Eli Hughes / CMSIS_DSP_401

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

FilteringFunctions/arm_fir_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?

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_q7.c
emh203 0:3d9c67d97d6f 9 *
emh203 0:3d9c67d97d6f 10 * Description: Q7 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
emh203 0:3d9c67d97d6f 41 #include "arm_math.h"
emh203 0:3d9c67d97d6f 42
emh203 0:3d9c67d97d6f 43 /**
emh203 0:3d9c67d97d6f 44 * @ingroup groupFilters
emh203 0:3d9c67d97d6f 45 */
emh203 0:3d9c67d97d6f 46
emh203 0:3d9c67d97d6f 47 /**
emh203 0:3d9c67d97d6f 48 * @addtogroup FIR
emh203 0:3d9c67d97d6f 49 * @{
emh203 0:3d9c67d97d6f 50 */
emh203 0:3d9c67d97d6f 51
emh203 0:3d9c67d97d6f 52 /**
emh203 0:3d9c67d97d6f 53 * @param[in] *S points to an instance of the Q7 FIR filter structure.
emh203 0:3d9c67d97d6f 54 * @param[in] *pSrc points to the block of input data.
emh203 0:3d9c67d97d6f 55 * @param[out] *pDst points to the block of output data.
emh203 0:3d9c67d97d6f 56 * @param[in] blockSize number of samples to process per call.
emh203 0:3d9c67d97d6f 57 * @return none.
emh203 0:3d9c67d97d6f 58 *
emh203 0:3d9c67d97d6f 59 * <b>Scaling and Overflow Behavior:</b>
emh203 0:3d9c67d97d6f 60 * \par
emh203 0:3d9c67d97d6f 61 * The function is implemented using a 32-bit internal accumulator.
emh203 0:3d9c67d97d6f 62 * Both coefficients and state variables are represented in 1.7 format and multiplications yield a 2.14 result.
emh203 0:3d9c67d97d6f 63 * The 2.14 intermediate results are accumulated in a 32-bit accumulator in 18.14 format.
emh203 0:3d9c67d97d6f 64 * There is no risk of internal overflow with this approach and the full precision of intermediate multiplications is preserved.
emh203 0:3d9c67d97d6f 65 * The accumulator is converted to 18.7 format by discarding the low 7 bits.
emh203 0:3d9c67d97d6f 66 * Finally, the result is truncated to 1.7 format.
emh203 0:3d9c67d97d6f 67 */
emh203 0:3d9c67d97d6f 68
emh203 0:3d9c67d97d6f 69 void arm_fir_q7(
emh203 0:3d9c67d97d6f 70 const arm_fir_instance_q7 * S,
emh203 0:3d9c67d97d6f 71 q7_t * pSrc,
emh203 0:3d9c67d97d6f 72 q7_t * pDst,
emh203 0:3d9c67d97d6f 73 uint32_t blockSize)
emh203 0:3d9c67d97d6f 74 {
emh203 0:3d9c67d97d6f 75
emh203 0:3d9c67d97d6f 76 #ifndef ARM_MATH_CM0_FAMILY
emh203 0:3d9c67d97d6f 77
emh203 0:3d9c67d97d6f 78 /* Run the below code for Cortex-M4 and Cortex-M3 */
emh203 0:3d9c67d97d6f 79
emh203 0:3d9c67d97d6f 80 q7_t *pState = S->pState; /* State pointer */
emh203 0:3d9c67d97d6f 81 q7_t *pCoeffs = S->pCoeffs; /* Coefficient pointer */
emh203 0:3d9c67d97d6f 82 q7_t *pStateCurnt; /* Points to the current sample of the state */
emh203 0:3d9c67d97d6f 83 q7_t x0, x1, x2, x3; /* Temporary variables to hold state */
emh203 0:3d9c67d97d6f 84 q7_t c0; /* Temporary variable to hold coefficient value */
emh203 0:3d9c67d97d6f 85 q7_t *px; /* Temporary pointer for state */
emh203 0:3d9c67d97d6f 86 q7_t *pb; /* Temporary pointer for coefficient buffer */
emh203 0:3d9c67d97d6f 87 q31_t acc0, acc1, acc2, acc3; /* Accumulators */
emh203 0:3d9c67d97d6f 88 uint32_t numTaps = S->numTaps; /* Number of filter coefficients in the filter */
emh203 0:3d9c67d97d6f 89 uint32_t i, tapCnt, blkCnt; /* Loop counters */
emh203 0:3d9c67d97d6f 90
emh203 0:3d9c67d97d6f 91 /* S->pState points to state array which contains previous frame (numTaps - 1) samples */
emh203 0:3d9c67d97d6f 92 /* pStateCurnt points to the location where the new input data should be written */
emh203 0:3d9c67d97d6f 93 pStateCurnt = &(S->pState[(numTaps - 1u)]);
emh203 0:3d9c67d97d6f 94
emh203 0:3d9c67d97d6f 95 /* Apply loop unrolling and compute 4 output values simultaneously.
