Official ARM version: v5.4.0

    Add CMSIS V5.4.0, please refer to index.html available under \docs folder.

    Note: content of \CMSIS\Core\Include has been copied under \Include to keep the same structure
         used in existing projects, and thus avoid projects mass update
    Note: the following components have been removed from ARM original delivery (as not used in ST packages)
        - CMSIS_EW2018.pdf
        - .gitattributes
        - .gitignore
        - \Device
        - \CMSIS
           - \CoreValidation
		   - \DAP
           - \Documentation
           - \DoxyGen
           - \Driver
           - \Pack
           - \RTOS\CMSIS_RTOS_Tutorial.pdf
           - \RTOS\RTX
           - \RTOS\Template
           - \RTOS2\RTX
           - \Utilities
           - All ARM/GCC projects files are deleted from \DSP, \RTOS and \RTOS2

Change-Id: Ia026c3f0f0d016627a4fb5a9032852c33d24b4d3

1 files changed, 151 insertions, 0 deletions

diff --git a/DSP/Source/MatrixFunctions/arm_mat_add_q15.c b/DSP/Source/MatrixFunctions/arm_mat_add_q15.c
new file mode 100644
index 0000000..896e60c
--- /dev/null
+++ b/DSP/Source/MatrixFunctions/arm_mat_add_q15.c
@@ -0,0 +1,151 @@
+/* ----------------------------------------------------------------------
+ * Project:      CMSIS DSP Library
+ * Title:        arm_mat_add_q15.c
+ * Description:  Q15 matrix addition
+ *
+ * $Date:        27. January 2017
+ * $Revision:    V.1.5.1
+ *
+ * Target Processor: Cortex-M cores
+ * -------------------------------------------------------------------- */
+/*
+ * Copyright (C) 2010-2017 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 MatrixAdd
+ * @{
+ */
+
+/**
+ * @brief Q15 matrix addition.
+ * @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 Q15 range [0x8000 0x7FFF] will be saturated.
+ */
+
+arm_status arm_mat_add_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 */
+  uint16_t numSamples;                           /* total number of elements in the matrix  */
+  uint32_t blkCnt;                               /* loop counters  */
+  arm_status status;                             /* status of matrix addition  */
+
+#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 the input matrix */
+    numSamples = (uint16_t) (pSrcA->numRows * pSrcA->numCols);
+
+#if defined (ARM_MATH_DSP)
+
+    /* Run the below code for Cortex-M4 and Cortex-M3 */
+
+    /* Loop unrolling */
+    blkCnt = (uint32_t) 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) */
+      /* Add, Saturate and then store the results in the destination buffer. */
+      *__SIMD32(pOut)++ = __QADD16(*__SIMD32(pInA)++, *__SIMD32(pInB)++);
+      *__SIMD32(pOut)++ = __QADD16(*__SIMD32(pInA)++, *__SIMD32(pInB)++);
+
+      /* 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 = (uint32_t) numSamples % 0x4U;
+
+    /* q15 pointers of input and output are initialized */
+
+    while (blkCnt > 0U)
+    {
+      /* C(m,n) = A(m,n) + B(m,n) */
+      /* Add, Saturate and then store the results in the destination buffer. */
+      *pOut++ = (q15_t) __QADD16(*pInA++, *pInB++);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+#else
+
+    /* Run the below code for Cortex-M0 */
+
+    /* Initialize blkCnt with number of samples */
+    blkCnt = (uint32_t) numSamples;
+
+
+    /* q15 pointers of input and output are initialized */
+    while (blkCnt > 0U)
+    {
+      /* C(m,n) = A(m,n) + B(m,n) */
+      /* Add, Saturate and then store the results in the destination buffer. */
+      *pOut++ = (q15_t) __SSAT(((q31_t) * pInA++ + *pInB++), 16);
+
+      /* Decrement the loop counter */
+      blkCnt--;
+    }
+
+#endif /* #if defined (ARM_MATH_DSP) */
+
+    /* set status as ARM_MATH_SUCCESS */
+    status = ARM_MATH_SUCCESS;
+  }
+
+  /* Return to application */
+  return (status);
+}
+
+/**
+ * @} end of MatrixAdd group
+ */