00001 /* ---------------------------------------------------------------------- 00002 * Copyright (C) 2010 ARM Limited. All rights reserved. 00003 * 00004 * $Date: 29. November 2010 00005 * $Revision: V1.0.3 00006 * 00007 * Project: CMSIS DSP Library 00008 * Title: arm_biquad_cascade_df2T_f32.c 00009 * 00010 * Description: Processing function for the floating-point transposed 00011 * direct form II Biquad cascade filter. 00012 * 00013 * Target Processor: Cortex-M4/Cortex-M3 00014 * 00015 * Version 1.0.3 2010/11/29 00016 * Re-organized the CMSIS folders and updated documentation. 00017 * 00018 * Version 1.0.2 2010/11/11 00019 * Documentation updated. 00020 * 00021 * Version 1.0.1 2010/10/05 00022 * Production release and review comments incorporated. 00023 * 00024 * Version 1.0.0 2010/09/20 00025 * Production release and review comments incorporated 00026 * 00027 * Version 0.0.7 2010/06/10 00028 * Misra-C changes done 00029 * -------------------------------------------------------------------- */ 00030 00031 #include "arm_math.h" 00032 00140 void arm_biquad_cascade_df2T_f32( 00141 const arm_biquad_cascade_df2T_instance_f32 * S, 00142 float32_t * pSrc, 00143 float32_t * pDst, 00144 uint32_t blockSize) 00145 { 00146 00147 float32_t *pIn = pSrc; /* source pointer */ 00148 float32_t *pOut = pDst; /* destination pointer */ 00149 float32_t *pState = S->pState; /* State pointer */ 00150 float32_t *pCoeffs = S->pCoeffs; /* coefficient pointer */ 00151 float32_t acc0; /* Simulates the accumulator */ 00152 float32_t b0, b1, b2, a1, a2; /* Filter coefficients */ 00153 float32_t Xn; /* temporary input */ 00154 float32_t d1, d2; /* state variables */ 00155 uint32_t sample, stage = S->numStages; /* loop counters */ 00156 00157 00158 do 00159 { 00160 /* Reading the coefficients */ 00161 b0 = *pCoeffs++; 00162 b1 = *pCoeffs++; 00163 b2 = *pCoeffs++; 00164 a1 = *pCoeffs++; 00165 a2 = *pCoeffs++; 00166 00167 /*Reading the state values */ 00168 d1 = pState[0]; 00169 d2 = pState[1]; 00170 00171 /* Apply loop unrolling and compute 4 output values simultaneously. */ 00172 sample = blockSize >> 2u; 00173 00174 /* First part of the processing with loop unrolling. Compute 4 outputs at a time. 00175 ** a second loop below computes the remaining 1 to 3 samples. */ 00176 while(sample > 0u) 00177 { 00178 /* Read the first input */ 00179 Xn = *pIn++; 00180 00181 /* y[n] = b0 * x[n] + d1 */ 00182 acc0 = (b0 * Xn) + d1; 00183 00184 /* Store the result in the accumulator in the destination buffer. */ 00185 *pOut++ = acc0; 00186 00187 /* Every time after the output is computed state should be updated. */ 00188 /* d1 = b1 * x[n] + a1 * y[n] + d2 */ 00189 d1 = ((b1 * Xn) + (a1 * acc0)) + d2; 00190 00191 /* d2 = b2 * x[n] + a2 * y[n] */ 00192 d2 = (b2 * Xn) + (a2 * acc0); 00193 00194 /* Read the second input */ 00195 Xn = *pIn++; 00196 00197 /* y[n] = b0 * x[n] + d1 */ 00198 acc0 = (b0 * Xn) + d1; 00199 00200 /* Store the result in the accumulator in the destination buffer. */ 00201 *pOut++ = acc0; 00202 00203 /* Every time after the output is computed state should be updated. */ 00204 /* d1 = b1 * x[n] + a1 * y[n] + d2 */ 00205 d1 = ((b1 * Xn) + (a1 * acc0)) + d2; 00206 00207 /* d2 = b2 * x[n] + a2 * y[n] */ 00208 d2 = (b2 * Xn) + (a2 * acc0); 00209 00210 /* Read the third input */ 00211 Xn = *pIn++; 00212 00213 /* y[n] = b0 * x[n] + d1 */ 00214 acc0 = (b0 * Xn) + d1; 00215 00216 /* Store the result in the accumulator in the destination buffer. */ 00217 *pOut++ = acc0; 00218 00219 /* Every time after the output is computed state should be updated. */ 00220 /* d1 = b1 * x[n] + a1 * y[n] + d2 */ 00221 d1 = ((b1 * Xn) + (a1 * acc0)) + d2; 00222 00223 /* d2 = b2 * x[n] + a2 * y[n] */ 00224 d2 = (b2 * Xn) + (a2 * acc0); 00225 00226 /* Read the fourth input */ 00227 Xn = *pIn++; 00228 00229 /* y[n] = b0 * x[n] + d1 */ 00230 acc0 = (b0 * Xn) + d1; 00231 00232 /* Store the result in the accumulator in the destination buffer. */ 00233 *pOut++ = acc0; 00234 00235 /* Every time after the output is computed state should be updated. */ 00236 /* d1 = b1 * x[n] + a1 * y[n] + d2 */ 00237 d1 = (b1 * Xn) + (a1 * acc0) + d2; 00238 00239 /* d2 = b2 * x[n] + a2 * y[n] */ 00240 d2 = (b2 * Xn) + (a2 * acc0); 00241 00242 /* decrement the loop counter */ 00243 sample--; 00244 00245 } 00246 00247 /* If the blockSize is not a multiple of 4, compute any remaining output samples here. 00248 ** No loop unrolling is used. */ 00249 sample = blockSize & 0x3u; 00250 00251 while(sample > 0u) 00252 { 00253 /* Read the input */ 00254 Xn = *pIn++; 00255 00256 /* y[n] = b0 * x[n] + d1 */ 00257 acc0 = (b0 * Xn) + d1; 00258 00259 /* Store the result in the accumulator in the destination buffer. */ 00260 *pOut++ = acc0; 00261 00262 /* Every time after the output is computed state should be updated. */ 00263 /* d1 = b1 * x[n] + a1 * y[n] + d2 */ 00264 d1 = ((b1 * Xn) + (a1 * acc0)) + d2; 00265 00266 /* d2 = b2 * x[n] + a2 * y[n] */ 00267 d2 = (b2 * Xn) + (a2 * acc0); 00268 00269 /* decrement the loop counter */ 00270 sample--; 00271 } 00272 00273 /* Store the updated state variables back into the state array */ 00274 *pState++ = d1; 00275 *pState++ = d2; 00276 00277 /* The current stage input is given as the output to the next stage */ 00278 pIn = pDst; 00279 00280 /*Reset the output working pointer */ 00281 pOut = pDst; 00282 00283 /* decrement the loop counter */ 00284 stage--; 00285 00286 } while(stage > 0u); 00287 00288 00289 } 00290 00291