CMSIS DSP library
Dependents: performance_timer Surfboard_ gps2rtty Capstone ... more
Legacy Warning
This is an mbed 2 library. To learn more about mbed OS 5, visit the docs.
cmsis_dsp/FilteringFunctions/arm_fir_decimate_fast_q31.c@2:da51fb522205, 2013-05-30 (annotated)
- Committer:
- emilmont
- Date:
- Thu May 30 17:10:11 2013 +0100
- Revision:
- 2:da51fb522205
- Parent:
- 1:fdd22bb7aa52
- Child:
- 3:7a284390b0ce
Keep "cmsis-dsp" module in synch with its source
Who changed what in which revision?
User | Revision | Line number | New contents of line |
---|---|---|---|
emilmont | 1:fdd22bb7aa52 | 1 | /* ---------------------------------------------------------------------- |
emilmont | 1:fdd22bb7aa52 | 2 | * Copyright (C) 2010 ARM Limited. All rights reserved. |
emilmont | 1:fdd22bb7aa52 | 3 | * |
emilmont | 1:fdd22bb7aa52 | 4 | * $Date: 15. February 2012 |
emilmont | 2:da51fb522205 | 5 | * $Revision: V1.1.0 |
emilmont | 1:fdd22bb7aa52 | 6 | * |
emilmont | 2:da51fb522205 | 7 | * Project: CMSIS DSP Library |
emilmont | 2:da51fb522205 | 8 | * Title: arm_fir_decimate_fast_q31.c |
emilmont | 1:fdd22bb7aa52 | 9 | * |
emilmont | 2:da51fb522205 | 10 | * Description: Fast Q31 FIR Decimator. |
emilmont | 1:fdd22bb7aa52 | 11 | * |
emilmont | 1:fdd22bb7aa52 | 12 | * Target Processor: Cortex-M4/Cortex-M3 |
emilmont | 1:fdd22bb7aa52 | 13 | * |
emilmont | 1:fdd22bb7aa52 | 14 | * Version 1.1.0 2012/02/15 |
emilmont | 1:fdd22bb7aa52 | 15 | * Updated with more optimizations, bug fixes and minor API changes. |
emilmont | 1:fdd22bb7aa52 | 16 | * |
emilmont | 1:fdd22bb7aa52 | 17 | * Version 1.0.10 2011/7/15 |
emilmont | 1:fdd22bb7aa52 | 18 | * Big Endian support added and Merged M0 and M3/M4 Source code. |
emilmont | 1:fdd22bb7aa52 | 19 | * |
emilmont | 1:fdd22bb7aa52 | 20 | * Version 1.0.3 2010/11/29 |
emilmont | 1:fdd22bb7aa52 | 21 | * Re-organized the CMSIS folders and updated documentation. |
emilmont | 1:fdd22bb7aa52 | 22 | * |
emilmont | 1:fdd22bb7aa52 | 23 | * Version 1.0.2 2010/11/11 |
emilmont | 1:fdd22bb7aa52 | 24 | * Documentation updated. |
emilmont | 1:fdd22bb7aa52 | 25 | * |
emilmont | 1:fdd22bb7aa52 | 26 | * Version 1.0.1 2010/10/05 |
emilmont | 1:fdd22bb7aa52 | 27 | * Production release and review comments incorporated. |
emilmont | 1:fdd22bb7aa52 | 28 | * |
emilmont | 1:fdd22bb7aa52 | 29 | * Version 1.0.0 2010/09/20 |
emilmont | 1:fdd22bb7aa52 | 30 | * Production release and review comments incorporated. |
emilmont | 1:fdd22bb7aa52 | 31 | * -------------------------------------------------------------------- */ |
emilmont | 1:fdd22bb7aa52 | 32 | |
emilmont | 1:fdd22bb7aa52 | 33 | #include "arm_math.h" |
emilmont | 1:fdd22bb7aa52 | 34 | |
emilmont | 1:fdd22bb7aa52 | 35 | /** |
emilmont | 1:fdd22bb7aa52 | 36 | * @ingroup groupFilters |
emilmont | 1:fdd22bb7aa52 | 37 | */ |
emilmont | 1:fdd22bb7aa52 | 38 | |
emilmont | 1:fdd22bb7aa52 | 39 | /** |
emilmont | 1:fdd22bb7aa52 | 40 | * @addtogroup FIR_decimate |
emilmont | 1:fdd22bb7aa52 | 41 | * @{ |
emilmont | 1:fdd22bb7aa52 | 42 | */ |
