From 13fc6703862862f4263d8d5d085b7a16b87190e1 Mon Sep 17 00:00:00 2001 From: Lorenz Meier Date: Sun, 28 Apr 2013 09:54:11 +0200 Subject: Moved last libs, drivers and headers, cleaned up IO build --- .../Source/BasicMathFunctions/arm_add_q15.c | 135 +++++++++++++++++++++ 1 file changed, 135 insertions(+) create mode 100644 src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q15.c (limited to 'src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q15.c') diff --git a/src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q15.c b/src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q15.c new file mode 100644 index 000000000..788b2ebb2 --- /dev/null +++ b/src/modules/mathlib/CMSIS/DSP_Lib/Source/BasicMathFunctions/arm_add_q15.c @@ -0,0 +1,135 @@ +/* ---------------------------------------------------------------------- +* Copyright (C) 2010 ARM Limited. All rights reserved. +* +* $Date: 15. February 2012 +* $Revision: V1.1.0 +* +* Project: CMSIS DSP Library +* Title: arm_add_q15.c +* +* Description: Q15 vector addition +* +* Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 +* +* Version 1.1.0 2012/02/15 +* Updated with more optimizations, bug fixes and minor API changes. +* +* Version 1.0.10 2011/7/15 +* Big Endian support added and Merged M0 and M3/M4 Source code. +* +* Version 1.0.3 2010/11/29 +* Re-organized the CMSIS folders and updated documentation. +* +* Version 1.0.2 2010/11/11 +* Documentation updated. +* +* Version 1.0.1 2010/10/05 +* Production release and review comments incorporated. +* +* Version 1.0.0 2010/09/20 +* Production release and review comments incorporated. +* +* Version 0.0.7 2010/06/10 +* Misra-C changes done +* -------------------------------------------------------------------- */ + +#include "arm_math.h" + +/** + * @ingroup groupMath + */ + +/** + * @addtogroup BasicAdd + * @{ + */ + +/** + * @brief Q15 vector addition. + * @param[in] *pSrcA points to the first input vector + * @param[in] *pSrcB points to the second input vector + * @param[out] *pDst points to the output vector + * @param[in] blockSize number of samples in each vector + * @return none. + * + * Scaling and Overflow Behavior: + * \par + * The function uses saturating arithmetic. + * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated. + */ + +void arm_add_q15( + q15_t * pSrcA, + q15_t * pSrcB, + q15_t * pDst, + uint32_t blockSize) +{ + uint32_t blkCnt; /* loop counter */ + +#ifndef ARM_MATH_CM0 + +/* Run the below code for Cortex-M4 and Cortex-M3 */ + q31_t inA1, inA2, inB1, inB2; + + /*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) + { + /* C = A + B */ + /* Add and then store the results in the destination buffer. */ + inA1 = *__SIMD32(pSrcA)++; + inA2 = *__SIMD32(pSrcA)++; + inB1 = *__SIMD32(pSrcB)++; + inB2 = *__SIMD32(pSrcB)++; + + *__SIMD32(pDst)++ = __QADD16(inA1, inB1); + *__SIMD32(pDst)++ = __QADD16(inA2, inB2); + + /* 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; + + while(blkCnt > 0u) + { + /* C = A + B */ + /* Add and then store the results in the destination buffer. */ + *pDst++ = (q15_t) __QADD16(*pSrcA++, *pSrcB++); + + /* Decrement the loop counter */ + blkCnt--; + } + +#else + + /* Run the below code for Cortex-M0 */ + + + + /* Initialize blkCnt with number of samples */ + blkCnt = blockSize; + + while(blkCnt > 0u) + { + /* C = A + B */ + /* Add and then store the results in the destination buffer. */ + *pDst++ = (q15_t) __SSAT(((q31_t) * pSrcA++ + *pSrcB++), 16); + + /* Decrement the loop counter */ + blkCnt--; + } + +#endif /* #ifndef ARM_MATH_CM0 */ + + +} + +/** + * @} end of BasicAdd group + */ -- cgit v1.2.3