Official ARM version: v5.6.0HEADmaster

37 files changed, 2282 insertions, 2445 deletions

diff --git a/DSP/Source/BasicMathFunctions/BasicMathFunctions.c b/DSP/Source/BasicMathFunctions/BasicMathFunctions.c
new file mode 100644
index 0000000..b444c11
--- /dev/null
+++ b/DSP/Source/BasicMathFunctions/BasicMathFunctions.c
@@ -0,0 +1,63 @@
+/* ----------------------------------------------------------------------
+ * Project:      CMSIS DSP Library
+ * Title:        BasicMathFunctions.c
+ * Description:  Combination of all basic math function source files.
+ *
+ * $Date:        18. March 2019
+ * $Revision:    V1.0.0
+ *
+ * Target Processor: Cortex-M cores
+ * -------------------------------------------------------------------- */
+/*
+ * Copyright (C) 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_abs_f32.c"
+#include "arm_abs_q15.c"
+#include "arm_abs_q31.c"
+#include "arm_abs_q7.c"
+#include "arm_add_f32.c"
+#include "arm_add_q15.c"
+#include "arm_add_q31.c"
+#include "arm_add_q7.c"
+#include "arm_dot_prod_f32.c"
+#include "arm_dot_prod_q15.c"
+#include "arm_dot_prod_q31.c"
+#include "arm_dot_prod_q7.c"
+#include "arm_mult_f32.c"
+#include "arm_mult_q15.c"
+#include "arm_mult_q31.c"
+#include "arm_mult_q7.c"
+#include "arm_negate_f32.c"
+#include "arm_negate_q15.c"
+#include "arm_negate_q31.c"
+#include "arm_negate_q7.c"
+#include "arm_offset_f32.c"
+#include "arm_offset_q15.c"
+#include "arm_offset_q31.c"
+#include "arm_offset_q7.c"
+#include "arm_scale_f32.c"
+#include "arm_scale_q15.c"
+#include "arm_scale_q31.c"
+#include "arm_scale_q7.c"
+#include "arm_shift_q15.c"
+#include "arm_shift_q31.c"
+#include "arm_shift_q7.c"
+#include "arm_sub_f32.c"
+#include "arm_sub_q15.c"
+#include "arm_sub_q31.c"
+#include "arm_sub_q7.c"
diff --git a/DSP/Source/BasicMathFunctions/CMakeLists.txt b/DSP/Source/BasicMathFunctions/CMakeLists.txt
new file mode 100644
index 0000000..717669f
--- /dev/null
+++ b/DSP/Source/BasicMathFunctions/CMakeLists.txt
@@ -0,0 +1,16 @@
+cmake_minimum_required (VERSION 3.6)
+
+project(CMSISDSPBasicMath)
+
+
+file(GLOB SRC "./*_*.c")
+
+add_library(CMSISDSPBasicMath STATIC ${SRC})
+
+configdsp(CMSISDSPBasicMath ..)
+
+### Includes
+target_include_directories(CMSISDSPBasicMath PUBLIC "${DSP}/../../Include")
+
+
+
diff --git a/DSP/Source/BasicMathFunctions/arm_abs_f32.c b/DSP/Source/BasicMathFunctions/arm_abs_f32.c
index f88ef95..a7d2624 100644
--- a/DSP/Source/BasicMathFunctions/arm_abs_f32.c
+++ b/DSP/Source/BasicMathFunctions/arm_abs_f32.c
@@ -3,13 +3,13 @@
  * Title:        arm_abs_f32.c
  * Description:  Floating-point vector absolute value
  *
- * $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
  *
@@ -30,124 +30,117 @@
 #include <math.h>
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @defgroup BasicAbs Vector Absolute Value
- *
- * Computes the absolute value of a vector on an element-by-element basis.
- *
- * <pre>
- *     pDst[n] = abs(pSrc[n]),   0 <= n < blockSize.
- * </pre>
- *
- * The functions support in-place computation allowing the source and
- * destination pointers to reference the same memory buffer.
- * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+  @defgroup BasicAbs Vector Absolute Value
+
+  Computes the absolute value of a vector on an element-by-element basis.
+
+  <pre>
+      pDst[n] = abs(pSrc[n]),   0 <= n < blockSize.
+  </pre>
+
+  The functions support in-place computation allowing the source and
+  destination pointers to reference the same memory buffer.
+  There are separate functions for floating-point, Q7, Q15, and Q31 data types.
  */
 
 /**
- * @addtogroup BasicAbs
- * @{
+  @addtogroup BasicAbs
+  @{
  */
 
 /**
- * @brief Floating-point vector absolute value.
- * @param[in]       *pSrc points to the input buffer
- * @param[out]      *pDst points to the output buffer
- * @param[in]       blockSize number of samples in each vector
- * @return none.
+  @brief         Floating-point vector absolute value.
+  @param[in]     pSrc       points to the input vector
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
  */
 
 void arm_abs_f32(
-  float32_t * pSrc,
-  float32_t * pDst,
-  uint32_t blockSize)
+  const float32_t * pSrc,
+        float32_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
 
-  /* Run the below code for Cortex-M4 and Cortex-M3 */
-  float32_t in1, in2, in3, in4;                  /* temporary variables */
-
-  /*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| */
-    /* Calculate absolute and then store the results in the destination buffer. */
-    /* read sample from source */
-    in1 = *pSrc;
-    in2 = *(pSrc + 1);
-    in3 = *(pSrc + 2);
+#if defined(ARM_MATH_NEON)
+    float32x4_t vec1;
+    float32x4_t res;
 
-    /* find absolute value */
-    in1 = fabsf(in1);
+    /* Compute 4 outputs at a time */
+    blkCnt = blockSize >> 2U;
 
-    /* read sample from source */
-    in4 = *(pSrc + 3);
+    while (blkCnt > 0U)
+    {
+        /* C = |A| */
 
-    /* find absolute value */
-    in2 = fabsf(in2);
+    	/* Calculate absolute values and then store the results in the destination buffer. */
+        vec1 = vld1q_f32(pSrc);
+        res = vabsq_f32(vec1);
+        vst1q_f32(pDst, res);
 
-    /* read sample from source */
-    *pDst = in1;
+        /* Increment pointers */
+        pSrc += 4;
+        pDst += 4;
+        
+        /* Decrement the loop counter */
+        blkCnt--;
+    }
 
-    /* find absolute value */
-    in3 = fabsf(in3);
+    /* Tail */
+    blkCnt = blockSize & 0x3;
 
-    /* find absolute value */
-    in4 = fabsf(in4);
+#else
+#if defined (ARM_MATH_LOOPUNROLL)
 
-    /* store result to destination */
-    *(pDst + 1) = in2;
+  /* Loop unrolling: Compute 4 outputs at a time */
+  blkCnt = blockSize >> 2U;
 
-    /* store result to destination */
-    *(pDst + 2) = in3;
+  while (blkCnt > 0U)
+  {
+    /* C = |A| */
 
-    /* store result to destination */
-    *(pDst + 3) = in4;
+    /* Calculate absolute and store result in destination buffer. */
+    *pDst++ = fabsf(*pSrc++);
 
+    *pDst++ = fabsf(*pSrc++);
 
-    /* Update source pointer to process next sampels */
-    pSrc += 4U;
+    *pDst++ = fabsf(*pSrc++);
 
-    /* Update destination pointer to process next sampels */
-    pDst += 4U;
+    *pDst++ = fabsf(*pSrc++);
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /*   #if defined (ARM_MATH_DSP)   */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+#endif /* #if defined(ARM_MATH_NEON) */
 
   while (blkCnt > 0U)
   {
     /* C = |A| */
-    /* Calculate absolute and then store the results in the destination buffer. */
+
+    /* Calculate absolute and store result in destination buffer. */
     *pDst++ = fabsf(*pSrc++);
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of BasicAbs group
+  @} end of BasicAbs group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_abs_q15.c b/DSP/Source/BasicMathFunctions/arm_abs_q15.c
index ec47fff..eb944ce 100644
--- a/DSP/Source/BasicMathFunctions/arm_abs_q15.c
+++ b/DSP/Source/BasicMathFunctions/arm_abs_q15.c
@@ -3,13 +3,13 @@
  * Title:        arm_abs_q15.c
  * Description:  Q15 vector absolute value
  *
- * $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
  *
@@ -29,139 +29,104 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicAbs
- * @{
+  @addtogroup BasicAbs
+  @{
  */
 
 /**
- * @brief Q15 vector absolute value.
- * @param[in]       *pSrc points to the input buffer
- * @param[out]      *pDst points to the output buffer
- * @param[in]       blockSize number of samples in each vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.
+  @brief         Q15 vector absolute value.
+  @param[in]     pSrc       points to the input vector
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.
  */
 
 void arm_abs_q15(
-  q15_t * pSrc,
-  q15_t * pDst,
-  uint32_t blockSize)
+  const q15_t * pSrc,
+        q15_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
-  __SIMD32_TYPE *simd;
+        uint32_t blkCnt;                               /* Loop counter */
+        q15_t in;                                      /* Temporary input variable */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  q15_t in1;                                     /* Input value1 */
-  q15_t in2;                                     /* Input value2 */
-
-
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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. */
-  simd = __SIMD32_CONST(pDst);
   while (blkCnt > 0U)
   {
     /* C = |A| */
-    /* Read two inputs */
-    in1 = *pSrc++;
-    in2 = *pSrc++;
-
-
-    /* Store the Absolute result in the destination buffer by packing the two values, in a single cycle */
-#ifndef  ARM_MATH_BIG_ENDIAN
-    *simd++ =
-      __PKHBT(((in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1)),
-              ((in2 > 0) ? in2 : (q15_t)__QSUB16(0, in2)), 16);
 
+    /* Calculate absolute of input (if -1 then saturated to 0x7fff) and store result in destination buffer. */
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q15_t)__QSUB16(0, in);
 #else
+    *pDst++ = (in > 0) ? in : ((in == (q15_t) 0x8000) ? 0x7fff : -in);
+#endif
 
-
-    *simd++ =
-      __PKHBT(((in2 > 0) ? in2 : (q15_t)__QSUB16(0, in2)),
-              ((in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1)), 16);
-
-#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
-
-    in1 = *pSrc++;
-    in2 = *pSrc++;
-
-
-#ifndef  ARM_MATH_BIG_ENDIAN
-
-    *simd++ =
-      __PKHBT(((in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1)),
-              ((in2 > 0) ? in2 : (q15_t)__QSUB16(0, in2)), 16);
-
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q15_t)__QSUB16(0, in);
 #else
+    *pDst++ = (in > 0) ? in : ((in == (q15_t) 0x8000) ? 0x7fff : -in);
+#endif
 
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q15_t)__QSUB16(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == (q15_t) 0x8000) ? 0x7fff : -in);
+#endif
 
-    *simd++ =
-      __PKHBT(((in2 > 0) ? in2 : (q15_t)__QSUB16(0, in2)),
-              ((in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1)), 16);
-
-#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q15_t)__QSUB16(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == (q15_t) 0x8000) ? 0x7fff : -in);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
-  pDst = (q15_t *)simd;
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
-  while (blkCnt > 0U)
-  {
-    /* C = |A| */
-    /* Read the input */
-    in1 = *pSrc++;
-
-    /* Calculate absolute value of input and then store the result in the destination buffer. */
-    *pDst++ = (in1 > 0) ? in1 : (q15_t)__QSUB16(0, in1);
-
-    /* Decrement the loop counter */
-    blkCnt--;
-  }
-
 #else
 
-  /* Run the below code for Cortex-M0 */
-
-  q15_t in;                                      /* Temporary input variable */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = |A| */
-    /* Read the input */
-    in = *pSrc++;
 
-    /* Calculate absolute value of input and then store the result in the destination buffer. */
+    /* Calculate absolute of input (if -1 then saturated to 0x7fff) and store result in destination buffer. */
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q15_t)__QSUB16(0, in);
+#else
     *pDst++ = (in > 0) ? in : ((in == (q15_t) 0x8000) ? 0x7fff : -in);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
 }
 
 /**
- * @} end of BasicAbs group
+  @} end of BasicAbs group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_abs_q31.c b/DSP/Source/BasicMathFunctions/arm_abs_q31.c
index 2733f51..bf7608b 100644
--- a/DSP/Source/BasicMathFunctions/arm_abs_q31.c
+++ b/DSP/Source/BasicMathFunctions/arm_abs_q31.c
@@ -3,13 +3,13 @@
  * Title:        arm_abs_q31.c
  * Description:  Q31 vector absolute value
  *
- * $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
  *
@@ -29,90 +29,104 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicAbs
- * @{
+  @addtogroup BasicAbs
+  @{
  */
 
-
 /**
- * @brief Q31 vector absolute value.
- * @param[in]       *pSrc points to the input buffer
- * @param[out]      *pDst points to the output buffer
- * @param[in]       blockSize number of samples in each vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.
+  @brief         Q31 vector absolute value.
+  @param[in]     pSrc       points to the input vector
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.
  */
 
 void arm_abs_q31(
-  q31_t * pSrc,
-  q31_t * pDst,
-  uint32_t blockSize)
+  const q31_t * pSrc,
+        q31_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-  q31_t in;                                      /* Input value */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+        q31_t in;                                      /* Temporary variable */
 
-  /* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t in1, in2, in3, in4;
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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| */
-    /* Calculate absolute of input (if -1 then saturated to 0x7fffffff) and then store the results in the destination buffer. */
-    in1 = *pSrc++;
-    in2 = *pSrc++;
-    in3 = *pSrc++;
-    in4 = *pSrc++;
-
-    *pDst++ = (in1 > 0) ? in1 : (q31_t)__QSUB(0, in1);
-    *pDst++ = (in2 > 0) ? in2 : (q31_t)__QSUB(0, in2);
-    *pDst++ = (in3 > 0) ? in3 : (q31_t)__QSUB(0, in3);
-    *pDst++ = (in4 > 0) ? in4 : (q31_t)__QSUB(0, in4);
-
-    /* Decrement the loop counter */
+
+    /* Calculate absolute of input (if -1 then saturated to 0x7fffffff) and store result in destination buffer. */
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q31_t)__QSUB(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == INT32_MIN) ? INT32_MAX : -in);
+#endif
+
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q31_t)__QSUB(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == INT32_MIN) ? INT32_MAX : -in);
+#endif
+
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q31_t)__QSUB(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == INT32_MIN) ? INT32_MAX : -in);
+#endif
+
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q31_t)__QSUB(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == INT32_MIN) ? INT32_MAX : -in);
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /*   #if defined (ARM_MATH_DSP)   */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   while (blkCnt > 0U)
   {
     /* C = |A| */
-    /* Calculate absolute value of the input (if -1 then saturated to 0x7fffffff) and then store the results in the destination buffer. */
+
+    /* Calculate absolute of input (if -1 then saturated to 0x7fffffff) and store result in destination buffer. */
     in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q31_t)__QSUB(0, in);
+#else
     *pDst++ = (in > 0) ? in : ((in == INT32_MIN) ? INT32_MAX : -in);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
 }
 
 /**
- * @} end of BasicAbs group
+  @} end of BasicAbs group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_abs_q7.c b/DSP/Source/BasicMathFunctions/arm_abs_q7.c
index d0acbfc..a6c4a6c 100644
--- a/DSP/Source/BasicMathFunctions/arm_abs_q7.c
+++ b/DSP/Source/BasicMathFunctions/arm_abs_q7.c
@@ -3,13 +3,13 @@
  * Title:        arm_abs_q7.c
  * Description:  Q7 vector absolute value
  *
- * $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
  *
@@ -29,117 +29,106 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicAbs
- * @{
+  @addtogroup BasicAbs
+  @{
  */
 
 /**
- * @brief Q7 vector absolute value.
- * @param[in]       *pSrc points to the input buffer
- * @param[out]      *pDst points to the output buffer
- * @param[in]       blockSize number of samples in each vector
- * @return none.
- *
- * \par Conditions for optimum performance
- *  Input and output buffers should be aligned by 32-bit
- *
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F.
+  @brief         Q7 vector absolute value.
+  @param[in]     pSrc       points to the input vector
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Conditions for optimum performance
+                   Input and output buffers should be aligned by 32-bit
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F.
  */
 
 void arm_abs_q7(
-  q7_t * pSrc,
-  q7_t * pDst,
-  uint32_t blockSize)
+  const q7_t * pSrc,
+        q7_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-  q7_t in;                                       /* Input value1 */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+        q7_t in;                                       /* Temporary input variable */
 
-  /* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t in1, in2, in3, in4;                      /* temporary input variables */
-  q31_t out1, out2, out3, out4;                  /* temporary output variables */
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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| */
-    /* Read inputs */
-    in1 = (q31_t) * pSrc;
-    in2 = (q31_t) * (pSrc + 1);
-    in3 = (q31_t) * (pSrc + 2);
-
-    /* find absolute value */
-    out1 = (in1 > 0) ? in1 : (q31_t)__QSUB8(0, in1);
-
-    /* read input */
-    in4 = (q31_t) * (pSrc + 3);
-
-    /* find absolute value */
-    out2 = (in2 > 0) ? in2 : (q31_t)__QSUB8(0, in2);
 
-    /* store result to destination */
-    *pDst = (q7_t) out1;
-
-    /* find absolute value */
-    out3 = (in3 > 0) ? in3 : (q31_t)__QSUB8(0, in3);
-
-    /* find absolute value */
-    out4 = (in4 > 0) ? in4 : (q31_t)__QSUB8(0, in4);
-
-    /* store result to destination */
-    *(pDst + 1) = (q7_t) out2;
+    /* Calculate absolute of input (if -1 then saturated to 0x7f) and store result in destination buffer. */
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q7_t)__QSUB(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in);
+#endif
 
-    /* store result to destination */
-    *(pDst + 2) = (q7_t) out3;
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q7_t)__QSUB(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in);
+#endif
 
-    /* store result to destination */
-    *(pDst + 3) = (q7_t) out4;
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q7_t)__QSUB(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in);
+#endif
 
-    /* update pointers to process next samples */
-    pSrc += 4U;
-    pDst += 4U;
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q7_t)__QSUB(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
+
 #else
 
-  /* Run the below code for Cortex-M0 */
+  /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #define ARM_MATH_CM0_FAMILY */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   while (blkCnt > 0U)
   {
     /* C = |A| */
-    /* Read the input */
-    in = *pSrc++;
 
-    /* Store the Absolute result in the destination buffer */
-    *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? 0x7f : -in);
+    /* Calculate absolute of input (if -1 then saturated to 0x7f) and store result in destination buffer. */
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (in > 0) ? in : (q7_t) __QSUB(0, in);
+#else
+    *pDst++ = (in > 0) ? in : ((in == (q7_t) 0x80) ? (q7_t) 0x7f : -in);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of BasicAbs group
+  @} end of BasicAbs group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_add_f32.c b/DSP/Source/BasicMathFunctions/arm_add_f32.c
index 78feb64..1c66a24 100644
--- a/DSP/Source/BasicMathFunctions/arm_add_f32.c
+++ b/DSP/Source/BasicMathFunctions/arm_add_f32.c
@@ -3,13 +3,13 @@
  * Title:        arm_add_f32.c
  * Description:  Floating-point vector addition
  *
- * $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
  *
@@ -29,110 +29,117 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @defgroup BasicAdd Vector Addition
- *
- * Element-by-element addition of two vectors.
- *
- * <pre>
- *     pDst[n] = pSrcA[n] + pSrcB[n],   0 <= n < blockSize.
- * </pre>
- *
- * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+  @defgroup BasicAdd Vector Addition
+
+  Element-by-element addition of two vectors.
+
+  <pre>
+      pDst[n] = pSrcA[n] + pSrcB[n],   0 <= n < blockSize.
+  </pre>
+
+  There are separate functions for floating-point, Q7, Q15, and Q31 data types.
  */
 
