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_lattice_q15.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_lattice_q15.c
emh203 0:3d9c67d97d6f 9 *
emh203 0:3d9c67d97d6f 10 * Description: Q15 FIR lattice 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_Lattice
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 Processing function for the Q15 FIR lattice filter.
emh203 0:3d9c67d97d6f 55 * @param[in] *S points to an instance of the Q15 FIR lattice structure.
emh203 0:3d9c67d97d6f 56 * @param[in] *pSrc points to the block of input data.
emh203 0:3d9c67d97d6f 57 * @param[out] *pDst points to the block of output data
emh203 0:3d9c67d97d6f 58 * @param[in] blockSize number of samples to process.
emh203 0:3d9c67d97d6f 59 * @return none.
emh203 0:3d9c67d97d6f 60 */
emh203 0:3d9c67d97d6f 61
emh203 0:3d9c67d97d6f 62 void arm_fir_lattice_q15(
emh203 0:3d9c67d97d6f 63 const arm_fir_lattice_instance_q15 * S,
emh203 0:3d9c67d97d6f 64 q15_t * pSrc,
emh203 0:3d9c67d97d6f 65 q15_t * pDst,
emh203 0:3d9c67d97d6f 66 uint32_t blockSize)
emh203 0:3d9c67d97d6f 67 {
emh203 0:3d9c67d97d6f 68 q15_t *pState; /* State pointer */
emh203 0:3d9c67d97d6f 69 q15_t *pCoeffs = S->pCoeffs; /* Coefficient pointer */
emh203 0:3d9c67d97d6f 70 q15_t *px; /* temporary state pointer */
emh203 0:3d9c67d97d6f 71 q15_t *pk; /* temporary coefficient pointer */
emh203 0:3d9c67d97d6f 72
emh203 0:3d9c67d97d6f 73
emh203 0:3d9c67d97d6f 74 #ifndef ARM_MATH_CM0_FAMILY
emh203 0:3d9c67d97d6f 75
emh203 0:3d9c67d97d6f 76 /* Run the below code for Cortex-M4 and Cortex-M3 */
emh203 0:3d9c67d97d6f 77
emh203 0:3d9c67d97d6f 78 q31_t fcurnt1, fnext1, gcurnt1 = 0, gnext1; /* temporary variables for first sample in loop unrolling */
emh203 0:3d9c67d97d6f 79 q31_t fcurnt2, fnext2, gnext2; /* temporary variables for second sample in loop unrolling */
emh203 0:3d9c67d97d6f 80 q31_t fcurnt3, fnext3, gnext3; /* temporary variables for third sample in loop unrolling */
emh203 0:3d9c67d97d6f 81 q31_t fcurnt4, fnext4, gnext4; /* temporary variables for fourth sample in loop unrolling */
emh203 0:3d9c67d97d6f 82 uint32_t numStages = S->numStages; /* Number of stages in the filter */
emh203 0:3d9c67d97d6f 83 uint32_t blkCnt, stageCnt; /* temporary variables for counts */
emh203 0:3d9c67d97d6f 84
emh203 0:3d9c67d97d6f 85 pState = &S->pState[0];
emh203 0:3d9c67d97d6f 86
emh203 0:3d9c67d97d6f 87 blkCnt = blockSize >> 2u;
emh203 0:3d9c67d97d6f 88
emh203 0:3d9c67d97d6f 89 /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
emh203 0:3d9c67d97d6f 90 ** a second loop below computes the remaining 1 to 3 samples. */
emh203 0:3d9c67d97d6f 91 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 92 {
emh203 0:3d9c67d97d6f 93
emh203 0:3d9c67d97d6f 94 /* Read two samples from input buffer */
emh203 0:3d9c67d97d6f 95 /* f0(n) = x(n) */
emh203 0:3d9c67d97d6f 96 fcurnt1 = *pSrc++;
emh203 0:3d9c67d97d6f 97 fcurnt2 = *pSrc++;
emh203 0:3d9c67d97d6f 98
emh203 0:3d9c67d97d6f 99 /* Initialize coeff pointer */
emh203 0:3d9c67d97d6f 100 pk = (pCoeffs);
