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

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?

UserRevisionLine numberNew 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_fir_sparse_f32.c
emh203 0:3d9c67d97d6f 9 *
emh203 0:3d9c67d97d6f 10 * Description: Floating-point sparse FIR filter processing function.
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 #include "arm_math.h"
emh203 0:3d9c67d97d6f 41
emh203 0:3d9c67d97d6f 42 /**
emh203 0:3d9c67d97d6f 43 * @ingroup groupFilters
emh203 0:3d9c67d97d6f 44 */
emh203 0:3d9c67d97d6f 45
emh203 0:3d9c67d97d6f 46 /**
emh203 0:3d9c67d97d6f 47 * @defgroup FIR_Sparse Finite Impulse Response (FIR) Sparse Filters
emh203 0:3d9c67d97d6f 48 *
emh203 0:3d9c67d97d6f 49 * This group of functions implements sparse FIR filters.
emh203 0:3d9c67d97d6f 50 * Sparse FIR filters are equivalent to standard FIR filters except that most of the coefficients are equal to zero.
emh203 0:3d9c67d97d6f 51 * Sparse filters are used for simulating reflections in communications and audio applications.
emh203 0:3d9c67d97d6f 52 *
emh203 0:3d9c67d97d6f 53 * There are separate functions for Q7, Q15, Q31, and floating-point data types.
emh203 0:3d9c67d97d6f 54 * The functions operate on blocks of input and output data and each call to the function processes
emh203 0:3d9c67d97d6f 55 * <code>blockSize</code> samples through the filter. <code>pSrc</code> and
emh203 0:3d9c67d97d6f 56 * <code>pDst</code> points to input and output arrays respectively containing <code>blockSize</code> values.
emh203 0:3d9c67d97d6f 57 *
emh203 0:3d9c67d97d6f 58 * \par Algorithm:
emh203 0:3d9c67d97d6f 59 * The sparse filter instant structure contains an array of tap indices <code>pTapDelay</code> which specifies the locations of the non-zero coefficients.
emh203 0:3d9c67d97d6f 60 * This is in addition to the coefficient array <code>b</code>.
emh203 0:3d9c67d97d6f 61 * The implementation essentially skips the multiplications by zero and leads to an efficient realization.
emh203 0:3d9c67d97d6f 62 * <pre>
emh203 0:3d9c67d97d6f 63 * y[n] = b[0] * x[n-pTapDelay[0]] + b[1] * x[n-pTapDelay[1]] + b[2] * x[n-pTapDelay[2]] + ...+ b[numTaps-1] * x[n-pTapDelay[numTaps-1]]
emh203 0:3d9c67d97d6f 64 * </pre>
emh203 0:3d9c67d97d6f 65 * \par
emh203 0:3d9c67d97d6f 66 * \image html FIRSparse.gif "Sparse FIR filter. b[n] represents the filter coefficients"
emh203 0:3d9c67d97d6f 67 * \par
emh203 0:3d9c67d97d6f 68 * <code>pCoeffs</code> points to a coefficient array of size <code>numTaps</code>;
emh203 0:3d9c67d97d6f 69 * <code>pTapDelay</code> points to an array of nonzero indices and is also of size <code>numTaps</code>;
emh203 0:3d9c67d97d6f 70 * <code>pState</code> points to a state array of size <code>maxDelay + blockSize</code>, where
emh203 0:3d9c67d97d6f 71 * <code>maxDelay</code> is the largest offset value that is ever used in the <code>pTapDelay</code> array.
emh203 0:3d9c67d97d6f 72 * Some of the processing functions also require temporary working buffers.
emh203 0:3d9c67d97d6f 73 *
emh203 0:3d9c67d97d6f 74 * \par Instance Structure
emh203 0:3d9c67d97d6f 75 * The coefficients and state variables for a filter are stored together in an instance data structure.
emh203 0:3d9c67d97d6f 76 * A separate instance structure must be defined for each filter.
emh203 0:3d9c67d97d6f 77 * Coefficient and offset arrays may be shared among several instances while state variable arrays cannot be shared.
emh203 0:3d9c67d97d6f 78 * There are separate instance structure declarations for each of the 4 supported data types.
emh203 0:3d9c67d97d6f 79 *
emh203 0:3d9c67d97d6f 80 * \par Initialization Functions
emh203 0:3d9c67d97d6f 81 * There is also an associated initialization function for each data type.
