|
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_mult_q7.c
|
|
|
9 *
|
|
|
10 * Description: Q7 vector multiplication.
|
|
|
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 BasicMult
|
|
|
49 * @{
|
|
|
50 */
|
|
|
51
|
|
|
52 /**
|
|
|
53 * @brief Q7 vector multiplication
|
|
|
54 * @param[in] *pSrcA points to the first input vector
|
|
|
55 * @param[in] *pSrcB points to the second input vector
|
|
|
56 * @param[out] *pDst points to the output vector
|
|
|
57 * @param[in] blockSize number of samples in each vector
|
|
|
58 * @return none.
|
|
|
59 *
|
|
|
60 * <b>Scaling and Overflow Behavior:</b>
|
|
|
61 * \par
|
|
|
62 * The function uses saturating arithmetic.
|
|
|
63 * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.
|
|
|
64 */
|
|
|
65
|
|
|
66 void arm_mult_q7(
|
|
|
67 q7_t * pSrcA,
|
|
|
68 q7_t * pSrcB,
|
|
|
69 q7_t * pDst,
|
|
|
70 uint32_t blockSize)
|
|
|
71 {
|
|
|
72 uint32_t blkCnt; /* loop counters */
|
|
|
73
|
|
|
74 #ifndef ARM_MATH_CM0_FAMILY
|
|
|
75
|
|
|
76 /* Run the below code for Cortex-M4 and Cortex-M3 */
|
|
|
77 q7_t out1, out2, out3, out4; /* Temporary variables to store the product */
|
|
|
78
|
|
|
79 /* loop Unrolling */
|
|
|
80 blkCnt = blockSize >> 2u;
|
|
|
81
|
|
|
82 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
|
|
|
83 ** a second loop below computes the remaining 1 to 3 samples. */
|
|
|
84 while(blkCnt > 0u)
|
|
|
85 {
|
|
|
86 /* C = A * B */
|
|
|
87 /* Multiply the inputs and store the results in temporary variables */
|
|
|
88 out1 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
|
|
|
89 out2 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
|
|
|
90 out3 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
|
|
|
91 out4 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
|
|
|
92
|
|
|
93 /* Store the results of 4 inputs in the destination buffer in single cycle by packing */
|
|
|
94 *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
|
|
|
95
|
|
|
96 /* Decrement the blockSize loop counter */
|
|
|
97 blkCnt--;
|
|
|
98 }
|
|
|
99
|
|
|
100 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
|
|
|
101 ** No loop unrolling is used. */
|
|
|
102 blkCnt = blockSize % 0x4u;
|
|
|
103
|
|
|
104 #else
|
|
|
105
|
|
|
106 /* Run the below code for Cortex-M0 */
|
|
|
107
|
|
|
108 /* Initialize blkCnt with number of samples */
|
|
|
109 blkCnt = blockSize;
|
|
|
110
|
|
|
111 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
|
|
|
112
|
|
|
113
|
|
|
114 while(blkCnt > 0u)
|
|
|
115 {
|
|
|
116 /* C = A * B */
|
|
|
117 /* Multiply the inputs and store the result in the destination buffer */
|
|
|
118 *pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
|
|
|
119
|
|
|
120 /* Decrement the blockSize loop counter */
|
|
|
121 blkCnt--;
|
|
|
122 }
|
|
|
123 }
|
|
|
124
|
|
|
125 /**
|
|
|
126 * @} end of BasicMult group
|
|
|
127 */
|