emh203 0:3d9c67d97d6f 101
emh203 0:3d9c67d97d6f 102 /* Initialize state pointer */
emh203 0:3d9c67d97d6f 103 px = pState;
emh203 0:3d9c67d97d6f 104
emh203 0:3d9c67d97d6f 105 /* Read g0(n-1) from state */
emh203 0:3d9c67d97d6f 106 gcurnt1 = *px;
emh203 0:3d9c67d97d6f 107
emh203 0:3d9c67d97d6f 108 /* Process first sample for first tap */
emh203 0:3d9c67d97d6f 109 /* f1(n) = f0(n) + K1 * g0(n-1) */
emh203 0:3d9c67d97d6f 110 fnext1 = (q31_t) ((gcurnt1 * (*pk)) >> 15u) + fcurnt1;
emh203 0:3d9c67d97d6f 111 fnext1 = __SSAT(fnext1, 16);
emh203 0:3d9c67d97d6f 112
emh203 0:3d9c67d97d6f 113 /* g1(n) = f0(n) * K1 + g0(n-1) */
emh203 0:3d9c67d97d6f 114 gnext1 = (q31_t) ((fcurnt1 * (*pk)) >> 15u) + gcurnt1;
emh203 0:3d9c67d97d6f 115 gnext1 = __SSAT(gnext1, 16);
emh203 0:3d9c67d97d6f 116
emh203 0:3d9c67d97d6f 117 /* Process second sample for first tap */
emh203 0:3d9c67d97d6f 118 /* for sample 2 processing */
emh203 0:3d9c67d97d6f 119 fnext2 = (q31_t) ((fcurnt1 * (*pk)) >> 15u) + fcurnt2;
emh203 0:3d9c67d97d6f 120 fnext2 = __SSAT(fnext2, 16);
emh203 0:3d9c67d97d6f 121
emh203 0:3d9c67d97d6f 122 gnext2 = (q31_t) ((fcurnt2 * (*pk)) >> 15u) + fcurnt1;
emh203 0:3d9c67d97d6f 123 gnext2 = __SSAT(gnext2, 16);
emh203 0:3d9c67d97d6f 124
emh203 0:3d9c67d97d6f 125
emh203 0:3d9c67d97d6f 126 /* Read next two samples from input buffer */
emh203 0:3d9c67d97d6f 127 /* f0(n+2) = x(n+2) */
emh203 0:3d9c67d97d6f 128 fcurnt3 = *pSrc++;
emh203 0:3d9c67d97d6f 129 fcurnt4 = *pSrc++;
emh203 0:3d9c67d97d6f 130
emh203 0:3d9c67d97d6f 131 /* Copy only last input samples into the state buffer
emh203 0:3d9c67d97d6f 132 which is used for next four samples processing */
emh203 0:3d9c67d97d6f 133 *px++ = (q15_t) fcurnt4;
emh203 0:3d9c67d97d6f 134
emh203 0:3d9c67d97d6f 135 /* Process third sample for first tap */
emh203 0:3d9c67d97d6f 136 fnext3 = (q31_t) ((fcurnt2 * (*pk)) >> 15u) + fcurnt3;
emh203 0:3d9c67d97d6f 137 fnext3 = __SSAT(fnext3, 16);
emh203 0:3d9c67d97d6f 138 gnext3 = (q31_t) ((fcurnt3 * (*pk)) >> 15u) + fcurnt2;
emh203 0:3d9c67d97d6f 139 gnext3 = __SSAT(gnext3, 16);
emh203 0:3d9c67d97d6f 140
emh203 0:3d9c67d97d6f 141 /* Process fourth sample for first tap */
emh203 0:3d9c67d97d6f 142 fnext4 = (q31_t) ((fcurnt3 * (*pk)) >> 15u) + fcurnt4;
emh203 0:3d9c67d97d6f 143 fnext4 = __SSAT(fnext4, 16);
emh203 0:3d9c67d97d6f 144 gnext4 = (q31_t) ((fcurnt4 * (*pk++)) >> 15u) + fcurnt3;
emh203 0:3d9c67d97d6f 145 gnext4 = __SSAT(gnext4, 16);
emh203 0:3d9c67d97d6f 146
emh203 0:3d9c67d97d6f 147 /* Update of f values for next coefficient set processing */
emh203 0:3d9c67d97d6f 148 fcurnt1 = fnext1;
emh203 0:3d9c67d97d6f 149 fcurnt2 = fnext2;
emh203 0:3d9c67d97d6f 150 fcurnt3 = fnext3;
emh203 0:3d9c67d97d6f 151 fcurnt4 = fnext4;
emh203 0:3d9c67d97d6f 152
emh203 0:3d9c67d97d6f 153
emh203 0:3d9c67d97d6f 154 /* Loop unrolling. Process 4 taps at a time . */
emh203 0:3d9c67d97d6f 155 stageCnt = (numStages - 1u) >> 2;
emh203 0:3d9c67d97d6f 156
emh203 0:3d9c67d97d6f 157
emh203 0:3d9c67d97d6f 158 /* Loop over the number of taps. Unroll by a factor of 4.