emh203 0:3d9c67d97d6f 96 * The variables acc0 ... acc3 hold output values that are being computed:
emh203 0:3d9c67d97d6f 97 *
emh203 0:3d9c67d97d6f 98 * acc0 = b[numTaps-1] * x[n-numTaps-1] + b[numTaps-2] * x[n-numTaps-2] + b[numTaps-3] * x[n-numTaps-3] +...+ b[0] * x[0]
emh203 0:3d9c67d97d6f 99 * acc1 = b[numTaps-1] * x[n-numTaps] + b[numTaps-2] * x[n-numTaps-1] + b[numTaps-3] * x[n-numTaps-2] +...+ b[0] * x[1]
emh203 0:3d9c67d97d6f 100 * acc2 = b[numTaps-1] * x[n-numTaps+1] + b[numTaps-2] * x[n-numTaps] + b[numTaps-3] * x[n-numTaps-1] +...+ b[0] * x[2]
emh203 0:3d9c67d97d6f 101 * acc3 = b[numTaps-1] * x[n-numTaps+2] + b[numTaps-2] * x[n-numTaps+1] + b[numTaps-3] * x[n-numTaps] +...+ b[0] * x[3]
emh203 0:3d9c67d97d6f 102 */
emh203 0:3d9c67d97d6f 103 blkCnt = blockSize >> 2;
emh203 0:3d9c67d97d6f 104
emh203 0:3d9c67d97d6f 105 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emh203 0:3d9c67d97d6f 106 ** a second loop below computes the remaining 1 to 3 samples. */
emh203 0:3d9c67d97d6f 107 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 108 {
emh203 0:3d9c67d97d6f 109 /* Copy four new input samples into the state buffer */
emh203 0:3d9c67d97d6f 110 *pStateCurnt++ = *pSrc++;
emh203 0:3d9c67d97d6f 111 *pStateCurnt++ = *pSrc++;
emh203 0:3d9c67d97d6f 112 *pStateCurnt++ = *pSrc++;
emh203 0:3d9c67d97d6f 113 *pStateCurnt++ = *pSrc++;
emh203 0:3d9c67d97d6f 114
emh203 0:3d9c67d97d6f 115 /* Set all accumulators to zero */
emh203 0:3d9c67d97d6f 116 acc0 = 0;
emh203 0:3d9c67d97d6f 117 acc1 = 0;
emh203 0:3d9c67d97d6f 118 acc2 = 0;
emh203 0:3d9c67d97d6f 119 acc3 = 0;
emh203 0:3d9c67d97d6f 120
emh203 0:3d9c67d97d6f 121 /* Initialize state pointer */
emh203 0:3d9c67d97d6f 122 px = pState;
emh203 0:3d9c67d97d6f 123
emh203 0:3d9c67d97d6f 124 /* Initialize coefficient pointer */
emh203 0:3d9c67d97d6f 125 pb = pCoeffs;
emh203 0:3d9c67d97d6f 126
emh203 0:3d9c67d97d6f 127 /* Read the first three samples from the state buffer:
emh203 0:3d9c67d97d6f 128 * x[n-numTaps], x[n-numTaps-1], x[n-numTaps-2] */
emh203 0:3d9c67d97d6f 129 x0 = *(px++);
emh203 0:3d9c67d97d6f 130 x1 = *(px++);
emh203 0:3d9c67d97d6f 131 x2 = *(px++);
emh203 0:3d9c67d97d6f 132
emh203 0:3d9c67d97d6f 133 /* Loop unrolling. Process 4 taps at a time. */