emh203 0:3d9c67d97d6f 82 * The initialization function performs the following operations:
emh203 0:3d9c67d97d6f 83 * - Sets the values of the internal structure fields.
emh203 0:3d9c67d97d6f 84 * - Zeros out the values in the state buffer.
emh203 0:3d9c67d97d6f 85 * To do this manually without calling the init function, assign the follow subfields of the instance structure:
emh203 0:3d9c67d97d6f 86 * numTaps, pCoeffs, pTapDelay, maxDelay, stateIndex, pState. Also set all of the values in pState to zero.
emh203 0:3d9c67d97d6f 87 *
emh203 0:3d9c67d97d6f 88 * \par
emh203 0:3d9c67d97d6f 89 * Use of the initialization function is optional.
emh203 0:3d9c67d97d6f 90 * However, if the initialization function is used, then the instance structure cannot be placed into a const data section.
emh203 0:3d9c67d97d6f 91 * To place an instance structure into a const data section, the instance structure must be manually initialized.
emh203 0:3d9c67d97d6f 92 * Set the values in the state buffer to zeros before static initialization.
emh203 0:3d9c67d97d6f 93 * The code below statically initializes each of the 4 different data type filter instance structures
emh203 0:3d9c67d97d6f 94 * <pre>
emh203 0:3d9c67d97d6f 95 *arm_fir_sparse_instance_f32 S = {numTaps, 0, pState, pCoeffs, maxDelay, pTapDelay};
emh203 0:3d9c67d97d6f 96 *arm_fir_sparse_instance_q31 S = {numTaps, 0, pState, pCoeffs, maxDelay, pTapDelay};
emh203 0:3d9c67d97d6f 97 *arm_fir_sparse_instance_q15 S = {numTaps, 0, pState, pCoeffs, maxDelay, pTapDelay};
emh203 0:3d9c67d97d6f 98 *arm_fir_sparse_instance_q7 S = {numTaps, 0, pState, pCoeffs, maxDelay, pTapDelay};
emh203 0:3d9c67d97d6f 99 * </pre>
emh203 0:3d9c67d97d6f 100 * \par
emh203 0:3d9c67d97d6f 101 *
emh203 0:3d9c67d97d6f 102 * \par Fixed-Point Behavior
emh203 0:3d9c67d97d6f 103 * Care must be taken when using the fixed-point versions of the sparse FIR filter functions.
emh203 0:3d9c67d97d6f 104 * In particular, the overflow and saturation behavior of the accumulator used in each function must be considered.
emh203 0:3d9c67d97d6f 105 * Refer to the function specific documentation below for usage guidelines.
emh203 0:3d9c67d97d6f 106 */
emh203 0:3d9c67d97d6f 107
emh203 0:3d9c67d97d6f 108 /**
emh203 0:3d9c67d97d6f 109 * @addtogroup FIR_Sparse
emh203 0:3d9c67d97d6f 110 * @{
emh203 0:3d9c67d97d6f 111 */
emh203 0:3d9c67d97d6f 112
emh203 0:3d9c67d97d6f 113 /**
emh203 0:3d9c67d97d6f 114 * @brief Processing function for the floating-point sparse FIR filter.
emh203 0:3d9c67d97d6f 115 * @param[in] *S points to an instance of the floating-point sparse FIR structure.
emh203 0:3d9c67d97d6f 116 * @param[in] *pSrc points to the block of input data.
emh203 0:3d9c67d97d6f 117 * @param[out] *pDst points to the block of output data
emh203 0:3d9c67d97d6f 118 * @param[in] *pScratchIn points to a temporary buffer of size blockSize.
emh203 0:3d9c67d97d6f 119 * @param[in] blockSize number of input samples to process per call.
emh203 0:3d9c67d97d6f 120 * @return none.
