| /* ---------------------------------------------------------------------- |
| * Copyright (C) 2010-2014 ARM Limited. All rights reserved. |
| * |
| * $Date: 19. March 2015 |
| * $Revision: V.1.4.5 |
| * |
| * Project: CMSIS DSP Library |
| * Title: arm_mat_scale_q15.c |
| * |
| * Description: Multiplies a Q15 matrix by a scalar. |
| * |
| * 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 groupMatrix |
| */ |
| |
| /** |
| * @addtogroup MatrixScale |
| * @{ |
| */ |
| |
| /** |
| * @brief Q15 matrix scaling. |
| * @param[in] *pSrc points to input matrix |
| * @param[in] scaleFract fractional portion of the scale factor |
| * @param[in] shift number of bits to shift the result by |
| * @param[out] *pDst points to output matrix structure |
| * @return The function returns either |
| * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking. |
| * |
| * @details |
| * <b>Scaling and Overflow Behavior:</b> |
| * \par |
| * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.15 format. |
| * These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format. |
| */ |
| |
| arm_status arm_mat_scale_q15( |
| const arm_matrix_instance_q15 * pSrc, |
| q15_t scaleFract, |
| int32_t shift, |
| arm_matrix_instance_q15 * pDst) |
| { |
| q15_t *pIn = pSrc->pData; /* input data matrix pointer */ |
| q15_t *pOut = pDst->pData; /* output data matrix pointer */ |
| uint32_t numSamples; /* total number of elements in the matrix */ |
| int32_t totShift = 15 - shift; /* total shift to apply after scaling */ |
| uint32_t blkCnt; /* loop counters */ |
| arm_status status; /* status of matrix scaling */ |
| |
| #ifndef ARM_MATH_CM0_FAMILY |
| |
| q15_t in1, in2, in3, in4; |
| q31_t out1, out2, out3, out4; |
| q31_t inA1, inA2; |
| |
| #endif // #ifndef ARM_MATH_CM0_FAMILY |
| |
| #ifdef ARM_MATH_MATRIX_CHECK |
| /* Check for matrix mismatch */ |
| if((pSrc->numRows != pDst->numRows) || (pSrc->numCols != pDst->numCols)) |
| { |
| /* Set status as ARM_MATH_SIZE_MISMATCH */ |
| status = ARM_MATH_SIZE_MISMATCH; |
| } |
| else |
| #endif // #ifdef ARM_MATH_MATRIX_CHECK |
| { |
| /* Total number of samples in the input matrix */ |
| numSamples = (uint32_t) pSrc->numRows * pSrc->numCols; |
| |
| #ifndef ARM_MATH_CM0_FAMILY |
| |
| /* Run the below code for Cortex-M4 and Cortex-M3 */ |
| /* Loop Unrolling */ |
| blkCnt = numSamples >> 2; |
| |
| /* First part of the processing with loop unrolling. Compute 4 outputs at a time. |
| ** a second loop below computes the remaining 1 to 3 samples. */ |
| while(blkCnt > 0u) |
| { |
| /* C(m,n) = A(m,n) * k */ |
| /* Scale, saturate and then store the results in the destination buffer. */ |
| /* Reading 2 inputs from memory */ |
| inA1 = _SIMD32_OFFSET(pIn); |
| inA2 = _SIMD32_OFFSET(pIn + 2); |
| |
| /* C = A * scale */ |
| /* Scale the inputs and then store the 2 results in the destination buffer |
| * in single cycle by packing the outputs */ |
| out1 = (q31_t) ((q15_t) (inA1 >> 16) * scaleFract); |
| out2 = (q31_t) ((q15_t) inA1 * scaleFract); |
| out3 = (q31_t) ((q15_t) (inA2 >> 16) * scaleFract); |
| out4 = (q31_t) ((q15_t) inA2 * scaleFract); |
| |
| out1 = out1 >> totShift; |
| inA1 = _SIMD32_OFFSET(pIn + 4); |
| out2 = out2 >> totShift; |
| inA2 = _SIMD32_OFFSET(pIn + 6); |
| out3 = out3 >> totShift; |
| out4 = out4 >> totShift; |
| |
| in1 = (q15_t) (__SSAT(out1, 16)); |
| in2 = (q15_t) (__SSAT(out2, 16)); |
| in3 = (q15_t) (__SSAT(out3, 16)); |
| in4 = (q15_t) (__SSAT(out4, 16)); |
| |
| _SIMD32_OFFSET(pOut) = __PKHBT(in2, in1, 16); |
| _SIMD32_OFFSET(pOut + 2) = __PKHBT(in4, in3, 16); |
| |
| /* update pointers to process next sampels */ |
| pIn += 4u; |
| pOut += 4u; |
| |
| |
| /* Decrement the numSamples loop counter */ |
| blkCnt--; |
| } |
| |
| /* If the numSamples is not a multiple of 4, compute any remaining output samples here. |
| ** No loop unrolling is used. */ |
| blkCnt = numSamples % 0x4u; |
| |
| #else |
| |
| /* Run the below code for Cortex-M0 */ |
| |
| /* Initialize blkCnt with number of samples */ |
| blkCnt = numSamples; |
| |
| #endif /* #ifndef ARM_MATH_CM0_FAMILY */ |
| |
| while(blkCnt > 0u) |
| { |
| /* C(m,n) = A(m,n) * k */ |
| /* Scale, saturate and then store the results in the destination buffer. */ |
| *pOut++ = |
| (q15_t) (__SSAT(((q31_t) (*pIn++) * scaleFract) >> totShift, 16)); |
| |
| /* Decrement the numSamples loop counter */ |
| blkCnt--; |
| } |
| /* Set status as ARM_MATH_SUCCESS */ |
| status = ARM_MATH_SUCCESS; |
| } |
| |
| /* Return to application */ |
| return (status); |
| } |
| |
| /** |
| * @} end of MatrixScale group |
| */ |