 /* read input */
|
|
100 in4 = (q31_t) * (pSrc + 3);
|
|
101
|
|
102 /* find absolute value */
|
|
103 out2 = (in2 > 0) ? in2 : (q31_t)__QSUB8(0, in2);
|
|
104
|
|
105 /* store result to destination */
|
|
106 *pDst = (q7_t) out1;
|
|
107
|
|
108 /* find absolute value */
|
|
109 out3 = (in3 > 0) ? in3 : (q31_t)__QSUB8(0, in3);
|
|
110
|
|
111 /* find absolute value */
|
|
112 out4 = (in4 > 0) ? in4 : (q31_t)__QSUB8(0, in4);
|
|
113
|
|
114 /* store result to destination */
|
|
115 *(pDst + 1) = (q7_t) out2;
|
|
116
|
|
117 /* store result to destination */
|
|
118 *(pDst + 2) = (q7_t) out3;
|
|
119
|
|
120 /* store result to destination */
|
|
121 *(pDst + 3) = (q7_t) out4;
|
|
122
|
|
123 /* update pointers to process next samples */
|
|
124 pSrc += 4u;
|
|
125 pDst += 4u;
|
|
126
|
|
127 /* Decrement the loop counter */
|
|
128 blkCnt--;
|
|
129 }
|
|
130
|
|
131 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
|
|
132 ** No loop unrolling is used. */
|
|
133 blkCnt = blockSize % 0x4u;
|
|
134 #else
|
|
135
|
|
136 /* Run the below code for Cortex-M0 */
|
|
137 blkCnt = blockSize;
|
|
138
|
|
139 #endif /* #define ARM_MATH_CM0_FAMILY */
|
|
140
|
|
141 while(blkCnt > 0u)
|
|
142 {
|
|
143 /* C = |A| */
|
|
144 /* Read the input */
|
|
145 in = *pSrc++;
|
|
146
|
|
147 /* Store the Absolute result in the destination buffer */
|
|
148 *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? 0x7f : -in);
|
|
149
|
|
150 /* Decrement the loop counter */
|
|
151 blkCnt--;
|
|
152 }
|
|
153 }
|
|
154
|
|
155 /**
|
|
156 * @} end of BasicAbs group
|
|
157 */
|