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_df1_32x64_q31.c 00009 * 00010 * Description: High precision Q31 Biquad cascade filter processing function 00011 * 00012 * Target Processor: Cortex-M4/Cortex-M3 00013 * 00014 * Version 1.0.3 2010/11/29 00015 * Re-organized the CMSIS folders and updated documentation. 00016 * 00017 * Version 1.0.2 2010/11/11 00018 * Documentation updated. 00019 * 00020 * Version 1.0.1 2010/10/05 00021 * Production release and review comments incorporated. 00022 * 00023 * Version 1.0.0 2010/09/20 00024 * Production release and review comments incorporated. 00025 * 00026 * Version 0.0.7 2010/06/10 00027 * Misra-C changes done 00028 * -------------------------------------------------------------------- */ 00029 00030 #include "arm_math.h" 00031 00173 void arm_biquad_cas_df1_32x64_q31( 00174 const arm_biquad_cas_df1_32x64_ins_q31 * S, 00175 q31_t * pSrc, 00176 q31_t * pDst, 00177 uint32_t blockSize) 00178 { 00179 q31_t *pIn = pSrc; /* input pointer initialization */ 00180 q31_t *pOut = pDst; /* output pointer initialization */ 00181 q63_t *pState = S->pState; /* state pointer initialization */ 00182 q31_t *pCoeffs = S->pCoeffs; /* coeff pointer initialization */ 00183 q63_t acc; /* accumulator */ 00184 q63_t Xn1, Xn2, Yn1, Yn2; /* Filter state variables */ 00185 q31_t b0, b1, b2, a1, a2; /* Filter coefficients */ 00186 q63_t Xn; /* temporary input */ 00187 int32_t shift = (int32_t) S->postShift + 1; /* Shift to be applied to the output */ 00188 uint32_t sample, stage = S->numStages; /* loop counters */ 00189 00190 00191 do 00192 { 00193 /* Reading the coefficients */ 00194 b0 = *pCoeffs++; 00195 b1 = *pCoeffs++; 00196 b2 = *pCoeffs++; 00197 a1 = *pCoeffs++; 00198 a2 = *pCoeffs++; 00199 00200 /* Reading the state values */ 00201 Xn1 = pState[0]; 00202 Xn2 = pState[1]; 00203 Yn1 = pState[2]; 00204 Yn2 = pState[3]; 00205 00206 /* Apply loop unrolling and compute 4 output values simultaneously. */ 00207 /* The variable acc hold output value that is being computed and 00208 * stored in the destination buffer 00209 * acc = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] 00210 */ 00211 00212 sample = blockSize >> 2u; 00213 00214 /* First part of the processing with loop unrolling. Compute 4 outputs at a time. 00215 ** a second loop below computes the remaining 1 to 3 samples. */ 00216 while(sample > 0u) 00217 { 00218 /* Read the input */ 00219 Xn = *pIn++; 00220 00221 /* The value is shifted to the MSB to perform 32x64 multiplication */ 00222 Xn = Xn << 32; 00223 00224 /* acc = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */ 00225 00226 /* acc = b0 * x[n] */ 00227 acc = mult32x64(Xn, b0); 00228 /* acc += b1 * x[n-1] */ 00229 acc += mult32x64(Xn1, b1); 00230 /* acc += b[2] * x[n-2] */ 00231 acc += mult32x64(Xn2, b2); 00232 /* acc += a1 * y[n-1] */ 00233 acc += mult32x64(Yn1, a1); 00234 /* acc += a2 * y[n-2] */ 00235 acc += mult32x64(Yn2, a2); 00236 00237 /* The result is converted to 1.63 , Yn2 variable is reused */ 00238 Yn2 = acc << shift; 00239 00240 /* Store the output in the destination buffer in 1.31 format. */ 00241 *pOut++ = (q31_t) (acc >> (32 - shift)); 00242 00243 /* Read the second input into Xn2, to reuse the value */ 00244 Xn2 = *pIn++; 00245 00246 /* The value is shifted to the MSB to perform 32x64 multiplication */ 00247 Xn2 = Xn2 << 32; 00248 00249 /* acc = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */ 00250 00251 /* acc = b0 * x[n] */ 00252 acc = mult32x64(Xn2, b0); 00253 /* acc += b1 * x[n-1] */ 00254 acc += mult32x64(Xn, b1); 00255 /* acc += b[2] * x[n-2] */ 00256 acc += mult32x64(Xn1, b2); 00257 /* acc += a1 * y[n-1] */ 00258 acc += mult32x64(Yn2, a1); 00259 /* acc += a2 * y[n-2] */ 00260 acc += mult32x64(Yn1, a2); 00261 00262 /* The result is converted to 