emh203 0:3d9c67d97d6f 121 */
emh203 0:3d9c67d97d6f 122
emh203 0:3d9c67d97d6f 123 void arm_fir_sparse_f32(
emh203 0:3d9c67d97d6f 124 arm_fir_sparse_instance_f32 * S,
emh203 0:3d9c67d97d6f 125 float32_t * pSrc,
emh203 0:3d9c67d97d6f 126 float32_t * pDst,
emh203 0:3d9c67d97d6f 127 float32_t * pScratchIn,
emh203 0:3d9c67d97d6f 128 uint32_t blockSize)
emh203 0:3d9c67d97d6f 129 {
emh203 0:3d9c67d97d6f 130
emh203 0:3d9c67d97d6f 131 float32_t *pState = S->pState; /* State pointer */
emh203 0:3d9c67d97d6f 132 float32_t *pCoeffs = S->pCoeffs; /* Coefficient pointer */
emh203 0:3d9c67d97d6f 133 float32_t *px; /* Scratch buffer pointer */
emh203 0:3d9c67d97d6f 134 float32_t *py = pState; /* Temporary pointers for state buffer */
emh203 0:3d9c67d97d6f 135 float32_t *pb = pScratchIn; /* Temporary pointers for scratch buffer */
emh203 0:3d9c67d97d6f 136 float32_t *pOut; /* Destination pointer */
emh203 0:3d9c67d97d6f 137 int32_t *pTapDelay = S->pTapDelay; /* Pointer to the array containing offset of the non-zero tap values. */
emh203 0:3d9c67d97d6f 138 uint32_t delaySize = S->maxDelay + blockSize; /* state length */
emh203 0:3d9c67d97d6f 139 uint16_t numTaps = S->numTaps; /* Number of filter coefficients in the filter */
emh203 0:3d9c67d97d6f 140 int32_t readIndex; /* Read index of the state buffer */
emh203 0:3d9c67d97d6f 141 uint32_t tapCnt, blkCnt; /* loop counters */
emh203 0:3d9c67d97d6f 142 float32_t coeff = *pCoeffs++; /* Read the first coefficient value */
emh203 0:3d9c67d97d6f 143
emh203 0:3d9c67d97d6f 144
emh203 0:3d9c67d97d6f 145
emh203 0:3d9c67d97d6f 146 /* BlockSize of Input samples are copied into the state buffer */
emh203 0:3d9c67d97d6f 147 /* StateIndex points to the starting position to write in the state buffer */
emh203 0:3d9c67d97d6f 148 arm_circularWrite_f32((int32_t *) py, delaySize, &S->stateIndex, 1,
emh203 0:3d9c67d97d6f 149 (int32_t *) pSrc, 1, blockSize);
emh203 0:3d9c67d97d6f 150
emh203 0:3d9c67d97d6f 151
emh203 0:3d9c67d97d6f 152 /* Read Index, from where the state buffer should be read, is calculated. */
emh203 0:3d9c67d97d6f 153 readIndex = ((int32_t) S->stateIndex - (int32_t) blockSize) - *pTapDelay++;
emh203 0:3d9c67d97d6f 154
emh203 0:3d9c67d97d6f 155 /* Wraparound of readIndex */
emh203 0:3d9c67d97d6f 156 if(readIndex < 0)
emh203 0:3d9c67d97d6f 157 {
emh203 0:3d9c67d97d6f 158 readIndex += (int32_t) delaySize;
emh203 0:3d9c67d97d6f 159 }
emh203 0:3d9c67d97d6f 160
emh203 0:3d9c67d97d6f 161 /* Working pointer for state buffer is updated */
emh203 0:3d9c67d97d6f 162 py = pState;
emh203 0:3d9c67d97d6f 163
emh203 0:3d9c67d97d6f 164 /* blockSize samples are read from the state buffer */
emh203 0:3d9c67d97d6f 165 arm_circularRead_f32((int32_t *) py, delaySize, &readIndex, 1,
emh203 0:3d9c67d97d6f 166 (int32_t *) pb, (int32_t *) pb, blockSize, 1,
emh203 0:3d9c67d97d6f 167 blockSize);
emh203 0:3d9c67d97d6f 168
emh203 0:3d9c67d97d6f 169 /* Working pointer for the scratch buffer */
emh203 0:3d9c67d97d6f 170 px = pb;
emh203 0:3d9c67d97d6f 171
emh203 0:3d9c67d97d6f 172 /* Working pointer for destination buffer */
emh203 0:3d9c67d97d6f 173 pOut = pDst;
emh203 0:3d9c67d97d6f 174
emh203 0:3d9c67d97d6f 175
emh203 0:3d9c67d97d6f 176 #ifndef ARM_MATH_CM0_FAMILY
emh203 0:3d9c67d97d6f 177
emh203 0:3d9c67d97d6f 178 /* Run the below code for Cortex-M4 and Cortex-M3 */
emh203 0:3d9c67d97d6f 179
emh203 0:3d9c67d97d6f 180 /* Loop over the blockSize. Unroll by a factor of 4.