 /**
- * @addtogroup BasicAdd
- * @{
+  @addtogroup BasicAdd
+  @{
  */
 
 /**
- * @brief Floating-point 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.
+  @brief         Floating-point vector addition.
+  @param[in]     pSrcA      points to first input vector
+  @param[in]     pSrcB      points to second input vector
+  @param[out]    pDst       points to output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
  */
 
 void arm_add_f32(
-  float32_t * pSrcA,
-  float32_t * pSrcB,
-  float32_t * pDst,
-  uint32_t blockSize)
+  const float32_t * pSrcA,
+  const float32_t * pSrcB,
+        float32_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+
+#if defined(ARM_MATH_NEON)
+    float32x4_t vec1;
+    float32x4_t vec2;
+    float32x4_t res;
+
+    /* Compute 4 outputs at a time */
+    blkCnt = blockSize >> 2U;
+
+    while (blkCnt > 0U)
+    {
+        /* C = A + B */
+
+    	/* Add and then store the results in the destination buffer. */
+        vec1 = vld1q_f32(pSrcA);
+        vec2 = vld1q_f32(pSrcB);
+        res = vaddq_f32(vec1, vec2);
+        vst1q_f32(pDst, res);
+
+        /* Increment pointers */
+        pSrcA += 4;
+        pSrcB += 4; 
+        pDst += 4;
+        
+        /* Decrement the loop counter */
+        blkCnt--;
+    }
+
+    /* Tail */
+    blkCnt = blockSize & 0x3;
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  float32_t inA1, inA2, inA3, inA4;              /* temporary input variabels */
-  float32_t inB1, inB2, inB3, inB4;              /* temporary input variables */
+#else
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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. */
-
-    /* read four inputs from sourceA and four inputs from sourceB */
-    inA1 = *pSrcA;
-    inB1 = *pSrcB;
-    inA2 = *(pSrcA + 1);
-    inB2 = *(pSrcB + 1);
-    inA3 = *(pSrcA + 2);
-    inB3 = *(pSrcB + 2);
-    inA4 = *(pSrcA + 3);
-    inB4 = *(pSrcB + 3);
-
-    /* C = A + B */
-    /* add and store result to destination */
-    *pDst = inA1 + inB1;
-    *(pDst + 1) = inA2 + inB2;
-    *(pDst + 2) = inA3 + inB3;
-    *(pDst + 3) = inA4 + inB4;
-
-    /* update pointers to process next samples */
-    pSrcA += 4U;
-    pSrcB += 4U;
-    pDst += 4U;
 
+    /* Add and store result in destination buffer. */
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
+    *pDst++ = (*pSrcA++) + (*pSrcB++);
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+#endif /* #if defined(ARM_MATH_NEON) */
 
   while (blkCnt > 0U)
   {
     /* C = A + B */
-    /* Add and then store the results in the destination buffer. */
+
+    /* Add and store result in destination buffer. */
     *pDst++ = (*pSrcA++) + (*pSrcB++);
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of BasicAdd group
+  @} end of BasicAdd group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_add_q15.c b/DSP/Source/BasicMathFunctions/arm_add_q15.c
index 80a523f..bc62937 100644
--- a/DSP/Source/BasicMathFunctions/arm_add_q15.c
+++ b/DSP/Source/BasicMathFunctions/arm_add_q15.c
@@ -3,13 +3,13 @@
  * Title:        arm_add_q15.c
  * Description:  Q15 vector addition
  *
- * $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
  *
@@ -29,100 +29,98 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicAdd
- * @{
+  @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.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
+  @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
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.
  */
 
 void arm_add_q15(
-  q15_t * pSrcA,
-  q15_t * pSrcB,
-  q15_t * pDst,
-  uint32_t blockSize)
+  const q15_t * pSrcA,
+  const q15_t * pSrcB,
+        q15_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
+        uint32_t blkCnt;                               /* Loop counter */
 
-#if defined (ARM_MATH_DSP)
+#if defined (ARM_MATH_LOOPUNROLL)
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t inA1, inA2, inB1, inB2;
+#if defined (ARM_MATH_DSP)
+  q31_t inA1, inA2;
+  q31_t inB1, inB2;
+#endif
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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);
+#if defined (ARM_MATH_DSP)
+    /* read 2 times 2 samples at a time from sourceA */
+    inA1 = read_q15x2_ia ((q15_t **) &pSrcA);
+    inA2 = read_q15x2_ia ((q15_t **) &pSrcA);
+    /* read 2 times 2 samples at a time from sourceB */
+    inB1 = read_q15x2_ia ((q15_t **) &pSrcB);
+    inB2 = read_q15x2_ia ((q15_t **) &pSrcB);
+
+    /* Add and store 2 times 2 samples at a time */
+    write_q15x2_ia (&pDst, __QADD16(inA1, inB1));
+    write_q15x2_ia (&pDst, __QADD16(inA2, inB2));
+#else
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 16);
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 16);
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 16);
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 16);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   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;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   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 */
+    /* Add and store result in destination buffer. */
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (q15_t) __QADD16(*pSrcA++, *pSrcB++);
+#else
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ + *pSrcB++), 16);
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
-
 }
 
 /**
- * @} end of BasicAdd group
+  @} end of BasicAdd group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_add_q31.c b/DSP/Source/BasicMathFunctions/arm_add_q31.c
index c008bcc..3c1cbc2 100644
--- a/DSP/Source/BasicMathFunctions/arm_add_q31.c
+++ b/DSP/Source/BasicMathFunctions/arm_add_q31.c
@@ -3,13 +3,13 @@
  * Title:        arm_add_q31.c
  * Description:  Q31 vector addition
  *
- * $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
  *
@@ -29,108 +29,80 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicAdd
- * @{
+  @addtogroup BasicAdd
+  @{
  */
 
-
 /**
- * @brief Q31 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.
- *
- * <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 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
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] are saturated.
  */
 
 void arm_add_q31(
-  q31_t * pSrcA,
-  q31_t * pSrcB,
-  q31_t * pDst,
-  uint32_t blockSize)
+  const q31_t * pSrcA,
+  const q31_t * pSrcB,
+        q31_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t inA1, inA2, inA3, inA4;
-  q31_t inB1, inB2, inB3, inB4;
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 = *pSrcA++;
-    inA2 = *pSrcA++;
-    inB1 = *pSrcB++;
-    inB2 = *pSrcB++;
-
-    inA3 = *pSrcA++;
-    inA4 = *pSrcA++;
-    inB3 = *pSrcB++;
-    inB4 = *pSrcB++;
-
-    *pDst++ = __QADD(inA1, inB1);
-    *pDst++ = __QADD(inA2, inB2);
-    *pDst++ = __QADD(inA3, inB3);
-    *pDst++ = __QADD(inA4, inB4);
-
-    /* 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;
+    /* Add and store result in destination buffer. */
+    *pDst++ = __QADD(*pSrcA++, *pSrcB++);
 
-  while (blkCnt > 0U)
-  {
-    /* C = A + B */
-    /* Add and then store the results in the destination buffer. */
     *pDst++ = __QADD(*pSrcA++, *pSrcB++);
 
-    /* Decrement the loop counter */
-    blkCnt--;
-  }
+    *pDst++ = __QADD(*pSrcA++, *pSrcB++);
 
-#else
+    *pDst++ = __QADD(*pSrcA++, *pSrcB++);
 
-  /* Run the below code for Cortex-M0 */
+    /* Decrement loop counter */
+    blkCnt--;
+  }
 
+  /* Loop unrolling: Compute remaining outputs */
+  blkCnt = blockSize % 0x4U;
 
+#else
 
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A + B */
-    /* Add and then store the results in the destination buffer. */
-    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrcA++ + *pSrcB++);
 
-    /* Decrement the loop counter */
+    /* Add and store result in destination buffer. */
+    *pDst++ = __QADD(*pSrcA++, *pSrcB++);
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
 }
 
 /**
- * @} end of BasicAdd group
+  @} end of BasicAdd group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_add_q7.c b/DSP/Source/BasicMathFunctions/arm_add_q7.c
index ab4e785..f9c4a95 100644
--- a/DSP/Source/BasicMathFunctions/arm_add_q7.c
+++ b/DSP/Source/BasicMathFunctions/arm_add_q7.c
@@ -3,13 +3,13 @@
  * Title:        arm_add_q7.c
  * Description:  Q7 vector addition
  *
- * $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
  *
@@ -29,94 +29,81 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicAdd
- * @{
+  @addtogroup BasicAdd
+  @{
  */
 
 /**
- * @brief Q7 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.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.
+  @brief         Q7 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
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q7 range [0x80 0x7F] are saturated.
  */
 
 void arm_add_q7(
-  q7_t * pSrcA,
-  q7_t * pSrcB,
-  q7_t * pDst,
-  uint32_t blockSize)
+  const q7_t * pSrcA,
+  const q7_t * pSrcB,
+        q7_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
 
-/* 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 = 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. */
-    *__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);
 
-    /* Decrement the loop counter */
+#if defined (ARM_MATH_DSP)
+    /* Add and store result in destination buffer (4 samples at a time). */
+    write_q7x4_ia (&pDst, __QADD8 (read_q7x4_ia ((q7_t **) &pSrcA), read_q7x4_ia ((q7_t **) &pSrcB)));
+#else
+    *pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
+    *pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
+    *pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
+    *pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
-  while (blkCnt > 0U)
-  {
-    /* C = A + B */
-    /* Add and then store the results in the destination buffer. */
-    *pDst++ = (q7_t) __SSAT(*pSrcA++ + *pSrcB++, 8);
-
-    /* Decrement the loop counter */
-    blkCnt--;
-  }
-
 #else
 
-  /* Run the below code for Cortex-M0 */
-
-
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A + B */
-    /* Add and then store the results in the destination buffer. */
-    *pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ + *pSrcB++, 8);
 
-    /* Decrement the loop counter */
+    /* Add and store result in destination buffer. */
+    *pDst++ = (q7_t) __SSAT((q15_t) *pSrcA++ + *pSrcB++, 8);
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
-
 }
 
 /**
- * @} end of BasicAdd group
+  @} end of BasicAdd group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_dot_prod_f32.c b/DSP/Source/BasicMathFunctions/arm_dot_prod_f32.c
index 0cd0afc..3eee3b9 100644
--- a/DSP/Source/BasicMathFunctions/arm_dot_prod_f32.c
+++ b/DSP/Source/BasicMathFunctions/arm_dot_prod_f32.c
@@ -3,13 +3,13 @@
  * Title:        arm_dot_prod_f32.c
  * Description:  Floating-point dot product
  *
- * $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
  *
@@ -29,95 +29,135 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @defgroup dot_prod Vector Dot Product
- *
- * Computes the dot product of two vectors.
- * The vectors are multiplied element-by-element and then summed.
- *
- * <pre>
- *     sum = pSrcA[0]*pSrcB[0] + pSrcA[1]*pSrcB[1] + ... + pSrcA[blockSize-1]*pSrcB[blockSize-1]
- * </pre>
- *
- * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+  @defgroup BasicDotProd Vector Dot Product
+
+  Computes the dot product of two vectors.
+  The vectors are multiplied element-by-element and then summed.
+
+  <pre>
+      sum = pSrcA[0]*pSrcB[0] + pSrcA[1]*pSrcB[1] + ... + pSrcA[blockSize-1]*pSrcB[blockSize-1]
+  </pre>
+
+  There are separate functions for floating-point, Q7, Q15, and Q31 data types.
  */
 
 /**
- * @addtogroup dot_prod
- * @{
+  @addtogroup BasicDotProd
+  @{
  */
 
 /**
- * @brief Dot product of floating-point vectors.
- * @param[in]       *pSrcA points to the first input vector
- * @param[in]       *pSrcB points to the second input vector
- * @param[in]       blockSize number of samples in each vector
- * @param[out]      *result output result returned here
- * @return none.
+  @brief         Dot product of floating-point vectors.
+  @param[in]     pSrcA      points to the first input vector.
+  @param[in]     pSrcB      points to the second input vector.
+  @param[in]     blockSize  number of samples in each vector.
+  @param[out]    result     output result returned here.
+  @return        none
  */
 
-
 void arm_dot_prod_f32(
-  float32_t * pSrcA,
-  float32_t * pSrcB,
-  uint32_t blockSize,
-  float32_t * result)
+  const float32_t * pSrcA,
+  const float32_t * pSrcB,
+        uint32_t blockSize,
+        float32_t * result)
 {
-  float32_t sum = 0.0f;                          /* Temporary result storage */
-  uint32_t blkCnt;                               /* loop counter */
+        uint32_t blkCnt;                               /* Loop counter */
+        float32_t sum = 0.0f;                          /* Temporary return variable */
+
+#if defined(ARM_MATH_NEON)
+    float32x4_t vec1;
+    float32x4_t vec2;
+    float32x4_t res;
+    float32x4_t accum = vdupq_n_f32(0);    
+
+    /* Compute 4 outputs at a time */
+    blkCnt = blockSize >> 2U;
+
+    vec1 = vld1q_f32(pSrcA);
+    vec2 = vld1q_f32(pSrcB);
+
+    while (blkCnt > 0U)
+    {
+        /* C = A[0]*B[0] + A[1]*B[1] + A[2]*B[2] + ... + A[blockSize-1]*B[blockSize-1] */
+        /* Calculate dot product and then store the result in a temporary buffer. */
+        
+	accum = vmlaq_f32(accum, vec1, vec2);
+	
+        /* Increment pointers */
+        pSrcA += 4;
+        pSrcB += 4; 
+
+        vec1 = vld1q_f32(pSrcA);
+        vec2 = vld1q_f32(pSrcB);
+        
+        /* Decrement the loop counter */
+        blkCnt--;
+    }
+    
+#if __aarch64__
+    sum = vpadds_f32(vpadd_f32(vget_low_f32(accum), vget_high_f32(accum)));
+#else
+    sum = (vpadd_f32(vget_low_f32(accum), vget_high_f32(accum)))[0] + (vpadd_f32(vget_low_f32(accum), vget_high_f32(accum)))[1];
+#endif    
 
+    /* Tail */
+    blkCnt = blockSize & 0x3;
 
-#if defined (ARM_MATH_DSP)
+#else
+#if defined (ARM_MATH_LOOPUNROLL)
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   blkCnt = blockSize >> 2U;
 
-  /* 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 (blkCnt > 0U)
   {
     /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
-    /* Calculate dot product and then store the result in a temporary buffer */
+
+    /* Calculate dot product and store result in a temporary buffer. */
     sum += (*pSrcA++) * (*pSrcB++);
+
     sum += (*pSrcA++) * (*pSrcB++);
+
     sum += (*pSrcA++) * (*pSrcB++);
+
     sum += (*pSrcA++) * (*pSrcB++);
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+#endif /* #if defined(ARM_MATH_NEON) */
 
   while (blkCnt > 0U)
   {
     /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
-    /* Calculate dot product and then store the result in a temporary buffer. */
+
+    /* Calculate dot product and store result in a temporary buffer. */
     sum += (*pSrcA++) * (*pSrcB++);
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
-  /* Store the result back in the destination buffer */
+
+  /* Store result in destination buffer */
   *result = sum;
 }
 
 /**
- * @} end of dot_prod group
+  @} end of BasicDotProd group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_dot_prod_q15.c b/DSP/Source/BasicMathFunctions/arm_dot_prod_q15.c
index dec4ec5..e303b09 100644
--- a/DSP/Source/BasicMathFunctions/arm_dot_prod_q15.c
+++ b/DSP/Source/BasicMathFunctions/arm_dot_prod_q15.c
@@ -3,13 +3,13 @@
  * Title:        arm_dot_prod_q15.c
  * Description:  Q15 dot product
  *
- * $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
  *
@@ -29,100 +29,92 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup dot_prod
- * @{
+  @addtogroup BasicDotProd
+  @{
  */
 
 /**
- * @brief Dot product of Q15 vectors.
- * @param[in]       *pSrcA points to the first input vector
- * @param[in]       *pSrcB points to the second input vector
- * @param[in]       blockSize number of samples in each vector
- * @param[out]      *result output result returned here
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The intermediate multiplications are in 1.15 x 1.15 = 2.30 format and these
- * results are added to a 64-bit accumulator in 34.30 format.
- * Nonsaturating additions are used and given that there are 33 guard bits in the accumulator
- * there is no risk of overflow.
- * The return result is in 34.30 format.
+  @brief         Dot product of Q15 vectors.
+  @param[in]     pSrcA      points to the first input vector
+  @param[in]     pSrcB      points to the second input vector
+  @param[in]     blockSize  number of samples in each vector
+  @param[out]    result     output result returned here
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The intermediate multiplications are in 1.15 x 1.15 = 2.30 format and these
+                   results are added to a 64-bit accumulator in 34.30 format.
+                   Nonsaturating additions are used and given that there are 33 guard bits in the accumulator
+                   there is no risk of overflow.
+                   The return result is in 34.30 format.
  */
 
 void arm_dot_prod_q15(
-  q15_t * pSrcA,
-  q15_t * pSrcB,
-  uint32_t blockSize,
-  q63_t * result)
+  const q15_t * pSrcA,
+  const q15_t * pSrcB,
+        uint32_t blockSize,
+        q63_t * result)
 {
-  q63_t sum = 0;                                 /* Temporary result storage */
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+        q63_t sum = 0;                                 /* Temporary return variable */
 
-/* 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 = 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[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
-    /* Calculate dot product and then store the result in a temporary buffer. */
-    sum = __SMLALD(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++, sum);
-    sum = __SMLALD(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++, sum);
-
-    /* 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[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
-    /* Calculate dot product and then store the results in a temporary buffer. */
-    sum = __SMLALD(*pSrcA++, *pSrcB++, sum);
+#if defined (ARM_MATH_DSP)
+    /* Calculate dot product and store result in a temporary buffer. */
+    sum = __SMLALD(read_q15x2_ia ((q15_t **) &pSrcA), read_q15x2_ia ((q15_t **) &pSrcB), sum);
+    sum = __SMLALD(read_q15x2_ia ((q15_t **) &pSrcA), read_q15x2_ia ((q15_t **) &pSrcB), sum);
+#else
+    sum += (q63_t)((q31_t) *pSrcA++ * *pSrcB++);
+    sum += (q63_t)((q31_t) *pSrcA++ * *pSrcB++);
+    sum += (q63_t)((q31_t) *pSrcA++ * *pSrcB++);
+    sum += (q63_t)((q31_t) *pSrcA++ * *pSrcB++);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
+  /* Loop unrolling: Compute remaining outputs */
+  blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
-    /* Calculate dot product and then store the results in a temporary buffer. */
-    sum += (q63_t) ((q31_t) * pSrcA++ * *pSrcB++);
 
-    /* Decrement the loop counter */
+    /* Calculate dot product and store result in a temporary buffer. */
+//#if defined (ARM_MATH_DSP)
+//    sum  = __SMLALD(*pSrcA++, *pSrcB++, sum);
+//#else
+    sum += (q63_t)((q31_t) *pSrcA++ * *pSrcB++);
+//#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
-  /* Store the result in the destination buffer in 34.30 format */
+  /* Store result in destination buffer in 34.30 format */
   *result = sum;
-
 }
 