emilmont | 1:fdd22bb7aa52 | 43 | |
emilmont | 1:fdd22bb7aa52 | 44 | /** |
emilmont | 1:fdd22bb7aa52 | 45 | * @brief Processing function for the Q31 FIR decimator (fast variant) for Cortex-M3 and Cortex-M4. |
emilmont | 1:fdd22bb7aa52 | 46 | * @param[in] *S points to an instance of the Q31 FIR decimator structure. |
emilmont | 1:fdd22bb7aa52 | 47 | * @param[in] *pSrc points to the block of input data. |
emilmont | 1:fdd22bb7aa52 | 48 | * @param[out] *pDst points to the block of output data |
emilmont | 1:fdd22bb7aa52 | 49 | * @param[in] blockSize number of input samples to process per call. |
emilmont | 1:fdd22bb7aa52 | 50 | * @return none |
emilmont | 1:fdd22bb7aa52 | 51 | * |
emilmont | 1:fdd22bb7aa52 | 52 | * <b>Scaling and Overflow Behavior:</b> |
emilmont | 1:fdd22bb7aa52 | 53 | * |
emilmont | 1:fdd22bb7aa52 | 54 | * \par |
emilmont | 1:fdd22bb7aa52 | 55 | * This function is optimized for speed at the expense of fixed-point precision and overflow protection. |
emilmont | 1:fdd22bb7aa52 | 56 | * The result of each 1.31 x 1.31 multiplication is truncated to 2.30 format. |
emilmont | 1:fdd22bb7aa52 | 57 | * These intermediate results are added to a 2.30 accumulator. |
emilmont | 1:fdd22bb7aa52 | 58 | * Finally, the accumulator is saturated and converted to a 1.31 result. |
emilmont | 1:fdd22bb7aa52 | 59 | * The fast version has the same overflow behavior as the standard version and provides less precision since it discards the low 32 bits of each multiplication result. |
emilmont | 1:fdd22bb7aa52 | 60 | * In order to avoid overflows completely the input signal must be scaled down by log2(numTaps) bits (where log2 is read as log to the base 2). |
emilmont | 1:fdd22bb7aa52 | 61 | * |
emilmont | 1:fdd22bb7aa52 | 62 | * \par |
emilmont | 1:fdd22bb7aa52 | 63 | * Refer to the function <code>arm_fir_decimate_q31()</code> for a slower implementation of this function which uses a 64-bit accumulator to provide higher precision. |
emilmont | 1:fdd22bb7aa52 | 64 | * Both the slow and the fast versions use the same instance structure. |
emilmont | 1:fdd22bb7aa52 | 65 | * Use the function <code>arm_fir_decimate_init_q31()</code> to initialize the filter structure. |
emilmont | 1:fdd22bb7aa52 | 66 | */ |
emilmont | 1:fdd22bb7aa52 | 67 | |
emilmont | 1:fdd22bb7aa52 | 68 | void arm_fir_decimate_fast_q31( |
emilmont | 1:fdd22bb7aa52 | 69 | arm_fir_decimate_instance_q31 * S, |
emilmont | 1:fdd22bb7aa52 | 70 | q31_t * pSrc, |
emilmont | 1:fdd22bb7aa52 | 71 | q31_t * pDst, |
emilmont | 1:fdd22bb7aa52 | 72 | uint32_t blockSize) |
emilmont | 1:fdd22bb7aa52 | 73 | { |
emilmont | 1:fdd22bb7aa52 | 74 | q31_t *pState = S->pState; /* State pointer */ |
emilmont | 1:fdd22bb7aa52 | 75 | q31_t *pCoeffs = S->pCoeffs; /* Coefficient pointer */ |
emilmont | 1:fdd22bb7aa52 | 76 | q31_t *pStateCurnt; /* Points to the current sample of the state */ |
emilmont | 1:fdd22bb7aa52 | 77 | q31_t x0, c0; /* Temporary variables to hold state and coefficient values */ |
emilmont | 1:fdd22bb7aa52 | 78 | q31_t *px; /* Temporary pointers for state buffer */ |
