summaryrefslogtreecommitdiff
path: root/DSP/Source/MatrixFunctions/arm_mat_sub_q31.c
diff options
context:
space:
mode:
Diffstat (limited to 'DSP/Source/MatrixFunctions/arm_mat_sub_q31.c')
-rw-r--r--DSP/Source/MatrixFunctions/arm_mat_sub_q31.c145
1 files changed, 44 insertions, 101 deletions
diff --git a/DSP/Source/MatrixFunctions/arm_mat_sub_q31.c b/DSP/Source/MatrixFunctions/arm_mat_sub_q31.c
index 3bf5508..40d1bef 100644
--- a/DSP/Source/MatrixFunctions/arm_mat_sub_q31.c
+++ b/DSP/Source/MatrixFunctions/arm_mat_sub_q31.c
@@ -3,13 +3,13 @@
* Title: arm_mat_sub_q31.c
* Description: Q31 matrix subtraction
*
- * $Date: 27. January 2017
- * $Revision: V.1.5.1
+ * $Date: 18. March 2019
+ * $Revision: V1.6.0
*
* Target Processor: Cortex-M cores
* -------------------------------------------------------------------- */
/*
- * Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved.
+ * Copyright (C) 2010-2019 ARM Limited or its affiliates. All rights reserved.
*
* SPDX-License-Identifier: Apache-2.0
*
@@ -29,157 +29,100 @@
#include "arm_math.h"
/**
- * @ingroup groupMatrix
+ @ingroup groupMatrix
*/
/**
- * @addtogroup MatrixSub
- * @{
+ @addtogroup MatrixSub
+ @{
*/
/**
- * @brief Q31 matrix subtraction.
- * @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
- * @return The function returns either
- * <code>ARM_MATH_SIZE_MISMATCH</code> or <code>ARM_MATH_SUCCESS</code> based on the outcome of size checking.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] will be saturated.
+ @brief Q31 matrix subtraction.
+ @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
+ @return execution status
+ - \ref ARM_MATH_SUCCESS : Operation successful
+ - \ref ARM_MATH_SIZE_MISMATCH : Matrix size check failed
+
+ @par Scaling and Overflow Behavior
+ The function uses saturating arithmetic.
+ Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] are saturated.
*/
-
arm_status arm_mat_sub_q31(
const arm_matrix_instance_q31 * pSrcA,
const arm_matrix_instance_q31 * pSrcB,
- arm_matrix_instance_q31 * pDst)
+ arm_matrix_instance_q31 * pDst)
{
- q31_t *pIn1 = pSrcA->pData; /* input data matrix pointer A */
- q31_t *pIn2 = pSrcB->pData; /* input data matrix pointer B */
+ q31_t *pInA = pSrcA->pData; /* input data matrix pointer A */
+ q31_t *pInB = pSrcB->pData; /* input data matrix pointer B */
q31_t *pOut = pDst->pData; /* output data matrix pointer */
- q31_t inA1, inB1; /* temporary variables */
-
-#if defined (ARM_MATH_DSP)
-
- q31_t inA2, inB2; /* temporary variables */
- q31_t out1, out2; /* temporary variables */
-#endif // #if defined (ARM_MATH_DSP)
-
- uint32_t numSamples; /* total number of elements in the matrix */
+ uint32_t numSamples; /* total number of elements in the matrix */
uint32_t blkCnt; /* loop counters */
arm_status status; /* status of matrix subtraction */
-
#ifdef ARM_MATH_MATRIX_CHECK
- /* Check for matrix mismatch condition */
+
+ /* Check for matrix mismatch condition */
if ((pSrcA->numRows != pSrcB->numRows) ||
- (pSrcA->numCols != pSrcB->numCols) ||
- (pSrcA->numRows != pDst->numRows) || (pSrcA->numCols != pDst->numCols))
+ (pSrcA->numCols != pSrcB->numCols) ||
+ (pSrcA->numRows != pDst->numRows) ||
+ (pSrcA->numCols != pDst->numCols) )
{
/* Set status as ARM_MATH_SIZE_MISMATCH */
status = ARM_MATH_SIZE_MISMATCH;
}
else
-#endif
+
+#endif /* #ifdef ARM_MATH_MATRIX_CHECK */
+
{
- /* Total number of samples in the input matrix */
+ /* Total number of samples in input matrix */
numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols;
-#if defined (ARM_MATH_DSP)
-
- /* Run the below code for Cortex-M4 and Cortex-M3 */
+#if defined (ARM_MATH_LOOPUNROLL)
- /* Loop Unrolling */
+ /* Loop unrolling: Compute 4 outputs at a time */
blkCnt = numSamples >> 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(m,n) = A(m,n) - B(m,n) */
- /* Subtract, saturate and then store the results in the destination buffer. */
- /* Read values from source A */
- inA1 = pIn1[0];
-
- /* Read values from source B */
- inB1 = pIn2[0];
-
- /* Read values from source A */
- inA2 = pIn1[1];
- /* Subtract and saturate */
- out1 = __QSUB(inA1, inB1);
-
- /* Read values from source B */
- inB2 = pIn2[1];
-
- /* Read values from source A */
- inA1 = pIn1[2];
-
- /* Subtract and saturate */
- out2 = __QSUB(inA2, inB2);
-
- /* Read values from source B */
- inB1 = pIn2[2];
-
- /* Store result in destination */
- pOut[0] = out1;
- pOut[1] = out2;
-
- /* Read values from source A */
- inA2 = pIn1[3];
-
- /* Read values from source B */
- inB2 = pIn2[3];
-
- /* Subtract and saturate */
- out1 = __QSUB(inA1, inB1);
+ /* Subtract, saturate and then store the results in the destination buffer. */
+ *pOut++ = __QSUB(*pInA++, *pInB++);
- /* Subtract and saturate */
- out2 = __QSUB(inA2, inB2);
+ *pOut++ = __QSUB(*pInA++, *pInB++);
- /* Store result in destination */
- pOut[2] = out1;
- pOut[3] = out2;
+ *pOut++ = __QSUB(*pInA++, *pInB++);
- /* update pointers to process next samples */
- pIn1 += 4U;
- pIn2 += 4U;
- pOut += 4U;
+ *pOut++ = __QSUB(*pInA++, *pInB++);
- /* Decrement the loop counter */
+ /* Decrement loop counter */
blkCnt--;
}
- /* If the numSamples is not a multiple of 4, compute any remaining output samples here.
- ** No loop unrolling is used. */
+ /* Loop unrolling: Compute remaining outputs */
blkCnt = numSamples % 0x4U;
#else
- /* Run the below code for Cortex-M0 */
-
/* Initialize blkCnt with number of samples */
blkCnt = numSamples;
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
while (blkCnt > 0U)
{
/* C(m,n) = A(m,n) - B(m,n) */
- /* Subtract, saturate and then store the results in the destination buffer. */
- inA1 = *pIn1++;
- inB1 = *pIn2++;
-
- inA1 = __QSUB(inA1, inB1);
- *pOut++ = inA1;
+ /* Subtract, saturate and store result in destination buffer. */
+ *pOut++ = __QSUB(*pInA++, *pInB++);
- /* Decrement the loop counter */
+ /* Decrement loop counter */
blkCnt--;
}
@@ -192,5 +135,5 @@ arm_status arm_mat_sub_q31(
}
/**
- * @} end of MatrixSub group
+ @} end of MatrixSub group
*/
generated by cgit (git 2.34.1) at 2024-11-16 02:04:33 +0000