From 86608c6770cf08c138a2bdab5855072f64be09ef Mon Sep 17 00:00:00 2001
From: joshua <joshua@joshuayun.com>
Date: Sat, 30 Dec 2023 23:54:31 -0500
Subject: initial commit

---
 .../DSP/Source/MatrixFunctions/arm_mat_sub_q15.c   | 144 +++++++++++++++++++++
 1 file changed, 144 insertions(+)
 create mode 100644 Drivers/CMSIS/DSP/Source/MatrixFunctions/arm_mat_sub_q15.c

(limited to 'Drivers/CMSIS/DSP/Source/MatrixFunctions/arm_mat_sub_q15.c')

diff --git a/Drivers/CMSIS/DSP/Source/MatrixFunctions/arm_mat_sub_q15.c b/Drivers/CMSIS/DSP/Source/MatrixFunctions/arm_mat_sub_q15.c
new file mode 100644
index 0000000..37496ea
--- /dev/null
+++ b/Drivers/CMSIS/DSP/Source/MatrixFunctions/arm_mat_sub_q15.c
@@ -0,0 +1,144 @@
+/* ----------------------------------------------------------------------
+ * Project:      CMSIS DSP Library
+ * Title:        arm_mat_sub_q15.c
+ * Description:  Q15 Matrix subtraction
+ *
+ * $Date:        18. March 2019
+ * $Revision:    V1.6.0
+ *
+ * Target Processor: Cortex-M cores
+ * -------------------------------------------------------------------- */
+/*
+ * Copyright (C) 2010-2019 ARM Limited or its affiliates. All rights reserved.
+ *
+ * SPDX-License-Identifier: Apache-2.0
+ *
+ * Licensed under the Apache License, Version 2.0 (the License); you may
+ * not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an AS IS BASIS, WITHOUT
+ * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include "arm_math.h"
+
+/**
+  @ingroup groupMatrix
+ */
+
+/**
+  @addtogroup MatrixSub
+  @{
+ */
+
+/**
+  @brief         Q15 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 Q15 range [0x8000 0x7FFF] are saturated.
+ */
+
+arm_status arm_mat_sub_q15(
+  const arm_matrix_instance_q15 * pSrcA,
+  const arm_matrix_instance_q15 * pSrcB,
+        arm_matrix_instance_q15 * pDst)
+{
+        q15_t *pInA = pSrcA->pData;                    /* input data matrix pointer A */
+        q15_t *pInB = pSrcB->pData;                    /* input data matrix pointer B */
+        q15_t *pOut = pDst->pData;                     /* output data matrix pointer */
+
+        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 */
+  if ((pSrcA->numRows != pSrcB->numRows) ||
+      (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 /* #ifdef ARM_MATH_MATRIX_CHECK */
+
+  {
+    /* Total number of samples in input matrix */
+    numSamples = (uint32_t) pSrcA->numRows * pSrcA->numCols;
+
+#if defined (ARM_MATH_LOOPUNROLL)
+
+    /* Loop unrolling: Compute 4 outputs at a time */
+    blkCnt = numSamples >> 2U;
+
+    while (blkCnt > 0U)
+    {
+      /* C(m,n) = A(m,n) - B(m,n) */
+
+      /* Subtract, Saturate and store result in destination buffer. */
+#if defined (ARM_MATH_DSP)
+      write_q15x2_ia (&pOut, __QSUB16(read_q15x2_ia ((q15_t **) &pInA), read_q15x2_ia ((q15_t **) &pInB)));
+      write_q15x2_ia (&pOut, __QSUB16(read_q15x2_ia ((q15_t **) &pInA), read_q15x2_ia ((q15_t **) &pInB)));
+#else
+      *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16);
+      *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16);
+      *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16);
+      *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16);
+#endif
+
+      /* Decrement loop counter */
+      blkCnt--;
+    }
+
+    /* Loop unrolling: Compute remaining outputs */
+    blkCnt = numSamples % 0x4U;
+
+#else
+
+    /* Initialize blkCnt with number of samples */
+    blkCnt = numSamples;
+
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
+    while (blkCnt > 0U)
+    {
+      /* C(m,n) = A(m,n) - B(m,n) */
+
+      /* Subtract and store result in destination buffer. */
+#if defined (ARM_MATH_DSP)
+      *pOut++ = (q15_t) __QSUB16(*pInA++, *pInB++);
+#else
+      *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ - *pInB++), 16);
+#endif
+
+      /* Decrement loop counter */
+      blkCnt--;
+    }
+
+    /* Set status as ARM_MATH_SUCCESS */
+    status = ARM_MATH_SUCCESS;
+  }
+
+  /* Return to application */
+  return (status);
+}
+
+/**
+  @} end of MatrixSub group
+ */
-- 
cgit v1.2.3