emilmont | 1:fdd22bb7aa52 | 79 | q31_t *pb; /* Temporary pointers for coefficient buffer */ |
emilmont | 1:fdd22bb7aa52 | 80 | q31_t sum0; /* Accumulator */ |
emilmont | 1:fdd22bb7aa52 | 81 | uint32_t numTaps = S->numTaps; /* Number of taps */ |
emilmont | 1:fdd22bb7aa52 | 82 | uint32_t i, tapCnt, blkCnt, outBlockSize = blockSize / S->M; /* Loop counters */ |
emilmont | 1:fdd22bb7aa52 | 83 | uint32_t blkCntN2; |
emilmont | 1:fdd22bb7aa52 | 84 | q31_t x1; |
emilmont | 1:fdd22bb7aa52 | 85 | q31_t acc0, acc1; |
emilmont | 1:fdd22bb7aa52 | 86 | q31_t *px0, *px1; |
emilmont | 1:fdd22bb7aa52 | 87 | |
emilmont | 1:fdd22bb7aa52 | 88 | /* S->pState buffer contains previous frame (numTaps - 1) samples */ |
emilmont | 1:fdd22bb7aa52 | 89 | /* pStateCurnt points to the location where the new input data should be written */ |
emilmont | 1:fdd22bb7aa52 | 90 | pStateCurnt = S->pState + (numTaps - 1u); |
emilmont | 1:fdd22bb7aa52 | 91 | |
emilmont | 1:fdd22bb7aa52 | 92 | /* Total number of output samples to be computed */ |
emilmont | 1:fdd22bb7aa52 | 93 | |
emilmont | 1:fdd22bb7aa52 | 94 | blkCnt = outBlockSize / 2; |
emilmont | 1:fdd22bb7aa52 | 95 | blkCntN2 = outBlockSize - (2 * blkCnt); |
emilmont | 1:fdd22bb7aa52 | 96 | |
emilmont | 1:fdd22bb7aa52 | 97 | while(blkCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 98 | { |
emilmont | 1:fdd22bb7aa52 | 99 | /* Copy decimation factor number of new input samples into the state buffer */ |
emilmont | 1:fdd22bb7aa52 | 100 | i = 2 * S->M; |
emilmont | 1:fdd22bb7aa52 | 101 | |
emilmont | 1:fdd22bb7aa52 | 102 | do |
emilmont | 1:fdd22bb7aa52 | 103 | { |
emilmont | 1:fdd22bb7aa52 | 104 | *pStateCurnt++ = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 105 | |
emilmont | 1:fdd22bb7aa52 | 106 | } while(--i); |
emilmont | 1:fdd22bb7aa52 | 107 | |
emilmont | 1:fdd22bb7aa52 | 108 | /* Set accumulator to zero */ |
emilmont | 1:fdd22bb7aa52 | 109 | acc0 = 0; |
emilmont | 1:fdd22bb7aa52 | 110 | acc1 = 0; |
emilmont | 1:fdd22bb7aa52 | 111 | |
emilmont | 1:fdd22bb7aa52 | 112 | /* Initialize state pointer */ |
emilmont | 1:fdd22bb7aa52 | 113 | px0 = pState; |
emilmont | 1:fdd22bb7aa52 | 114 | px1 = pState + S->M; |
emilmont | 1:fdd22bb7aa52 | 115 | |
emilmont | 1:fdd22bb7aa52 | 116 | /* Initialize coeff pointer */ |
emilmont | 1:fdd22bb7aa52 | 117 | pb = pCoeffs; |
emilmont | 1:fdd22bb7aa52 | 118 | |
emilmont | 1:fdd22bb7aa52 | 119 | /* Loop unrolling. Process 4 taps at a time. */ |
emilmont | 1:fdd22bb7aa52 | 120 | tapCnt = numTaps >> 2; |
emilmont | 1:fdd22bb7aa52 | 121 | |
emilmont | 1:fdd22bb7aa52 | 122 | /* Loop over the number of taps. Unroll by a factor of 4. |
emilmont | 1:fdd22bb7aa52 | 123 | ** Repeat until we've computed numTaps-4 coefficients. */ |
emilmont | 1:fdd22bb7aa52 | 124 | while(tapCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 125 | { |
emilmont | 1:fdd22bb7aa52 | 126 | /* Read the b[numTaps-1] coefficient */ |
emilmont | 1:fdd22bb7aa52 | 127 | c0 = *(pb); |
emilmont | 1:fdd22bb7aa52 | 128 | |
