From 76177aa280494bb36d7a0bcbda1078d4db717020 Mon Sep 17 00:00:00 2001 From: Ali Labbene Date: Mon, 9 Dec 2019 11:25:19 +0100 Subject: Official ARM version: v4.5 --- DSP_Lib/Source/StatisticsFunctions/arm_power_q7.c | 141 ++++++++++++++++++++++ 1 file changed, 141 insertions(+) create mode 100644 DSP_Lib/Source/StatisticsFunctions/arm_power_q7.c (limited to 'DSP_Lib/Source/StatisticsFunctions/arm_power_q7.c') diff --git a/DSP_Lib/Source/StatisticsFunctions/arm_power_q7.c b/DSP_Lib/Source/StatisticsFunctions/arm_power_q7.c new file mode 100644 index 0000000..4f38156 --- /dev/null +++ b/DSP_Lib/Source/StatisticsFunctions/arm_power_q7.c @@ -0,0 +1,141 @@ +/* ---------------------------------------------------------------------- +* Copyright (C) 2010-2014 ARM Limited. All rights reserved. +* +* $Date: 19. March 2015 +* $Revision: V.1.4.5 +* +* Project: CMSIS DSP Library +* Title: arm_power_q7.c +* +* Description: Sum of the squares of the elements of a Q7 vector. +* +* 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 groupStats + */ + +/** + * @addtogroup power + * @{ + */ + +/** + * @brief Sum of the squares of the elements of a Q7 vector. + * @param[in] *pSrc points to the input vector + * @param[in] blockSize length of the input vector + * @param[out] *pResult sum of the squares value returned here + * @return none. + * + * @details + * Scaling and Overflow Behavior: + * + * \par + * The function is implemented using a 32-bit internal accumulator. + * The input is represented in 1.7 format. + * Intermediate multiplication yields a 2.14 format, and this + * result is added without saturation to an accumulator in 18.14 format. + * With 17 guard bits in the accumulator, there is no risk of overflow, and the + * full precision of the intermediate multiplication is preserved. + * Finally, the return result is in 18.14 format. + * + */ + +void arm_power_q7( + q7_t * pSrc, + uint32_t blockSize, + q31_t * pResult) +{ + q31_t sum = 0; /* Temporary result storage */ + q7_t in; /* Temporary variable to store input */ + uint32_t blkCnt; /* loop counter */ + +#ifndef ARM_MATH_CM0_FAMILY + + /* Run the below code for Cortex-M4 and Cortex-M3 */ + + q31_t input1; /* Temporary variable to store packed input */ + q31_t in1, in2; /* Temporary variables to store input */ + + /*loop Unrolling */ + blkCnt = blockSize >> 2u; + + /* 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) + { + /* Reading two inputs of pSrc vector and packing */ + input1 = *__SIMD32(pSrc)++; + + in1 = __SXTB16(__ROR(input1, 8)); + in2 = __SXTB16(input1); + + /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ + /* calculate power and accumulate to accumulator */ + sum = __SMLAD(in1, in1, sum); + sum = __SMLAD(in2, in2, sum); + + /* Decrement the loop counter */ + blkCnt--; + } + + /* If the blockSize is not a multiple of 4, compute any remaining output samples here. + ** No loop unrolling is used. */ + blkCnt = blockSize % 0x4u; + +#else + + /* Run the below code for Cortex-M0 */ + + /* Loop over blockSize number of values */ + blkCnt = blockSize; + +#endif /* #ifndef ARM_MATH_CM0_FAMILY */ + + while(blkCnt > 0u) + { + /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */ + /* Compute Power and then store the result in a temporary variable, sum. */ + in = *pSrc++; + sum += ((q15_t) in * in); + + /* Decrement the loop counter */ + blkCnt--; + } + + /* Store the result in 18.14 format */ + *pResult = sum; +} + +/** + * @} end of power group + */ -- cgit