 /**
- * @} end of dot_prod group
+  @} end of BasicDotProd group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c b/DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c
index 67ae887..76cd577 100644
--- a/DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c
+++ b/DSP/Source/BasicMathFunctions/arm_dot_prod_q31.c
@@ -3,13 +3,13 @@
  * Title:        arm_dot_prod_q31.c
  * Description:  Q31 dot product
  *
- * $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
  *
@@ -29,103 +29,87 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup dot_prod
- * @{
+  @addtogroup BasicDotProd
+  @{
  */
 
 /**
- * @brief Dot product of Q31 vectors.
- * @param[in]       *pSrcA points to the first input vector
- * @param[in]       *pSrcB points to the second input vector
- * @param[in]       blockSize number of samples in each vector
- * @param[out]      *result output result returned here
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The intermediate multiplications are in 1.31 x 1.31 = 2.62 format and these
- * are truncated to 2.48 format by discarding the lower 14 bits.
- * The 2.48 result is then added without saturation to a 64-bit accumulator in 16.48 format.
- * There are 15 guard bits in the accumulator and there is no risk of overflow as long as
- * the length of the vectors is less than 2^16 elements.
- * The return result is in 16.48 format.
+  @brief         Dot product of Q31 vectors.
+  @param[in]     pSrcA      points to the first input vector.
+  @param[in]     pSrcB      points to the second input vector.
+  @param[in]     blockSize  number of samples in each vector.
+  @param[out]    result     output result returned here.
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The intermediate multiplications are in 1.31 x 1.31 = 2.62 format and these
+                   are truncated to 2.48 format by discarding the lower 14 bits.
+                   The 2.48 result is then added without saturation to a 64-bit accumulator in 16.48 format.
+                   There are 15 guard bits in the accumulator and there is no risk of overflow as long as
+                   the length of the vectors is less than 2^16 elements.
+                   The return result is in 16.48 format.
  */
 
 void arm_dot_prod_q31(
-  q31_t * pSrcA,
-  q31_t * pSrcB,
-  uint32_t blockSize,
-  q63_t * result)
+  const q31_t * pSrcA,
+  const q31_t * pSrcB,
+        uint32_t blockSize,
+        q63_t * result)
 {
-  q63_t sum = 0;                                 /* Temporary result storage */
-  uint32_t blkCnt;                               /* loop counter */
-
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+        q63_t sum = 0;                                 /* Temporary return variable */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t inA1, inA2, inA3, inA4;
-  q31_t inB1, inB2, inB3, inB4;
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
-    /* Calculate dot product and then store the result in a temporary buffer. */
-    inA1 = *pSrcA++;
-    inA2 = *pSrcA++;
-    inA3 = *pSrcA++;
-    inA4 = *pSrcA++;
-    inB1 = *pSrcB++;
-    inB2 = *pSrcB++;
-    inB3 = *pSrcB++;
-    inB4 = *pSrcB++;
-
-    sum += ((q63_t) inA1 * inB1) >> 14U;
-    sum += ((q63_t) inA2 * inB2) >> 14U;
-    sum += ((q63_t) inA3 * inB3) >> 14U;
-    sum += ((q63_t) inA4 * inB4) >> 14U;
-
-    /* Decrement the loop counter */
+
+    /* Calculate dot product and store result in a temporary buffer. */
+    sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U;
+
+    sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U;
+
+    sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U;
+
+    sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U;
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   while (blkCnt > 0U)
   {
     /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
-    /* Calculate dot product and then store the result in a temporary buffer. */
-    sum += ((q63_t) * pSrcA++ * *pSrcB++) >> 14U;
 
-    /* Decrement the loop counter */
+    /* Calculate dot product and store result in a temporary buffer. */
+    sum += ((q63_t) *pSrcA++ * *pSrcB++) >> 14U;
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* Store the result in the destination buffer in 16.48 format */
+  /* Store result in destination buffer in 16.48 format */
   *result = sum;
 }
 
 /**
- * @} end of dot_prod group
+  @} end of BasicDotProd group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_dot_prod_q7.c b/DSP/Source/BasicMathFunctions/arm_dot_prod_q7.c
index 487efe3..8e18a73 100644
--- a/DSP/Source/BasicMathFunctions/arm_dot_prod_q7.c
+++ b/DSP/Source/BasicMathFunctions/arm_dot_prod_q7.c
@@ -3,13 +3,13 @@
  * Title:        arm_dot_prod_q7.c
  * Description:  Q7 dot product
  *
- * $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
  *
@@ -29,61 +29,58 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup dot_prod
- * @{
+  @addtogroup BasicDotProd
+  @{
  */
 
 /**
- * @brief Dot product of Q7 vectors.
- * @param[in]       *pSrcA points to the first input vector
- * @param[in]       *pSrcB points to the second input vector
- * @param[in]       blockSize number of samples in each vector
- * @param[out]      *result output result returned here
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The intermediate multiplications are in 1.7 x 1.7 = 2.14 format and these
- * results are added to an accumulator in 18.14 format.
- * Nonsaturating additions are used and there is no danger of wrap around as long as
- * the vectors are less than 2^18 elements long.
- * The return result is in 18.14 format.
+  @brief         Dot product of Q7 vectors.
+  @param[in]     pSrcA      points to the first input vector
+  @param[in]     pSrcB      points to the second input vector
+  @param[in]     blockSize  number of samples in each vector
+  @param[out]    result     output result returned here
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The intermediate multiplications are in 1.7 x 1.7 = 2.14 format and these
+                   results are added to an accumulator in 18.14 format.
+                   Nonsaturating additions are used and there is no danger of wrap around as long as
+                   the vectors are less than 2^18 elements long.
+                   The return result is in 18.14 format.
  */
 
 void arm_dot_prod_q7(
-  q7_t * pSrcA,
-  q7_t * pSrcB,
-  uint32_t blockSize,
-  q31_t * result)
+  const q7_t * pSrcA,
+  const q7_t * pSrcB,
+        uint32_t blockSize,
+        q31_t * result)
 {
-  uint32_t blkCnt;                               /* loop counter */
+        uint32_t blkCnt;                               /* Loop counter */
+        q31_t sum = 0;                                 /* Temporary return variable */
 
-  q31_t sum = 0;                                 /* Temporary variables to store output */
+#if defined (ARM_MATH_LOOPUNROLL)
 
 #if defined (ARM_MATH_DSP)
+  q31_t input1, input2;                          /* Temporary variables */
+  q31_t inA1, inA2, inB1, inB2;                  /* Temporary variables */
+#endif
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-
-  q31_t input1, input2;                          /* Temporary variables to store input */
-  q31_t inA1, inA2, inB1, inB2;                  /* Temporary variables to store input */
-
-
-
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
+
+#if defined (ARM_MATH_DSP)
     /* read 4 samples at a time from sourceA */
-    input1 = *__SIMD32(pSrcA)++;
+    input1 = read_q7x4_ia ((q7_t **) &pSrcA);
     /* read 4 samples at a time from sourceB */
-    input2 = *__SIMD32(pSrcB)++;
+    input2 = read_q7x4_ia ((q7_t **) &pSrcB);
 
     /* extract two q7_t samples to q15_t samples */
     inA1 = __SXTB16(__ROR(input1, 8));
@@ -97,51 +94,46 @@ void arm_dot_prod_q7(
     /* multiply and accumulate two samples at a time */
     sum = __SMLAD(inA1, inB1, sum);
     sum = __SMLAD(inA2, inB2, sum);
+#else
+    sum += (q31_t) ((q15_t) *pSrcA++ * *pSrcB++);
+    sum += (q31_t) ((q15_t) *pSrcA++ * *pSrcB++);
+    sum += (q31_t) ((q15_t) *pSrcA++ * *pSrcB++);
+    sum += (q31_t) ((q15_t) *pSrcA++ * *pSrcB++);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
-  while (blkCnt > 0U)
-  {
-    /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
-    /* Dot product and then store the results in a temporary buffer. */
-    sum = __SMLAD(*pSrcA++, *pSrcB++, sum);
-
-    /* Decrement the loop counter */
-    blkCnt--;
-  }
-
 #else
 
-  /* Run the below code for Cortex-M0 */
-
-
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
-    /* Dot product and then store the results in a temporary buffer. */
-    sum += (q31_t) ((q15_t) * pSrcA++ * *pSrcB++);
 
-    /* Decrement the loop counter */
+    /* Calculate dot product and store result in a temporary buffer. */
+//#if defined (ARM_MATH_DSP)
+//    sum  = __SMLAD(*pSrcA++, *pSrcB++, sum);
+//#else
+    sum += (q31_t) ((q15_t) *pSrcA++ * *pSrcB++);
+//#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
-
-  /* Store the result in the destination buffer in 18.14 format */
+  /* Store result in destination buffer in 18.14 format */
   *result = sum;
 }
 
 /**
- * @} end of dot_prod group
+  @} end of BasicDotProd group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_mult_f32.c b/DSP/Source/BasicMathFunctions/arm_mult_f32.c
index e4a9ef2..53ad73c 100644
--- a/DSP/Source/BasicMathFunctions/arm_mult_f32.c
+++ b/DSP/Source/BasicMathFunctions/arm_mult_f32.c
@@ -3,13 +3,13 @@
  * Title:        arm_mult_f32.c
  * Description:  Floating-point vector multiplication
  *
- * $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
  *
@@ -29,134 +29,120 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @defgroup BasicMult Vector Multiplication
- *
- * Element-by-element multiplication of two vectors.
- *
- * <pre>
- *     pDst[n] = pSrcA[n] * pSrcB[n],   0 <= n < blockSize.
- * </pre>
- *
- * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+  @defgroup BasicMult Vector Multiplication
+
+  Element-by-element multiplication of two vectors.
+
+  <pre>
+      pDst[n] = pSrcA[n] * pSrcB[n],   0 <= n < blockSize.
+  </pre>
+
+  There are separate functions for floating-point, Q7, Q15, and Q31 data types.
  */
 
 /**
- * @addtogroup BasicMult
- * @{
+  @addtogroup BasicMult
+  @{
  */
 
 /**
- * @brief Floating-point vector multiplication.
- * @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.
+  @brief         Floating-point vector multiplication.
+  @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
  */
 
 void arm_mult_f32(
-  float32_t * pSrcA,
-  float32_t * pSrcB,
-  float32_t * pDst,
-  uint32_t blockSize)
+  const float32_t * pSrcA,
+  const float32_t * pSrcB,
+        float32_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counters */
-#if defined (ARM_MATH_DSP)
+    uint32_t blkCnt;                               /* Loop counter */
+
+#if defined(ARM_MATH_NEON)
+    float32x4_t vec1;
+    float32x4_t vec2;
+    float32x4_t res;
+
+    /* Compute 4 outputs at a time */
+    blkCnt = blockSize >> 2U;
+
+    while (blkCnt > 0U)
+    {
+        /* C = A * B */
+
+    	/* Multiply the inputs and then store the results in the destination buffer. */
+        vec1 = vld1q_f32(pSrcA);
+        vec2 = vld1q_f32(pSrcB);
+        res = vmulq_f32(vec1, vec2);
+        vst1q_f32(pDst, res);
+
+        /* Increment pointers */
+        pSrcA += 4;
+        pSrcB += 4; 
+        pDst += 4;
+        
+        /* Decrement the loop counter */
+        blkCnt--;
+    }
+
+    /* Tail */
+    blkCnt = blockSize & 0x3;
 
-  /* Run the below code for Cortex-M4 and Cortex-M3 */
-  float32_t inA1, inA2, inA3, inA4;              /* temporary input variables */
-  float32_t inB1, inB2, inB3, inB4;              /* temporary input variables */
-  float32_t out1, out2, out3, out4;              /* temporary output variables */
+#else
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /* loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 */
-    /* Multiply the inputs and store the results in output buffer */
-    /* read sample from sourceA */
-    inA1 = *pSrcA;
-    /* read sample from sourceB */
-    inB1 = *pSrcB;
-    /* read sample from sourceA */
-    inA2 = *(pSrcA + 1);
-    /* read sample from sourceB */
-    inB2 = *(pSrcB + 1);
-
-    /* out = sourceA * sourceB */
-    out1 = inA1 * inB1;
-
-    /* read sample from sourceA */
-    inA3 = *(pSrcA + 2);
-    /* read sample from sourceB */
-    inB3 = *(pSrcB + 2);
-
-    /* out = sourceA * sourceB */
-    out2 = inA2 * inB2;
-
-    /* read sample from sourceA */
-    inA4 = *(pSrcA + 3);
 
-    /* store result to destination buffer */
-    *pDst = out1;
-
-    /* read sample from sourceB */
-    inB4 = *(pSrcB + 3);
-
-    /* out = sourceA * sourceB */
-    out3 = inA3 * inB3;
-
-    /* store result to destination buffer */
-    *(pDst + 1) = out2;
+    /* Multiply inputs and store result in destination buffer. */
+    *pDst++ = (*pSrcA++) * (*pSrcB++);
 
-    /* out = sourceA * sourceB */
-    out4 = inA4 * inB4;
-    /* store result to destination buffer */
-    *(pDst + 2) = out3;
-    /* store result to destination buffer */
-    *(pDst + 3) = out4;
+    *pDst++ = (*pSrcA++) * (*pSrcB++);
 
+    *pDst++ = (*pSrcA++) * (*pSrcB++);
 
-    /* update pointers to process next samples */
-    pSrcA += 4U;
-    pSrcB += 4U;
-    pDst += 4U;
+    *pDst++ = (*pSrcA++) * (*pSrcB++);
 
-    /* Decrement the blockSize loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+#endif /* #if defined(ARM_MATH_NEON) */
 
   while (blkCnt > 0U)
   {
     /* C = A * B */
-    /* Multiply the inputs and store the results in output buffer */
+
+    /* Multiply input and store result in destination buffer. */
     *pDst++ = (*pSrcA++) * (*pSrcB++);
 
-    /* Decrement the blockSize loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of BasicMult group
+  @} end of BasicMult group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_mult_q15.c b/DSP/Source/BasicMathFunctions/arm_mult_q15.c
index 8e20963..37aa924 100644
--- a/DSP/Source/BasicMathFunctions/arm_mult_q15.c
+++ b/DSP/Source/BasicMathFunctions/arm_mult_q15.c
@@ -3,13 +3,13 @@
  * Title:        arm_mult_q15.c
  * Description:  Q15 vector multiplication
  *
- * $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
  *
@@ -29,65 +29,65 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicMult
- * @{
+  @addtogroup BasicMult
+  @{
  */
 
-
 /**
- * @brief           Q15 vector multiplication
- * @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.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
+  @brief         Q15 vector multiplication
+  @param[in]     pSrcA      points to first input vector
+  @param[in]     pSrcB      points to second input vector
+  @param[out]    pDst       points to output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.
  */
 
 void arm_mult_q15(
-  q15_t * pSrcA,
-  q15_t * pSrcB,
-  q15_t * pDst,
-  uint32_t blockSize)
+  const q15_t * pSrcA,
+  const q15_t * pSrcB,
+        q15_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counters */
+        uint32_t blkCnt;                               /* Loop counter */
 
-#if defined (ARM_MATH_DSP)
+#if defined (ARM_MATH_LOOPUNROLL)
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t inA1, inA2, inB1, inB2;                  /* temporary input variables */
-  q15_t out1, out2, out3, out4;                  /* temporary output variables */
-  q31_t mul1, mul2, mul3, mul4;                  /* temporary variables */
+#if defined (ARM_MATH_DSP)
+  q31_t inA1, inA2, inB1, inB2;                  /* Temporary input variables */
+  q15_t out1, out2, out3, out4;                  /* Temporary output variables */
+  q31_t mul1, mul2, mul3, mul4;                  /* Temporary variables */
+#endif
 
-  /* loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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)
   {
-    /* read two samples at a time from sourceA */
-    inA1 = *__SIMD32(pSrcA)++;
-    /* read two samples at a time from sourceB */
-    inB1 = *__SIMD32(pSrcB)++;
-    /* read two samples at a time from sourceA */
-    inA2 = *__SIMD32(pSrcA)++;
-    /* read two samples at a time from sourceB */
-    inB2 = *__SIMD32(pSrcB)++;
+    /* C = A * B */
+
+#if defined (ARM_MATH_DSP)
+    /* read 2 samples at a time from sourceA */
+    inA1 = read_q15x2_ia ((q15_t **) &pSrcA);
+    /* read 2 samples at a time from sourceB */
+    inB1 = read_q15x2_ia ((q15_t **) &pSrcB);
+    /* read 2 samples at a time from sourceA */
+    inA2 = read_q15x2_ia ((q15_t **) &pSrcA);
+    /* read 2 samples at a time from sourceB */
+    inB2 = read_q15x2_ia ((q15_t **) &pSrcB);
 
     /* multiply mul = sourceA * sourceB */
     mul1 = (q31_t) ((q15_t) (inA1 >> 16) * (q15_t) (inB1 >> 16));
-    mul2 = (q31_t) ((q15_t) inA1 * (q15_t) inB1);
+    mul2 = (q31_t) ((q15_t) (inA1      ) * (q15_t) (inB1      ));
     mul3 = (q31_t) ((q15_t) (inA2 >> 16) * (q15_t) (inB2 >> 16));
-    mul4 = (q31_t) ((q15_t) inA2 * (q15_t) inB2);
+    mul4 = (q31_t) ((q15_t) (inA2      ) * (q15_t) (inB2      ));
 
     /* saturate result to 16 bit */
     out1 = (q15_t) __SSAT(mul1 >> 15, 16);
@@ -95,48 +95,49 @@ void arm_mult_q15(
     out3 = (q15_t) __SSAT(mul3 >> 15, 16);
     out4 = (q15_t) __SSAT(mul4 >> 15, 16);
 
-    /* store the result */
+    /* store result to destination */
 #ifndef ARM_MATH_BIG_ENDIAN
-
-    *__SIMD32(pDst)++ = __PKHBT(out2, out1, 16);
-    *__SIMD32(pDst)++ = __PKHBT(out4, out3, 16);
-
+    write_q15x2_ia (&pDst, __PKHBT(out2, out1, 16));
+    write_q15x2_ia (&pDst, __PKHBT(out4, out3, 16));
 #else
-
-    *__SIMD32(pDst)++ = __PKHBT(out2, out1, 16);
-    *__SIMD32(pDst)++ = __PKHBT(out4, out3, 16);
-
+    write_q15x2_ia (&pDst, __PKHBT(out1, out2, 16));
+    write_q15x2_ia (&pDst, __PKHBT(out3, out4, 16));
 #endif /* #ifndef ARM_MATH_BIG_ENDIAN */
 
-    /* Decrement the blockSize loop counter */
+#else
+    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
+    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
+    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
+    *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   while (blkCnt > 0U)
   {
     /* C = A * B */
-    /* Multiply the inputs and store the result in the destination buffer */
+
+    /* Multiply inputs and store result in destination buffer. */
     *pDst++ = (q15_t) __SSAT((((q31_t) (*pSrcA++) * (*pSrcB++)) >> 15), 16);
 
-    /* Decrement the blockSize loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of BasicMult group
+  @} end of BasicMult group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_mult_q31.c b/DSP/Source/BasicMathFunctions/arm_mult_q31.c
index c302b01..9592684 100644
--- a/DSP/Source/BasicMathFunctions/arm_mult_q31.c
+++ b/DSP/Source/BasicMathFunctions/arm_mult_q31.c
@@ -3,13 +3,13 @@
  * Title:        arm_mult_q31.c
  * Description:  Q31 vector multiplication
  *
- * $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
  *
@@ -29,120 +29,91 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicMult
- * @{
+  @addtogroup BasicMult
+  @{
  */
 