emh203 0:3d9c67d97d6f 134 tapCnt = numTaps >> 2;
emh203 0:3d9c67d97d6f 135 i = tapCnt;
emh203 0:3d9c67d97d6f 136
emh203 0:3d9c67d97d6f 137 while(i > 0u)
emh203 0:3d9c67d97d6f 138 {
emh203 0:3d9c67d97d6f 139 /* Read the b[numTaps] coefficient */
emh203 0:3d9c67d97d6f 140 c0 = *(pb++);
emh203 0:3d9c67d97d6f 141
emh203 0:3d9c67d97d6f 142 /* Read x[n-numTaps-3] sample */
emh203 0:3d9c67d97d6f 143 x3 = *(px++);
emh203 0:3d9c67d97d6f 144
emh203 0:3d9c67d97d6f 145 /* acc0 += b[numTaps] * x[n-numTaps] */
emh203 0:3d9c67d97d6f 146 acc0 += ((q15_t) x0 * c0);
emh203 0:3d9c67d97d6f 147
emh203 0:3d9c67d97d6f 148 /* acc1 += b[numTaps] * x[n-numTaps-1] */
emh203 0:3d9c67d97d6f 149 acc1 += ((q15_t) x1 * c0);
emh203 0:3d9c67d97d6f 150
emh203 0:3d9c67d97d6f 151 /* acc2 += b[numTaps] * x[n-numTaps-2] */
emh203 0:3d9c67d97d6f 152 acc2 += ((q15_t) x2 * c0);
emh203 0:3d9c67d97d6f 153
emh203 0:3d9c67d97d6f 154 /* acc3 += b[numTaps] * x[n-numTaps-3] */
emh203 0:3d9c67d97d6f 155 acc3 += ((q15_t) x3 * c0);
emh203 0:3d9c67d97d6f 156
emh203 0:3d9c67d97d6f 157 /* Read the b[numTaps-1] coefficient */
emh203 0:3d9c67d97d6f 158 c0 = *(pb++);
emh203 0:3d9c67d97d6f 159
emh203 0:3d9c67d97d6f 160 /* Read x[n-numTaps-4] sample */
emh203 0:3d9c67d97d6f 161 x0 = *(px++);
emh203 0:3d9c67d97d6f 162
emh203 0:3d9c67d97d6f 163 /* Perform the multiply-accumulates */
emh203 0:3d9c67d97d6f 164 acc0 += ((q15_t) x1 * c0);
emh203 0:3d9c67d97d6f 165 acc1 += ((q15_t) x2 * c0);
emh203 0:3d9c67d97d6f 166 acc2 += ((q15_t) x3 * c0);
emh203 0:3d9c67d97d6f 167 acc3 += ((q15_t) x0 * c0);
emh203 0:3d9c67d97d6f 168
emh203 0:3d9c67d97d6f 169 /* Read the b[numTaps-2] coefficient */
emh203 0:3d9c67d97d6f 170 c0 = *(pb++);
emh203 0:3d9c67d97d6f 171
emh203 0:3d9c67d97d6f 172 /* Read x[n-numTaps-5] sample */
emh203 0:3d9c67d97d6f 173 x1 = *(px++);
emh203 0:3d9c67d97d6f 174
emh203 0:3d9c67d97d6f 175 /* Perform the multiply-accumulates */
emh203 0:3d9c67d97d6f 176 acc0 += ((q15_t) x2 * c0);
emh203 0:3d9c67d97d6f 177 acc1 += ((q15_t) x3 * c0);
emh203 0:3d9c67d97d6f 178 acc2 += ((q15_t) x0 * c0);
emh203 0:3d9c67d97d6f 179 acc3 += ((q15_t) x1 * c0);
emh203 0:3d9c67d97d6f 180 /* Read the b[numTaps-3] coefficients */
emh203 0:3d9c67d97d6f 181 c0 = *(pb++);
emh203 0:3d9c67d97d6f 182