emh203 0:3d9c67d97d6f 159 ** Repeat until we've computed numStages-3 coefficients. */
emh203 0:3d9c67d97d6f 160
emh203 0:3d9c67d97d6f 161 /* Process 2nd, 3rd, 4th and 5th taps ... here */
emh203 0:3d9c67d97d6f 162 while(stageCnt > 0u)
emh203 0:3d9c67d97d6f 163 {
emh203 0:3d9c67d97d6f 164 /* Read g1(n-1), g3(n-1) .... from state */
emh203 0:3d9c67d97d6f 165 gcurnt1 = *px;
emh203 0:3d9c67d97d6f 166
emh203 0:3d9c67d97d6f 167 /* save g1(n) in state buffer */
emh203 0:3d9c67d97d6f 168 *px++ = (q15_t) gnext4;
emh203 0:3d9c67d97d6f 169
emh203 0:3d9c67d97d6f 170 /* Process first sample for 2nd, 6th .. tap */
emh203 0:3d9c67d97d6f 171 /* Sample processing for K2, K6.... */
emh203 0:3d9c67d97d6f 172 /* f1(n) = f0(n) + K1 * g0(n-1) */
emh203 0:3d9c67d97d6f 173 fnext1 = (q31_t) ((gcurnt1 * (*pk)) >> 15u) + fcurnt1;
emh203 0:3d9c67d97d6f 174 fnext1 = __SSAT(fnext1, 16);
emh203 0:3d9c67d97d6f 175
emh203 0:3d9c67d97d6f 176
emh203 0:3d9c67d97d6f 177 /* Process second sample for 2nd, 6th .. tap */
emh203 0:3d9c67d97d6f 178 /* for sample 2 processing */
emh203 0:3d9c67d97d6f 179 fnext2 = (q31_t) ((gnext1 * (*pk)) >> 15u) + fcurnt2;
emh203 0:3d9c67d97d6f 180 fnext2 = __SSAT(fnext2, 16);
emh203 0:3d9c67d97d6f 181 /* Process third sample for 2nd, 6th .. tap */
emh203 0:3d9c67d97d6f 182 fnext3 = (q31_t) ((gnext2 * (*pk)) >> 15u) + fcurnt3;
emh203 0:3d9c67d97d6f 183 fnext3 = __SSAT(fnext3, 16);
emh203 0:3d9c67d97d6f 184 /* Process fourth sample for 2nd, 6th .. tap */
emh203 0:3d9c67d97d6f 185 /* fnext4 = fcurnt4 + (*pk) * gnext3; */
emh203 0:3d9c67d97d6f 186 fnext4 = (q31_t) ((gnext3 * (*pk)) >> 15u) + fcurnt4;
emh203 0:3d9c67d97d6f 187 fnext4 = __SSAT(fnext4, 16);
emh203 0:3d9c67d97d6f 188
emh203 0:3d9c67d97d6f 189 /* g1(n) = f0(n) * K1 + g0(n-1) */
emh203 0:3d9c67d97d6f 190 /* Calculation of state values for next stage */
emh203 0:3d9c67d97d6f 191 gnext4 = (q31_t) ((fcurnt4 * (*pk)) >> 15u) + gnext3;
emh203 0:3d9c67d97d6f 192 gnext4 = __SSAT(gnext4, 16);
emh203 0:3d9c67d97d6f 193 gnext3 = (q31_t) ((fcurnt3 * (*pk)) >> 15u) + gnext2;
emh203 0:3d9c67d97d6f 194 gnext3 = __SSAT(gnext3, 16);
emh203 0:3d9c67d97d6f 195
emh203 0:3d9c67d97d6f 196 gnext2 = (q31_t) ((fcurnt2 * (*pk)) >> 15u) + gnext1;
emh203 0:3d9c67d97d6f 197 gnext2 = __SSAT(gnext2, 16);
emh203 0:3d9c67d97d6f 198
emh203 0:3d9c67d97d6f 199 gnext1 = (q31_t) ((fcurnt1 * (*pk++)) >> 15u) + gcurnt1;
emh203 0:3d9c67d97d6f 200 gnext1 = __SSAT(gnext1, 16);
emh203 0:3d9c67d97d6f 201
emh203 0:3d9c67d97d6f 202
emh203 0:3d9c67d97d6f 203 /* Read g2(n-1), g4(n-1) .... from state */
emh203 0:3d9c67d97d6f 204 gcurnt1 = *px;
emh203 0:3d9c67d97d6f 205
emh203 0:3d9c67d97d6f 206 /* save g1(n) in state buffer */
emh203 0:3d9c67d97d6f 207 *px++ = (q15_t) gnext4;
emh203 0:3d9c67d97d6f 208
emh203 0:3d9c67d97d6f 209 /* Sample processing for K3, K7.... */
emh203 0:3d9c67d97d6f 210 /* Process first sample for 3rd, 7th .. tap */
emh203 0:3d9c67d97d6f 211 /* f3(n) = f2(n) + K3 * g2(n-1) */
emh203 0:3d9c67d97d6f 212 fcurnt1 = (q31_t) ((gcurnt1 * (*pk)) >> 15u) + fnext1;
emh203 0:3d9c67d97d6f 213 fcurnt1 = __SSAT(fcurnt1, 16);
emh203 0:3d9c67d97d6f 214
emh203 0:3d9c67d97d6f 215 /* Process second sample for 3rd, 7th .. tap */