 /**
- * @brief Q31 vector multiplication.
- * @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.
- *
- * <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 vector multiplication.
+  @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
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q31 range[0x80000000 0x7FFFFFFF] are saturated.
  */
 
 void arm_mult_q31(
-  q31_t * pSrcA,
-  q31_t * pSrcB,
-  q31_t * pDst,
-  uint32_t blockSize)
+  const q31_t * pSrcA,
+  const q31_t * pSrcB,
+        q31_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counters */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+        q31_t out;                                     /* Temporary output variable */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t inA1, inA2, inA3, inA4;                  /* temporary input variables */
-  q31_t inB1, inB2, inB3, inB4;                  /* temporary input variables */
-  q31_t out1, out2, out3, out4;                  /* temporary output variables */
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /* loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 */
-    /* Multiply the inputs and then store the results in the destination buffer. */
-    inA1 = *pSrcA++;
-    inA2 = *pSrcA++;
-    inA3 = *pSrcA++;
-    inA4 = *pSrcA++;
-    inB1 = *pSrcB++;
-    inB2 = *pSrcB++;
-    inB3 = *pSrcB++;
-    inB4 = *pSrcB++;
-
-    out1 = ((q63_t) inA1 * inB1) >> 32;
-    out2 = ((q63_t) inA2 * inB2) >> 32;
-    out3 = ((q63_t) inA3 * inB3) >> 32;
-    out4 = ((q63_t) inA4 * inB4) >> 32;
-
-    out1 = __SSAT(out1, 31);
-    out2 = __SSAT(out2, 31);
-    out3 = __SSAT(out3, 31);
-    out4 = __SSAT(out4, 31);
-
-    *pDst++ = out1 << 1U;
-    *pDst++ = out2 << 1U;
-    *pDst++ = out3 << 1U;
-    *pDst++ = out4 << 1U;
-
-    /* Decrement the blockSize 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;
+    /* Multiply inputs and store result in destination buffer. */
+    out = ((q63_t) *pSrcA++ * *pSrcB++) >> 32;
+    out = __SSAT(out, 31);
+    *pDst++ = out << 1U;
 
-  while (blkCnt > 0U)
-  {
-    /* C = A * B */
-    /* Multiply the inputs and then store the results in the destination buffer. */
-    inA1 = *pSrcA++;
-    inB1 = *pSrcB++;
-    out1 = ((q63_t) inA1 * inB1) >> 32;
-    out1 = __SSAT(out1, 31);
-    *pDst++ = out1 << 1U;
-
-    /* Decrement the blockSize loop counter */
+    out = ((q63_t) *pSrcA++ * *pSrcB++) >> 32;
+    out = __SSAT(out, 31);
+    *pDst++ = out << 1U;
+
+    out = ((q63_t) *pSrcA++ * *pSrcB++) >> 32;
+    out = __SSAT(out, 31);
+    *pDst++ = out << 1U;
+
+    out = ((q63_t) *pSrcA++ * *pSrcB++) >> 32;
+    out = __SSAT(out, 31);
+    *pDst++ = out << 1U;
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#else
+  /* Loop unrolling: Compute remaining outputs */
+  blkCnt = blockSize % 0x4U;
 
-  /* Run the below code for Cortex-M0 */
+#else
 
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   while (blkCnt > 0U)
   {
     /* C = A * B */
-    /* Multiply the inputs and then store the results in the destination buffer. */
-    *pDst++ =
-      (q31_t) clip_q63_to_q31(((q63_t) (*pSrcA++) * (*pSrcB++)) >> 31);
 
-    /* Decrement the blockSize loop counter */
+    /* Multiply inputs and store result in destination buffer. */
+    out = ((q63_t) *pSrcA++ * *pSrcB++) >> 32;
+    out = __SSAT(out, 31);
+    *pDst++ = out << 1U;
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
 }
 
 /**
- * @} end of BasicMult group
+  @} end of BasicMult group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_mult_q7.c b/DSP/Source/BasicMathFunctions/arm_mult_q7.c
index d8a2f8a..5587ce5 100644
--- a/DSP/Source/BasicMathFunctions/arm_mult_q7.c
+++ b/DSP/Source/BasicMathFunctions/arm_mult_q7.c
@@ -3,13 +3,13 @@
  * Title:        arm_mult_q7.c
  * Description:  Q7 vector multiplication
  *
- * $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
  *
@@ -29,87 +29,91 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicMult
- * @{
+  @addtogroup BasicMult
+  @{
  */
 
 /**
- * @brief           Q7 vector multiplication
- * @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.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.
+  @brief         Q7 vector multiplication
+  @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
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q7 range [0x80 0x7F] are saturated.
  */
 
 void arm_mult_q7(
-  q7_t * pSrcA,
-  q7_t * pSrcB,
-  q7_t * pDst,
-  uint32_t blockSize)
+  const q7_t * pSrcA,
+  const q7_t * pSrcB,
+        q7_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counters */
+        uint32_t blkCnt;                               /* Loop counter */
 
-#if defined (ARM_MATH_DSP)
+#if defined (ARM_MATH_LOOPUNROLL)
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q7_t out1, out2, out3, out4;                   /* Temporary variables to store the product */
+#if defined (ARM_MATH_DSP)
+  q7_t out1, out2, out3, out4;                   /* Temporary output variables */
+#endif
 
-  /* loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 */
-    /* Multiply the inputs and store the results in temporary variables */
+
+#if defined (ARM_MATH_DSP)
+    /* Multiply inputs and store results in temporary variables */
     out1 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
     out2 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
     out3 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
     out4 = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
 
-    /* Store the results of 4 inputs in the destination buffer in single cycle by packing */
-    *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
+    /* Pack and store result in destination buffer (in single write) */
+    write_q7x4_ia (&pDst, __PACKq7(out1, out2, out3, out4));
+#else
+    *pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    *pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    *pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+    *pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
+#endif
 
-    /* Decrement the blockSize loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   while (blkCnt > 0U)
   {
     /* C = A * B */
-    /* Multiply the inputs and store the result in the destination buffer */
+
+    /* Multiply input and store result in destination buffer. */
     *pDst++ = (q7_t) __SSAT((((q15_t) (*pSrcA++) * (*pSrcB++)) >> 7), 8);
 
-    /* Decrement the blockSize loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of BasicMult group
+  @} end of BasicMult group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_negate_f32.c b/DSP/Source/BasicMathFunctions/arm_negate_f32.c
index e39624c..f807112 100644
--- a/DSP/Source/BasicMathFunctions/arm_negate_f32.c
+++ b/DSP/Source/BasicMathFunctions/arm_negate_f32.c
@@ -3,13 +3,13 @@
  * Title:        arm_negate_f32.c
  * Description:  Negates floating-point vectors
  *
- * $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
  *
@@ -29,106 +29,117 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @defgroup negate Vector Negate
- *
- * Negates the elements of a vector.
- *
- * <pre>
- *     pDst[n] = -pSrc[n],   0 <= n < blockSize.
- * </pre>
- *
- * The functions support in-place computation allowing the source and
- * destination pointers to reference the same memory buffer.
- * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+  @defgroup BasicNegate Vector Negate
+
+  Negates the elements of a vector.
+
+  <pre>
+      pDst[n] = -pSrc[n],   0 <= n < blockSize.
+  </pre>
+
+  The functions support in-place computation allowing the source and
+  destination pointers to reference the same memory buffer.
+  There are separate functions for floating-point, Q7, Q15, and Q31 data types.
  */
 
 /**
- * @addtogroup negate
- * @{
+  @addtogroup BasicNegate
+  @{
  */
 
 /**
- * @brief  Negates the elements of a floating-point vector.
- * @param[in]  *pSrc points to the input vector
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
+  @brief         Negates the elements of a floating-point vector.
+  @param[in]     pSrc       points to input vector.
+  @param[out]    pDst       points to output vector.
+  @param[in]     blockSize  number of samples in each vector.
+  @return        none
  */
 
 void arm_negate_f32(
-  float32_t * pSrc,
-  float32_t * pDst,
-  uint32_t blockSize)
+  const float32_t * pSrc,
+        float32_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
+        uint32_t blkCnt;                               /* Loop counter */
 
+#if defined(ARM_MATH_NEON_EXPERIMENTAL)
+    float32x4_t vec1;
+    float32x4_t res;
 
-#if defined (ARM_MATH_DSP)
+    /* Compute 4 outputs at a time */
+    blkCnt = blockSize >> 2U;
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  float32_t in1, in2, in3, in4;                  /* temporary variables */
+    while (blkCnt > 0U)
+    {
+        /* C = -A */
 
-  /*loop Unrolling */
+    	/* Negate and then store the results in the destination buffer. */
+        vec1 = vld1q_f32(pSrc);
+        res = vnegq_f32(vec1);
+        vst1q_f32(pDst, res);
+
+        /* Increment pointers */
+        pSrc += 4;
+        pDst += 4;
+        
+        /* Decrement the loop counter */
+        blkCnt--;
+    }
+
+    /* Tail */
+    blkCnt = blockSize & 0x3;
+
+#else
+#if defined (ARM_MATH_LOOPUNROLL)
+
+  /* Loop unrolling: Compute 4 outputs at a time */
   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)
   {
-    /* read inputs from source */
-    in1 = *pSrc;
-    in2 = *(pSrc + 1);
-    in3 = *(pSrc + 2);
-    in4 = *(pSrc + 3);
-
-    /* negate the input */
-    in1 = -in1;
-    in2 = -in2;
-    in3 = -in3;
-    in4 = -in4;
-
-    /* store the result to destination */
-    *pDst = in1;
-    *(pDst + 1) = in2;
-    *(pDst + 2) = in3;
-    *(pDst + 3) = in4;
-
-    /* update pointers to process next samples */
-    pSrc += 4U;
-    pDst += 4U;
-
-    /* Decrement the loop counter */
+    /* C = -A */
+
+    /* Negate and store result in destination buffer. */
+    *pDst++ = -*pSrc++;
+
+    *pDst++ = -*pSrc++;
+
+    *pDst++ = -*pSrc++;
+
+    *pDst++ = -*pSrc++;
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+#endif /* #if defined(ARM_MATH_NEON_EXPERIMENTAL) */
 
   while (blkCnt > 0U)
   {
     /* C = -A */
-    /* Negate and then store the results in the destination buffer. */
+
+    /* Negate and store result in destination buffer. */
     *pDst++ = -*pSrc++;
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of negate group
+  @} end of BasicNegate group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_negate_q15.c b/DSP/Source/BasicMathFunctions/arm_negate_q15.c
index 9624160..267e4cc 100644
--- a/DSP/Source/BasicMathFunctions/arm_negate_q15.c
+++ b/DSP/Source/BasicMathFunctions/arm_negate_q15.c
@@ -3,13 +3,13 @@
  * Title:        arm_negate_q15.c
  * Description:  Negates Q15 vectors
  *
- * $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
  *
@@ -29,103 +29,98 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup negate
- * @{
+  @addtogroup BasicNegate
+  @{
  */
 
 /**
- * @brief  Negates the elements of a Q15 vector.
- * @param[in]  *pSrc points to the input vector
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
- *
- * \par Conditions for optimum performance
- *  Input and output buffers should be aligned by 32-bit
- *
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * The Q15 value -1 (0x8000) will be saturated to the maximum allowable positive value 0x7FFF.
+  @brief         Negates the elements of a Q15 vector.
+  @param[in]     pSrc       points to the input vector.
+  @param[out]    pDst       points to the output vector.
+  @param[in]     blockSize  number of samples in each vector.
+  @return        none
+
+  @par           Conditions for optimum performance
+                   Input and output buffers should be aligned by 32-bit
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   The Q15 value -1 (0x8000) is saturated to the maximum allowable positive value 0x7FFF.
  */
 
 void arm_negate_q15(
-  q15_t * pSrc,
-  q15_t * pDst,
-  uint32_t blockSize)
+  const q15_t * pSrc,
+        q15_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-  q15_t in;
-
-#if defined (ARM_MATH_DSP)
-
-/* Run the below code for Cortex-M4 and Cortex-M3 */
+        uint32_t blkCnt;                               /* Loop counter */
+        q15_t in;                                      /* Temporary input variable */
 
-  q31_t in1, in2;                                /* Temporary variables */
+#if defined (ARM_MATH_LOOPUNROLL)
 
+#if defined (ARM_MATH_DSP)
+  q31_t in1;                                    /* Temporary input variables */
+#endif
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 */
-    /* Read two inputs at a time */
-    in1 = _SIMD32_OFFSET(pSrc);
-    in2 = _SIMD32_OFFSET(pSrc + 2);
 
-    /* negate two samples at a time */
-    in1 = __QSUB16(0, in1);
+#if defined (ARM_MATH_DSP)
+    /* Negate and store result in destination buffer (2 samples at a time). */
+    in1 = read_q15x2_ia ((q15_t **) &pSrc);
+    write_q15x2_ia (&pDst, __QSUB16(0, in1));
 
-    /* negate two samples at a time */
-    in2 = __QSUB16(0, in2);
+    in1 = read_q15x2_ia ((q15_t **) &pSrc);
+    write_q15x2_ia (&pDst, __QSUB16(0, in1));
+#else
+    in = *pSrc++;
+    *pDst++ = (in == (q15_t) 0x8000) ? (q15_t) 0x7fff : -in;
 
-    /* store the result to destination 2 samples at a time */
-    _SIMD32_OFFSET(pDst) = in1;
-    /* store the result to destination 2 samples at a time */
-    _SIMD32_OFFSET(pDst + 2) = in2;
+    in = *pSrc++;
+    *pDst++ = (in == (q15_t) 0x8000) ? (q15_t) 0x7fff : -in;
 
+    in = *pSrc++;
+    *pDst++ = (in == (q15_t) 0x8000) ? (q15_t) 0x7fff : -in;
 
-    /* update pointers to process next samples */
-    pSrc += 4U;
-    pDst += 4U;
+    in = *pSrc++;
+    *pDst++ = (in == (q15_t) 0x8000) ? (q15_t) 0x7fff : -in;
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   while (blkCnt > 0U)
   {
     /* C = -A */
-    /* Negate and then store the result in the destination buffer. */
+
+    /* Negate and store result in destination buffer. */
     in = *pSrc++;
-    *pDst++ = (in == (q15_t) 0x8000) ? 0x7fff : -in;
+    *pDst++ = (in == (q15_t) 0x8000) ? (q15_t) 0x7fff : -in;
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of negate group
+  @} end of BasicNegate group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_negate_q31.c b/DSP/Source/BasicMathFunctions/arm_negate_q31.c
index 4a5a58d..645fb0a 100644
--- a/DSP/Source/BasicMathFunctions/arm_negate_q31.c
+++ b/DSP/Source/BasicMathFunctions/arm_negate_q31.c
@@ -3,13 +3,13 @@
  * Title:        arm_negate_q31.c
  * Description:  Negates Q31 vectors
  *
- * $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
  *
@@ -29,89 +29,104 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup negate
- * @{
+  @addtogroup BasicNegate
+  @{
  */
 
 /**
- * @brief  Negates the elements of a Q31 vector.
- * @param[in]  *pSrc points to the input vector
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * The Q31 value -1 (0x80000000) will be saturated to the maximum allowable positive value 0x7FFFFFFF.
+  @brief         Negates the elements of a Q31 vector.
+  @param[in]     pSrc       points to the input vector.
+  @param[out]    pDst       points to the output vector.
+  @param[in]     blockSize   number of samples in each vector.
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   The Q31 value -1 (0x80000000) is saturated to the maximum allowable positive value 0x7FFFFFFF.
  */
 
 void arm_negate_q31(
-  q31_t * pSrc,
-  q31_t * pDst,
-  uint32_t blockSize)
+  const q31_t * pSrc,
+        q31_t * pDst,
+        uint32_t blockSize)
 {
-  q31_t in;                                      /* Temporary variable */
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+        q31_t in;                                      /* Temporary input variable */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t in1, in2, in3, in4;
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 */
-    /* Negate and then store the results in the destination buffer. */
-    in1 = *pSrc++;
-    in2 = *pSrc++;
-    in3 = *pSrc++;
-    in4 = *pSrc++;
-
-    *pDst++ = __QSUB(0, in1);
-    *pDst++ = __QSUB(0, in2);
-    *pDst++ = __QSUB(0, in3);
-    *pDst++ = __QSUB(0, in4);
-
-    /* Decrement the loop counter */
+
+    /* Negate and store result in destination buffer. */
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = __QSUB(0, in);
+#else
+    *pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
+#endif
+
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = __QSUB(0, in);
+#else
+    *pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
+#endif
+
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = __QSUB(0, in);
+#else
+    *pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
+#endif
+
+    in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = __QSUB(0, in);
+#else
+    *pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   while (blkCnt > 0U)
   {
     /* C = -A */
-    /* Negate and then store the result in the destination buffer. */
+
+    /* Negate and store result in destination buffer. */
     in = *pSrc++;
+#if defined (ARM_MATH_DSP)
+    *pDst++ = __QSUB(0, in);
+#else
     *pDst++ = (in == INT32_MIN) ? INT32_MAX : -in;
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of negate group
+  @} end of BasicNegate group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_negate_q7.c b/DSP/Source/BasicMathFunctions/arm_negate_q7.c
index d72c317..40a373e 100644
--- a/DSP/Source/BasicMathFunctions/arm_negate_q7.c
+++ b/DSP/Source/BasicMathFunctions/arm_negate_q7.c
@@ -3,13 +3,13 @@
  * Title:        arm_negate_q7.c
  * Description:  Negates Q7 vectors
  *
- * $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
  *
@@ -29,85 +29,98 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup negate
- * @{
+  @addtogroup BasicNegate
+  @{
  */
 
 /**
- * @brief  Negates the elements of a Q7 vector.
- * @param[in]  *pSrc points to the input vector
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * The Q7 value -1 (0x80) will be saturated to the maximum allowable positive value 0x7F.
+  @brief         Negates the elements of a Q7 vector.
+  @param[in]     pSrc       points to the input vector.
+  @param[out]    pDst       points to the output vector.
+  @param[in]     blockSize   number of samples in each vector.
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   The Q7 value -1 (0x80) is saturated to the maximum allowable positive value 0x7F.
  */
 
 void arm_negate_q7(
-  q7_t * pSrc,
-  q7_t * pDst,
-  uint32_t blockSize)
+  const q7_t * pSrc,
+        q7_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-  q7_t in;
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+        q7_t in;                                       /* Temporary input variable */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t input;                                   /* Input values1-4 */
-  q31_t zero = 0x00000000;
+#if defined (ARM_MATH_LOOPUNROLL)
 
+#if defined (ARM_MATH_DSP)
+  q31_t in1;                                    /* Temporary input variable */
+#endif
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 */
-    /* Read four inputs */
-    input = *__SIMD32(pSrc)++;
 