emh203 0:3d9c67d97d6f 181 * Compute 4 Multiplications at a time. */
emh203 0:3d9c67d97d6f 182 blkCnt = blockSize >> 2u;
emh203 0:3d9c67d97d6f 183
emh203 0:3d9c67d97d6f 184 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 185 {
emh203 0:3d9c67d97d6f 186 /* Perform Multiplications and store in destination buffer */
emh203 0:3d9c67d97d6f 187 *pOut++ = *px++ * coeff;
emh203 0:3d9c67d97d6f 188 *pOut++ = *px++ * coeff;
emh203 0:3d9c67d97d6f 189 *pOut++ = *px++ * coeff;
emh203 0:3d9c67d97d6f 190 *pOut++ = *px++ * coeff;
emh203 0:3d9c67d97d6f 191
emh203 0:3d9c67d97d6f 192 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 193 blkCnt--;
emh203 0:3d9c67d97d6f 194 }
emh203 0:3d9c67d97d6f 195
emh203 0:3d9c67d97d6f 196 /* If the blockSize is not a multiple of 4,
emh203 0:3d9c67d97d6f 197 * compute the remaining samples */
emh203 0:3d9c67d97d6f 198 blkCnt = blockSize % 0x4u;
emh203 0:3d9c67d97d6f 199
emh203 0:3d9c67d97d6f 200 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 201 {
emh203 0:3d9c67d97d6f 202 /* Perform Multiplications and store in destination buffer */
emh203 0:3d9c67d97d6f 203 *pOut++ = *px++ * coeff;
emh203 0:3d9c67d97d6f 204
emh203 0:3d9c67d97d6f 205 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 206 blkCnt--;
emh203 0:3d9c67d97d6f 207 }
emh203 0:3d9c67d97d6f 208
emh203 0:3d9c67d97d6f 209 /* Load the coefficient value and
emh203 0:3d9c67d97d6f 210 * increment the coefficient buffer for the next set of state values */
emh203 0:3d9c67d97d6f 211 coeff = *pCoeffs++;
emh203 0:3d9c67d97d6f 212
emh203 0:3d9c67d97d6f 213 /* Read Index, from where the state buffer should be read, is calculated. */
emh203 0:3d9c67d97d6f 214 readIndex = ((int32_t) S->stateIndex - (int32_t) blockSize) - *pTapDelay++;
emh203 0:3d9c67d97d6f 215
emh203 0:3d9c67d97d6f 216 /* Wraparound of readIndex */
emh203 0:3d9c67d97d6f 217 if(readIndex < 0)
emh203 0:3d9c67d97d6f 218 {
emh203 0:3d9c67d97d6f 219 readIndex += (int32_t) delaySize;
emh203 0:3d9c67d97d6f 220 }
emh203 0:3d9c67d97d6f 221
emh203 0:3d9c67d97d6f 222 /* Loop over the number of taps. */
emh203 0:3d9c67d97d6f 223 tapCnt = (uint32_t) numTaps - 1u;
emh203 0:3d9c67d97d6f 224
emh203 0:3d9c67d97d6f 225 while(tapCnt > 0u)
emh203 0:3d9c67d97d6f 226 {
emh203 0:3d9c67d97d6f 227
emh203 0:3d9c67d97d6f 228 /* Working pointer for state buffer is updated */
emh203 0:3d9c67d97d6f 229 py = pState;
emh203 0:3d9c67d97d6f 230
emh203 0:3d9c67d97d6f 231 /* blockSize samples are read from the state buffer */
emh203 0:3d9c67d97d6f 232 arm_circularRead_f32((int32_t *) py, delaySize, &readIndex, 1,
emh203 0:3d9c67d97d6f 233 (int32_t *) pb, (int32_t *) pb, blockSize, 1,
emh203 0:3d9c67d97d6f 234 blockSize);
emh203 0:3d9c67d97d6f 235
emh203 0:3d9c67d97d6f 236 /* Working pointer for the scratch buffer */
emh203 0:3d9c67d97d6f 237 px = pb;
emh203 0:3d9c67d97d6f 238
emh203 0:3d9c67d97d6f 239 /* Working pointer for destination buffer */
emh203 0:3d9c67d97d6f 240 pOut = pDst;
emh203 0:3d9c67d97d6f 241
emh203 0:3d9c67d97d6f 242 /* Loop over the blockSize. Unroll by a factor of 4.
