V4.0.1 of the ARM CMSIS DSP libraries. Note that arm_bitreversal2.s, arm_cfft_f32.c and arm_rfft_fast_f32.c had to be removed. arm_bitreversal2.s will not assemble with the online tools. So, the fast f32 FFT functions are not yet available. All the other FFT functions are available.
Dependents: MPU9150_Example fir_f32 fir_f32 MPU9150_nucleo_noni2cdev ... more
BasicMathFunctions/arm_shift_q7.c@0:3d9c67d97d6f, 2014-07-28 (annotated)
- Committer:
- emh203
- Date:
- Mon Jul 28 15:03:15 2014 +0000
- Revision:
- 0:3d9c67d97d6f
1st working commit. Had to remove arm_bitreversal2.s arm_cfft_f32.c and arm_rfft_fast_f32.c. The .s will not assemble. For now I removed these functions so we could at least have a library for the other functions.
Who changed what in which revision?
User | Revision | Line number | New contents of line |
---|---|---|---|
emh203 | 0:3d9c67d97d6f | 1 | /* ---------------------------------------------------------------------- |
emh203 | 0:3d9c67d97d6f | 2 | * Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
emh203 | 0:3d9c67d97d6f | 3 | * |
emh203 | 0:3d9c67d97d6f | 4 | * $Date: 12. March 2014 |
emh203 | 0:3d9c67d97d6f | 5 | * $Revision: V1.4.3 |
emh203 | 0:3d9c67d97d6f | 6 | * |
emh203 | 0:3d9c67d97d6f | 7 | * Project: CMSIS DSP Library |
emh203 | 0:3d9c67d97d6f | 8 | * Title: arm_shift_q7.c |
emh203 | 0:3d9c67d97d6f | 9 | * |
emh203 | 0:3d9c67d97d6f | 10 | * Description: Processing function for the Q7 Shifting |
emh203 | 0:3d9c67d97d6f | 11 | * |
emh203 | 0:3d9c67d97d6f | 12 | * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 |
emh203 | 0:3d9c67d97d6f | 13 | * |
emh203 | 0:3d9c67d97d6f | 14 | * Redistribution and use in source and binary forms, with or without |
emh203 | 0:3d9c67d97d6f | 15 | * modification, are permitted provided that the following conditions |
emh203 | 0:3d9c67d97d6f | 16 | * are met: |
emh203 | 0:3d9c67d97d6f | 17 | * - Redistributions of source code must retain the above copyright |
emh203 | 0:3d9c67d97d6f | 18 | * notice, this list of conditions and the following disclaimer. |
emh203 | 0:3d9c67d97d6f | 19 | * - Redistributions in binary form must reproduce the above copyright |
emh203 | 0:3d9c67d97d6f | 20 | * notice, this list of conditions and the following disclaimer in |
emh203 | 0:3d9c67d97d6f | 21 | * the documentation and/or other materials provided with the |
emh203 | 0:3d9c67d97d6f | 22 | * distribution. |
emh203 | 0:3d9c67d97d6f | 23 | * - Neither the name of ARM LIMITED nor the names of its contributors |
emh203 | 0:3d9c67d97d6f | 24 | * may be used to endorse or promote products derived from this |
emh203 | 0:3d9c67d97d6f | 25 | * software without specific prior written permission. |
emh203 | 0:3d9c67d97d6f | 26 | * |
emh203 | 0:3d9c67d97d6f | 27 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
emh203 | 0:3d9c67d97d6f | 28 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
emh203 | 0:3d9c67d97d6f | 29 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS |
emh203 | 0:3d9c67d97d6f | 30 | * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE |
emh203 | 0:3d9c67d97d6f | 31 | * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, |
emh203 | 0:3d9c67d97d6f | 32 | * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, |
emh203 | 0:3d9c67d97d6f | 33 | * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
emh203 | 0:3d9c67d97d6f | 34 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER |
emh203 | 0:3d9c67d97d6f | 35 | * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT |
