123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372 |
- /* ----------------------------------------------------------------------
- * Copyright (C) 2010-2013 ARM Limited. All rights reserved.
- *
- * $Date: 17. January 2013
- * $Revision: V1.4.1
- *
- * Project: CMSIS DSP Library
- * Title: arm_fir_sparse_f32.c
- *
- * Description: Floating-point sparse FIR filter processing function.
- *
- * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * - Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * - Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * - Neither the name of ARM LIMITED nor the names of its contributors
- * may be used to endorse or promote products derived from this
- * software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
- * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
- * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
- * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
- * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
- * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
- * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
- * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- * ------------------------------------------------------------------- */
- #include "arm_math.h"
-
- /**
- * @ingroup groupFilters
- */
-
- /**
- * @defgroup FIR_Sparse Finite Impulse Response (FIR) Sparse Filters
- *
- * This group of functions implements sparse FIR filters.
- * Sparse FIR filters are equivalent to standard FIR filters except that most of the coefficients are equal to zero.
- * Sparse filters are used for simulating reflections in communications and audio applications.
- *
- * There are separate functions for Q7, Q15, Q31, and floating-point data types.
- * The functions operate on blocks of input and output data and each call to the function processes
- * <code>blockSize</code> samples through the filter. <code>pSrc</code> and
- * <code>pDst</code> points to input and output arrays respectively containing <code>blockSize</code> values.
- *
- * \par Algorithm:
- * The sparse filter instant structure contains an array of tap indices <code>pTapDelay</code> which specifies the locations of the non-zero coefficients.
- * This is in addition to the coefficient array <code>b</code>.
- * The implementation essentially skips the multiplications by zero and leads to an efficient realization.
- * <pre>
- * 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]]
- * </pre>
- * \par
- * \image html FIRSparse.gif "Sparse FIR filter. b[n] represents the filter coefficients"
- * \par
- * <code>pCoeffs</code> points to a coefficient array of size <code>numTaps</code>;
- * <code>pTapDelay</code> points to an array of nonzero indices and is also of size <code>numTaps</code>;
- * <code>pState</code> points to a state array of size <code>maxDelay + blockSize</code>, where
- * <code>maxDelay</code> is the largest offset value that is ever used in the <code>pTapDelay</code> array.
- * Some of the processing functions also require temporary working buffers.
- *
- * \par Instance Structure
- * The coefficients and state variables for a filter are stored together in an instance data structure.
- * A separate instance structure must be defined for each filter.
- * Coefficient and offset arrays may be shared among several instances while state variable arrays cannot be shared.
- * There are separate instance structure declarations for each of the 4 supported data types.
- *
- * \par Initialization Functions
- * There is also an associated initialization function for each data type.
- * The initialization function performs the following operations:
- * - Sets the values of the internal structure fields.
- * - Zeros out the values in the state buffer.
- * To do this manually without calling the init function, assign the follow subfields of the instance structure:
- * numTaps, pCoeffs, pTapDelay, maxDelay, stateIndex, pState. Also set all of the values in pState to zero.
- *
- * \par
- * Use of the initialization function is optional.
- * However, if the initialization function is used, then the instance structure cannot be placed into a const data section.
- * To place an instance structure into a const data section, the instance structure must be manually initialized.
- * Set the values in the state buffer to zeros before static initialization.
- * The code below statically initializes each of the 4 different data type filter instance structures
- * <pre>
- *arm_fir_sparse_instance_f32 S = {numTaps, 0, pState, pCoeffs, maxDelay, pTapDelay};
- *arm_fir_sparse_instance_q31 S = {numTaps, 0, pState, pCoeffs, maxDelay, pTapDelay};
- *arm_fir_sparse_instance_q15 S = {numTaps, 0, pState, pCoeffs, maxDelay, pTapDelay};
- *arm_fir_sparse_instance_q7 S = {numTaps, 0, pState, pCoeffs, maxDelay, pTapDelay};
- * </pre>
- * \par
- *
- * \par Fixed-Point Behavior
- * Care must be taken when using the fixed-point versions of the sparse FIR filter functions.
- * In particular, the overflow and saturation behavior of the accumulator used in each function must be considered.
- * Refer to the function specific documentation below for usage guidelines.