-    /* Store the Negated results in the destination buffer in a single cycle by packing the results */
-    *__SIMD32(pDst)++ = __QSUB8(zero, input);
+#if defined (ARM_MATH_DSP)
+    /* Negate and store result in destination buffer (4 samples at a time). */
+    in1 = read_q7x4_ia ((q7_t **) &pSrc);
+    write_q7x4_ia (&pDst, __QSUB8(0, in1));
+#else
+    in = *pSrc++;
+    *pDst++ = (in == (q7_t) 0x80) ? (q7_t) 0x7f : -in;
+
+    in = *pSrc++;
+    *pDst++ = (in == (q7_t) 0x80) ? (q7_t) 0x7f : -in;
+
+    in = *pSrc++;
+    *pDst++ = (in == (q7_t) 0x80) ? (q7_t) 0x7f : -in;
 
-    /* Decrement the loop counter */
+    in = *pSrc++;
+    *pDst++ = (in == (q7_t) 0x80) ? (q7_t) 0x7f : -in;
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   while (blkCnt > 0U)
   {
     /* C = -A */
-    /* Negate and then store the results in the destination buffer. */ \
-      in = *pSrc++;
-    *pDst++ = (in == (q7_t) 0x80) ? 0x7f : -in;
 
-    /* Decrement the loop counter */
+    /* Negate and store result in destination buffer. */
+    in = *pSrc++;
+
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (q7_t) __QSUB(0, in);
+#else
+    *pDst++ = (in == (q7_t) 0x80) ? (q7_t) 0x7f : -in;
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of negate group
+  @} end of BasicNegate group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_offset_f32.c b/DSP/Source/BasicMathFunctions/arm_offset_f32.c
index ebc20a4..b10e3f1 100644
--- a/DSP/Source/BasicMathFunctions/arm_offset_f32.c
+++ b/DSP/Source/BasicMathFunctions/arm_offset_f32.c
@@ -3,13 +3,13 @@
  * Title:        arm_offset_f32.c
  * Description:  Floating-point vector offset
  *
- * $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
  *
@@ -29,126 +29,119 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @defgroup offset Vector Offset
- *
- * Adds a constant offset to each element of a vector.
- *
- * <pre>
- *     pDst[n] = pSrc[n] + offset,   0 <= n < blockSize.
- * </pre>
- *
- * The functions support in-place computation allowing the source and
- * destination pointers to reference the same memory buffer.
- * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+  @defgroup BasicOffset Vector Offset
+
+  Adds a constant offset to each element of a vector.
+
+  <pre>
+      pDst[n] = pSrc[n] + offset,   0 <= n < blockSize.
+  </pre>
+
+  The functions support in-place computation allowing the source and
+  destination pointers to reference the same memory buffer.
+  There are separate functions for floating-point, Q7, Q15, and Q31 data types.
  */
 
 /**
- * @addtogroup offset
- * @{
+  @addtogroup BasicOffset
+  @{
  */
 
 /**
- * @brief  Adds a constant offset to a floating-point vector.
- * @param[in]  *pSrc points to the input vector
- * @param[in]  offset is the offset to be added
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
+  @brief         Adds a constant offset to a floating-point vector.
+  @param[in]     pSrc       points to the input vector
+  @param[in]     offset     is the offset to be added
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
  */
 
-
 void arm_offset_f32(
-  float32_t * pSrc,
-  float32_t offset,
-  float32_t * pDst,
-  uint32_t blockSize)
+  const float32_t * pSrc,
+        float32_t offset,
+        float32_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+
+#if defined(ARM_MATH_NEON_EXPERIMENTAL)
+    float32x4_t vec1;
+    float32x4_t res;
+
+    /* Compute 4 outputs at a time */
+    blkCnt = blockSize >> 2U;
+
+    while (blkCnt > 0U)
+    {
+        /* C = A + offset */
+ 
+        /* Add offset and then store the results in the destination buffer. */
+        vec1 = vld1q_f32(pSrc);
+        res = vaddq_f32(vec1,vdupq_n_f32(offset));
+        vst1q_f32(pDst, res);
+
+        /* Increment pointers */
+        pSrc += 4;
+        pDst += 4;
+        
+        /* Decrement the loop counter */
+        blkCnt--;
+    }
+
+    /* Tail */
+    blkCnt = blockSize & 0x3;
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  float32_t in1, in2, in3, in4;
+#else
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 + offset */
-    /* Add offset and then store the results in the destination buffer. */
-    /* read samples from source */
-    in1 = *pSrc;
-    in2 = *(pSrc + 1);
-
-    /* add offset to input */
-    in1 = in1 + offset;
-
-    /* read samples from source */
-    in3 = *(pSrc + 2);
-
-    /* add offset to input */
-    in2 = in2 + offset;
 
-    /* read samples from source */
-    in4 = *(pSrc + 3);
-
-    /* add offset to input */
-    in3 = in3 + offset;
-
-    /* store result to destination */
-    *pDst = in1;
-
-    /* add offset to input */
-    in4 = in4 + offset;
-
-    /* store result to destination */
-    *(pDst + 1) = in2;
+    /* Add offset and store result in destination buffer. */
+    *pDst++ = (*pSrc++) + offset;
 
-    /* store result to destination */
-    *(pDst + 2) = in3;
+    *pDst++ = (*pSrc++) + offset;
 
-    /* store result to destination */
-    *(pDst + 3) = in4;
+    *pDst++ = (*pSrc++) + offset;
 
-    /* update pointers to process next samples */
-    pSrc += 4U;
-    pDst += 4U;
+    *pDst++ = (*pSrc++) + offset;
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+#endif /* #if defined(ARM_MATH_NEON_EXPERIMENTAL) */
 
   while (blkCnt > 0U)
   {
     /* C = A + offset */
-    /* Add offset and then store the result in the destination buffer. */
+
+    /* Add offset and store result in destination buffer. */
     *pDst++ = (*pSrc++) + offset;
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of offset group
+  @} end of BasicOffset group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_offset_q15.c b/DSP/Source/BasicMathFunctions/arm_offset_q15.c
index dab0b10..cd2f22b 100644
--- a/DSP/Source/BasicMathFunctions/arm_offset_q15.c
+++ b/DSP/Source/BasicMathFunctions/arm_offset_q15.c
@@ -3,13 +3,13 @@
  * Title:        arm_offset_q15.c
  * Description:  Q15 vector offset
  *
- * $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
  *
@@ -29,96 +29,93 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup offset
- * @{
+  @addtogroup BasicOffset
+  @{
  */
 
 /**
- * @brief  Adds a constant offset to a Q15 vector.
- * @param[in]  *pSrc points to the input vector
- * @param[in]  offset is the offset to be added
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.
+  @brief         Adds a constant offset to a Q15 vector.
+  @param[in]     pSrc       points to the input vector
+  @param[in]     offset     is the offset to be added
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.
  */
 
 void arm_offset_q15(
-  q15_t * pSrc,
-  q15_t offset,
-  q15_t * pDst,
-  uint32_t blockSize)
+  const q15_t * pSrc,
+        q15_t offset,
+        q15_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
+        uint32_t blkCnt;                               /* Loop counter */
 
-#if defined (ARM_MATH_DSP)
+#if defined (ARM_MATH_LOOPUNROLL)
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
+#if defined (ARM_MATH_DSP)
   q31_t offset_packed;                           /* Offset packed to 32 bit */
 
-
-  /*loop Unrolling */
-  blkCnt = blockSize >> 2U;
-
   /* Offset is packed to 32 bit in order to use SIMD32 for addition */
   offset_packed = __PKHBT(offset, offset, 16);
+#endif
+
+  /* Loop unrolling: Compute 4 outputs at a time */
+  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 + offset */
-    /* Add offset and then store the results in the destination buffer, 2 samples at a time. */
-    *__SIMD32(pDst)++ = __QADD16(*__SIMD32(pSrc)++, offset_packed);
-    *__SIMD32(pDst)++ = __QADD16(*__SIMD32(pSrc)++, offset_packed);
 
-    /* Decrement the loop counter */
+#if defined (ARM_MATH_DSP)
+    /* Add offset and store result in destination buffer (2 samples at a time). */
+    write_q15x2_ia (&pDst, __QADD16(read_q15x2_ia ((q15_t **) &pSrc), offset_packed));
+    write_q15x2_ia (&pDst, __QADD16(read_q15x2_ia ((q15_t **) &pSrc), offset_packed));
+#else
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrc++ + offset), 16);
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrc++ + offset), 16);
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrc++ + offset), 16);
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrc++ + offset), 16);
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
-  while (blkCnt > 0U)
-  {
-    /* C = A + offset */
-    /* Add offset and then store the results in the destination buffer. */
-    *pDst++ = (q15_t) __QADD16(*pSrc++, offset);
-
-    /* Decrement the loop counter */
-    blkCnt--;
-  }
-
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A + offset */
-    /* Add offset and then store the results in the destination buffer. */
-    *pDst++ = (q15_t) __SSAT(((q31_t) * pSrc++ + offset), 16);
 
-    /* Decrement the loop counter */
+    /* Add offset and store result in destination buffer. */
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (q15_t) __QADD16(*pSrc++, offset);
+#else
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrc++ + offset), 16);
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
 }
 
 /**
- * @} end of offset group
+  @} end of BasicOffset group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_offset_q31.c b/DSP/Source/BasicMathFunctions/arm_offset_q31.c
index 655426e..5de36b4 100644
--- a/DSP/Source/BasicMathFunctions/arm_offset_q31.c
+++ b/DSP/Source/BasicMathFunctions/arm_offset_q31.c
@@ -3,13 +3,13 @@
  * Title:        arm_offset_q31.c
  * Description:  Q31 vector offset
  *
- * $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
  *
@@ -29,100 +29,100 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup offset
- * @{
+  @addtogroup BasicOffset
+  @{
  */
 
 /**
- * @brief  Adds a constant offset to a Q31 vector.
- * @param[in]  *pSrc points to the input vector
- * @param[in]  offset is the offset to be added
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] are saturated.
+  @brief         Adds a constant offset to a Q31 vector.
+  @param[in]     pSrc       points to the input vector
+  @param[in]     offset     is the offset to be added
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] are saturated.
  */
 
 void arm_offset_q31(
-  q31_t * pSrc,
-  q31_t offset,
-  q31_t * pDst,
-  uint32_t blockSize)
+  const q31_t * pSrc,
+        q31_t offset,
+        q31_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t in1, in2, in3, in4;
+#if defined (ARM_MATH_LOOPUNROLL)
 
-
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 + offset */
-    /* Add offset and then store the results in the destination buffer. */
-    in1 = *pSrc++;
-    in2 = *pSrc++;
-    in3 = *pSrc++;
-    in4 = *pSrc++;
-
-    *pDst++ = __QADD(in1, offset);
-    *pDst++ = __QADD(in2, offset);
-    *pDst++ = __QADD(in3, offset);
-    *pDst++ = __QADD(in4, offset);
-
-    /* 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;
+    /* Add offset and store result in destination buffer. */
+#if defined (ARM_MATH_DSP)
+    *pDst++ = __QADD(*pSrc++, offset);
+#else
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrc++ + offset);
+#endif
 
-  while (blkCnt > 0U)
-  {
-    /* C = A + offset */
-    /* Add offset and then store the result in the destination buffer. */
+#if defined (ARM_MATH_DSP)
+    *pDst++ = __QADD(*pSrc++, offset);
+#else
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrc++ + offset);
+#endif
+
+#if defined (ARM_MATH_DSP)
     *pDst++ = __QADD(*pSrc++, offset);
+#else
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrc++ + offset);
+#endif
+
+#if defined (ARM_MATH_DSP)
+    *pDst++ = __QADD(*pSrc++, offset);
+#else
+    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrc++ + offset);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#else
+  /* Loop unrolling: Compute remaining outputs */
+  blkCnt = blockSize % 0x4U;
 
-  /* Run the below code for Cortex-M0 */
+#else
 
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A + offset */
-    /* Add offset and then store the result in the destination buffer. */
+
+    /* Add offset and store result in destination buffer. */
+#if defined (ARM_MATH_DSP)
+    *pDst++ = __QADD(*pSrc++, offset);
+#else
     *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrc++ + offset);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
 }
 
 /**
- * @} end of offset group
+  @} end of BasicOffset group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_offset_q7.c b/DSP/Source/BasicMathFunctions/arm_offset_q7.c
index 5de6241..f67db45 100644
--- a/DSP/Source/BasicMathFunctions/arm_offset_q7.c
+++ b/DSP/Source/BasicMathFunctions/arm_offset_q7.c
@@ -3,13 +3,13 @@
  * Title:        arm_offset_q7.c
  * Description:  Q7 vector offset
  *
- * $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
  *
@@ -29,95 +29,88 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup offset
- * @{
+  @addtogroup BasicOffset
+  @{
  */
 
 /**
- * @brief  Adds a constant offset to a Q7 vector.
- * @param[in]  *pSrc points to the input vector
- * @param[in]  offset is the offset to be added
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q7 range [0x80 0x7F] are saturated.
+  @brief         Adds a constant offset to a Q7 vector.
+  @param[in]     pSrc       points to the input vector
+  @param[in]     offset     is the offset to be added
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q7 range [0x80 0x7F] are saturated.
  */
 
 void arm_offset_q7(
-  q7_t * pSrc,
-  q7_t offset,
-  q7_t * pDst,
-  uint32_t blockSize)
+  const q7_t * pSrc,
+        q7_t offset,
+        q7_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
+        uint32_t blkCnt;                               /* Loop counter */
 
-#if defined (ARM_MATH_DSP)
+#if defined (ARM_MATH_LOOPUNROLL)
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
+#if defined (ARM_MATH_DSP)
   q31_t offset_packed;                           /* Offset packed to 32 bit */
 
-
-  /*loop Unrolling */
-  blkCnt = blockSize >> 2U;
-
   /* Offset is packed to 32 bit in order to use SIMD32 for addition */
   offset_packed = __PACKq7(offset, offset, offset, offset);
+#endif
 
-  /* 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 + offset */
-    /* Add offset and then store the results in the destination bufferfor 4 samples at a time. */
-    *__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrc)++, offset_packed);
-
-    /* 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;
+  /* Loop unrolling: Compute 4 outputs at a time */
+  blkCnt = blockSize >> 2U;
 
   while (blkCnt > 0U)
   {
     /* C = A + offset */
-    /* Add offset and then store the result in the destination buffer. */
+
+#if defined (ARM_MATH_DSP)
+    /* Add offset and store result in destination buffer (4 samples at a time). */
+    write_q7x4_ia (&pDst, __QADD8(read_q7x4_ia ((q7_t **) &pSrc), offset_packed));
+#else
+    *pDst++ = (q7_t) __SSAT(*pSrc++ + offset, 8);
+    *pDst++ = (q7_t) __SSAT(*pSrc++ + offset, 8);
+    *pDst++ = (q7_t) __SSAT(*pSrc++ + offset, 8);
     *pDst++ = (q7_t) __SSAT(*pSrc++ + offset, 8);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#else
+  /* Loop unrolling: Compute remaining outputs */
+  blkCnt = blockSize % 0x4U;
 
-  /* Run the below code for Cortex-M0 */
+#else
 
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A + offset */
-    /* Add offset and then store the result in the destination buffer. */
-    *pDst++ = (q7_t) __SSAT((q15_t) * pSrc++ + offset, 8);
 
-    /* Decrement the loop counter */
+    /* Add offset and store result in destination buffer. */
+    *pDst++ = (q7_t) __SSAT((q15_t) *pSrc++ + offset, 8);
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
 }
 
 /**
- * @} end of offset group
+  @} end of BasicOffset group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_scale_f32.c b/DSP/Source/BasicMathFunctions/arm_scale_f32.c
index c90c037..72ecbe5 100644
--- a/DSP/Source/BasicMathFunctions/arm_scale_f32.c
+++ b/DSP/Source/BasicMathFunctions/arm_scale_f32.c
@@ -3,13 +3,13 @@
  * Title:        arm_scale_f32.c
  * Description:  Multiplies a floating-point vector by a scalar
  *
- * $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
  *
@@ -29,129 +29,131 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @defgroup scale Vector Scale
- *
- * Multiply a vector by a scalar value.  For floating-point data, the algorithm used is:
- *
- * <pre>
- *     pDst[n] = pSrc[n] * scale,   0 <= n < blockSize.
- * </pre>
- *
- * In the fixed-point Q7, Q15, and Q31 functions, <code>scale</code> is represented by
- * a fractional multiplication <code>scaleFract</code> and an arithmetic shift <code>shift</code>.
- * The shift allows the gain of the scaling operation to exceed 1.0.
- * The algorithm used with fixed-point data is:
- *
- * <pre>
- *     pDst[n] = (pSrc[n] * scaleFract) << shift,   0 <= n < blockSize.
- * </pre>
- *
- * The overall scale factor applied to the fixed-point data is
- * <pre>
- *     scale = scaleFract * 2^shift.
- * </pre>
- *
- * The functions support in-place computation allowing the source and destination
- * pointers to reference the same memory buffer.
+  @defgroup BasicScale Vector Scale
+
+  Multiply a vector by a scalar value.  For floating-point data, the algorithm used is:
+
+  <pre>
+      pDst[n] = pSrc[n] * scale,   0 <= n < blockSize.
+  </pre>
+
+  In the fixed-point Q7, Q15, and Q31 functions, <code>scale</code> is represented by
+  a fractional multiplication <code>scaleFract</code> and an arithmetic shift <code>shift</code>.
+  The shift allows the gain of the scaling operation to exceed 1.0.
+  The algorithm used with fixed-point data is:
+
+  <pre>
+      pDst[n] = (pSrc[n] * scaleFract) << shift,   0 <= n < blockSize.
+  </pre>
+
+  The overall scale factor applied to the fixed-point data is
+  <pre>
+      scale = scaleFract * 2^shift.
+  </pre>
+
+  The functions support in-place computation allowing the source and destination
+  pointers to reference the same memory buffer.
  */
 
 /**
- * @addtogroup scale
- * @{
+  @addtogroup BasicScale
+  @{
  */
 
 /**
- * @brief Multiplies a floating-point vector by a scalar.
- * @param[in]       *pSrc points to the input vector
- * @param[in]       scale scale factor to be applied
- * @param[out]      *pDst points to the output vector
- * @param[in]       blockSize number of samples in the vector
- * @return none.
+  @brief         Multiplies a floating-point vector by a scalar.
+  @param[in]     pSrc       points to the input vector
+  @param[in]     scale      scale factor to be applied
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
  */
 
-
 void arm_scale_f32(
-  float32_t * pSrc,
-  float32_t scale,
-  float32_t * pDst,
-  uint32_t blockSize)
+  const float32_t *pSrc,
+        float32_t scale,
+        float32_t *pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-#if defined (ARM_MATH_DSP)
+  uint32_t blkCnt;                               /* Loop counter */
+#if defined(ARM_MATH_NEON_EXPERIMENTAL)
+    float32x4_t vec1;
+    float32x4_t res;
+
+    /* Compute 4 outputs at a time */
+    blkCnt = blockSize >> 2U;
+
+    while (blkCnt > 0U)
+    {
+        /* C = A * scale */
+
+    	/* Scale the input and then store the results in the destination buffer. */
+        vec1 = vld1q_f32(pSrc);
+        res = vmulq_f32(vec1, vdupq_n_f32(scale));
+        vst1q_f32(pDst, res);
+
+        /* Increment pointers */
+        pSrc += 4; 
+        pDst += 4;
+        
+        /* Decrement the loop counter */
+        blkCnt--;
+    }
+
+    /* Tail */
+    blkCnt = blockSize & 0x3;
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  float32_t in1, in2, in3, in4;                  /* temporary variabels */
+#else
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 * scale */
-    /* Scale the input and then store the results in the destination buffer. */
-    /* read input samples from source */
-    in1 = *pSrc;
-    in2 = *(pSrc + 1);
-
-    /* multiply with scaling factor */
-    in1 = in1 * scale;
 
