1  /* ----------------------------------------------------------------------
  2   * Project:      CMSIS DSP Library
  3   * Title:        arm_or_u16.c
  4   * Description:  uint16_t bitwise inclusive OR
  5   *
  6   * $Date:        23 April 2021
  7   * $Revision:    V1.9.0
  8   *
  9   * Target Processor: Cortex-M and Cortex-A cores
 10   * -------------------------------------------------------------------- */
 11  /*
 12   * Copyright (C) 2010-2021 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 "dsp/basic_math_functions.h"
 30  
 31  /**
 32    @ingroup groupMath
 33   */
 34  
 35  /**
 36    @defgroup Or Vector bitwise inclusive OR
 37  
 38    Compute the logical bitwise OR.
 39  
 40    There are separate functions for uint32_t, uint16_t, and uint8_t data types.
 41   */
 42  
 43  /**
 44    @addtogroup Or
 45    @{
 46   */
 47  
 48  /**
 49    @brief         Compute the logical bitwise OR of two fixed-point vectors.
 50    @param[in]     pSrcA      points to input vector A
 51    @param[in]     pSrcB      points to input vector B
 52    @param[out]    pDst       points to output vector
 53    @param[in]     blockSize  number of samples in each vector
 54    @return        none
 55   */
 56  
 57  void arm_or_u16(
 58      const uint16_t * pSrcA,
 59      const uint16_t * pSrcB,
 60            uint16_t * pDst,
 61            uint32_t blockSize)
 62  {
 63      uint32_t blkCnt;      /* Loop counter */
 64  
 65  #if defined(ARM_MATH_MVEI) && !defined(ARM_MATH_AUTOVECTORIZE)
 66      uint16x8_t vecSrcA, vecSrcB;
 67  
 68      /* Compute 8 outputs at a time */
 69      blkCnt = blockSize >> 3;
 70  
 71      while (blkCnt > 0U)
 72      {
 73          vecSrcA = vld1q(pSrcA);
 74          vecSrcB = vld1q(pSrcB);
 75  
 76          vst1q(pDst, vorrq_u16(vecSrcA, vecSrcB) );
 77  
 78          pSrcA += 8;
 79          pSrcB += 8;
 80          pDst  += 8;
 81  
 82          /* Decrement the loop counter */
 83          blkCnt--;
 84      }
 85  
 86      /* Tail */
 87      blkCnt = blockSize & 7;
 88  
 89      if (blkCnt > 0U)
 90      {
 91          mve_pred16_t p0 = vctp16q(blkCnt);
 92          vecSrcA = vld1q(pSrcA);
 93          vecSrcB = vld1q(pSrcB);
 94          vstrhq_p(pDst, vorrq_u16(vecSrcA, vecSrcB), p0);
 95      }
 96  #else
 97  #if defined(ARM_MATH_NEON) && !defined(ARM_MATH_AUTOVECTORIZE)
 98      uint16x8_t vecA, vecB;
 99  
100      /* Compute 8 outputs at a time */
101      blkCnt = blockSize >> 3U;
102  
103      while (blkCnt > 0U)
104      {
105          vecA = vld1q_u16(pSrcA);
106          vecB = vld1q_u16(pSrcB);
107  
108          vst1q_u16(pDst, vorrq_u16(vecA, vecB) );
109  
110          pSrcA += 8;
111          pSrcB += 8;
112          pDst  += 8;
113  
114          /* Decrement the loop counter */
115          blkCnt--;
116      }
117  
118      /* Tail */
119      blkCnt = blockSize & 7;
120  #else
121      /* Initialize blkCnt with number of samples */
122      blkCnt = blockSize;
123  #endif
124  
125      while (blkCnt > 0U)
126      {
127          *pDst++ = (*pSrcA++)|(*pSrcB++);
128  
129          /* Decrement the loop counter */
130          blkCnt--;
131      }
132  #endif /* if defined(ARM_MATH_MVEI) */
133  }
134  
135  /**
136    @} end of Or group
137   */