emh203 | 0:3d9c67d97d6f | 36 | * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN |
emh203 | 0:3d9c67d97d6f | 37 | * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
emh203 | 0:3d9c67d97d6f | 38 | * POSSIBILITY OF SUCH DAMAGE. |
emh203 | 0:3d9c67d97d6f | 39 | * -------------------------------------------------------------------- */ |
emh203 | 0:3d9c67d97d6f | 40 | |
emh203 | 0:3d9c67d97d6f | 41 | #include "arm_math.h" |
emh203 | 0:3d9c67d97d6f | 42 | |
emh203 | 0:3d9c67d97d6f | 43 | /** |
emh203 | 0:3d9c67d97d6f | 44 | * @ingroup groupMath |
emh203 | 0:3d9c67d97d6f | 45 | */ |
emh203 | 0:3d9c67d97d6f | 46 | |
emh203 | 0:3d9c67d97d6f | 47 | /** |
emh203 | 0:3d9c67d97d6f | 48 | * @addtogroup shift |
emh203 | 0:3d9c67d97d6f | 49 | * @{ |
emh203 | 0:3d9c67d97d6f | 50 | */ |
emh203 | 0:3d9c67d97d6f | 51 | |
emh203 | 0:3d9c67d97d6f | 52 | |
emh203 | 0:3d9c67d97d6f | 53 | /** |
emh203 | 0:3d9c67d97d6f | 54 | * @brief Shifts the elements of a Q7 vector a specified number of bits. |
emh203 | 0:3d9c67d97d6f | 55 | * @param[in] *pSrc points to the input vector |
emh203 | 0:3d9c67d97d6f | 56 | * @param[in] shiftBits number of bits to shift. A positive value shifts left; a negative value shifts right. |
emh203 | 0:3d9c67d97d6f | 57 | * @param[out] *pDst points to the output vector |
emh203 | 0:3d9c67d97d6f | 58 | * @param[in] blockSize number of samples in the vector |
emh203 | 0:3d9c67d97d6f | 59 | * @return none. |
emh203 | 0:3d9c67d97d6f | 60 | * |
emh203 | 0:3d9c67d97d6f | 61 | * \par Conditions for optimum performance |
emh203 | 0:3d9c67d97d6f | 62 | * Input and output buffers should be aligned by 32-bit |
emh203 | 0:3d9c67d97d6f | 63 | * |
emh203 | 0:3d9c67d97d6f | 64 | * |
emh203 | 0:3d9c67d97d6f | 65 | * <b>Scaling and Overflow Behavior:</b> |
emh203 | 0:3d9c67d97d6f | 66 | * \par |
emh203 | 0:3d9c67d97d6f | 67 | * The function uses saturating arithmetic. |
emh203 | 0:3d9c67d97d6f | 68 | * Results outside of the allowable Q7 range [0x8 0x7F] will be saturated. |
emh203 | 0:3d9c67d97d6f | 69 | */ |
emh203 | 0:3d9c67d97d6f | 70 | |
emh203 | 0:3d9c67d97d6f | 71 | void arm_shift_q7( |
emh203 | 0:3d9c67d97d6f | 72 | q7_t * pSrc, |
emh203 | 0:3d9c67d97d6f | 73 | int8_t shiftBits, |
emh203 | 0:3d9c67d97d6f | 74 | q7_t * pDst, |
emh203 | 0:3d9c67d97d6f | 75 | uint32_t blockSize) |
emh203 | 0:3d9c67d97d6f | 76 | { |
emh203 | 0:3d9c67d97d6f | 77 | uint32_t blkCnt; /* loop counter */ |
emh203 | 0:3d9c67d97d6f | 78 | uint8_t sign; /* Sign of shiftBits */ |
emh203 | 0:3d9c67d97d6f | 79 | |
emh203 | 0:3d9c67d97d6f | 80 | #ifndef ARM_MATH_CM0_FAMILY |
emh203 | 0:3d9c67d97d6f | 81 | |
emh203 | 0:3d9c67d97d6f | 82 | /* Run the below code for Cortex-M4 and Cortex-M3 */ |
emh203 | 0:3d9c67d97d6f | 83 | q7_t in1; /* Input value1 */ |
emh203 | 0:3d9c67d97d6f | 84 | q7_t in2; /* Input value2 */ |
emh203 | 0:3d9c67d97d6f | 85 | q7_t in3; /* Input value3 */ |
emh203 | 0:3d9c67d97d6f | 86 | q7_t in4; /* Input value4 */ |
emh203 | 0:3d9c67d97d6f | 87 | |
emh203 | 0:3d9c67d97d6f | 88 | |
emh203 | 0:3d9c67d97d6f | 89 | /*loop Unrolling */ |
emh203 | 0:3d9c67d97d6f | 90 | blkCnt = blockSize >> 2u; |
emh203 | 0:3d9c67d97d6f | 91 | |
emh203 | 0:3d9c67d97d6f | 92 | /* Getting the sign of shiftBits */ |
emh203 | 0:3d9c67d97d6f | 93 | sign = (shiftBits & 0x80); |
emh203 | 0:3d9c67d97d6f | 94 | |
emh203 | 0:3d9c67d97d6f | 95 | /* If the shift value is positive then do right shift else left shift */ |