emh203 0:3d9c67d97d6f 216 fcurnt2 = (q31_t) ((gnext1 * (*pk)) >> 15u) + fnext2;
emh203 0:3d9c67d97d6f 217 fcurnt2 = __SSAT(fcurnt2, 16);
emh203 0:3d9c67d97d6f 218
emh203 0:3d9c67d97d6f 219 /* Process third sample for 3rd, 7th .. tap */
emh203 0:3d9c67d97d6f 220 fcurnt3 = (q31_t) ((gnext2 * (*pk)) >> 15u) + fnext3;
emh203 0:3d9c67d97d6f 221 fcurnt3 = __SSAT(fcurnt3, 16);
emh203 0:3d9c67d97d6f 222
emh203 0:3d9c67d97d6f 223 /* Process fourth sample for 3rd, 7th .. tap */
emh203 0:3d9c67d97d6f 224 fcurnt4 = (q31_t) ((gnext3 * (*pk)) >> 15u) + fnext4;
emh203 0:3d9c67d97d6f 225 fcurnt4 = __SSAT(fcurnt4, 16);
emh203 0:3d9c67d97d6f 226
emh203 0:3d9c67d97d6f 227 /* Calculation of state values for next stage */
emh203 0:3d9c67d97d6f 228 /* g3(n) = f2(n) * K3 + g2(n-1) */
emh203 0:3d9c67d97d6f 229 gnext4 = (q31_t) ((fnext4 * (*pk)) >> 15u) + gnext3;
emh203 0:3d9c67d97d6f 230 gnext4 = __SSAT(gnext4, 16);
emh203 0:3d9c67d97d6f 231
emh203 0:3d9c67d97d6f 232 gnext3 = (q31_t) ((fnext3 * (*pk)) >> 15u) + gnext2;
emh203 0:3d9c67d97d6f 233 gnext3 = __SSAT(gnext3, 16);
emh203 0:3d9c67d97d6f 234
emh203 0:3d9c67d97d6f 235 gnext2 = (q31_t) ((fnext2 * (*pk)) >> 15u) + gnext1;
emh203 0:3d9c67d97d6f 236 gnext2 = __SSAT(gnext2, 16);
emh203 0:3d9c67d97d6f 237
emh203 0:3d9c67d97d6f 238 gnext1 = (q31_t) ((fnext1 * (*pk++)) >> 15u) + gcurnt1;
emh203 0:3d9c67d97d6f 239 gnext1 = __SSAT(gnext1, 16);
emh203 0:3d9c67d97d6f 240
emh203 0:3d9c67d97d6f 241 /* Read g1(n-1), g3(n-1) .... from state */
emh203 0:3d9c67d97d6f 242 gcurnt1 = *px;
emh203 0:3d9c67d97d6f 243
emh203 0:3d9c67d97d6f 244 /* save g1(n) in state buffer */
emh203 0:3d9c67d97d6f 245 *px++ = (q15_t) gnext4;
emh203 0:3d9c67d97d6f 246
emh203 0:3d9c67d97d6f 247 /* Sample processing for K4, K8.... */
emh203 0:3d9c67d97d6f 248 /* Process first sample for 4th, 8th .. tap */
emh203 0:3d9c67d97d6f 249 /* f4(n) = f3(n) + K4 * g3(n-1) */
emh203 0:3d9c67d97d6f 250 fnext1 = (q31_t) ((gcurnt1 * (*pk)) >> 15u) + fcurnt1;
emh203 0:3d9c67d97d6f 251 fnext1 = __SSAT(fnext1, 16);
emh203 0:3d9c67d97d6f 252
emh203 0:3d9c67d97d6f 253 /* Process second sample for 4th, 8th .. tap */
emh203 0:3d9c67d97d6f 254 /* for sample 2 processing */
emh203 0:3d9c67d97d6f 255 fnext2 = (q31_t) ((gnext1 * (*pk)) >> 15u) + fcurnt2;
emh203 0:3d9c67d97d6f 256 fnext2 = __SSAT(fnext2, 16);
emh203 0:3d9c67d97d6f 257
emh203 0:3d9c67d97d6f 258 /* Process third sample for 4th, 8th .. tap */
emh203 0:3d9c67d97d6f 259 fnext3 = (q31_t) ((gnext2 * (*pk)) >> 15u) + fcurnt3;
emh203 0:3d9c67d97d6f 260 fnext3 = __SSAT(fnext3, 16);
emh203 0:3d9c67d97d6f 261
emh203 0:3d9c67d97d6f 262 /* Process fourth sample for 4th, 8th .. tap */
emh203 0:3d9c67d97d6f 263 fnext4 = (q31_t) ((gnext3 * (*pk)) >> 15u) + fcurnt4;
emh203 0:3d9c67d97d6f 264 fnext4 = __SSAT(fnext4, 16);
emh203 0:3d9c67d97d6f 265
emh203 0:3d9c67d97d6f 266 /* g4(n) = f3(n) * K4 + g3(n-1) */
emh203 0:3d9c67d97d6f 267 /* Calculation of state values for next stage */
emh203 0:3d9c67d97d6f 268 gnext4 = (q31_t) ((fcurnt4 * (*pk)) >> 15u) + gnext3;
emh203 0:3d9c67d97d6f 269 gnext4 = __SSAT(gnext4, 16);
emh203 0:3d9c67d97d6f 270