emh203 0:3d9c67d97d6f 183 /* Read x[n-numTaps-6] sample */
emh203 0:3d9c67d97d6f 184 x2 = *(px++);
emh203 0:3d9c67d97d6f 185
emh203 0:3d9c67d97d6f 186 /* Perform the multiply-accumulates */
emh203 0:3d9c67d97d6f 187 acc0 += ((q15_t) x3 * c0);
emh203 0:3d9c67d97d6f 188 acc1 += ((q15_t) x0 * c0);
emh203 0:3d9c67d97d6f 189 acc2 += ((q15_t) x1 * c0);
emh203 0:3d9c67d97d6f 190 acc3 += ((q15_t) x2 * c0);
emh203 0:3d9c67d97d6f 191 i--;
emh203 0:3d9c67d97d6f 192 }
emh203 0:3d9c67d97d6f 193
emh203 0:3d9c67d97d6f 194 /* If the filter length is not a multiple of 4, compute the remaining filter taps */
emh203 0:3d9c67d97d6f 195
emh203 0:3d9c67d97d6f 196 i = numTaps - (tapCnt * 4u);
emh203 0:3d9c67d97d6f 197 while(i > 0u)
emh203 0:3d9c67d97d6f 198 {
emh203 0:3d9c67d97d6f 199 /* Read coefficients */
emh203 0:3d9c67d97d6f 200 c0 = *(pb++);
emh203 0:3d9c67d97d6f 201
emh203 0:3d9c67d97d6f 202 /* Fetch 1 state variable */
emh203 0:3d9c67d97d6f 203 x3 = *(px++);
emh203 0:3d9c67d97d6f 204
emh203 0:3d9c67d97d6f 205 /* Perform the multiply-accumulates */
emh203 0:3d9c67d97d6f 206 acc0 += ((q15_t) x0 * c0);
emh203 0:3d9c67d97d6f 207 acc1 += ((q15_t) x1 * c0);
emh203 0:3d9c67d97d6f 208 acc2 += ((q15_t) x2 * c0);
emh203 0:3d9c67d97d6f 209 acc3 += ((q15_t) x3 * c0);
emh203 0:3d9c67d97d6f 210
emh203 0:3d9c67d97d6f 211 /* Reuse the present sample states for next sample */
emh203 0:3d9c67d97d6f 212 x0 = x1;
emh203 0:3d9c67d97d6f 213 x1 = x2;
emh203 0:3d9c67d97d6f 214 x2 = x3;
emh203 0:3d9c67d97d6f 215
emh203 0:3d9c67d97d6f 216 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 217 i--;
emh203 0:3d9c67d97d6f 218 }
emh203 0:3d9c67d97d6f 219
emh203 0:3d9c67d97d6f 220 /* Advance the state pointer by 4 to process the next group of 4 samples */
emh203 0:3d9c67d97d6f 221 pState = pState + 4;
emh203 0:3d9c67d97d6f 222
emh203 0:3d9c67d97d6f 223 /* The results in the 4 accumulators are in 2.62 format. Convert to 1.31
emh203 0:3d9c67d97d6f 224 ** Then store the 4 outputs in the destination buffer. */
emh203 0:3d9c67d97d6f 225 acc0 = __SSAT((acc0 >> 7u), 8);
emh203 0:3d9c67d97d6f 226 *pDst++ = acc0;
emh203 0:3d9c67d97d6f 227 acc1 = __SSAT((acc1 >> 7u), 8);
emh203 0:3d9c67d97d6f 228 *pDst++ = acc1;
emh203 0:3d9c67d97d6f 229 acc2 = __SSAT((acc2 >> 7u), 8);