emh203 | 0:3d9c67d97d6f | 96 | if(sign == 0u) |
emh203 | 0:3d9c67d97d6f | 97 | { |
emh203 | 0:3d9c67d97d6f | 98 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emh203 | 0:3d9c67d97d6f | 99 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emh203 | 0:3d9c67d97d6f | 100 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 101 | { |
emh203 | 0:3d9c67d97d6f | 102 | /* C = A << shiftBits */ |
emh203 | 0:3d9c67d97d6f | 103 | /* Read 4 inputs */ |
emh203 | 0:3d9c67d97d6f | 104 | in1 = *pSrc; |
emh203 | 0:3d9c67d97d6f | 105 | in2 = *(pSrc + 1); |
emh203 | 0:3d9c67d97d6f | 106 | in3 = *(pSrc + 2); |
emh203 | 0:3d9c67d97d6f | 107 | in4 = *(pSrc + 3); |
emh203 | 0:3d9c67d97d6f | 108 | |
emh203 | 0:3d9c67d97d6f | 109 | /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */ |
emh203 | 0:3d9c67d97d6f | 110 | *__SIMD32(pDst)++ = __PACKq7(__SSAT((in1 << shiftBits), 8), |
emh203 | 0:3d9c67d97d6f | 111 | __SSAT((in2 << shiftBits), 8), |
emh203 | 0:3d9c67d97d6f | 112 | __SSAT((in3 << shiftBits), 8), |
emh203 | 0:3d9c67d97d6f | 113 | __SSAT((in4 << shiftBits), 8)); |
emh203 | 0:3d9c67d97d6f | 114 | /* Update source pointer to process next sampels */ |
emh203 | 0:3d9c67d97d6f | 115 | pSrc += 4u; |
emh203 | 0:3d9c67d97d6f | 116 | |
emh203 | 0:3d9c67d97d6f | 117 | /* Decrement the loop counter */ |
emh203 | 0:3d9c67d97d6f | 118 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 119 | } |
emh203 | 0:3d9c67d97d6f | 120 | |
emh203 | 0:3d9c67d97d6f | 121 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
emh203 | 0:3d9c67d97d6f | 122 | ** No loop unrolling is used. */ |
emh203 | 0:3d9c67d97d6f | 123 | blkCnt = blockSize % 0x4u; |
emh203 | 0:3d9c67d97d6f | 124 | |
emh203 | 0:3d9c67d97d6f | 125 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 126 | { |
emh203 | 0:3d9c67d97d6f | 127 | /* C = A << shiftBits */ |
emh203 | 0:3d9c67d97d6f | 128 | /* Shift the input and then store the result in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 129 | *pDst++ = (q7_t) __SSAT((*pSrc++ << shiftBits), 8); |
emh203 | 0:3d9c67d97d6f | 130 | |
emh203 | 0:3d9c67d97d6f | 131 | /* Decrement the loop counter */ |
emh203 | 0:3d9c67d97d6f | 132 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 133 | } |
emh203 | 0:3d9c67d97d6f | 134 | } |
emh203 | 0:3d9c67d97d6f | 135 | else |
emh203 | 0:3d9c67d97d6f | 136 | { |
emh203 | 0:3d9c67d97d6f | 137 | shiftBits = -shiftBits; |
emh203 | 0:3d9c67d97d6f | 138 | /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
emh203 | 0:3d9c67d97d6f | 139 | ** a second loop below computes the remaining 1 to 3 samples. */ |
emh203 | 0:3d9c67d97d6f | 140 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 141 | { |
emh203 | 0:3d9c67d97d6f | 142 | /* C = A >> shiftBits */ |
emh203 | 0:3d9c67d97d6f | 143 | /* Read 4 inputs */ |
emh203 | 0:3d9c67d97d6f | 144 | in1 = *pSrc; |
emh203 | 0:3d9c67d97d6f | 145 | in2 = *(pSrc + 1); |
emh203 | 0:3d9c67d97d6f | 146 | in3 = *(pSrc + 2); |
emh203 | 0:3d9c67d97d6f | 147 | in4 = *(pSrc + 3); |
emh203 | 0:3d9c67d97d6f | 148 | |
emh203 | 0:3d9c67d97d6f | 149 | /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */ |
emh203 | 0:3d9c67d97d6f | 150 | *__SIMD32(pDst)++ = __PACKq7((in1 >> shiftBits), (in2 >> shiftBits), |
emh203 | 0:3d9c67d97d6f | 151 | (in3 >> shiftBits), (in4 >> shiftBits)); |
emh203 | 0:3d9c67d97d6f | 152 | |
emh203 | 0:3d9c67d97d6f | 153 | |
emh203 | 0:3d9c67d97d6f | 154 | pSrc += 4u; |
emh203 | 0:3d9c67d97d6f | 155 | |
emh203 | 0:3d9c67d97d6f | 156 | /* Decrement the loop counter */ |
