blob: bbbcc6f4a3b7aa53165e0ef6687813975bb98366 (
plain) (
blame)
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
|
/* ----------------------------------------------------------------------------
* Copyright (C) 2010 ARM Limited. All rights reserved.
*
* $Date: 15. February 2012
* $Revision: V1.1.0
*
* Project: CMSIS DSP Library
* Title: arm_q7_to_q31.c
*
* Description: Converts the elements of the Q7 vector to Q31 vector.
*
* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
*
* Version 1.1.0 2012/02/15
* Updated with more optimizations, bug fixes and minor API changes.
*
* Version 1.0.10 2011/7/15
* Big Endian support added and Merged M0 and M3/M4 Source code.
*
* Version 1.0.3 2010/11/29
* Re-organized the CMSIS folders and updated documentation.
*
* Version 1.0.2 2010/11/11
* Documentation updated.
*
* Version 1.0.1 2010/10/05
* Production release and review comments incorporated.
*
* Version 1.0.0 2010/09/20
* Production release and review comments incorporated.
* ---------------------------------------------------------------------------- */
#include "arm_math.h"
/**
* @ingroup groupSupport
*/
/**
* @addtogroup q7_to_x
* @{
*/
/**
* @brief Converts the elements of the Q7 vector to Q31 vector.
* @param[in] *pSrc points to the Q7 input vector
* @param[out] *pDst points to the Q31 output vector
* @param[in] blockSize length of the input vector
* @return none.
*
* \par Description:
*
* The equation used for the conversion process is:
*
* <pre>
* pDst[n] = (q31_t) pSrc[n] << 24; 0 <= n < blockSize.
* </pre>
*
*/
void arm_q7_to_q31(
q7_t * pSrc,
q31_t * pDst,
uint32_t blockSize)
{
q7_t *pIn = pSrc; /* Src pointer */
uint32_t blkCnt; /* loop counter */
#ifndef ARM_MATH_CM0
q31_t in;
/* Run the below code for Cortex-M4 and Cortex-M3 */
/*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 = (q31_t) A << 24 */
/* convert from q7 to q31 and then store the results in the destination buffer */
in = *__SIMD32(pIn)++;
#ifndef ARM_MATH_BIG_ENDIAN
*pDst++ = (__ROR(in, 8)) & 0xFF000000;
*pDst++ = (__ROR(in, 16)) & 0xFF000000;
*pDst++ = (__ROR(in, 24)) & 0xFF000000;
*pDst++ = (in & 0xFF000000);
#else
*pDst++ = (in & 0xFF000000);
*pDst++ = (__ROR(in, 24)) & 0xFF000000;
*pDst++ = (__ROR(in, 16)) & 0xFF000000;
*pDst++ = (__ROR(in, 8)) & 0xFF000000;
#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;
#else
/* Run the below code for Cortex-M0 */
/* Loop over blockSize number of values */
blkCnt = blockSize;
#endif /* #ifndef ARM_MATH_CM0 */
while(blkCnt > 0u)
{
/* C = (q31_t) A << 24 */
/* convert from q7 to q31 and then store the results in the destination buffer */
*pDst++ = (q31_t) * pIn++ << 24;
/* Decrement the loop counter */
blkCnt--;
}
}
/**
* @} end of q7_to_x group
*/
|
