diff --git a/Source/MatrixFunctions/arm_mat_mult_q15.c b/Source/MatrixFunctions/arm_mat_mult_q15.c index 9e8d26dd..821355ba 100644 --- a/Source/MatrixFunctions/arm_mat_mult_q15.c +++ b/Source/MatrixFunctions/arm_mat_mult_q15.c @@ -1,24 +1,24 @@ -/* ---------------------------------------------------------------------- -* Copyright (C) 2010-2014 ARM Limited. All rights reserved. -* +/* ---------------------------------------------------------------------- +* 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_mult_q15.c -* -* Description: Q15 matrix multiplication. -* +* $Revision: V.1.4.5a +* +* Project: CMSIS DSP Library +* Title: arm_mat_mult_q15.c +* +* Description: Q15 matrix multiplication. +* * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0 -* -* Redistribution and use in source and binary forms, with or without +* +* 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 +* 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 @@ -27,7 +27,7 @@ * 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 +* 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; @@ -35,52 +35,52 @@ * 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. +* POSSIBILITY OF SUCH DAMAGE. * -------------------------------------------------------------------- */ #include "arm_math.h" -/** - * @ingroup groupMatrix +/** + * @ingroup groupMatrix */ -/** - * @addtogroup MatrixMult - * @{ +/** + * @addtogroup MatrixMult + * @{ */ -/** - * @brief Q15 matrix multiplication - * @param[in] *pSrcA points to the first input matrix structure - * @param[in] *pSrcB points to the second input matrix structure - * @param[out] *pDst points to output matrix structure - * @param[in] *pState points to the array for storing intermediate results (Unused) - * @return The function returns either - * ARM_MATH_SIZE_MISMATCH or ARM_MATH_SUCCESS based on the outcome of size checking. - * - * @details - * Scaling and Overflow Behavior: - * - * \par - * The function is implemented using a 64-bit internal accumulator. The inputs to the - * multiplications are in 1.15 format and multiplications yield a 2.30 result. - * The 2.30 intermediate - * results are accumulated in a 64-bit accumulator in 34.30 format. This approach - * provides 33 guard bits and there is no risk of overflow. The 34.30 result is then - * truncated to 34.15 format by discarding the low 15 bits and then saturated to - * 1.15 format. - * - * \par - * Refer to arm_mat_mult_fast_q15() for a faster but less precise version of this function for Cortex-M3 and Cortex-M4. - * +/** + * @brief Q15 matrix multiplication + * @param[in] *pSrcA points to the first input matrix structure + * @param[in] *pSrcB points to the second input matrix structure + * @param[out] *pDst points to output matrix structure + * @param[in] *pState points to the array for storing intermediate results (Unused) + * @return The function returns either + * ARM_MATH_SIZE_MISMATCH or ARM_MATH_SUCCESS based on the outcome of size checking. + * + * @details + * Scaling and Overflow Behavior: + * + * \par + * The function is implemented using a 64-bit internal accumulator. The inputs to the + * multiplications are in 1.15 format and multiplications yield a 2.30 result. + * The 2.30 intermediate + * results are accumulated in a 64-bit accumulator in 34.30 format. This approach + * provides 33 guard bits and there is no risk of overflow. The 34.30 result is then + * truncated to 34.15 format by discarding the low 15 bits and then saturated to + * 1.15 format. + * + * \par + * Refer to arm_mat_mult_fast_q15() for a faster but less precise version of this function for Cortex-M3 and Cortex-M4. + * */ arm_status arm_mat_mult_q15( const arm_matrix_instance_q15 * pSrcA, const arm_matrix_instance_q15 * pSrcB, arm_matrix_instance_q15 * pDst, - q15_t * pState CMSIS_UNUSED) + q15_t * pState) { q63_t sum; /* accumulator */ @@ -109,7 +109,7 @@ arm_status arm_mat_mult_q15( q15_t in; /* Temporary variable to hold the input value */ q15_t inA1, inB1, inA2, inB2; -#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ +#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ #ifdef ARM_MATH_MATRIX_CHECK /* Check for matrix mismatch condition */ @@ -131,7 +131,7 @@ arm_status arm_mat_mult_q15( /* The pointer px is set to starting address of the column being processed */ px = pSrcBT + i; - /* First part of the processing with loop unrolling. Compute 4 outputs at a time. + /* 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(col > 0u) { @@ -149,7 +149,7 @@ arm_status arm_mat_mult_q15( *px = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); -#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ +#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ /* Update the pointer px to point to the next row of the transposed matrix */ px += numRowsB; @@ -163,7 +163,7 @@ arm_status arm_mat_mult_q15( *px = (q15_t) in; -#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ +#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ /* Update the pointer px to point to the next row of the transposed matrix */ px += numRowsB; @@ -180,7 +180,7 @@ arm_status arm_mat_mult_q15( *px = (q15_t) ((in & (q31_t) 0xffff0000) >> 16); -#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ +#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ /* Update the pointer px to point to the next row of the transposed matrix */ px += numRowsB; @@ -195,7 +195,7 @@ arm_status arm_mat_mult_q15( *px = (q15_t) in; -#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ +#endif /* #ifndef ARM_MATH_BIG_ENDIAN */ /* Update the pointer px to point to the next row of the transposed matrix */ px += numRowsB; @@ -207,7 +207,7 @@ arm_status arm_mat_mult_q15( /* Store one element in the destination */ *px = in; - + /* Update the pointer px to point to the next row of the transposed matrix */ px += numRowsB; @@ -216,7 +216,7 @@ arm_status arm_mat_mult_q15( /* Store one element in the destination */ *px = in; - + /* Update the pointer px to point to the next row of the transposed matrix */ px += numRowsB; @@ -225,7 +225,7 @@ arm_status arm_mat_mult_q15( /* Store one element in the destination */ *px = in; - + /* Update the pointer px to point to the next row of the transposed matrix */ px += numRowsB; @@ -234,17 +234,17 @@ arm_status arm_mat_mult_q15( /* Store one element in the destination */ *px = in; - + /* Update the pointer px to point to the next row of the transposed matrix */ px += numRowsB; -#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ +#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ /* Decrement the column loop counter */ col--; } - /* If the columns of pSrcB is not a multiple of 4, compute any remaining output samples here. + /* If the columns of pSrcB is not a multiple of 4, compute any remaining output samples here. ** No loop unrolling is used. */ col = numColsB % 0x4u; @@ -279,7 +279,7 @@ arm_status arm_mat_mult_q15( /* For every row wise process, the column loop counter is to be initiated */ col = numColsB; - /* For every row wise process, the pIn2 pointer is set + /* For every row wise process, the pIn2 pointer is set ** to the starting address of the transposed pSrcB data */ pInB = pSrcBT; @@ -333,7 +333,7 @@ arm_status arm_mat_mult_q15( sum += inA1 * inB1; sum += inA2 * inB2; -#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ +#endif /* #ifndef UNALIGNED_SUPPORT_DISABLE */ /* Decrement the loop counter */ colCnt--; @@ -393,7 +393,7 @@ arm_status arm_mat_mult_q15( status = ARM_MATH_SIZE_MISMATCH; } else -#endif /* #ifdef ARM_MATH_MATRIX_CHECK */ +#endif /* #ifdef ARM_MATH_MATRIX_CHECK */ { /* The following loop performs the dot-product of each row in pSrcA with each column in pSrcB */ @@ -406,7 +406,7 @@ arm_status arm_mat_mult_q15( /* For every row wise process, the column loop counter is to be initiated */ col = numColsB; - /* For every row wise process, the pIn2 pointer is set + /* For every row wise process, the pIn2 pointer is set ** to the starting address of the pSrcB data */ pIn2 = pSrcB->pData; @@ -464,6 +464,6 @@ arm_status arm_mat_mult_q15( return (status); } -/** - * @} end of MatrixMult group +/** + * @} end of MatrixMult group */