-    /* read input sample from source */
-    in3 = *(pSrc + 2);
-
-    /* multiply with scaling factor */
-    in2 = in2 * scale;
+    /* Scale input and store result in destination buffer. */
+    *pDst++ = (*pSrc++) * scale;
 
-    /* read input sample from source */
-    in4 = *(pSrc + 3);
+    *pDst++ = (*pSrc++) * scale;
 
-    /* multiply with scaling factor */
-    in3 = in3 * scale;
-    in4 = in4 * scale;
-    /* store the result to destination */
-    *pDst = in1;
-    *(pDst + 1) = in2;
-    *(pDst + 2) = in3;
-    *(pDst + 3) = in4;
+    *pDst++ = (*pSrc++) * scale;
 
-    /* update pointers to process next samples */
-    pSrc += 4U;
-    pDst += 4U;
+    *pDst++ = (*pSrc++) * scale;
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+#endif /* #if defined(ARM_MATH_NEON_EXPERIMENTAL) */
 
   while (blkCnt > 0U)
   {
     /* C = A * scale */
-    /* Scale the input and then store the result in the destination buffer. */
+
+    /* Scale input and store result in destination buffer. */
     *pDst++ = (*pSrc++) * scale;
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of scale group
+  @} end of BasicScale group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_scale_q15.c b/DSP/Source/BasicMathFunctions/arm_scale_q15.c
index 9d5727d..039b93d 100644
--- a/DSP/Source/BasicMathFunctions/arm_scale_q15.c
+++ b/DSP/Source/BasicMathFunctions/arm_scale_q15.c
@@ -3,13 +3,13 @@
  * Title:        arm_scale_q15.c
  * Description:  Multiplies a Q15 vector by a scalar
  *
- * $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
  *
@@ -29,66 +29,66 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup scale
- * @{
+  @addtogroup BasicScale
+  @{
  */
 
 /**
- * @brief Multiplies a Q15 vector by a scalar.
- * @param[in]       *pSrc points to the input vector
- * @param[in]       scaleFract fractional portion of the scale value
- * @param[in]       shift number of bits to shift the result by
- * @param[out]      *pDst points to the output vector
- * @param[in]       blockSize number of samples in the vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.15 format.
- * These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format.
+  @brief         Multiplies a Q15 vector by a scalar.
+  @param[in]     pSrc       points to the input vector
+  @param[in]     scaleFract fractional portion of the scale value
+  @param[in]     shift      number of bits to shift the result by
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.15 format.
+                   These are multiplied to yield a 2.30 intermediate result and this is shifted with saturation to 1.15 format.
  */
 
-
 void arm_scale_q15(
-  q15_t * pSrc,
-  q15_t scaleFract,
-  int8_t shift,
-  q15_t * pDst,
-  uint32_t blockSize)
+  const q15_t *pSrc,
+        q15_t scaleFract,
+        int8_t shift,
+        q15_t *pDst,
+        uint32_t blockSize)
 {
-  int8_t kShift = 15 - shift;                    /* shift to apply after scaling */
-  uint32_t blkCnt;                               /* loop counter */
+        uint32_t blkCnt;                               /* Loop counter */
+        int8_t kShift = 15 - shift;                    /* Shift to apply after scaling */
 
+#if defined (ARM_MATH_LOOPUNROLL)
 #if defined (ARM_MATH_DSP)
+  q31_t inA1, inA2;
+  q31_t out1, out2, out3, out4;                  /* Temporary output variables */
+  q15_t in1, in2, in3, in4;                      /* Temporary input variables */
+#endif
+#endif
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q15_t in1, in2, in3, in4;
-  q31_t inA1, inA2;                              /* Temporary variables */
-  q31_t out1, out2, out3, out4;
-
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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)
   {
-    /* Reading 2 inputs from memory */
-    inA1 = *__SIMD32(pSrc)++;
-    inA2 = *__SIMD32(pSrc)++;
-
     /* C = A * scale */
-    /* Scale the inputs and then store the 2 results in the destination buffer
+
+#if defined (ARM_MATH_DSP)
+    /* read 2 times 2 samples at a time from source */
+    inA1 = read_q15x2_ia ((q15_t **) &pSrc);
+    inA2 = read_q15x2_ia ((q15_t **) &pSrc);
+
+    /* Scale inputs and store result in temporary variables
      * in single cycle by packing the outputs */
     out1 = (q31_t) ((q15_t) (inA1 >> 16) * scaleFract);
-    out2 = (q31_t) ((q15_t) inA1 * scaleFract);
+    out2 = (q31_t) ((q15_t) (inA1      ) * scaleFract);
     out3 = (q31_t) ((q15_t) (inA2 >> 16) * scaleFract);
-    out4 = (q31_t) ((q15_t) inA2 * scaleFract);
+    out4 = (q31_t) ((q15_t) (inA2      ) * scaleFract);
 
     /* apply shifting */
     out1 = out1 >> kShift;
@@ -102,49 +102,43 @@ void arm_scale_q15(
     in3 = (q15_t) (__SSAT(out3, 16));
     in4 = (q15_t) (__SSAT(out4, 16));
 
-    /* store the result to destination */
-    *__SIMD32(pDst)++ = __PKHBT(in2, in1, 16);
-    *__SIMD32(pDst)++ = __PKHBT(in4, in3, 16);
+    /* store result to destination */
+    write_q15x2_ia (&pDst, __PKHBT(in2, in1, 16));
+    write_q15x2_ia (&pDst, __PKHBT(in4, in3, 16));
+#else
+    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 16));
+    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 16));
+    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 16));
+    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 16));
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
-  while (blkCnt > 0U)
-  {
-    /* C = A * scale */
-    /* Scale the input and then store the result in the destination buffer. */
-    *pDst++ = (q15_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 16));
-
-    /* Decrement the loop counter */
-    blkCnt--;
-  }
-
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A * scale */
-    /* Scale the input and then store the result in the destination buffer. */
-    *pDst++ = (q15_t) (__SSAT(((q31_t) * pSrc++ * scaleFract) >> kShift, 16));
 
-    /* Decrement the loop counter */
+    /* Scale input and store result in destination buffer. */
+    *pDst++ = (q15_t) (__SSAT(((q31_t) *pSrc++ * scaleFract) >> kShift, 16));
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
 }
 
 /**
- * @} end of scale group
+  @} end of BasicScale group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_scale_q31.c b/DSP/Source/BasicMathFunctions/arm_scale_q31.c
index e89524d..d762ca7 100644
--- a/DSP/Source/BasicMathFunctions/arm_scale_q31.c
+++ b/DSP/Source/BasicMathFunctions/arm_scale_q31.c
@@ -3,13 +3,13 @@
  * Title:        arm_scale_q31.c
  * Description:  Multiplies a Q31 vector by a scalar
  *
- * $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
  *
@@ -29,199 +29,163 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup scale
- * @{
+  @addtogroup BasicScale
+  @{
  */
 
 /**
- * @brief Multiplies a Q31 vector by a scalar.
- * @param[in]       *pSrc points to the input vector
- * @param[in]       scaleFract fractional portion of the scale value
- * @param[in]       shift number of bits to shift the result by
- * @param[out]      *pDst points to the output vector
- * @param[in]       blockSize number of samples in the vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format.
- * These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format.
+  @brief         Multiplies a Q31 vector by a scalar.
+  @param[in]     pSrc       points to the input vector
+  @param[in]     scaleFract fractional portion of the scale value
+  @param[in]     shift      number of bits to shift the result by
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.31 format.
+                   These are multiplied to yield a 2.62 intermediate result and this is shifted with saturation to 1.31 format.
  */
 
 void arm_scale_q31(
-  q31_t * pSrc,
-  q31_t scaleFract,
-  int8_t shift,
-  q31_t * pDst,
-  uint32_t blockSize)
+  const q31_t *pSrc,
+        q31_t scaleFract,
+        int8_t shift,
+        q31_t *pDst,
+        uint32_t blockSize)
 {
-  int8_t kShift = shift + 1;                     /* Shift to apply after scaling */
-  int8_t sign = (kShift & 0x80);
-  uint32_t blkCnt;                               /* loop counter */
-  q31_t in, out;
-
-#if defined (ARM_MATH_DSP)
-
-/* Run the below code for Cortex-M4 and Cortex-M3 */
+        uint32_t blkCnt;                               /* Loop counter */
+        q31_t in, out;                                 /* Temporary variables */
+        int8_t kShift = shift + 1;                     /* Shift to apply after scaling */
+        int8_t sign = (kShift & 0x80);
 
-  q31_t in1, in2, in3, in4;                      /* temporary input variables */
-  q31_t out1, out2, out3, out4;                  /* temporary output variabels */
+#if defined (ARM_MATH_LOOPUNROLL)
 
-
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   blkCnt = blockSize >> 2U;
 
   if (sign == 0U)
   {
-    /* 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)
     {
-      /* read four inputs from source */
-      in1 = *pSrc;
-      in2 = *(pSrc + 1);
-      in3 = *(pSrc + 2);
-      in4 = *(pSrc + 3);
-
-      /* multiply input with scaler value */
-      in1 = ((q63_t) in1 * scaleFract) >> 32;
-      in2 = ((q63_t) in2 * scaleFract) >> 32;
-      in3 = ((q63_t) in3 * scaleFract) >> 32;
-      in4 = ((q63_t) in4 * scaleFract) >> 32;
-
-      /* apply shifting */
-      out1 = in1 << kShift;
-      out2 = in2 << kShift;
-
-      /* saturate the results. */
-      if (in1 != (out1 >> kShift))
-        out1 = 0x7FFFFFFF ^ (in1 >> 31);
-
-      if (in2 != (out2 >> kShift))
-        out2 = 0x7FFFFFFF ^ (in2 >> 31);
-
-      out3 = in3 << kShift;
-      out4 = in4 << kShift;
-
-      *pDst = out1;
-      *(pDst + 1) = out2;
-
-      if (in3 != (out3 >> kShift))
-        out3 = 0x7FFFFFFF ^ (in3 >> 31);
-
-      if (in4 != (out4 >> kShift))
-        out4 = 0x7FFFFFFF ^ (in4 >> 31);
-
-      /* Store result destination */
-      *(pDst + 2) = out3;
-      *(pDst + 3) = out4;
-
-      /* Update pointers to process next sampels */
-      pSrc += 4U;
-      pDst += 4U;
-
-      /* Decrement the loop counter */
+      /* C = A * scale */
+
+      /* Scale input and store result in destination buffer. */
+      in = *pSrc++;                                /* read input from source */
+      in = ((q63_t) in * scaleFract) >> 32;        /* multiply input with scaler value */
+      out = in << kShift;                          /* apply shifting */
+      if (in != (out >> kShift))                   /* saturate the result */
+        out = 0x7FFFFFFF ^ (in >> 31);
+      *pDst++ = out;                               /* Store result destination */
+
+      in = *pSrc++;
+      in = ((q63_t) in * scaleFract) >> 32;
+      out = in << kShift;
+      if (in != (out >> kShift))
+        out = 0x7FFFFFFF ^ (in >> 31);
+      *pDst++ = out;
+
+      in = *pSrc++;
+      in = ((q63_t) in * scaleFract) >> 32;
+      out = in << kShift;
+      if (in != (out >> kShift))
+        out = 0x7FFFFFFF ^ (in >> 31);
+      *pDst++ = out;
+
+      in = *pSrc++;
+      in = ((q63_t) in * scaleFract) >> 32;
+      out = in << kShift;
+      if (in != (out >> kShift))
+        out = 0x7FFFFFFF ^ (in >> 31);
+      *pDst++ = out;
+
+      /* Decrement loop counter */
       blkCnt--;
     }
-
   }
   else
   {
-    /* 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)
     {
-      /* read four inputs from source */
-      in1 = *pSrc;
-      in2 = *(pSrc + 1);
-      in3 = *(pSrc + 2);
-      in4 = *(pSrc + 3);
-
-      /* multiply input with scaler value */
-      in1 = ((q63_t) in1 * scaleFract) >> 32;
-      in2 = ((q63_t) in2 * scaleFract) >> 32;
-      in3 = ((q63_t) in3 * scaleFract) >> 32;
-      in4 = ((q63_t) in4 * scaleFract) >> 32;
-
-      /* apply shifting */
-      out1 = in1 >> -kShift;
-      out2 = in2 >> -kShift;
-
-      out3 = in3 >> -kShift;
-      out4 = in4 >> -kShift;
-
-      /* Store result destination */
-      *pDst = out1;
-      *(pDst + 1) = out2;
-
-      *(pDst + 2) = out3;
-      *(pDst + 3) = out4;
-
-      /* Update pointers to process next sampels */
-      pSrc += 4U;
-      pDst += 4U;
-
-      /* Decrement the loop counter */
+      /* C = A * scale */
+
+      /* Scale input and store result in destination buffer. */
+      in = *pSrc++;                                /* read four inputs from source */
+      in = ((q63_t) in * scaleFract) >> 32;        /* multiply input with scaler value */
+      out = in >> -kShift;                         /* apply shifting */
+      *pDst++ = out;                               /* Store result destination */
+
+      in = *pSrc++;
+      in = ((q63_t) in * scaleFract) >> 32;
+      out = in >> -kShift;
+      *pDst++ = out;
+
+      in = *pSrc++;
+      in = ((q63_t) in * scaleFract) >> 32;
+      out = in >> -kShift;
+      *pDst++ = out;
+
+      in = *pSrc++;
+      in = ((q63_t) in * scaleFract) >> 32;
+      out = in >> -kShift;
+      *pDst++ = out;
+
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
-  if (sign == 0)
+  if (sign == 0U)
   {
-	  while (blkCnt > 0U)
-	  {
-		/* C = A * scale */
-		/* Scale the input and then store the result in the destination buffer. */
-		in = *pSrc++;
-		in = ((q63_t) in * scaleFract) >> 32;
-
-		out = in << kShift;
-
-		if (in != (out >> kShift))
-			out = 0x7FFFFFFF ^ (in >> 31);
+    while (blkCnt > 0U)
+    {
+      /* C = A * scale */
 
-		*pDst++ = out;
+      /* Scale input and store result in destination buffer. */
+      in = *pSrc++;
+      in = ((q63_t) in * scaleFract) >> 32;
+      out = in << kShift;
+      if (in != (out >> kShift))
+          out = 0x7FFFFFFF ^ (in >> 31);
+      *pDst++ = out;
 
-		/* Decrement the loop counter */
-		blkCnt--;
-	  }
+      /* Decrement loop counter */
+      blkCnt--;
+    }
   }
   else
   {
-	  while (blkCnt > 0U)
-	  {
-		/* C = A * scale */
-		/* Scale the input and then store the result in the destination buffer. */
-		in = *pSrc++;
-		in = ((q63_t) in * scaleFract) >> 32;
-
-		out = in >> -kShift;
-
-		*pDst++ = out;
+    while (blkCnt > 0U)
+    {
+      /* C = A * scale */
 
-		/* Decrement the loop counter */
-		blkCnt--;
-	  }
+      /* Scale input and store result in destination buffer. */
+      in = *pSrc++;
+      in = ((q63_t) in * scaleFract) >> 32;
+      out = in >> -kShift;
+      *pDst++ = out;
 
+      /* Decrement loop counter */
+      blkCnt--;
+    }
   }
+
 }
 
 /**
- * @} end of scale group
+  @} end of BasicScale group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_scale_q7.c b/DSP/Source/BasicMathFunctions/arm_scale_q7.c
index 6cf1bbb..cb967d2 100644
--- a/DSP/Source/BasicMathFunctions/arm_scale_q7.c
+++ b/DSP/Source/BasicMathFunctions/arm_scale_q7.c
@@ -3,13 +3,13 @@
  * Title:        arm_scale_q7.c
  * Description:  Multiplies a Q7 vector by a scalar
  *
- * $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
  *
@@ -29,109 +29,101 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup scale
- * @{
+  @addtogroup BasicScale
+  @{
  */
 
 /**
- * @brief Multiplies a Q7 vector by a scalar.
- * @param[in]       *pSrc points to the input vector
- * @param[in]       scaleFract fractional portion of the scale value
- * @param[in]       shift number of bits to shift the result by
- * @param[out]      *pDst points to the output vector
- * @param[in]       blockSize number of samples in the vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.7 format.
- * These are multiplied to yield a 2.14 intermediate result and this is shifted with saturation to 1.7 format.
+  @brief         Multiplies a Q7 vector by a scalar.
+  @param[in]     pSrc       points to the input vector
+  @param[in]     scaleFract fractional portion of the scale value
+  @param[in]     shift      number of bits to shift the result by
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The input data <code>*pSrc</code> and <code>scaleFract</code> are in 1.7 format.
+                   These are multiplied to yield a 2.14 intermediate result and this is shifted with saturation to 1.7 format.
  */
 
 void arm_scale_q7(
-  q7_t * pSrc,
-  q7_t scaleFract,
-  int8_t shift,
-  q7_t * pDst,
-  uint32_t blockSize)
+  const q7_t * pSrc,
+        q7_t scaleFract,
+        int8_t shift,
+        q7_t * pDst,
+        uint32_t blockSize)
 {
-  int8_t kShift = 7 - shift;                     /* shift to apply after scaling */
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+        int8_t kShift = 7 - shift;                     /* Shift to apply after scaling */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q7_t in1, in2, in3, in4, out1, out2, out3, out4;      /* Temporary variables to store input & output */
+#if defined (ARM_MATH_LOOPUNROLL)
 
+#if defined (ARM_MATH_DSP)
+  q7_t in1,  in2,  in3,  in4;                    /* Temporary input variables */
+  q7_t out1, out2, out3, out4;                   /* Temporary output variables */
+#endif
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 * scale */
+
+#if defined (ARM_MATH_DSP)
     /* Reading 4 inputs from memory */
     in1 = *pSrc++;
     in2 = *pSrc++;
     in3 = *pSrc++;
     in4 = *pSrc++;
 
-    /* C = A * scale */
-    /* Scale the inputs and then store the results in the temporary variables. */
+    /* Scale inputs and store result in the temporary variable. */
     out1 = (q7_t) (__SSAT(((in1) * scaleFract) >> kShift, 8));
     out2 = (q7_t) (__SSAT(((in2) * scaleFract) >> kShift, 8));
     out3 = (q7_t) (__SSAT(((in3) * scaleFract) >> kShift, 8));
     out4 = (q7_t) (__SSAT(((in4) * scaleFract) >> kShift, 8));
 
-    /* Packing the individual outputs into 32bit and storing in
-     * destination buffer in single write */
-    *__SIMD32(pDst)++ = __PACKq7(out1, out2, out3, out4);
+    /* Pack and store result in destination buffer (in single write) */
+    write_q7x4_ia (&pDst, __PACKq7(out1, out2, out3, out4));
+#else
+    *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8));
+    *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8));
+    *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8));
+    *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8));
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
-  while (blkCnt > 0U)
-  {
-    /* C = A * scale */
-    /* Scale the input and then store the result in the destination buffer. */
-    *pDst++ = (q7_t) (__SSAT(((*pSrc++) * scaleFract) >> kShift, 8));
-
-    /* Decrement the loop counter */
-    blkCnt--;
-  }
-
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A * scale */
-    /* Scale the input and then store the result in the destination buffer. */
-    *pDst++ = (q7_t) (__SSAT((((q15_t) * pSrc++ * scaleFract) >> kShift), 8));
 