emh203 | 0:3d9c67d97d6f | 157 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 158 | } |
emh203 | 0:3d9c67d97d6f | 159 | |
emh203 | 0:3d9c67d97d6f | 160 | /* If the blockSize is not a multiple of 4, compute any remaining output samples here. |
emh203 | 0:3d9c67d97d6f | 161 | ** No loop unrolling is used. */ |
emh203 | 0:3d9c67d97d6f | 162 | blkCnt = blockSize % 0x4u; |
emh203 | 0:3d9c67d97d6f | 163 | |
emh203 | 0:3d9c67d97d6f | 164 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 165 | { |
emh203 | 0:3d9c67d97d6f | 166 | /* C = A >> shiftBits */ |
emh203 | 0:3d9c67d97d6f | 167 | /* Shift the input and then store the result in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 168 | in1 = *pSrc++; |
emh203 | 0:3d9c67d97d6f | 169 | *pDst++ = (in1 >> shiftBits); |
emh203 | 0:3d9c67d97d6f | 170 | |
emh203 | 0:3d9c67d97d6f | 171 | /* Decrement the loop counter */ |
emh203 | 0:3d9c67d97d6f | 172 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 173 | } |
emh203 | 0:3d9c67d97d6f | 174 | } |
emh203 | 0:3d9c67d97d6f | 175 | |
emh203 | 0:3d9c67d97d6f | 176 | #else |
emh203 | 0:3d9c67d97d6f | 177 | |
emh203 | 0:3d9c67d97d6f | 178 | /* Run the below code for Cortex-M0 */ |
emh203 | 0:3d9c67d97d6f | 179 | |
emh203 | 0:3d9c67d97d6f | 180 | /* Getting the sign of shiftBits */ |
emh203 | 0:3d9c67d97d6f | 181 | sign = (shiftBits & 0x80); |
emh203 | 0:3d9c67d97d6f | 182 | |
emh203 | 0:3d9c67d97d6f | 183 | /* If the shift value is positive then do right shift else left shift */ |
emh203 | 0:3d9c67d97d6f | 184 | if(sign == 0u) |
emh203 | 0:3d9c67d97d6f | 185 | { |
emh203 | 0:3d9c67d97d6f | 186 | /* Initialize blkCnt with number of samples */ |
emh203 | 0:3d9c67d97d6f | 187 | blkCnt = blockSize; |
emh203 | 0:3d9c67d97d6f | 188 | |
emh203 | 0:3d9c67d97d6f | 189 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 190 | { |
emh203 | 0:3d9c67d97d6f | 191 | /* C = A << shiftBits */ |
emh203 | 0:3d9c67d97d6f | 192 | /* Shift the input and then store the result in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 193 | *pDst++ = (q7_t) __SSAT(((q15_t) * pSrc++ << shiftBits), 8); |
emh203 | 0:3d9c67d97d6f | 194 | |
emh203 | 0:3d9c67d97d6f | 195 | /* Decrement the loop counter */ |
emh203 | 0:3d9c67d97d6f | 196 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 197 | } |
emh203 | 0:3d9c67d97d6f | 198 | } |
emh203 | 0:3d9c67d97d6f | 199 | else |
emh203 | 0:3d9c67d97d6f | 200 | { |
emh203 | 0:3d9c67d97d6f | 201 | /* Initialize blkCnt with number of samples */ |
emh203 | 0:3d9c67d97d6f | 202 | blkCnt = blockSize; |
emh203 | 0:3d9c67d97d6f | 203 | |
emh203 | 0:3d9c67d97d6f | 204 | while(blkCnt > 0u) |
emh203 | 0:3d9c67d97d6f | 205 | { |
emh203 | 0:3d9c67d97d6f | 206 | /* C = A >> shiftBits */ |
emh203 | 0:3d9c67d97d6f | 207 | /* Shift the input and then store the result in the destination buffer. */ |
emh203 | 0:3d9c67d97d6f | 208 | *pDst++ = (*pSrc++ >> -shiftBits); |
emh203 | 0:3d9c67d97d6f | 209 | |
emh203 | 0:3d9c67d97d6f | 210 | /* Decrement the loop counter */ |
emh203 | 0:3d9c67d97d6f | 211 | blkCnt--; |
emh203 | 0:3d9c67d97d6f | 212 | } |
emh203 | 0:3d9c67d97d6f | 213 | } |
emh203 | 0:3d9c67d97d6f | 214 | |
emh203 | 0:3d9c67d97d6f | 215 | #endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
emh203 | 0:3d9c67d97d6f | 216 | } |
emh203 | 0:3d9c67d97d6f | 217 | |
emh203 | 0:3d9c67d97d6f | 218 | /** |
emh203 | 0:3d9c67d97d6f | 219 | * @} end of shift group |
emh203 | 0:3d9c67d97d6f | 220 | */ |