- */
-
- /**
- * @addtogroup FIR_Sparse
- * @{
- */
-
- /**
- * @brief Processing function for the floating-point sparse FIR filter.
- * @param[in] *S points to an instance of the floating-point sparse FIR structure.
- * @param[in] *pSrc points to the block of input data.
- * @param[out] *pDst points to the block of output data
- * @param[in] *pScratchIn points to a temporary buffer of size blockSize.
- * @param[in] blockSize number of input samples to process per call.
- * @return none.
- */
-
- void arm_fir_sparse_f32(
- arm_fir_sparse_instance_f32 * S,
- float32_t * pSrc,
- float32_t * pDst,
- float32_t * pScratchIn,
- uint32_t blockSize)
- {
-
- float32_t *pState = S->pState; /* State pointer */
- float32_t *pCoeffs = S->pCoeffs; /* Coefficient pointer */
- float32_t *px; /* Scratch buffer pointer */
- float32_t *py = pState; /* Temporary pointers for state buffer */
- float32_t *pb = pScratchIn; /* Temporary pointers for scratch buffer */
- float32_t *pOut; /* Destination pointer */
- int32_t *pTapDelay = S->pTapDelay; /* Pointer to the array containing offset of the non-zero tap values. */
- uint32_t delaySize = S->maxDelay + blockSize; /* state length */
- uint16_t numTaps = S->numTaps; /* Number of filter coefficients in the filter */
- int32_t readIndex; /* Read index of the state buffer */
- uint32_t tapCnt, blkCnt; /* loop counters */
- float32_t coeff = *pCoeffs++; /* Read the first coefficient value */
-
-
-
- /* BlockSize of Input samples are copied into the state buffer */
- /* StateIndex points to the starting position to write in the state buffer */
- arm_circularWrite_f32((int32_t *) py, delaySize, &S->stateIndex, 1,
- (int32_t *) pSrc, 1, blockSize);
-
-
- /* Read Index, from where the state buffer should be read, is calculated. */
- readIndex = ((int32_t) S->stateIndex - (int32_t) blockSize) - *pTapDelay++;
-
- /* Wraparound of readIndex */
- if(readIndex < 0)
- {
- readIndex += (int32_t) delaySize;
- }
-
- /* Working pointer for state buffer is updated */
- py = pState;
-
- /* blockSize samples are read from the state buffer */
- arm_circularRead_f32((int32_t *) py, delaySize, &readIndex, 1,
- (int32_t *) pb, (int32_t *) pb, blockSize, 1,
- blockSize);
-
- /* Working pointer for the scratch buffer */
- px = pb;
-
- /* Working pointer for destination buffer */
- pOut = pDst;
-
-
- #ifndef ARM_MATH_CM0_FAMILY
-
- /* Run the below code for Cortex-M4 and Cortex-M3 */
-
- /* Loop over the blockSize. Unroll by a factor of 4.
- * Compute 4 Multiplications at a time. */
- blkCnt = blockSize >> 2u;
-
- while(blkCnt > 0u)
- {
- /* Perform Multiplications and store in destination buffer */
- *pOut++ = *px++ * coeff;
- *pOut++ = *px++ * coeff;
- *pOut++ = *px++ * coeff;
- *pOut++ = *px++ * coeff;
-
- /* Decrement the loop counter */
- blkCnt--;
- }
-
- /* If the blockSize is not a multiple of 4,
- * compute the remaining samples */
- blkCnt = blockSize % 0x4u;
-
- while(blkCnt > 0u)
- {
- /* Perform Multiplications and store in destination buffer */
- *pOut++ = *px++ * coeff;
-
- /* Decrement the loop counter */
- blkCnt--;
- }
-
- /* Load the coefficient value and
- * increment the coefficient buffer for the next set of state values */
- coeff = *pCoeffs++;
-
- /* Read Index, from where the state buffer should be read, is calculated. */
- readIndex = ((int32_t) S->stateIndex - (int32_t) blockSize) - *pTapDelay++;
-
- /* Wraparound of readIndex */
- if(readIndex < 0)
- {
- readIndex += (int32_t) delaySize;
- }
-
- /* Loop over the number of taps. */
- tapCnt = (uint32_t) numTaps - 1u;
-
- while(tapCnt > 0u)
- {
-
- /* Working pointer for state buffer is updated */
- py = pState;
-
- /* blockSize samples are read from the state buffer */
- arm_circularRead_f32((int32_t *) py, delaySize, &readIndex, 1,
- (int32_t *) pb, (int32_t *) pb, blockSize, 1,
- blockSize);
-
- /* Working pointer for the scratch buffer */
- px = pb;
-
- /* Working pointer for destination buffer */
- pOut = pDst;
-
- /* Loop over the blockSize. Unroll by a factor of 4.