-    /* Decrement the loop counter */
+    /* Scale input and store result in destination buffer. */
+    *pDst++ = (q7_t) (__SSAT((((q15_t) *pSrc++ * scaleFract) >> kShift), 8));
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
 }
 
 /**
- * @} end of scale group
+  @} end of BasicScale group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_shift_q15.c b/DSP/Source/BasicMathFunctions/arm_shift_q15.c
index d2cd037..8a15155 100644
--- a/DSP/Source/BasicMathFunctions/arm_shift_q15.c
+++ b/DSP/Source/BasicMathFunctions/arm_shift_q15.c
@@ -3,13 +3,13 @@
  * Title:        arm_shift_q15.c
  * Description:  Shifts the elements of a Q15 vector by a specified number of bits
  *
- * $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
  *
@@ -29,208 +29,173 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup shift
- * @{
+  @addtogroup BasicShift
+  @{
  */
 
 /**
- * @brief  Shifts the elements of a Q15 vector a specified number of bits.
- * @param[in]  *pSrc points to the input vector
- * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
+  @brief         Shifts the elements of a Q15 vector a specified number of bits
+  @param[in]     pSrc       points to the input vector
+  @param[in]     shiftBits  number of bits to shift.  A positive value shifts left; a negative value shifts right.
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.
  */
 
 void arm_shift_q15(
-  q15_t * pSrc,
-  int8_t shiftBits,
-  q15_t * pDst,
-  uint32_t blockSize)
+  const q15_t * pSrc,
+        int8_t shiftBits,
+        q15_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-  uint8_t sign;                                  /* Sign of shiftBits */
-
-#if defined (ARM_MATH_DSP)
-
-/* Run the below code for Cortex-M4 and Cortex-M3 */
+        uint32_t blkCnt;                               /* Loop counter */
+        uint8_t sign = (shiftBits & 0x80);             /* Sign of shiftBits */
 
-  q15_t in1, in2;                                /* Temporary variables */
+#if defined (ARM_MATH_LOOPUNROLL)
 
+#if defined (ARM_MATH_DSP)
+  q15_t in1, in2;                                /* Temporary input variables */
+#endif
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   blkCnt = blockSize >> 2U;
 
-  /* Getting the sign of shiftBits */
-  sign = (shiftBits & 0x80);
-
   /* If the shift value is positive then do right shift else left shift */
   if (sign == 0U)
   {
-    /* 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)
     {
-      /* Read 2 inputs */
-      in1 = *pSrc++;
-      in2 = *pSrc++;
       /* C = A << shiftBits */
-      /* Shift the inputs and then store the results in the destination buffer. */
-#ifndef  ARM_MATH_BIG_ENDIAN
 
-      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16),
-                                  __SSAT((in2 << shiftBits), 16), 16);
+#if defined (ARM_MATH_DSP)
+      /* read 2 samples from source */
+      in1 = *pSrc++;
+      in2 = *pSrc++;
 
+      /* Shift the inputs and then store the results in the destination buffer. */
+#ifndef ARM_MATH_BIG_ENDIAN
+      write_q15x2_ia (&pDst, __PKHBT(__SSAT((in1 << shiftBits), 16),
+                                     __SSAT((in2 << shiftBits), 16), 16));
 #else
+      write_q15x2_ia (&pDst, __PKHBT(__SSAT((in2 << shiftBits), 16),
+                                      __SSAT((in1 << shiftBits), 16), 16));
+#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
 
-      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16),
-                                  __SSAT((in1 << shiftBits), 16), 16);
-
-#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
-
+      /* read 2 samples from source */
       in1 = *pSrc++;
       in2 = *pSrc++;
 
-#ifndef  ARM_MATH_BIG_ENDIAN
-
-      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in1 << shiftBits), 16),
-                                  __SSAT((in2 << shiftBits), 16), 16);
-
+#ifndef ARM_MATH_BIG_ENDIAN
+      write_q15x2_ia (&pDst, __PKHBT(__SSAT((in1 << shiftBits), 16),
+                                     __SSAT((in2 << shiftBits), 16), 16));
 #else
+      write_q15x2_ia (&pDst, __PKHBT(__SSAT((in2 << shiftBits), 16),
+                                     __SSAT((in1 << shiftBits), 16), 16));
+#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
 
-      *__SIMD32(pDst)++ = __PKHBT(__SSAT((in2 << shiftBits), 16),
-                                  __SSAT((in1 << shiftBits), 16), 16);
-
-#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
-
-      /* 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 << shiftBits */
-      /* Shift and then store the results in the destination buffer. */
-      *pDst++ = __SSAT((*pSrc++ << shiftBits), 16);
+#else
+      *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16);
+      *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16);
+      *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16);
+      *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16);
+#endif
 
-      /* Decrement the loop counter */
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
   else
   {
-    /* 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)
     {
-      /* Read 2 inputs */
+      /* C = A >> shiftBits */
+
+#if defined (ARM_MATH_DSP)
+      /* read 2 samples from source */
       in1 = *pSrc++;
       in2 = *pSrc++;
 
-      /* C = A >> shiftBits */
       /* Shift the inputs and then store the results in the destination buffer. */
-#ifndef  ARM_MATH_BIG_ENDIAN
-
-      *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits),
-                                  (in2 >> -shiftBits), 16);
-
+#ifndef ARM_MATH_BIG_ENDIAN
+      write_q15x2_ia (&pDst, __PKHBT((in1 >> -shiftBits),
+                                     (in2 >> -shiftBits), 16));
 #else
+      write_q15x2_ia (&pDst, __PKHBT((in2 >> -shiftBits),
+                                     (in1 >> -shiftBits), 16));
+#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
 
-      *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits),
-                                  (in1 >> -shiftBits), 16);
-
-#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
-
+      /* read 2 samples from source */
       in1 = *pSrc++;
       in2 = *pSrc++;
 
-#ifndef  ARM_MATH_BIG_ENDIAN
-
-      *__SIMD32(pDst)++ = __PKHBT((in1 >> -shiftBits),
-                                  (in2 >> -shiftBits), 16);
-
+#ifndef ARM_MATH_BIG_ENDIAN
+      write_q15x2_ia (&pDst, __PKHBT((in1 >> -shiftBits),
+                                     (in2 >> -shiftBits), 16));
 #else
+      write_q15x2_ia (&pDst, __PKHBT((in2 >> -shiftBits),
+                                     (in1 >> -shiftBits), 16));
+#endif /* #ifndef ARM_MATH_BIG_ENDIAN */
 
-      *__SIMD32(pDst)++ = __PKHBT((in2 >> -shiftBits),
-                                  (in1 >> -shiftBits), 16);
-
-#endif /* #ifndef  ARM_MATH_BIG_ENDIAN    */
-
-      /* 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 >> shiftBits */
-      /* Shift the inputs and then store the results in the destination buffer. */
+#else
+      *pDst++ = (*pSrc++ >> -shiftBits);
+      *pDst++ = (*pSrc++ >> -shiftBits);
+      *pDst++ = (*pSrc++ >> -shiftBits);
       *pDst++ = (*pSrc++ >> -shiftBits);
+#endif
 
-      /* Decrement the loop counter */
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
 
+  /* Loop unrolling: Compute remaining outputs */
+  blkCnt = blockSize % 0x4U;
+
 #else
 
-  /* Run the below code for Cortex-M0 */
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
 
-  /* Getting the sign of shiftBits */
-  sign = (shiftBits & 0x80);
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   /* If the shift value is positive then do right shift else left shift */
   if (sign == 0U)
   {
-    /* Initialize blkCnt with number of samples */
-    blkCnt = blockSize;
-
     while (blkCnt > 0U)
     {
       /* C = A << shiftBits */
-      /* Shift and then store the results in the destination buffer. */
-      *pDst++ = __SSAT(((q31_t) * pSrc++ << shiftBits), 16);
 
-      /* Decrement the loop counter */
+      /* Shift input and store result in destination buffer. */
+      *pDst++ = __SSAT(((q31_t) *pSrc++ << shiftBits), 16);
+
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
   else
   {
-    /* Initialize blkCnt with number of samples */
-    blkCnt = blockSize;
-
     while (blkCnt > 0U)
     {
       /* C = A >> shiftBits */
-      /* Shift the inputs and then store the results in the destination buffer. */
+
+      /* Shift input and store result in destination buffer. */
       *pDst++ = (*pSrc++ >> -shiftBits);
 
-      /* Decrement the loop counter */
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
 }
 
 /**
- * @} end of shift group
+  @} end of BasicShift group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_shift_q31.c b/DSP/Source/BasicMathFunctions/arm_shift_q31.c
index 7e728d4..db6060a 100644
--- a/DSP/Source/BasicMathFunctions/arm_shift_q31.c
+++ b/DSP/Source/BasicMathFunctions/arm_shift_q31.c
@@ -3,13 +3,13 @@
  * Title:        arm_shift_q31.c
  * Description:  Shifts the elements of a Q31 vector by a specified number of bits
  *
- * $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
  *
@@ -29,163 +29,153 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 /**
- * @defgroup shift Vector Shift
- *
- * Shifts the elements of a fixed-point vector by a specified number of bits.
- * There are separate functions for Q7, Q15, and Q31 data types.
- * The underlying algorithm used is:
- *
- * <pre>
- *     pDst[n] = pSrc[n] << shift,   0 <= n < blockSize.
- * </pre>
- *
- * If <code>shift</code> is positive then the elements of the vector are shifted to the left.
- * If <code>shift</code> is negative then the elements of the vector are shifted to the right.
- *
- * The functions support in-place computation allowing the source and destination
- * pointers to reference the same memory buffer.
+  @defgroup BasicShift Vector Shift
+
+  Shifts the elements of a fixed-point vector by a specified number of bits.
+  There are separate functions for Q7, Q15, and Q31 data types.
+  The underlying algorithm used is:
+
+  <pre>
+      pDst[n] = pSrc[n] << shift,   0 <= n < blockSize.
+  </pre>
+
+  If <code>shift</code> is positive then the elements of the vector are shifted to the left.
+  If <code>shift</code> is negative then the elements of the vector are shifted to the right.
+
+  The functions support in-place computation allowing the source and destination
+  pointers to reference the same memory buffer.
  */
 
 /**
- * @addtogroup shift
- * @{
+  @addtogroup BasicShift
+  @{
  */
 
 /**
- * @brief  Shifts the elements of a Q31 vector a specified number of bits.
- * @param[in]  *pSrc points to the input vector
- * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
- *
- *
- * <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         Shifts the elements of a Q31 vector a specified number of bits.
+  @param[in]     pSrc       points to the input vector
+  @param[in]     shiftBits  number of bits to shift.  A positive value shifts left; a negative value shifts right.
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in the vector
+  @return        none
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] are saturated.
  */
 
 void arm_shift_q31(
-  q31_t * pSrc,
-  int8_t shiftBits,
-  q31_t * pDst,
-  uint32_t blockSize)
+  const q31_t * pSrc,
+        int8_t shiftBits,
+        q31_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-  uint8_t sign = (shiftBits & 0x80);             /* Sign of shiftBits */
+        uint32_t blkCnt;                               /* Loop counter */
+        uint8_t sign = (shiftBits & 0x80);             /* Sign of shiftBits */
 
-#if defined (ARM_MATH_DSP)
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  q31_t in1, in2, in3, in4;                      /* Temporary input variables */
-  q31_t out1, out2, out3, out4;                  /* Temporary output variables */
+  q31_t in, out;                                 /* Temporary variables */
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   blkCnt = blockSize >> 2U;
 
-
+  /* If the shift value is positive then do right shift else left shift */
   if (sign == 0U)
   {
-    /* 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  << shiftBits */
-      /* Shift the input and then store the results in the destination buffer. */
-      in1 = *pSrc;
-      in2 = *(pSrc + 1);
-      out1 = in1 << shiftBits;
-      in3 = *(pSrc + 2);
-      out2 = in2 << shiftBits;
-      in4 = *(pSrc + 3);
-      if (in1 != (out1 >> shiftBits))
-        out1 = 0x7FFFFFFF ^ (in1 >> 31);
-
-      if (in2 != (out2 >> shiftBits))
-        out2 = 0x7FFFFFFF ^ (in2 >> 31);
-
-      *pDst = out1;
-      out3 = in3 << shiftBits;
-      *(pDst + 1) = out2;
-      out4 = in4 << shiftBits;
-
-      if (in3 != (out3 >> shiftBits))
-        out3 = 0x7FFFFFFF ^ (in3 >> 31);
-
-      if (in4 != (out4 >> shiftBits))
-        out4 = 0x7FFFFFFF ^ (in4 >> 31);
-
-      *(pDst + 2) = out3;
-      *(pDst + 3) = out4;
-
-      /* Update destination pointer to process next sampels */
-      pSrc += 4U;
-      pDst += 4U;
-
-      /* Decrement the loop counter */
+      /* C = A << shiftBits */
+
+      /* Shift input and store result in destination buffer. */
+      in = *pSrc++;
+      out = in << shiftBits;
+      if (in != (out >> shiftBits))
+        out = 0x7FFFFFFF ^ (in >> 31);
+      *pDst++ = out;
+
+      in = *pSrc++;
+      out = in << shiftBits;
+      if (in != (out >> shiftBits))
+        out = 0x7FFFFFFF ^ (in >> 31);
+      *pDst++ = out;
+
+      in = *pSrc++;
+      out = in << shiftBits;
+      if (in != (out >> shiftBits))
+        out = 0x7FFFFFFF ^ (in >> 31);
+      *pDst++ = out;
+
+      in = *pSrc++;
+      out = in << shiftBits;
+      if (in != (out >> shiftBits))
+        out = 0x7FFFFFFF ^ (in >> 31);
+      *pDst++ = out;
+
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
   else
   {
-
-    /* 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 >>  shiftBits */
-      /* Shift the input and then store the results in the destination buffer. */
-      in1 = *pSrc;
-      in2 = *(pSrc + 1);
-      in3 = *(pSrc + 2);
-      in4 = *(pSrc + 3);
+      /* C = A >> shiftBits */
 
-      *pDst = (in1 >> -shiftBits);
-      *(pDst + 1) = (in2 >> -shiftBits);
-      *(pDst + 2) = (in3 >> -shiftBits);
-      *(pDst + 3) = (in4 >> -shiftBits);
-
-
-      pSrc += 4U;
-      pDst += 4U;
+      /* Shift input and store results in destination buffer. */
+      *pDst++ = (*pSrc++ >> -shiftBits);
+      *pDst++ = (*pSrc++ >> -shiftBits);
+      *pDst++ = (*pSrc++ >> -shiftBits);
+      *pDst++ = (*pSrc++ >> -shiftBits);
 
+      /* Decrement loop counter */
       blkCnt--;
     }
-
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
-  while (blkCnt > 0U)
+  /* If the shift value is positive then do right shift else left shift */
+  if (sign == 0U)
   {
-    /* C = A (>> or <<) shiftBits */
-    /* Shift the input and then store the result in the destination buffer. */
-    *pDst++ = (sign == 0U) ? clip_q63_to_q31((q63_t) * pSrc++ << shiftBits) :
-      (*pSrc++ >> -shiftBits);
+    while (blkCnt > 0U)
+    {
+      /* C = A << shiftBits */
+
+      /* Shift input and store result in destination buffer. */
+      *pDst++ = clip_q63_to_q31((q63_t) *pSrc++ << shiftBits);
 
-    /* Decrement the loop counter */
-    blkCnt--;
+      /* Decrement loop counter */
+      blkCnt--;
+    }
   }
+  else
+  {
+    while (blkCnt > 0U)
+    {
+      /* C = A >> shiftBits */
 
+      /* Shift input and store result in destination buffer. */
+      *pDst++ = (*pSrc++ >> -shiftBits);
+
+      /* Decrement loop counter */
+      blkCnt--;
+    }
+  }
 
 }
 
 /**
- * @} end of shift group
+  @} end of BasicShift group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_shift_q7.c b/DSP/Source/BasicMathFunctions/arm_shift_q7.c
index fd508b4..c4163fc 100644
--- a/DSP/Source/BasicMathFunctions/arm_shift_q7.c
+++ b/DSP/Source/BasicMathFunctions/arm_shift_q7.c
@@ -3,13 +3,13 @@
  * Title:        arm_shift_q7.c
  * Description:  Processing function for the Q7 Shifting
  *
- * $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
  *
@@ -29,180 +29,147 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup shift
- * @{
+  @addtogroup BasicShift
+  @{
  */
 
-
 /**
- * @brief  Shifts the elements of a Q7 vector a specified number of bits.
- * @param[in]  *pSrc points to the input vector
- * @param[in]  shiftBits number of bits to shift.  A positive value shifts left; a negative value shifts right.
- * @param[out]  *pDst points to the output vector
- * @param[in]  blockSize number of samples in the vector
- * @return none.
- *
- * \par Conditions for optimum performance
- *  Input and output buffers should be aligned by 32-bit
- *
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q7 range [0x8 0x7F] will be saturated.
+  @brief         Shifts the elements of a Q7 vector a specified number of bits
+  @param[in]     pSrc       points to the input vector
+  @param[in]     shiftBits  number of bits to shift.  A positive value shifts left; a negative value shifts right.
+  @param[out]    pDst       points to the output vector
+  @param[in]     blockSize  number of samples in each vector
+  @return        none
+
+  @par           onditions for optimum performance
+                   Input and output buffers should be aligned by 32-bit
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q7 range [0x80 0x7F] are saturated.
  */
 
 void arm_shift_q7(
-  q7_t * pSrc,
-  int8_t shiftBits,
-  q7_t * pDst,
-  uint32_t blockSize)
+  const q7_t * pSrc,
+        int8_t shiftBits,
+        q7_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-  uint8_t sign;                                  /* Sign of shiftBits */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+        uint8_t sign = (shiftBits & 0x80);             /* Sign of shiftBits */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q7_t in1;                                      /* Input value1 */
-  q7_t in2;                                      /* Input value2 */
-  q7_t in3;                                      /* Input value3 */
-  q7_t in4;                                      /* Input value4 */
+#if defined (ARM_MATH_LOOPUNROLL)
 
+#if defined (ARM_MATH_DSP)
+  q7_t in1,  in2,  in3,  in4;                    /* Temporary input variables */
+#endif
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   blkCnt = blockSize >> 2U;
 
-  /* Getting the sign of shiftBits */
-  sign = (shiftBits & 0x80);
-
   /* If the shift value is positive then do right shift else left shift */
   if (sign == 0U)
   {
-    /* 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 << shiftBits */
-      /* Read 4 inputs */
-      in1 = *pSrc;
-      in2 = *(pSrc + 1);
-      in3 = *(pSrc + 2);
-      in4 = *(pSrc + 3);
-
-      /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */
-      *__SIMD32(pDst)++ = __PACKq7(__SSAT((in1 << shiftBits), 8),
-                                   __SSAT((in2 << shiftBits), 8),
-                                   __SSAT((in3 << shiftBits), 8),
-                                   __SSAT((in4 << shiftBits), 8));
-      /* Update source pointer to process next sampels */
-      pSrc += 4U;
-
-      /* 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 << shiftBits */
-      /* Shift the input and then store the result in the destination buffer. */
-      *pDst++ = (q7_t) __SSAT((*pSrc++ << shiftBits), 8);
+#if defined (ARM_MATH_DSP)
+      /* Read 4 inputs */
+      in1 = *pSrc++;
+      in2 = *pSrc++;
+      in3 = *pSrc++;
+      in4 = *pSrc++;
+
+    /* Pack and store result in destination buffer (in single write) */
+      write_q7x4_ia (&pDst, __PACKq7(__SSAT((in1 << shiftBits), 8),
+                                     __SSAT((in2 << shiftBits), 8),
+                                     __SSAT((in3 << shiftBits), 8),
+                                     __SSAT((in4 << shiftBits), 8) ));
+#else
+      *pDst++ = (q7_t) __SSAT(((q15_t) *pSrc++ << shiftBits), 8);
+      *pDst++ = (q7_t) __SSAT(((q15_t) *pSrc++ << shiftBits), 8);
+      *pDst++ = (q7_t) __SSAT(((q15_t) *pSrc++ << shiftBits), 8);
+      *pDst++ = (q7_t) __SSAT(((q15_t) *pSrc++ << shiftBits), 8);
+#endif
 
