lib/main/CMSIS/DSP/Source/BasicMathFunctions/arm_offset_q7.c

   1 /* ----------------------------------------------------------------------
   2  * Project:      CMSIS DSP Library
   3  * Title:        arm_offset_q7.c
   4  * Description:  Q7 vector offset
   5  *
   6  * $Date:        27. January 2017
   7  * $Revision:    V.1.5.1
   8  *
   9  * Target Processor: Cortex-M cores
  10  * -------------------------------------------------------------------- */
  11 /*
  12  * Copyright (C) 2010-2017 ARM Limited or its affiliates. All rights reserved.
  13  *
  14  * SPDX-License-Identifier: Apache-2.0
  15  *
  16  * Licensed under the Apache License, Version 2.0 (the License); you may
  17  * not use this file except in compliance with the License.
  18  * You may obtain a copy of the License at
  19  *
  20  * www.apache.org/licenses/LICENSE-2.0
  21  *
  22  * Unless required by applicable law or agreed to in writing, software
  23  * distributed under the License is distributed on an AS IS BASIS, WITHOUT
  24  * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  25  * See the License for the specific language governing permissions and
  26  * limitations under the License.
  27  */
  28
  29 #include "arm_math.h"
  30
  31 /**
  32  * @ingroup groupMath
  33  */
  34
  35 /**
  36  * @addtogroup offset
  37  * @{
  38  */
  39
  40 /**
  41  * @brief  Adds a constant offset to a Q7 vector.
  42  * @param[in]  *pSrc points to the input vector
  43  * @param[in]  offset is the offset to be added
  44  * @param[out]  *pDst points to the output vector
  45  * @param[in]  blockSize number of samples in the vector
  46  * @return none.
  47  *
  48  * <b>Scaling and Overflow Behavior:</b>
  49  * \par
  50  * The function uses saturating arithmetic.
  51  * Results outside of the allowable Q7 range [0x80 0x7F] are saturated.
  52  */
  53
  54 void arm_offset_q7(
  55   q7_t * pSrc,
  56   q7_t offset,
  57   q7_t * pDst,
  58   uint32_t blockSize)
  59 {
  60   uint32_t blkCnt;                               /* loop counter */
  61
  62 #if defined (ARM_MATH_DSP)
  63
  64 /* Run the below code for Cortex-M4 and Cortex-M3 */
  65   q31_t offset_packed;                           /* Offset packed to 32 bit */
  66
  67
  68   /*loop Unrolling */
  69   blkCnt = blockSize >> 2U;
  70
  71   /* Offset is packed to 32 bit in order to use SIMD32 for addition */
  72   offset_packed = __PACKq7(offset, offset, offset, offset);
  73
  74   /* First part of the processing with loop unrolling.  Compute 4 outputs at a time.
  75    ** a second loop below computes the remaining 1 to 3 samples. */
  76   while (blkCnt > 0U)
  77   {
  78     /* C = A + offset */
  79     /* Add offset and then store the results in the destination bufferfor 4 samples at a time. */
  80     *__SIMD32(pDst)++ = __QADD8(*__SIMD32(pSrc)++, offset_packed);
  81
  82     /* Decrement the loop counter */
  83     blkCnt--;
  84   }
  85
  86   /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
  87    ** No loop unrolling is used. */
  88   blkCnt = blockSize % 0x4U;
  89
  90   while (blkCnt > 0U)
  91   {
  92     /* C = A + offset */
  93     /* Add offset and then store the result in the destination buffer. */
  94     *pDst++ = (q7_t) __SSAT(*pSrc++ + offset, 8);
  95
  96     /* Decrement the loop counter */
  97     blkCnt--;
  98   }
  99
 100 #else
 101
 102   /* Run the below code for Cortex-M0 */
 103
 104   /* Initialize blkCnt with number of samples */
 105   blkCnt = blockSize;
 106
 107   while (blkCnt > 0U)
 108   {
 109     /* C = A + offset */
 110     /* Add offset and then store the result in the destination buffer. */
 111     *pDst++ = (q7_t) __SSAT((q15_t) * pSrc++ + offset, 8);
 112
 113     /* Decrement the loop counter */
 114     blkCnt--;
 115   }
 116
 117 #endif /* #if defined (ARM_MATH_DSP) */
 118
 119 }
 120
 121 /**
 122  * @} end of offset group
 123  */