1.63, Yn1 variable is reused */ 00263 Yn1 = acc << shift; 00264 00265 /* The result is converted to 1.31 */ 00266 /* Store the output in the destination buffer. */ 00267 *pOut++ = (q31_t) (acc >> (32 - shift)); 00268 00269 /* Read the third input into Xn1, to reuse the value */ 00270 Xn1 = *pIn++; 00271 00272 /* The value is shifted to the MSB to perform 32x64 multiplication */ 00273 Xn1 = Xn1 << 32; 00274 00275 /* acc = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */ 00276 /* acc = b0 * x[n] */ 00277 acc = mult32x64(Xn1, b0); 00278 /* acc += b1 * x[n-1] */ 00279 acc += mult32x64(Xn2, b1); 00280 /* acc += b[2] * x[n-2] */ 00281 acc += mult32x64(Xn, b2); 00282 /* acc += a1 * y[n-1] */ 00283 acc += mult32x64(Yn1, a1); 00284 /* acc += a2 * y[n-2] */ 00285 acc += mult32x64(Yn2, a2); 00286 00287 /* The result is converted to 1.63, Yn2 variable is reused */ 00288 Yn2 = acc << shift; 00289 00290 /* Store the output in the destination buffer in 1.31 format. */ 00291 *pOut++ = (q31_t) (acc >> (32 - shift)); 00292 00293 /* Read the fourth input into Xn, to reuse the value */ 00294 Xn = *pIn++; 00295 00296 /* The value is shifted to the MSB to perform 32x64 multiplication */ 00297 Xn = Xn << 32; 00298 00299 /* acc = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */ 00300 /* acc = b0 * x[n] */ 00301 acc = mult32x64(Xn, b0); 00302 /* acc += b1 * x[n-1] */ 00303 acc += mult32x64(Xn1, b1); 00304 /* acc += b[2] * x[n-2] */ 00305 acc += mult32x64(Xn2, b2); 00306 /* acc += a1 * y[n-1] */ 00307 acc += mult32x64(Yn2, a1); 00308 /* acc += a2 * y[n-2] */ 00309 acc += mult32x64(Yn1, a2); 00310 00311 /* The result is converted to 1.63, Yn1 variable is reused */ 00312 Yn1 = acc << shift; 00313 00314 /* Every time after the output is computed state should be updated. */ 00315 /* The states should be updated as: */ 00316 /* Xn2 = Xn1 */ 00317 /* Xn1 = Xn */ 00318 /* Yn2 = Yn1 */ 00319 /* Yn1 = acc */ 00320 Xn2 = Xn1; 00321 Xn1 = Xn; 00322 00323 /* Store the output in the destination buffer in 1.31 format. */ 00324 *pOut++ = (q31_t) (acc >> (32 - shift)); 00325 00326 /* decrement the loop counter */ 00327 sample--; 00328 } 00329 00330 /* If the blockSize is not a multiple of 4, compute any remaining output samples here. 00331 ** No loop unrolling is used. */ 00332 sample = (blockSize & 0x3u); 00333 00334 while(sample > 0u) 00335 { 00336 /* Read the input */ 00337 Xn = *pIn++; 00338 00339 /* The value is shifted to the MSB to perform 32x64 multiplication */ 00340 Xn = Xn << 32; 00341 00342 /* acc = b0 * x[n] + b1 * x[n-1] + b2 * x[n-2] + a1 * y[n-1] + a2 * y[n-2] */ 00343 /* acc = b0 * x[n] */ 00344 acc = mult32x64(Xn, b0); 00345 /* acc += b1 * x[n-1] */ 00346 acc += mult32x64(Xn1, b1); 00347 /* acc += b[2] * x[n-2] */ 00348 acc += mult32x64(Xn2, b2); 00349 /* acc += a1 * y[n-1] */ 00350 acc += mult32x64(Yn1, a1); 00351 /* acc += a2 * y[n-2] */ 00352 acc += mult32x64(Yn2, a2); 00353 00354 /* Every time after the output is computed state should be updated. */ 00355 /* The states should be updated as: */ 00356 /* Xn2 = Xn1 */ 00357 /* Xn1 = Xn */ 00358 /* Yn2 = Yn1 */ 00359 /* Yn1 = acc */ 00360 Xn2 = Xn1; 00361 Xn1 = Xn; 00362 Yn2 = Yn1; 00363 Yn1 = acc << shift; 00364 00365 /* Store the output in the destination buffer in 1.31 format. */ 00366 *pOut++ = (q31_t) (acc >> (32 - shift)); 00367 00368 /* decrement the loop counter */ 00369 sample--; 00370 } 00371 00372 /* The first stage output is given as input to the second stage. */ 00373 pIn = pDst; 00374 00375 /* Reset to destination buffer working pointer */ 00376 pOut = pDst; 00377 00378 /* Store the updated state variables back into the pState array */ 00379 *pState++ = Xn1; 00380 *pState++ = Xn2; 00381 *pState++ = Yn1; 00382 *pState++ = Yn2; 00383 00384 } while(--stage); 00385 } 00386