emilmont | 1:fdd22bb7aa52 | 129 | /* Read x[n-numTaps-1] for sample 0 sample 1 */ |
emilmont | 1:fdd22bb7aa52 | 130 | x0 = *(px0); |
emilmont | 1:fdd22bb7aa52 | 131 | x1 = *(px1); |
emilmont | 1:fdd22bb7aa52 | 132 | |
emilmont | 1:fdd22bb7aa52 | 133 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 134 | acc0 = (q31_t) ((((q63_t) acc0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 135 | acc1 = (q31_t) ((((q63_t) acc1 << 32) + ((q63_t) x1 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 136 | |
emilmont | 1:fdd22bb7aa52 | 137 | /* Read the b[numTaps-2] coefficient */ |
emilmont | 1:fdd22bb7aa52 | 138 | c0 = *(pb + 1u); |
emilmont | 1:fdd22bb7aa52 | 139 | |
emilmont | 1:fdd22bb7aa52 | 140 | /* Read x[n-numTaps-2] for sample 0 sample 1 */ |
emilmont | 1:fdd22bb7aa52 | 141 | x0 = *(px0 + 1u); |
emilmont | 1:fdd22bb7aa52 | 142 | x1 = *(px1 + 1u); |
emilmont | 1:fdd22bb7aa52 | 143 | |
emilmont | 1:fdd22bb7aa52 | 144 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 145 | acc0 = (q31_t) ((((q63_t) acc0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 146 | acc1 = (q31_t) ((((q63_t) acc1 << 32) + ((q63_t) x1 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 147 | |
emilmont | 1:fdd22bb7aa52 | 148 | /* Read the b[numTaps-3] coefficient */ |
emilmont | 1:fdd22bb7aa52 | 149 | c0 = *(pb + 2u); |
emilmont | 1:fdd22bb7aa52 | 150 | |
emilmont | 1:fdd22bb7aa52 | 151 | /* Read x[n-numTaps-3] for sample 0 sample 1 */ |
emilmont | 1:fdd22bb7aa52 | 152 | x0 = *(px0 + 2u); |
emilmont | 1:fdd22bb7aa52 | 153 | x1 = *(px1 + 2u); |
emilmont | 1:fdd22bb7aa52 | 154 | pb += 4u; |
emilmont | 1:fdd22bb7aa52 | 155 | |
emilmont | 1:fdd22bb7aa52 | 156 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 157 | acc0 = (q31_t) ((((q63_t) acc0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 158 | acc1 = (q31_t) ((((q63_t) acc1 << 32) + ((q63_t) x1 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 159 | |
emilmont | 1:fdd22bb7aa52 | 160 | /* Read the b[numTaps-4] coefficient */ |
emilmont | 1:fdd22bb7aa52 | 161 | c0 = *(pb - 1u); |
emilmont | 1:fdd22bb7aa52 | 162 | |
emilmont | 1:fdd22bb7aa52 | 163 | /* Read x[n-numTaps-4] for sample 0 sample 1 */ |
emilmont | 1:fdd22bb7aa52 | 164 | x0 = *(px0 + 3u); |
emilmont | 1:fdd22bb7aa52 | 165 | x1 = *(px1 + 3u); |
emilmont | 1:fdd22bb7aa52 | 166 | |
emilmont | 1:fdd22bb7aa52 | 167 | |
emilmont | 1:fdd22bb7aa52 | 168 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 169 | acc0 = (q31_t) ((((q63_t) acc0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 170 | acc1 = (q31_t) ((((q63_t) acc1 << 32) + ((q63_t) x1 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 171 | |
emilmont | 1:fdd22bb7aa52 | 172 | /* update state pointers */ |
emilmont | 1:fdd22bb7aa52 | 173 | px0 += 4u; |
emilmont | 1:fdd22bb7aa52 | 174 | px1 += 4u; |
emilmont | 1:fdd22bb7aa52 | 175 | |
emilmont | 1:fdd22bb7aa52 | 176 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 177 | tapCnt--; |
emilmont | 1:fdd22bb7aa52 | 178 | } |
emilmont | 1:fdd22bb7aa52 | 179 | |