emh203 0:3d9c67d97d6f 271 gnext3 = (q31_t) ((fcurnt3 * (*pk)) >> 15u) + gnext2;
emh203 0:3d9c67d97d6f 272 gnext3 = __SSAT(gnext3, 16);
emh203 0:3d9c67d97d6f 273
emh203 0:3d9c67d97d6f 274 gnext2 = (q31_t) ((fcurnt2 * (*pk)) >> 15u) + gnext1;
emh203 0:3d9c67d97d6f 275 gnext2 = __SSAT(gnext2, 16);
emh203 0:3d9c67d97d6f 276 gnext1 = (q31_t) ((fcurnt1 * (*pk++)) >> 15u) + gcurnt1;
emh203 0:3d9c67d97d6f 277 gnext1 = __SSAT(gnext1, 16);
emh203 0:3d9c67d97d6f 278
emh203 0:3d9c67d97d6f 279
emh203 0:3d9c67d97d6f 280 /* Read g2(n-1), g4(n-1) .... from state */
emh203 0:3d9c67d97d6f 281 gcurnt1 = *px;
emh203 0:3d9c67d97d6f 282
emh203 0:3d9c67d97d6f 283 /* save g4(n) in state buffer */
emh203 0:3d9c67d97d6f 284 *px++ = (q15_t) gnext4;
emh203 0:3d9c67d97d6f 285
emh203 0:3d9c67d97d6f 286 /* Sample processing for K5, K9.... */
emh203 0:3d9c67d97d6f 287 /* Process first sample for 5th, 9th .. tap */
emh203 0:3d9c67d97d6f 288 /* f5(n) = f4(n) + K5 * g4(n-1) */
emh203 0:3d9c67d97d6f 289 fcurnt1 = (q31_t) ((gcurnt1 * (*pk)) >> 15u) + fnext1;
emh203 0:3d9c67d97d6f 290 fcurnt1 = __SSAT(fcurnt1, 16);
emh203 0:3d9c67d97d6f 291
emh203 0:3d9c67d97d6f 292 /* Process second sample for 5th, 9th .. tap */
emh203 0:3d9c67d97d6f 293 fcurnt2 = (q31_t) ((gnext1 * (*pk)) >> 15u) + fnext2;
emh203 0:3d9c67d97d6f 294 fcurnt2 = __SSAT(fcurnt2, 16);
emh203 0:3d9c67d97d6f 295
emh203 0:3d9c67d97d6f 296 /* Process third sample for 5th, 9th .. tap */
emh203 0:3d9c67d97d6f 297 fcurnt3 = (q31_t) ((gnext2 * (*pk)) >> 15u) + fnext3;
emh203 0:3d9c67d97d6f 298 fcurnt3 = __SSAT(fcurnt3, 16);
emh203 0:3d9c67d97d6f 299
emh203 0:3d9c67d97d6f 300 /* Process fourth sample for 5th, 9th .. tap */
emh203 0:3d9c67d97d6f 301 fcurnt4 = (q31_t) ((gnext3 * (*pk)) >> 15u) + fnext4;
emh203 0:3d9c67d97d6f 302 fcurnt4 = __SSAT(fcurnt4, 16);
emh203 0:3d9c67d97d6f 303
emh203 0:3d9c67d97d6f 304 /* Calculation of state values for next stage */
emh203 0:3d9c67d97d6f 305 /* g5(n) = f4(n) * K5 + g4(n-1) */
emh203 0:3d9c67d97d6f 306 gnext4 = (q31_t) ((fnext4 * (*pk)) >> 15u) + gnext3;
emh203 0:3d9c67d97d6f 307 gnext4 = __SSAT(gnext4, 16);
emh203 0:3d9c67d97d6f 308 gnext3 = (q31_t) ((fnext3 * (*pk)) >> 15u) + gnext2;
emh203 0:3d9c67d97d6f 309 gnext3 = __SSAT(gnext3, 16);
emh203 0:3d9c67d97d6f 310 gnext2 = (q31_t) ((fnext2 * (*pk)) >> 15u) + gnext1;
emh203 0:3d9c67d97d6f 311 gnext2 = __SSAT(gnext2, 16);
emh203 0:3d9c67d97d6f 312 gnext1 = (q31_t) ((fnext1 * (*pk++)) >> 15u) + gcurnt1;
emh203 0:3d9c67d97d6f 313 gnext1 = __SSAT(gnext1, 16);
emh203 0:3d9c67d97d6f 314
emh203 0:3d9c67d97d6f 315 stageCnt--;
emh203 0:3d9c67d97d6f 316 }
emh203 0:3d9c67d97d6f 317
emh203 0:3d9c67d97d6f 318 /* If the (filter length -1) is not a multiple of 4, compute the remaining filter taps */
emh203 0:3d9c67d97d6f 319 stageCnt = (numStages - 1u) % 0x4u;
emh203 0:3d9c67d97d6f 320
emh203 0:3d9c67d97d6f 321 while(stageCnt > 0u)
emh203 0:3d9c67d97d6f 322 {
emh203 0:3d9c67d97d6f 323 gcurnt1 = *px;
emh203 0:3d9c67d97d6f 324
emh203 0:3d9c67d97d6f 325 /* save g value in state buffer */
emh203 0:3d9c67d97d6f 326 *px++ = (q15_t) gnext4;
emh203 0:3d9c67d97d6f 327
emh203 0:3d9c67d97d6f 328 /* Process four samples for last three taps here */