emh203 0:3d9c67d97d6f 243 * Compute 4 MACS at a time. */
emh203 0:3d9c67d97d6f 244 blkCnt = blockSize >> 2u;
emh203 0:3d9c67d97d6f 245
emh203 0:3d9c67d97d6f 246 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 247 {
emh203 0:3d9c67d97d6f 248 /* Perform Multiply-Accumulate */
emh203 0:3d9c67d97d6f 249 *pOut++ += *px++ * coeff;
emh203 0:3d9c67d97d6f 250 *pOut++ += *px++ * coeff;
emh203 0:3d9c67d97d6f 251 *pOut++ += *px++ * coeff;
emh203 0:3d9c67d97d6f 252 *pOut++ += *px++ * coeff;
emh203 0:3d9c67d97d6f 253
emh203 0:3d9c67d97d6f 254 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 255 blkCnt--;
emh203 0:3d9c67d97d6f 256 }
emh203 0:3d9c67d97d6f 257
emh203 0:3d9c67d97d6f 258 /* If the blockSize is not a multiple of 4,
emh203 0:3d9c67d97d6f 259 * compute the remaining samples */
emh203 0:3d9c67d97d6f 260 blkCnt = blockSize % 0x4u;
emh203 0:3d9c67d97d6f 261
emh203 0:3d9c67d97d6f 262 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 263 {
emh203 0:3d9c67d97d6f 264 /* Perform Multiply-Accumulate */
emh203 0:3d9c67d97d6f 265 *pOut++ += *px++ * coeff;
emh203 0:3d9c67d97d6f 266
emh203 0:3d9c67d97d6f 267 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 268 blkCnt--;
emh203 0:3d9c67d97d6f 269 }
emh203 0:3d9c67d97d6f 270
emh203 0:3d9c67d97d6f 271 /* Load the coefficient value and
emh203 0:3d9c67d97d6f 272 * increment the coefficient buffer for the next set of state values */
emh203 0:3d9c67d97d6f 273 coeff = *pCoeffs++;
emh203 0:3d9c67d97d6f 274
emh203 0:3d9c67d97d6f 275 /* Read Index, from where the state buffer should be read, is calculated. */
emh203 0:3d9c67d97d6f 276 readIndex = ((int32_t) S->stateIndex -
emh203 0:3d9c67d97d6f 277 (int32_t) blockSize) - *pTapDelay++;
emh203 0:3d9c67d97d6f 278
emh203 0:3d9c67d97d6f 279 /* Wraparound of readIndex */
emh203 0:3d9c67d97d6f 280 if(readIndex < 0)
emh203 0:3d9c67d97d6f 281 {
emh203 0:3d9c67d97d6f 282 readIndex += (int32_t) delaySize;
emh203 0:3d9c67d97d6f 283 }
emh203 0:3d9c67d97d6f 284
emh203 0:3d9c67d97d6f 285 /* Decrement the tap loop counter */
emh203 0:3d9c67d97d6f 286 tapCnt--;
emh203 0:3d9c67d97d6f 287 }
emh203 0:3d9c67d97d6f 288
emh203 0:3d9c67d97d6f 289 #else
emh203 0:3d9c67d97d6f 290
emh203 0:3d9c67d97d6f 291 /* Run the below code for Cortex-M0 */
emh203 0:3d9c67d97d6f 292
emh203 0:3d9c67d97d6f 293 blkCnt = blockSize;
emh203 0:3d9c67d97d6f 294
emh203 0:3d9c67d97d6f 295 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 296 {
emh203 0:3d9c67d97d6f 297 /* Perform Multiplications and store in destination buffer */
emh203 0:3d9c67d97d6f 298 *pOut++ = *px++ * coeff;
emh203 0:3d9c67d97d6f 299
emh203 0:3d9c67d97d6f 300 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 301 blkCnt--;
emh203 0:3d9c67d97d6f 302 }
emh203 0:3d9c67d97d6f 303
emh203 0:3d9c67d97d6f 304 /* Load the coefficient value and
emh203 0:3d9c67d97d6f 305 * increment the coefficient buffer for the next set of state values */
emh203 0:3d9c67d97d6f 306 coeff = *pCoeffs++;
emh203 0:3d9c67d97d6f 307