emilmont | 1:fdd22bb7aa52 | 180 | /* If the filter length is not a multiple of 4, compute the remaining filter taps */ |
emilmont | 1:fdd22bb7aa52 | 181 | tapCnt = numTaps % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 182 | |
emilmont | 1:fdd22bb7aa52 | 183 | while(tapCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 184 | { |
emilmont | 1:fdd22bb7aa52 | 185 | /* Read coefficients */ |
emilmont | 1:fdd22bb7aa52 | 186 | c0 = *(pb++); |
emilmont | 1:fdd22bb7aa52 | 187 | |
emilmont | 1:fdd22bb7aa52 | 188 | /* Fetch 1 state variable */ |
emilmont | 1:fdd22bb7aa52 | 189 | x0 = *(px0++); |
emilmont | 1:fdd22bb7aa52 | 190 | x1 = *(px1++); |
emilmont | 1:fdd22bb7aa52 | 191 | |
emilmont | 1:fdd22bb7aa52 | 192 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 193 | acc0 = (q31_t) ((((q63_t) acc0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 194 | acc1 = (q31_t) ((((q63_t) acc1 << 32) + ((q63_t) x1 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 195 | |
emilmont | 1:fdd22bb7aa52 | 196 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 197 | tapCnt--; |
emilmont | 1:fdd22bb7aa52 | 198 | } |
emilmont | 1:fdd22bb7aa52 | 199 | |
emilmont | 1:fdd22bb7aa52 | 200 | /* Advance the state pointer by the decimation factor |
emilmont | 1:fdd22bb7aa52 | 201 | * to process the next group of decimation factor number samples */ |
emilmont | 1:fdd22bb7aa52 | 202 | pState = pState + S->M * 2; |
emilmont | 1:fdd22bb7aa52 | 203 | |
emilmont | 1:fdd22bb7aa52 | 204 | /* The result is in the accumulator, store in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 205 | *pDst++ = (q31_t) (acc0 << 1); |
emilmont | 1:fdd22bb7aa52 | 206 | *pDst++ = (q31_t) (acc1 << 1); |
emilmont | 1:fdd22bb7aa52 | 207 | |
emilmont | 1:fdd22bb7aa52 | 208 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 209 | blkCnt--; |
emilmont | 1:fdd22bb7aa52 | 210 | } |
emilmont | 1:fdd22bb7aa52 | 211 | |
emilmont | 1:fdd22bb7aa52 | 212 | while(blkCntN2 > 0u) |
emilmont | 1:fdd22bb7aa52 | 213 | { |
emilmont | 1:fdd22bb7aa52 | 214 | /* Copy decimation factor number of new input samples into the state buffer */ |
emilmont | 1:fdd22bb7aa52 | 215 | i = S->M; |
emilmont | 1:fdd22bb7aa52 | 216 | |
emilmont | 1:fdd22bb7aa52 | 217 | do |
emilmont | 1:fdd22bb7aa52 | 218 | { |
emilmont | 1:fdd22bb7aa52 | 219 | *pStateCurnt++ = *pSrc++; |
emilmont | 1:fdd22bb7aa52 | 220 | |
emilmont | 1:fdd22bb7aa52 | 221 | } while(--i); |
emilmont | 1:fdd22bb7aa52 | 222 | |
emilmont | 1:fdd22bb7aa52 | 223 | /* Set accumulator to zero */ |
emilmont | 1:fdd22bb7aa52 | 224 | sum0 = 0; |
emilmont | 1:fdd22bb7aa52 | 225 | |
emilmont | 1:fdd22bb7aa52 | 226 | /* Initialize state pointer */ |
emilmont | 1:fdd22bb7aa52 | 227 | px = pState; |
emilmont | 1:fdd22bb7aa52 | 228 | |
emilmont | 1:fdd22bb7aa52 | 229 | /* Initialize coeff pointer */ |
emilmont | 1:fdd22bb7aa52 | 230 | pb = pCoeffs; |
emilmont | 1:fdd22bb7aa52 | 231 | |
emilmont | 1:fdd22bb7aa52 | 232 | /* Loop unrolling. Process 4 taps at a time. */ |
emilmont | 1:fdd22bb7aa52 | 233 | tapCnt = numTaps >> 2; |