emh203 0:3d9c67d97d6f 329 fnext1 = (q31_t) ((gcurnt1 * (*pk)) >> 15u) + fcurnt1;
emh203 0:3d9c67d97d6f 330 fnext1 = __SSAT(fnext1, 16);
emh203 0:3d9c67d97d6f 331 fnext2 = (q31_t) ((gnext1 * (*pk)) >> 15u) + fcurnt2;
emh203 0:3d9c67d97d6f 332 fnext2 = __SSAT(fnext2, 16);
emh203 0:3d9c67d97d6f 333
emh203 0:3d9c67d97d6f 334 fnext3 = (q31_t) ((gnext2 * (*pk)) >> 15u) + fcurnt3;
emh203 0:3d9c67d97d6f 335 fnext3 = __SSAT(fnext3, 16);
emh203 0:3d9c67d97d6f 336
emh203 0:3d9c67d97d6f 337 fnext4 = (q31_t) ((gnext3 * (*pk)) >> 15u) + fcurnt4;
emh203 0:3d9c67d97d6f 338 fnext4 = __SSAT(fnext4, 16);
emh203 0:3d9c67d97d6f 339
emh203 0:3d9c67d97d6f 340 /* g1(n) = f0(n) * K1 + g0(n-1) */
emh203 0:3d9c67d97d6f 341 gnext4 = (q31_t) ((fcurnt4 * (*pk)) >> 15u) + gnext3;
emh203 0:3d9c67d97d6f 342 gnext4 = __SSAT(gnext4, 16);
emh203 0:3d9c67d97d6f 343 gnext3 = (q31_t) ((fcurnt3 * (*pk)) >> 15u) + gnext2;
emh203 0:3d9c67d97d6f 344 gnext3 = __SSAT(gnext3, 16);
emh203 0:3d9c67d97d6f 345 gnext2 = (q31_t) ((fcurnt2 * (*pk)) >> 15u) + gnext1;
emh203 0:3d9c67d97d6f 346 gnext2 = __SSAT(gnext2, 16);
emh203 0:3d9c67d97d6f 347 gnext1 = (q31_t) ((fcurnt1 * (*pk++)) >> 15u) + gcurnt1;
emh203 0:3d9c67d97d6f 348 gnext1 = __SSAT(gnext1, 16);
emh203 0:3d9c67d97d6f 349
emh203 0:3d9c67d97d6f 350 /* Update of f values for next coefficient set processing */
emh203 0:3d9c67d97d6f 351 fcurnt1 = fnext1;
emh203 0:3d9c67d97d6f 352 fcurnt2 = fnext2;
emh203 0:3d9c67d97d6f 353 fcurnt3 = fnext3;
emh203 0:3d9c67d97d6f 354 fcurnt4 = fnext4;
emh203 0:3d9c67d97d6f 355
emh203 0:3d9c67d97d6f 356 stageCnt--;
emh203 0:3d9c67d97d6f 357
emh203 0:3d9c67d97d6f 358 }
emh203 0:3d9c67d97d6f 359
emh203 0:3d9c67d97d6f 360 /* The results in the 4 accumulators, store in the destination buffer. */
emh203 0:3d9c67d97d6f 361 /* y(n) = fN(n) */
emh203 0:3d9c67d97d6f 362
emh203 0:3d9c67d97d6f 363 #ifndef ARM_MATH_BIG_ENDIAN
emh203 0:3d9c67d97d6f 364
emh203 0:3d9c67d97d6f 365 *__SIMD32(pDst)++ = __PKHBT(fcurnt1, fcurnt2, 16);
emh203 0:3d9c67d97d6f 366 *__SIMD32(pDst)++ = __PKHBT(fcurnt3, fcurnt4, 16);
emh203 0:3d9c67d97d6f 367
emh203 0:3d9c67d97d6f 368 #else
emh203 0:3d9c67d97d6f 369
emh203 0:3d9c67d97d6f 370 *__SIMD32(pDst)++ = __PKHBT(fcurnt2, fcurnt1, 16);
emh203 0:3d9c67d97d6f 371 *__SIMD32(pDst)++ = __PKHBT(fcurnt4, fcurnt3, 16);
emh203 0:3d9c67d97d6f 372
emh203 0:3d9c67d97d6f 373 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
emh203 0:3d9c67d97d6f 374
emh203 0:3d9c67d97d6f 375 blkCnt--;
emh203 0:3d9c67d97d6f 376 }
emh203 0:3d9c67d97d6f 377
emh203 0:3d9c67d97d6f 378 /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
emh203 0:3d9c67d97d6f 379 ** No loop unrolling is used. */
emh203 0:3d9c67d97d6f 380 blkCnt = blockSize % 0x4u;
emh203 0:3d9c67d97d6f 381
emh203 0:3d9c67d97d6f 382 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 383 {
emh203 0:3d9c67d97d6f 384 /* f0(n) = x(n) */
emh203 0:3d9c67d97d6f 385 fcurnt1 = *pSrc++;
emh203 0:3d9c67d97d6f 386
emh203 0:3d9c67d97d6f 387 /* Initialize coeff pointer */
emh203 0:3d9c67d97d6f 388 pk = (pCoeffs);
emh203 0:3d9c67d97d6f 389
emh203 0:3d9c67d97d6f 390 /* Initialize state pointer */
emh203 0:3d9c67d97d6f 391 px = pState;