emh203 0:3d9c67d97d6f 230 *pDst++ = acc2;
emh203 0:3d9c67d97d6f 231 acc3 = __SSAT((acc3 >> 7u), 8);
emh203 0:3d9c67d97d6f 232 *pDst++ = acc3;
emh203 0:3d9c67d97d6f 233
emh203 0:3d9c67d97d6f 234 /* Decrement the samples loop counter */
emh203 0:3d9c67d97d6f 235 blkCnt--;
emh203 0:3d9c67d97d6f 236 }
emh203 0:3d9c67d97d6f 237
emh203 0:3d9c67d97d6f 238
emh203 0:3d9c67d97d6f 239 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emh203 0:3d9c67d97d6f 240 ** No loop unrolling is used. */
emh203 0:3d9c67d97d6f 241 blkCnt = blockSize % 4u;
emh203 0:3d9c67d97d6f 242
emh203 0:3d9c67d97d6f 243 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 244 {
emh203 0:3d9c67d97d6f 245 /* Copy one sample at a time into state buffer */
emh203 0:3d9c67d97d6f 246 *pStateCurnt++ = *pSrc++;
emh203 0:3d9c67d97d6f 247
emh203 0:3d9c67d97d6f 248 /* Set the accumulator to zero */
emh203 0:3d9c67d97d6f 249 acc0 = 0;
emh203 0:3d9c67d97d6f 250
emh203 0:3d9c67d97d6f 251 /* Initialize state pointer */
emh203 0:3d9c67d97d6f 252 px = pState;
emh203 0:3d9c67d97d6f 253
emh203 0:3d9c67d97d6f 254 /* Initialize Coefficient pointer */
emh203 0:3d9c67d97d6f 255 pb = (pCoeffs);
emh203 0:3d9c67d97d6f 256
emh203 0:3d9c67d97d6f 257 i = numTaps;
emh203 0:3d9c67d97d6f 258
emh203 0:3d9c67d97d6f 259 /* Perform the multiply-accumulates */
emh203 0:3d9c67d97d6f 260 do
emh203 0:3d9c67d97d6f 261 {
emh203 0:3d9c67d97d6f 262 acc0 += (q15_t) * (px++) * (*(pb++));
emh203 0:3d9c67d97d6f 263 i--;
emh203 0:3d9c67d97d6f 264 } while(i > 0u);
emh203 0:3d9c67d97d6f 265
emh203 0:3d9c67d97d6f 266 /* The result is in 2.14 format. Convert to 1.7
emh203 0:3d9c67d97d6f 267 ** Then store the output in the destination buffer. */
emh203 0:3d9c67d97d6f 268 *pDst++ = __SSAT((acc0 >> 7u), 8);
emh203 0:3d9c67d97d6f 269
emh203 0:3d9c67d97d6f 270 /* Advance state pointer by 1 for the next sample */
emh203 0:3d9c67d97d6f 271 pState = pState + 1;
emh203 0:3d9c67d97d6f 272
emh203 0:3d9c67d97d6f 273 /* Decrement the samples loop counter */
emh203 0:3d9c67d97d6f 274 blkCnt--;
emh203 0:3d9c67d97d6f 275 }
emh203 0:3d9c67d97d6f 276
emh203 0:3d9c67d97d6f 277 /* Processing is complete.
emh203 0:3d9c67d97d6f 278 ** Now copy the last numTaps - 1 samples to the satrt of the state buffer.