-      /* Decrement the loop counter */
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
   else
   {
-    shiftBits = -shiftBits;
-    /* 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 >> shiftBits */
-      /* Read 4 inputs */
-      in1 = *pSrc;
-      in2 = *(pSrc + 1);
-      in3 = *(pSrc + 2);
-      in4 = *(pSrc + 3);
-
-      /* Store the Shifted result in the destination buffer in single cycle by packing the outputs */
-      *__SIMD32(pDst)++ = __PACKq7((in1 >> shiftBits), (in2 >> shiftBits),
-                                   (in3 >> shiftBits), (in4 >> shiftBits));
 
-
-      pSrc += 4U;
-
-      /* 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 >> shiftBits */
-      /* Shift the input and then store the result in the destination buffer. */
+#if defined (ARM_MATH_DSP)
+      /* Read 4 inputs */
       in1 = *pSrc++;
-      *pDst++ = (in1 >> shiftBits);
+      in2 = *pSrc++;
+      in3 = *pSrc++;
+      in4 = *pSrc++;
+
+    /* Pack and store result in destination buffer (in single write) */
+      write_q7x4_ia (&pDst, __PACKq7((in1 >> -shiftBits),
+                                     (in2 >> -shiftBits),
+                                     (in3 >> -shiftBits),
+                                     (in4 >> -shiftBits) ));
+#else
+      *pDst++ = (*pSrc++ >> -shiftBits);
+      *pDst++ = (*pSrc++ >> -shiftBits);
+      *pDst++ = (*pSrc++ >> -shiftBits);
+      *pDst++ = (*pSrc++ >> -shiftBits);
+#endif
 
-      /* Decrement the loop counter */
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
 
+  /* Loop unrolling: Compute remaining outputs */
+  blkCnt = blockSize % 0x4U;
+
 #else
 
-  /* Run the below code for Cortex-M0 */
+  /* Initialize blkCnt with number of samples */
+  blkCnt = blockSize;
 
-  /* Getting the sign of shiftBits */
-  sign = (shiftBits & 0x80);
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
 
   /* If the shift value is positive then do right shift else left shift */
   if (sign == 0U)
   {
-    /* Initialize blkCnt with number of samples */
-    blkCnt = blockSize;
-
     while (blkCnt > 0U)
     {
       /* C = A << shiftBits */
-      /* Shift the input and then store the result in the destination buffer. */
-      *pDst++ = (q7_t) __SSAT(((q15_t) * pSrc++ << shiftBits), 8);
 
-      /* Decrement the loop counter */
+      /* Shift input and store result in destination buffer. */
+      *pDst++ = (q7_t) __SSAT(((q15_t) *pSrc++ << shiftBits), 8);
+
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
   else
   {
-    /* Initialize blkCnt with number of samples */
-    blkCnt = blockSize;
-
     while (blkCnt > 0U)
     {
       /* C = A >> shiftBits */
-      /* Shift the input and then store the result in the destination buffer. */
+
+      /* Shift input and store result in destination buffer. */
       *pDst++ = (*pSrc++ >> -shiftBits);
 
-      /* Decrement the loop counter */
+      /* Decrement loop counter */
       blkCnt--;
     }
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
 }
 
 /**
- * @} end of shift group
+  @} end of BasicShift group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_sub_f32.c b/DSP/Source/BasicMathFunctions/arm_sub_f32.c
index 74a2944..4c97af3 100644
--- a/DSP/Source/BasicMathFunctions/arm_sub_f32.c
+++ b/DSP/Source/BasicMathFunctions/arm_sub_f32.c
@@ -1,15 +1,15 @@
 /* ----------------------------------------------------------------------
  * Project:      CMSIS DSP Library
  * Title:        arm_sub_f32.c
- * Description:  Floating-point vector subtraction.
+ * Description:  Floating-point vector 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
  *
@@ -29,110 +29,120 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @defgroup BasicSub Vector Subtraction
- *
- * Element-by-element subtraction of two vectors.
- *
- * <pre>
- *     pDst[n] = pSrcA[n] - pSrcB[n],   0 <= n < blockSize.
- * </pre>
- *
- * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
+  @defgroup BasicSub Vector Subtraction
+
+  Element-by-element subtraction of two vectors.
+
+  <pre>
+      pDst[n] = pSrcA[n] - pSrcB[n],   0 <= n < blockSize.
+  </pre>
+
+  There are separate functions for floating-point, Q7, Q15, and Q31 data types.
  */
 
 /**
- * @addtogroup BasicSub
- * @{
+  @addtogroup BasicSub
+  @{
  */
 
-
 /**
- * @brief Floating-point vector subtraction.
- * @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.
+  @brief         Floating-point vector subtraction.
+  @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
  */
 
 void arm_sub_f32(
-  float32_t * pSrcA,
-  float32_t * pSrcB,
-  float32_t * pDst,
-  uint32_t blockSize)
+  const float32_t * pSrcA,
+  const float32_t * pSrcB,
+        float32_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
+
+#if defined(ARM_MATH_NEON)
+    float32x4_t vec1;
+    float32x4_t vec2;
+    float32x4_t res;
+
+    /* Compute 4 outputs at a time */
+    blkCnt = blockSize >> 2U;
+
+    while (blkCnt > 0U)
+    {
+        /* C = A - B */
+
+        /* Subtract and then store the results in the destination buffer. */
+        vec1 = vld1q_f32(pSrcA);
+        vec2 = vld1q_f32(pSrcB);
+        res = vsubq_f32(vec1, vec2);
+        vst1q_f32(pDst, res);
+
+        /* Increment pointers */
+        pSrcA += 4;
+        pSrcB += 4; 
+        pDst += 4;
+        
+        /* Decrement the loop counter */
+        blkCnt--;
+    }
+
+    /* Tail */
+    blkCnt = blockSize & 0x3;
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  float32_t inA1, inA2, inA3, inA4;              /* temporary variables */
-  float32_t inB1, inB2, inB3, inB4;              /* temporary variables */
+#else
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 */
-    /* Subtract and then store the results in the destination buffer. */
-    /* Read 4 input samples from sourceA and sourceB */
-    inA1 = *pSrcA;
-    inB1 = *pSrcB;
-    inA2 = *(pSrcA + 1);
-    inB2 = *(pSrcB + 1);
-    inA3 = *(pSrcA + 2);
-    inB3 = *(pSrcB + 2);
-    inA4 = *(pSrcA + 3);
-    inB4 = *(pSrcB + 3);
-
-    /* dst = srcA - srcB */
-    /* subtract and store the result */
-    *pDst = inA1 - inB1;
-    *(pDst + 1) = inA2 - inB2;
-    *(pDst + 2) = inA3 - inB3;
-    *(pDst + 3) = inA4 - inB4;
-
-
-    /* Update pointers to process next sampels */
-    pSrcA += 4U;
-    pSrcB += 4U;
-    pDst += 4U;
-
-    /* Decrement the loop counter */
+
+    /* Subtract and store result in destination buffer. */
+    *pDst++ = (*pSrcA++) - (*pSrcB++);
+
+    *pDst++ = (*pSrcA++) - (*pSrcB++);
+
+    *pDst++ = (*pSrcA++) - (*pSrcB++);
+
+    *pDst++ = (*pSrcA++) - (*pSrcB++);
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
-#endif /* #if defined (ARM_MATH_DSP) */
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+#endif /* #if defined(ARM_MATH_NEON) */
 
   while (blkCnt > 0U)
   {
     /* C = A - B */
-    /* Subtract and then store the results in the destination buffer. */
+
+    /* Subtract and store result in destination buffer. */
     *pDst++ = (*pSrcA++) - (*pSrcB++);
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
+
 }
 
 /**
- * @} end of BasicSub group
+  @} end of BasicSub group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_sub_q15.c b/DSP/Source/BasicMathFunctions/arm_sub_q15.c
index 17942eb..835917e 100644
--- a/DSP/Source/BasicMathFunctions/arm_sub_q15.c
+++ b/DSP/Source/BasicMathFunctions/arm_sub_q15.c
@@ -3,13 +3,13 @@
  * Title:        arm_sub_q15.c
  * Description:  Q15 vector 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
  *
@@ -29,100 +29,98 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicSub
- * @{
+  @addtogroup BasicSub
+  @{
  */
 
 /**
- * @brief Q15 vector subtraction.
- * @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.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q15 range [0x8000 0x7FFF] will be saturated.
+  @brief         Q15 vector subtraction.
+  @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
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q15 range [0x8000 0x7FFF] are saturated.
  */
 
 void arm_sub_q15(
-  q15_t * pSrcA,
-  q15_t * pSrcB,
-  q15_t * pDst,
-  uint32_t blockSize)
+  const q15_t * pSrcA,
+  const q15_t * pSrcB,
+        q15_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
+        uint32_t blkCnt;                               /* Loop counter */
 
+#if defined (ARM_MATH_LOOPUNROLL)
 
 #if defined (ARM_MATH_DSP)
-
-/* Run the below code for Cortex-M4 and Cortex-M3 */
   q31_t inA1, inA2;
   q31_t inB1, inB2;
+#endif
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 */
-    /* Subtract and then store the results in the destination buffer two samples at a time. */
-    inA1 = *__SIMD32(pSrcA)++;
-    inA2 = *__SIMD32(pSrcA)++;
-    inB1 = *__SIMD32(pSrcB)++;
-    inB2 = *__SIMD32(pSrcB)++;
 
-    *__SIMD32(pDst)++ = __QSUB16(inA1, inB1);
-    *__SIMD32(pDst)++ = __QSUB16(inA2, inB2);
+#if defined (ARM_MATH_DSP)
+    /* read 2 times 2 samples at a time from sourceA */
+    inA1 = read_q15x2_ia ((q15_t **) &pSrcA);
+    inA2 = read_q15x2_ia ((q15_t **) &pSrcA);
+    /* read 2 times 2 samples at a time from sourceB */
+    inB1 = read_q15x2_ia ((q15_t **) &pSrcB);
+    inB2 = read_q15x2_ia ((q15_t **) &pSrcB);
+
+    /* Subtract and store 2 times 2 samples at a time */
+    write_q15x2_ia (&pDst, __QSUB16(inA1, inB1));
+    write_q15x2_ia (&pDst, __QSUB16(inA2, inB2));
+#else
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ - *pSrcB++), 16);
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ - *pSrcB++), 16);
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ - *pSrcB++), 16);
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ - *pSrcB++), 16);
+#endif
 
-    /* Decrement the loop counter */
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
-  while (blkCnt > 0U)
-  {
-    /* C = A - B */
-    /* Subtract and then store the result in the destination buffer. */
-    *pDst++ = (q15_t) __QSUB16(*pSrcA++, *pSrcB++);
-
-    /* Decrement the loop counter */
-    blkCnt--;
-  }
-
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A - B */
-    /* Subtract and then store the result in the destination buffer. */
-    *pDst++ = (q15_t) __SSAT(((q31_t) * pSrcA++ - *pSrcB++), 16);
 
-    /* Decrement the loop counter */
+    /* Subtract and store result in destination buffer. */
+#if defined (ARM_MATH_DSP)
+    *pDst++ = (q15_t) __QSUB16(*pSrcA++, *pSrcB++);
+#else
+    *pDst++ = (q15_t) __SSAT(((q31_t) *pSrcA++ - *pSrcB++), 16);
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
-
 }
 
 /**
- * @} end of BasicSub group
+  @} end of BasicSub group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_sub_q31.c b/DSP/Source/BasicMathFunctions/arm_sub_q31.c
index 72b8597..bac1927 100644
--- a/DSP/Source/BasicMathFunctions/arm_sub_q31.c
+++ b/DSP/Source/BasicMathFunctions/arm_sub_q31.c
@@ -3,13 +3,13 @@
  * Title:        arm_sub_q31.c
  * Description:  Q31 vector 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
  *
@@ -29,106 +29,80 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicSub
- * @{
+  @addtogroup BasicSub
+  @{
  */
 
 /**
- * @brief Q31 vector subtraction.
- * @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.
- *
- * <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 vector subtraction.
+  @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
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q31 range [0x80000000 0x7FFFFFFF] are saturated.
  */
 
 void arm_sub_q31(
-  q31_t * pSrcA,
-  q31_t * pSrcB,
-  q31_t * pDst,
-  uint32_t blockSize)
+  const q31_t * pSrcA,
+  const q31_t * pSrcB,
+        q31_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
 
-/* Run the below code for Cortex-M4 and Cortex-M3 */
-  q31_t inA1, inA2, inA3, inA4;
-  q31_t inB1, inB2, inB3, inB4;
+#if defined (ARM_MATH_LOOPUNROLL)
 
-  /*loop Unrolling */
+  /* Loop unrolling: Compute 4 outputs at a time */
   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 */
-    /* Subtract and then store the results in the destination buffer. */
-    inA1 = *pSrcA++;
-    inA2 = *pSrcA++;
-    inB1 = *pSrcB++;
-    inB2 = *pSrcB++;
-
-    inA3 = *pSrcA++;
-    inA4 = *pSrcA++;
-    inB3 = *pSrcB++;
-    inB4 = *pSrcB++;
-
-    *pDst++ = __QSUB(inA1, inB1);
-    *pDst++ = __QSUB(inA2, inB2);
-    *pDst++ = __QSUB(inA3, inB3);
-    *pDst++ = __QSUB(inA4, inB4);
-
-    /* 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;
+    /* Subtract and store result in destination buffer. */
+    *pDst++ = __QSUB(*pSrcA++, *pSrcB++);
 
-  while (blkCnt > 0U)
-  {
-    /* C = A - B */
-    /* Subtract and then store the result in the destination buffer. */
     *pDst++ = __QSUB(*pSrcA++, *pSrcB++);
 
-    /* Decrement the loop counter */
+    *pDst++ = __QSUB(*pSrcA++, *pSrcB++);
+
+    *pDst++ = __QSUB(*pSrcA++, *pSrcB++);
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#else
+  /* Loop unrolling: Compute remaining outputs */
+  blkCnt = blockSize % 0x4U;
 
-  /* Run the below code for Cortex-M0 */
+#else
 
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A - B */
-    /* Subtract and then store the result in the destination buffer. */
-    *pDst++ = (q31_t) clip_q63_to_q31((q63_t) * pSrcA++ - *pSrcB++);
 
-    /* Decrement the loop counter */
+    /* Subtract and store result in destination buffer. */
+    *pDst++ = __QSUB(*pSrcA++, *pSrcB++);
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
 }
 
 /**
- * @} end of BasicSub group
+  @} end of BasicSub group
  */
diff --git a/DSP/Source/BasicMathFunctions/arm_sub_q7.c b/DSP/Source/BasicMathFunctions/arm_sub_q7.c
index d211f40..a55a8fd 100644
--- a/DSP/Source/BasicMathFunctions/arm_sub_q7.c
+++ b/DSP/Source/BasicMathFunctions/arm_sub_q7.c
@@ -3,13 +3,13 @@
  * Title:        arm_sub_q7.c
  * Description:  Q7 vector 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
  *
@@ -29,91 +29,81 @@
 #include "arm_math.h"
 
 /**
- * @ingroup groupMath
+  @ingroup groupMath
  */
 
 /**
- * @addtogroup BasicSub
- * @{
+  @addtogroup BasicSub
+  @{
  */
 
 /**
- * @brief Q7 vector subtraction.
- * @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.
- *
- * <b>Scaling and Overflow Behavior:</b>
- * \par
- * The function uses saturating arithmetic.
- * Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.
+  @brief         Q7 vector subtraction.
+  @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
+
+  @par           Scaling and Overflow Behavior
+                   The function uses saturating arithmetic.
+                   Results outside of the allowable Q7 range [0x80 0x7F] will be saturated.
  */
 
 void arm_sub_q7(
-  q7_t * pSrcA,
-  q7_t * pSrcB,
-  q7_t * pDst,
-  uint32_t blockSize)
+  const q7_t * pSrcA,
+  const q7_t * pSrcB,
+        q7_t * pDst,
+        uint32_t blockSize)
 {
-  uint32_t blkCnt;                               /* loop counter */
-
-#if defined (ARM_MATH_DSP)
+        uint32_t blkCnt;                               /* Loop counter */
 
-/* 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 = 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 */
-    /* Subtract and then store the results in the destination buffer 4 samples at a time. */
-    *__SIMD32(pDst)++ = __QSUB8(*__SIMD32(pSrcA)++, *__SIMD32(pSrcB)++);
 
-    /* Decrement the loop counter */
+#if defined (ARM_MATH_DSP)
+    /* Subtract and store result in destination buffer (4 samples at a time). */
+    write_q7x4_ia (&pDst, __QSUB8(read_q7x4_ia ((q7_t **) &pSrcA), read_q7x4_ia ((q7_t **) &pSrcB)));
+#else
+    *pDst++ = (q7_t) __SSAT((q15_t) *pSrcA++ - *pSrcB++, 8);
+    *pDst++ = (q7_t) __SSAT((q15_t) *pSrcA++ - *pSrcB++, 8);
+    *pDst++ = (q7_t) __SSAT((q15_t) *pSrcA++ - *pSrcB++, 8);
+    *pDst++ = (q7_t) __SSAT((q15_t) *pSrcA++ - *pSrcB++, 8);
+#endif
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-  /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
-   ** No loop unrolling is used. */
+  /* Loop unrolling: Compute remaining outputs */
   blkCnt = blockSize % 0x4U;
 
-  while (blkCnt > 0U)
-  {
-    /* C = A - B */
-    /* Subtract and then store the result in the destination buffer. */
-    *pDst++ = __SSAT(*pSrcA++ - *pSrcB++, 8);
-
-    /* Decrement the loop counter */
-    blkCnt--;
-  }
-
 #else
 
-  /* Run the below code for Cortex-M0 */
-
   /* Initialize blkCnt with number of samples */
   blkCnt = blockSize;
 
+#endif /* #if defined (ARM_MATH_LOOPUNROLL) */
+
   while (blkCnt > 0U)
   {
     /* C = A - B */
-    /* Subtract and then store the result in the destination buffer. */
-    *pDst++ = (q7_t) __SSAT((q15_t) * pSrcA++ - *pSrcB++, 8);
 
-    /* Decrement the loop counter */
+    /* Subtract and store result in destination buffer. */
+    *pDst++ = (q7_t) __SSAT((q15_t) *pSrcA++ - *pSrcB++, 8);
+
+    /* Decrement loop counter */
     blkCnt--;
   }
 
-#endif /* #if defined (ARM_MATH_DSP) */
-
-
 }
 
 /**
- * @} end of BasicSub group
+  @} end of BasicSub group
  */