emh203 0:3d9c67d97d6f 392
emh203 0:3d9c67d97d6f 393 /* read g2(n) from state buffer */
emh203 0:3d9c67d97d6f 394 gcurnt1 = *px;
emh203 0:3d9c67d97d6f 395
emh203 0:3d9c67d97d6f 396 /* for sample 1 processing */
emh203 0:3d9c67d97d6f 397 /* f1(n) = f0(n) + K1 * g0(n-1) */
emh203 0:3d9c67d97d6f 398 fnext1 = (((q31_t) gcurnt1 * (*pk)) >> 15u) + fcurnt1;
emh203 0:3d9c67d97d6f 399 fnext1 = __SSAT(fnext1, 16);
emh203 0:3d9c67d97d6f 400
emh203 0:3d9c67d97d6f 401
emh203 0:3d9c67d97d6f 402 /* g1(n) = f0(n) * K1 + g0(n-1) */
emh203 0:3d9c67d97d6f 403 gnext1 = (((q31_t) fcurnt1 * (*pk++)) >> 15u) + gcurnt1;
emh203 0:3d9c67d97d6f 404 gnext1 = __SSAT(gnext1, 16);
emh203 0:3d9c67d97d6f 405
emh203 0:3d9c67d97d6f 406 /* save g1(n) in state buffer */
emh203 0:3d9c67d97d6f 407 *px++ = (q15_t) fcurnt1;
emh203 0:3d9c67d97d6f 408
emh203 0:3d9c67d97d6f 409 /* f1(n) is saved in fcurnt1
emh203 0:3d9c67d97d6f 410 for next stage processing */
emh203 0:3d9c67d97d6f 411 fcurnt1 = fnext1;
emh203 0:3d9c67d97d6f 412
emh203 0:3d9c67d97d6f 413 stageCnt = (numStages - 1u);
emh203 0:3d9c67d97d6f 414
emh203 0:3d9c67d97d6f 415 /* stage loop */
emh203 0:3d9c67d97d6f 416 while(stageCnt > 0u)
emh203 0:3d9c67d97d6f 417 {
emh203 0:3d9c67d97d6f 418 /* read g2(n) from state buffer */
emh203 0:3d9c67d97d6f 419 gcurnt1 = *px;
emh203 0:3d9c67d97d6f 420
emh203 0:3d9c67d97d6f 421 /* save g1(n) in state buffer */
emh203 0:3d9c67d97d6f 422 *px++ = (q15_t) gnext1;
emh203 0:3d9c67d97d6f 423
emh203 0:3d9c67d97d6f 424 /* Sample processing for K2, K3.... */
emh203 0:3d9c67d97d6f 425 /* f2(n) = f1(n) + K2 * g1(n-1) */
emh203 0:3d9c67d97d6f 426 fnext1 = (((q31_t) gcurnt1 * (*pk)) >> 15u) + fcurnt1;
emh203 0:3d9c67d97d6f 427 fnext1 = __SSAT(fnext1, 16);
emh203 0:3d9c67d97d6f 428
emh203 0:3d9c67d97d6f 429 /* g2(n) = f1(n) * K2 + g1(n-1) */
emh203 0:3d9c67d97d6f 430 gnext1 = (((q31_t) fcurnt1 * (*pk++)) >> 15u) + gcurnt1;
emh203 0:3d9c67d97d6f 431 gnext1 = __SSAT(gnext1, 16);
emh203 0:3d9c67d97d6f 432
emh203 0:3d9c67d97d6f 433
emh203 0:3d9c67d97d6f 434 /* f1(n) is saved in fcurnt1
emh203 0:3d9c67d97d6f 435 for next stage processing */
emh203 0:3d9c67d97d6f 436 fcurnt1 = fnext1;
emh203 0:3d9c67d97d6f 437
emh203 0:3d9c67d97d6f 438 stageCnt--;
emh203 0:3d9c67d97d6f 439
emh203 0:3d9c67d97d6f 440 }
emh203 0:3d9c67d97d6f 441
emh203 0:3d9c67d97d6f 442 /* y(n) = fN(n) */
emh203 0:3d9c67d97d6f 443 *pDst++ = __SSAT(fcurnt1, 16);
emh203 0:3d9c67d97d6f 444
emh203 0:3d9c67d97d6f 445
emh203 0:3d9c67d97d6f 446 blkCnt--;
emh203 0:3d9c67d97d6f 447
emh203 0:3d9c67d97d6f 448 }
emh203 0:3d9c67d97d6f 449
emh203 0:3d9c67d97d6f 450 #else
emh203 0:3d9c67d97d6f 451
emh203 0:3d9c67d97d6f 452 /* Run the below code for Cortex-M0 */
emh203 0:3d9c67d97d6f 453
emh203 0:3d9c67d97d6f 454 q31_t fcurnt, fnext, gcurnt, gnext; /* temporary variables */
emh203 0:3d9c67d97d6f 455 uint32_t numStages = S->numStages; /* Length of the filter */
emh203 0:3d9c67d97d6f 456 uint32_t blkCnt, stageCnt; /* temporary variables for counts */
emh203 0:3d9c67d97d6f 457
emh203 0:3d9c67d97d6f 458 pState = &S->pState[0];
emh203 0:3d9c67d97d6f 459
emh203 0:3d9c67d97d6f 460 blkCnt = blockSize;
emh203 0:3d9c67d97d6f 461