- * Compute 4 MACS at a time. */
- blkCnt = blockSize >> 2u;
-
- while(blkCnt > 0u)
- {
- /* Perform Multiply-Accumulate */
- *pOut++ += *px++ * coeff;
- *pOut++ += *px++ * coeff;
- *pOut++ += *px++ * coeff;
- *pOut++ += *px++ * coeff;
-
- /* Decrement the loop counter */
- blkCnt--;
- }
-
- /* If the blockSize is not a multiple of 4,
- * compute the remaining samples */
- blkCnt = blockSize % 0x4u;
-
- while(blkCnt > 0u)
- {
- /* Perform Multiply-Accumulate */
- *pOut++ += *px++ * coeff;
-
- /* Decrement the loop counter */
- blkCnt--;
- }
-
- /* Load the coefficient value and
- * increment the coefficient buffer for the next set of state values */
- coeff = *pCoeffs++;
-
- /* Read Index, from where the state buffer should be read, is calculated. */
- readIndex = ((int32_t) S->stateIndex -
- (int32_t) blockSize) - *pTapDelay++;
-
- /* Wraparound of readIndex */
- if(readIndex < 0)
- {
- readIndex += (int32_t) delaySize;
- }
-
- /* Decrement the tap loop counter */
- tapCnt--;
- }
-
- #else
-
- /* Run the below code for Cortex-M0 */
-
- blkCnt = blockSize;
-
- while(blkCnt > 0u)
- {
- /* Perform Multiplications and store in destination buffer */
- *pOut++ = *px++ * coeff;
-
- /* Decrement the loop counter */
- blkCnt--;
- }
-
- /* Load the coefficient value and
- * increment the coefficient buffer for the next set of state values */
- coeff = *pCoeffs++;
-
- /* Read Index, from where the state buffer should be read, is calculated. */
- readIndex = ((int32_t) S->stateIndex - (int32_t) blockSize) - *pTapDelay++;
-
- /* Wraparound of readIndex */
- if(readIndex < 0)
- {
- readIndex += (int32_t) delaySize;
- }
-
- /* Loop over the number of taps. */
- tapCnt = (uint32_t) numTaps - 1u;
-
- while(tapCnt > 0u)
- {
-
- /* Working pointer for state buffer is updated */
- py = pState;
-
- /* blockSize samples are read from the state buffer */
- arm_circularRead_f32((int32_t *) py, delaySize, &readIndex, 1,
- (int32_t *) pb, (int32_t *) pb, blockSize, 1,
- blockSize);
-
- /* Working pointer for the scratch buffer */
- px = pb;
-
- /* Working pointer for destination buffer */
- pOut = pDst;
-
- blkCnt = blockSize;
-
- while(blkCnt > 0u)
- {
- /* Perform Multiply-Accumulate */
- *pOut++ += *px++ * coeff;
-
- /* Decrement the loop counter */
- blkCnt--;
- }
-
- /* Load the coefficient value and
- * increment the coefficient buffer for the next set of state values */
- coeff = *pCoeffs++;
-
- /* Read Index, from where the state buffer should be read, is calculated. */
- readIndex =
- ((int32_t) S->stateIndex - (int32_t) blockSize) - *pTapDelay++;
-
- /* Wraparound of readIndex */
- if(readIndex < 0)
- {
- readIndex += (int32_t) delaySize;
- }
-
- /* Decrement the tap loop counter */
- tapCnt--;
- }
-
- #endif /* #ifndef ARM_MATH_CM0_FAMILY */
-
- }
-
- /**
- * @} end of FIR_Sparse group
- */
|