emh203 0:3d9c67d97d6f 308 /* Read Index, from where the state buffer should be read, is calculated. */
emh203 0:3d9c67d97d6f 309 readIndex = ((int32_t) S->stateIndex - (int32_t) blockSize) - *pTapDelay++;
emh203 0:3d9c67d97d6f 310
emh203 0:3d9c67d97d6f 311 /* Wraparound of readIndex */
emh203 0:3d9c67d97d6f 312 if(readIndex < 0)
emh203 0:3d9c67d97d6f 313 {
emh203 0:3d9c67d97d6f 314 readIndex += (int32_t) delaySize;
emh203 0:3d9c67d97d6f 315 }
emh203 0:3d9c67d97d6f 316
emh203 0:3d9c67d97d6f 317 /* Loop over the number of taps. */
emh203 0:3d9c67d97d6f 318 tapCnt = (uint32_t) numTaps - 1u;
emh203 0:3d9c67d97d6f 319
emh203 0:3d9c67d97d6f 320 while(tapCnt > 0u)
emh203 0:3d9c67d97d6f 321 {
emh203 0:3d9c67d97d6f 322
emh203 0:3d9c67d97d6f 323 /* Working pointer for state buffer is updated */
emh203 0:3d9c67d97d6f 324 py = pState;
emh203 0:3d9c67d97d6f 325
emh203 0:3d9c67d97d6f 326 /* blockSize samples are read from the state buffer */
emh203 0:3d9c67d97d6f 327 arm_circularRead_f32((int32_t *) py, delaySize, &readIndex, 1,
emh203 0:3d9c67d97d6f 328 (int32_t *) pb, (int32_t *) pb, blockSize, 1,
emh203 0:3d9c67d97d6f 329 blockSize);
emh203 0:3d9c67d97d6f 330
emh203 0:3d9c67d97d6f 331 /* Working pointer for the scratch buffer */
emh203 0:3d9c67d97d6f 332 px = pb;
emh203 0:3d9c67d97d6f 333
emh203 0:3d9c67d97d6f 334 /* Working pointer for destination buffer */
emh203 0:3d9c67d97d6f 335 pOut = pDst;
emh203 0:3d9c67d97d6f 336
emh203 0:3d9c67d97d6f 337 blkCnt = blockSize;
emh203 0:3d9c67d97d6f 338
emh203 0:3d9c67d97d6f 339 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 340 {
emh203 0:3d9c67d97d6f 341 /* Perform Multiply-Accumulate */
emh203 0:3d9c67d97d6f 342 *pOut++ += *px++ * coeff;
emh203 0:3d9c67d97d6f 343
emh203 0:3d9c67d97d6f 344 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 345 blkCnt--;
emh203 0:3d9c67d97d6f 346 }
emh203 0:3d9c67d97d6f 347
emh203 0:3d9c67d97d6f 348 /* Load the coefficient value and
emh203 0:3d9c67d97d6f 349 * increment the coefficient buffer for the next set of state values */
emh203 0:3d9c67d97d6f 350 coeff = *pCoeffs++;
emh203 0:3d9c67d97d6f 351
emh203 0:3d9c67d97d6f 352 /* Read Index, from where the state buffer should be read, is calculated. */
emh203 0:3d9c67d97d6f 353 readIndex =
emh203 0:3d9c67d97d6f 354 ((int32_t) S->stateIndex - (int32_t) blockSize) - *pTapDelay++;
emh203 0:3d9c67d97d6f 355
emh203 0:3d9c67d97d6f 356 /* Wraparound of readIndex */
emh203 0:3d9c67d97d6f 357 if(readIndex < 0)
emh203 0:3d9c67d97d6f 358 {
emh203 0:3d9c67d97d6f 359 readIndex += (int32_t) delaySize;
emh203 0:3d9c67d97d6f 360 }
emh203 0:3d9c67d97d6f 361
emh203 0:3d9c67d97d6f 362 /* Decrement the tap loop counter */
emh203 0:3d9c67d97d6f 363 tapCnt--;
emh203 0:3d9c67d97d6f 364 }
emh203 0:3d9c67d97d6f 365
emh203 0:3d9c67d97d6f 366 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emh203 0:3d9c67d97d6f 367
emh203 0:3d9c67d97d6f 368 }
emh203 0:3d9c67d97d6f 369
emh203 0:3d9c67d97d6f 370 /**
emh203 0:3d9c67d97d6f 371 * @} end of FIR_Sparse group
emh203 0:3d9c67d97d6f 372 */