emh203 0:3d9c67d97d6f 279 ** This prepares the state buffer for the next function call. */
emh203 0:3d9c67d97d6f 280
emh203 0:3d9c67d97d6f 281 /* Points to the start of the state buffer */
emh203 0:3d9c67d97d6f 282 pStateCurnt = S->pState;
emh203 0:3d9c67d97d6f 283
emh203 0:3d9c67d97d6f 284 tapCnt = (numTaps - 1u) >> 2u;
emh203 0:3d9c67d97d6f 285
emh203 0:3d9c67d97d6f 286 /* copy data */
emh203 0:3d9c67d97d6f 287 while(tapCnt > 0u)
emh203 0:3d9c67d97d6f 288 {
emh203 0:3d9c67d97d6f 289 *pStateCurnt++ = *pState++;
emh203 0:3d9c67d97d6f 290 *pStateCurnt++ = *pState++;
emh203 0:3d9c67d97d6f 291 *pStateCurnt++ = *pState++;
emh203 0:3d9c67d97d6f 292 *pStateCurnt++ = *pState++;
emh203 0:3d9c67d97d6f 293
emh203 0:3d9c67d97d6f 294 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 295 tapCnt--;
emh203 0:3d9c67d97d6f 296 }
emh203 0:3d9c67d97d6f 297
emh203 0:3d9c67d97d6f 298 /* Calculate remaining number of copies */
emh203 0:3d9c67d97d6f 299 tapCnt = (numTaps - 1u) % 0x4u;
emh203 0:3d9c67d97d6f 300
emh203 0:3d9c67d97d6f 301 /* Copy the remaining q31_t data */
emh203 0:3d9c67d97d6f 302 while(tapCnt > 0u)
emh203 0:3d9c67d97d6f 303 {
emh203 0:3d9c67d97d6f 304 *pStateCurnt++ = *pState++;
emh203 0:3d9c67d97d6f 305
emh203 0:3d9c67d97d6f 306 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 307 tapCnt--;
emh203 0:3d9c67d97d6f 308 }
emh203 0:3d9c67d97d6f 309
emh203 0:3d9c67d97d6f 310 #else
emh203 0:3d9c67d97d6f 311
emh203 0:3d9c67d97d6f 312 /* Run the below code for Cortex-M0 */
emh203 0:3d9c67d97d6f 313
emh203 0:3d9c67d97d6f 314 uint32_t numTaps = S->numTaps; /* Number of taps in the filter */
emh203 0:3d9c67d97d6f 315 uint32_t i, blkCnt; /* Loop counters */
emh203 0:3d9c67d97d6f 316 q7_t *pState = S->pState; /* State pointer */
emh203 0:3d9c67d97d6f 317 q7_t *pCoeffs = S->pCoeffs; /* Coefficient pointer */
emh203 0:3d9c67d97d6f 318 q7_t *px, *pb; /* Temporary pointers to state and coeff */
emh203 0:3d9c67d97d6f 319 q31_t acc = 0; /* Accumlator */
emh203 0:3d9c67d97d6f 320 q7_t *pStateCurnt; /* Points to the current sample of the state */
emh203 0:3d9c67d97d6f 321
emh203 0:3d9c67d97d6f 322
emh203 0:3d9c67d97d6f 323 /* S->pState points to state array which contains previous frame (numTaps - 1) samples */
emh203 0:3d9c67d97d6f 324 /* pStateCurnt points to the location where the new input data should be written */
emh203 0:3d9c67d97d6f 325 pStateCurnt = S->pState + (numTaps - 1u);
emh203 0:3d9c67d97d6f 326
emh203 0:3d9c67d97d6f 327 /* Initialize blkCnt with blockSize */
emh203 0:3d9c67d97d6f 328 blkCnt = blockSize;
emh203 0:3d9c67d97d6f 329
emh203 0:3d9c67d97d6f 330 /* Perform filtering upto BlockSize - BlockSize%4 */