emh203 0:3d9c67d97d6f 462 while(blkCnt > 0u)
emh203 0:3d9c67d97d6f 463 {
emh203 0:3d9c67d97d6f 464 /* f0(n) = x(n) */
emh203 0:3d9c67d97d6f 465 fcurnt = *pSrc++;
emh203 0:3d9c67d97d6f 466
emh203 0:3d9c67d97d6f 467 /* Initialize coeff pointer */
emh203 0:3d9c67d97d6f 468 pk = (pCoeffs);
emh203 0:3d9c67d97d6f 469
emh203 0:3d9c67d97d6f 470 /* Initialize state pointer */
emh203 0:3d9c67d97d6f 471 px = pState;
emh203 0:3d9c67d97d6f 472
emh203 0:3d9c67d97d6f 473 /* read g0(n-1) from state buffer */
emh203 0:3d9c67d97d6f 474 gcurnt = *px;
emh203 0:3d9c67d97d6f 475
emh203 0:3d9c67d97d6f 476 /* for sample 1 processing */
emh203 0:3d9c67d97d6f 477 /* f1(n) = f0(n) + K1 * g0(n-1) */
emh203 0:3d9c67d97d6f 478 fnext = ((gcurnt * (*pk)) >> 15u) + fcurnt;
emh203 0:3d9c67d97d6f 479 fnext = __SSAT(fnext, 16);
emh203 0:3d9c67d97d6f 480
emh203 0:3d9c67d97d6f 481
emh203 0:3d9c67d97d6f 482 /* g1(n) = f0(n) * K1 + g0(n-1) */
emh203 0:3d9c67d97d6f 483 gnext = ((fcurnt * (*pk++)) >> 15u) + gcurnt;
emh203 0:3d9c67d97d6f 484 gnext = __SSAT(gnext, 16);
emh203 0:3d9c67d97d6f 485
emh203 0:3d9c67d97d6f 486 /* save f0(n) in state buffer */
emh203 0:3d9c67d97d6f 487 *px++ = (q15_t) fcurnt;
emh203 0:3d9c67d97d6f 488
emh203 0:3d9c67d97d6f 489 /* f1(n) is saved in fcurnt
emh203 0:3d9c67d97d6f 490 for next stage processing */
emh203 0:3d9c67d97d6f 491 fcurnt = fnext;
emh203 0:3d9c67d97d6f 492
emh203 0:3d9c67d97d6f 493 stageCnt = (numStages - 1u);
emh203 0:3d9c67d97d6f 494
emh203 0:3d9c67d97d6f 495 /* stage loop */
emh203 0:3d9c67d97d6f 496 while(stageCnt > 0u)
emh203 0:3d9c67d97d6f 497 {
emh203 0:3d9c67d97d6f 498 /* read g1(n-1) from state buffer */
emh203 0:3d9c67d97d6f 499 gcurnt = *px;
emh203 0:3d9c67d97d6f 500
emh203 0:3d9c67d97d6f 501 /* save g0(n-1) in state buffer */
emh203 0:3d9c67d97d6f 502 *px++ = (q15_t) gnext;
emh203 0:3d9c67d97d6f 503
emh203 0:3d9c67d97d6f 504 /* Sample processing for K2, K3.... */
emh203 0:3d9c67d97d6f 505 /* f2(n) = f1(n) + K2 * g1(n-1) */
emh203 0:3d9c67d97d6f 506 fnext = ((gcurnt * (*pk)) >> 15u) + fcurnt;
emh203 0:3d9c67d97d6f 507 fnext = __SSAT(fnext, 16);
emh203 0:3d9c67d97d6f 508
emh203 0:3d9c67d97d6f 509 /* g2(n) = f1(n) * K2 + g1(n-1) */
emh203 0:3d9c67d97d6f 510 gnext = ((fcurnt * (*pk++)) >> 15u) + gcurnt;
emh203 0:3d9c67d97d6f 511 gnext = __SSAT(gnext, 16);
emh203 0:3d9c67d97d6f 512
emh203 0:3d9c67d97d6f 513
emh203 0:3d9c67d97d6f 514 /* f1(n) is saved in fcurnt
emh203 0:3d9c67d97d6f 515 for next stage processing */
emh203 0:3d9c67d97d6f 516 fcurnt = fnext;
emh203 0:3d9c67d97d6f 517
emh203 0:3d9c67d97d6f 518 stageCnt--;
emh203 0:3d9c67d97d6f 519
emh203 0:3d9c67d97d6f 520 }
emh203 0:3d9c67d97d6f 521
emh203 0:3d9c67d97d6f 522 /* y(n) = fN(n) */
emh203 0:3d9c67d97d6f 523 *pDst++ = __SSAT(fcurnt, 16);
emh203 0:3d9c67d97d6f 524
emh203 0:3d9c67d97d6f 525
emh203 0:3d9c67d97d6f 526 blkCnt--;
emh203 0:3d9c67d97d6f 527
emh203 0:3d9c67d97d6f 528 }
emh203 0:3d9c67d97d6f 529
emh203 0:3d9c67d97d6f 530 #endif /* #ifndef ARM_MATH_CM0_FAMILY */
emh203 0:3d9c67d97d6f 531
emh203 0:3d9c67d97d6f 532 }
emh203 0:3d9c67d97d6f 533
emh203 0:3d9c67d97d6f 534 /**
emh203 0:3d9c67d97d6f 535 * @} end of FIR_Lattice group
emh203 0:3d9c67d97d6f 536 */