emilmont | 1:fdd22bb7aa52 | 234 | |
emilmont | 1:fdd22bb7aa52 | 235 | /* Loop over the number of taps. Unroll by a factor of 4. |
emilmont | 1:fdd22bb7aa52 | 236 | ** Repeat until we've computed numTaps-4 coefficients. */ |
emilmont | 1:fdd22bb7aa52 | 237 | while(tapCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 238 | { |
emilmont | 1:fdd22bb7aa52 | 239 | /* Read the b[numTaps-1] coefficient */ |
emilmont | 1:fdd22bb7aa52 | 240 | c0 = *(pb++); |
emilmont | 1:fdd22bb7aa52 | 241 | |
emilmont | 1:fdd22bb7aa52 | 242 | /* Read x[n-numTaps-1] sample */ |
emilmont | 1:fdd22bb7aa52 | 243 | x0 = *(px++); |
emilmont | 1:fdd22bb7aa52 | 244 | |
emilmont | 1:fdd22bb7aa52 | 245 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 246 | sum0 = (q31_t) ((((q63_t) sum0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 247 | |
emilmont | 1:fdd22bb7aa52 | 248 | /* Read the b[numTaps-2] coefficient */ |
emilmont | 1:fdd22bb7aa52 | 249 | c0 = *(pb++); |
emilmont | 1:fdd22bb7aa52 | 250 | |
emilmont | 1:fdd22bb7aa52 | 251 | /* Read x[n-numTaps-2] sample */ |
emilmont | 1:fdd22bb7aa52 | 252 | x0 = *(px++); |
emilmont | 1:fdd22bb7aa52 | 253 | |
emilmont | 1:fdd22bb7aa52 | 254 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 255 | sum0 = (q31_t) ((((q63_t) sum0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 256 | |
emilmont | 1:fdd22bb7aa52 | 257 | /* Read the b[numTaps-3] coefficient */ |
emilmont | 1:fdd22bb7aa52 | 258 | c0 = *(pb++); |
emilmont | 1:fdd22bb7aa52 | 259 | |
emilmont | 1:fdd22bb7aa52 | 260 | /* Read x[n-numTaps-3] sample */ |
emilmont | 1:fdd22bb7aa52 | 261 | x0 = *(px++); |
emilmont | 1:fdd22bb7aa52 | 262 | |
emilmont | 1:fdd22bb7aa52 | 263 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 264 | sum0 = (q31_t) ((((q63_t) sum0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 265 | |
emilmont | 1:fdd22bb7aa52 | 266 | /* Read the b[numTaps-4] coefficient */ |
emilmont | 1:fdd22bb7aa52 | 267 | c0 = *(pb++); |
emilmont | 1:fdd22bb7aa52 | 268 | |
emilmont | 1:fdd22bb7aa52 | 269 | /* Read x[n-numTaps-4] sample */ |
emilmont | 1:fdd22bb7aa52 | 270 | x0 = *(px++); |
emilmont | 1:fdd22bb7aa52 | 271 | |
emilmont | 1:fdd22bb7aa52 | 272 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 273 | sum0 = (q31_t) ((((q63_t) sum0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 274 | |
emilmont | 1:fdd22bb7aa52 | 275 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 276 | tapCnt--; |
emilmont | 1:fdd22bb7aa52 | 277 | } |
emilmont | 1:fdd22bb7aa52 | 278 | |
emilmont | 1:fdd22bb7aa52 | 279 | /* If the filter length is not a multiple of 4, compute the remaining filter taps */ |
emilmont | 1:fdd22bb7aa52 | 280 | tapCnt = numTaps % 0x4u; |
emilmont | 1:fdd22bb7aa52 | 281 | |
emilmont | 1:fdd22bb7aa52 | 282 | while(tapCnt > 0u) |
emilmont | 1:fdd22bb7aa52 | 283 | { |
emilmont | 1:fdd22bb7aa52 | 284 | /* Read coefficients */ |
emilmont | 1:fdd22bb7aa52 | 285 | c0 = *(pb++); |
emilmont | 1:fdd22bb7aa52 | 286 | |
emilmont | 1:fdd22bb7aa52 | 287 | /* Fetch 1 state variable */ |