emh203 0:3d9c67d97d6f 331 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 332 {
emh203 0:3d9c67d97d6f 333 /* Copy one sample at a time into state buffer */
emh203 0:3d9c67d97d6f 334 *pStateCurnt++ = *pSrc++;
emh203 0:3d9c67d97d6f 335
emh203 0:3d9c67d97d6f 336 /* Set accumulator to zero */
emh203 0:3d9c67d97d6f 337 acc = 0;
emh203 0:3d9c67d97d6f 338
emh203 0:3d9c67d97d6f 339 /* Initialize state pointer of type q7 */
emh203 0:3d9c67d97d6f 340 px = pState;
emh203 0:3d9c67d97d6f 341
emh203 0:3d9c67d97d6f 342 /* Initialize coeff pointer of type q7 */
emh203 0:3d9c67d97d6f 343 pb = pCoeffs;
emh203 0:3d9c67d97d6f 344
emh203 0:3d9c67d97d6f 345
emh203 0:3d9c67d97d6f 346 i = numTaps;
emh203 0:3d9c67d97d6f 347
emh203 0:3d9c67d97d6f 348 while(i > 0u)
emh203 0:3d9c67d97d6f 349 {
emh203 0:3d9c67d97d6f 350 /* acc = b[numTaps-1] * x[n-numTaps-1] + b[numTaps-2] * x[n-numTaps-2] + b[numTaps-3] * x[n-numTaps-3] +...+ b[0] * x[0] */
emh203 0:3d9c67d97d6f 351 acc += (q15_t) * px++ * *pb++;
emh203 0:3d9c67d97d6f 352 i--;
emh203 0:3d9c67d97d6f 353 }
emh203 0:3d9c67d97d6f 354
emh203 0:3d9c67d97d6f 355 /* Store the 1.7 format filter output in destination buffer */
emh203 0:3d9c67d97d6f 356 *pDst++ = (q7_t) __SSAT((acc >> 7), 8);
emh203 0:3d9c67d97d6f 357
emh203 0:3d9c67d97d6f 358 /* Advance the state pointer by 1 to process the next sample */
emh203 0:3d9c67d97d6f 359 pState = pState + 1;
emh203 0:3d9c67d97d6f 360
emh203 0:3d9c67d97d6f 361 /* Decrement the loop counter */
emh203 0:3d9c67d97d6f 362 blkCnt--;
emh203 0:3d9c67d97d6f 363 }
emh203 0:3d9c67d97d6f 364
emh203 0:3d9c67d97d6f 365 /* Processing is complete.
emh203 0:3d9c67d97d6f 366 ** Now copy the last numTaps - 1 samples to the satrt of the state buffer.
emh203 0:3d9c67d97d6f 367 ** This prepares the state buffer for the next function call. */
emh203 0:3d9c67d97d6f 368
emh203 0:3d9c67d97d6f 369
emh203 0:3d9c67d97d6f 370 /* Points to the start of the state buffer */
emh203 0:3d9c67d97d6f 371 pStateCurnt = S->pState;
emh203 0:3d9c67d97d6f 372
emh203 0:3d9c67d97d6f 373
emh203 0:3d9c67d97d6f 374 /* Copy numTaps number of values */
emh203 0:3d9c67d97d6f 375 i = (numTaps - 1u);
emh203 0:3d9c67d97d6f 376
emh203 0:3d9c67d97d6f 377 /* Copy q7_t data */
emh203 0:3d9c67d97d6f 378 while(i > 0u)
emh203 0:3d9c67d97d6f 379 {
emh203 0:3d9c67d97d6f 380 *pStateCurnt++ = *pState++;
emh203 0:3d9c67d97d6f 381 i--;
emh203 0:3d9c67d97d6f 382 }
emh203 0:3d9c67d97d6f 383
emh203 0:3d9c67d97d6f 384 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emh203 0:3d9c67d97d6f 385
emh203 0:3d9c67d97d6f 386 }
emh203 0:3d9c67d97d6f 387
emh203 0:3d9c67d97d6f 388 /**
emh203 0:3d9c67d97d6f 389 * @} end of FIR group
emh203 0:3d9c67d97d6f 390 */