emilmont | 1:fdd22bb7aa52 | 288 | x0 = *(px++); |
emilmont | 1:fdd22bb7aa52 | 289 | |
emilmont | 1:fdd22bb7aa52 | 290 | /* Perform the multiply-accumulate */ |
emilmont | 1:fdd22bb7aa52 | 291 | sum0 = (q31_t) ((((q63_t) sum0 << 32) + ((q63_t) x0 * c0)) >> 32); |
emilmont | 1:fdd22bb7aa52 | 292 | |
emilmont | 1:fdd22bb7aa52 | 293 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 294 | tapCnt--; |
emilmont | 1:fdd22bb7aa52 | 295 | } |
emilmont | 1:fdd22bb7aa52 | 296 | |
emilmont | 1:fdd22bb7aa52 | 297 | /* Advance the state pointer by the decimation factor |
emilmont | 1:fdd22bb7aa52 | 298 | * to process the next group of decimation factor number samples */ |
emilmont | 1:fdd22bb7aa52 | 299 | pState = pState + S->M; |
emilmont | 1:fdd22bb7aa52 | 300 | |
emilmont | 1:fdd22bb7aa52 | 301 | /* The result is in the accumulator, store in the destination buffer. */ |
emilmont | 1:fdd22bb7aa52 | 302 | *pDst++ = (q31_t) (sum0 << 1); |
emilmont | 1:fdd22bb7aa52 | 303 | |
emilmont | 1:fdd22bb7aa52 | 304 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 305 | blkCntN2--; |
emilmont | 1:fdd22bb7aa52 | 306 | } |
emilmont | 1:fdd22bb7aa52 | 307 | |
emilmont | 1:fdd22bb7aa52 | 308 | /* Processing is complete. |
emilmont | 1:fdd22bb7aa52 | 309 | ** Now copy the last numTaps - 1 samples to the satrt of the state buffer. |
emilmont | 1:fdd22bb7aa52 | 310 | ** This prepares the state buffer for the next function call. */ |
emilmont | 1:fdd22bb7aa52 | 311 | |
emilmont | 1:fdd22bb7aa52 | 312 | /* Points to the start of the state buffer */ |
emilmont | 1:fdd22bb7aa52 | 313 | pStateCurnt = S->pState; |
emilmont | 1:fdd22bb7aa52 | 314 | |
emilmont | 1:fdd22bb7aa52 | 315 | i = (numTaps - 1u) >> 2u; |
emilmont | 1:fdd22bb7aa52 | 316 | |
emilmont | 1:fdd22bb7aa52 | 317 | /* copy data */ |
emilmont | 1:fdd22bb7aa52 | 318 | while(i > 0u) |
emilmont | 1:fdd22bb7aa52 | 319 | { |
emilmont | 1:fdd22bb7aa52 | 320 | *pStateCurnt++ = *pState++; |
emilmont | 1:fdd22bb7aa52 | 321 | *pStateCurnt++ = *pState++; |
emilmont | 1:fdd22bb7aa52 | 322 | *pStateCurnt++ = *pState++; |
emilmont | 1:fdd22bb7aa52 | 323 | *pStateCurnt++ = *pState++; |
emilmont | 1:fdd22bb7aa52 | 324 | |
emilmont | 1:fdd22bb7aa52 | 325 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 326 | i--; |
emilmont | 1:fdd22bb7aa52 | 327 | } |
emilmont | 1:fdd22bb7aa52 | 328 | |
emilmont | 1:fdd22bb7aa52 | 329 | i = (numTaps - 1u) % 0x04u; |
emilmont | 1:fdd22bb7aa52 | 330 | |
emilmont | 1:fdd22bb7aa52 | 331 | /* copy data */ |
emilmont | 1:fdd22bb7aa52 | 332 | while(i > 0u) |
emilmont | 1:fdd22bb7aa52 | 333 | { |
emilmont | 1:fdd22bb7aa52 | 334 | *pStateCurnt++ = *pState++; |
emilmont | 1:fdd22bb7aa52 | 335 | |
emilmont | 1:fdd22bb7aa52 | 336 | /* Decrement the loop counter */ |
emilmont | 1:fdd22bb7aa52 | 337 | i--; |
emilmont | 1:fdd22bb7aa52 | 338 | } |
emilmont | 1:fdd22bb7aa52 | 339 | } |
emilmont | 1:fdd22bb7aa52 | 340 | |
emilmont | 1:fdd22bb7aa52 | 341 | /** |
emilmont | 1:fdd22bb7aa52 | 342 | * @} end of FIR_decimate group |
emilmont | 1:fdd22bb7aa52 | 343 | */ |