arm_add_q7.c 2.9 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109
  1. /* ----------------------------------------------------------------------
  2. * Project: CMSIS DSP Library
  3. * Title: arm_add_q7.c
  4. * Description: Q7 vector addition
  5. *
  6. * $Date: 18. March 2019
  7. * $Revision: V1.6.0
  8. *
  9. * Target Processor: Cortex-M cores
  10. * -------------------------------------------------------------------- */
  11. /*
  12. * Copyright (C) 2010-2019 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. #include "arm_math.h"
  29. /**
  30. @ingroup groupMath
  31. */
  32. /**
  33. @addtogroup BasicAdd
  34. @{
  35. */
  36. /**
  37. @brief Q7 vector addition.
  38. @param[in] pSrcA points to the first input vector
  39. @param[in] pSrcB points to the second input vector
  40. @param[out] pDst points to the output vector
  41. @param[in] blockSize number of samples in each vector
  42. @return none
  43. @par Scaling and Overflow Behavior
  44. The function uses saturating arithmetic.
  45. Results outside of the allowable Q7 range [0x80 0x7F] are saturated.
  46. */
  47. void arm_add_q7(
  48. const q7_t * pSrcA,
  49. const q7_t * pSrcB,
  50. q7_t * pDst,
  51. uint32_t blockSize)
  52. {
  53. uint32_t blkCnt; /* Loop counter */
  54. #if defined (ARM_MATH_LOOPUNROLL)
  55. /* Loop unrolling: Compute 4 outputs at a time */
  56. blkCnt = blockSize >> 2U;
  57. while (blkCnt > 0U)
  58. {
  59. /* C = A + B */
  60. #if defined (ARM_MATH_DSP)
  61. /* Add and store result in destination buffer (4 samples at a time). */
  62. write_q7x4_ia (&pDst, __QADD8 (read_q7x4_ia ((q7_t **) &pSrcA), read_q7x4_ia ((q7_t **) &pSrcB)));
  63. #else
  64. *pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
  65. *pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
  66. *pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
  67. *pDst++ = (q7_t) __SSAT ((q15_t) *pSrcA++ + *pSrcB++, 8);
  68. #endif
  69. /* Decrement loop counter */
  70. blkCnt--;
  71. }
  72. /* Loop unrolling: Compute remaining outputs */
  73. blkCnt = blockSize % 0x4U;
  74. #else
  75. /* Initialize blkCnt with number of samples */
  76. blkCnt = blockSize;
  77. #endif /* #if defined (ARM_MATH_LOOPUNROLL) */
  78. while (blkCnt > 0U)
  79. {
  80. /* C = A + B */
  81. /* Add and store result in destination buffer. */
  82. *pDst++ = (q7_t) __SSAT((q15_t) *pSrcA++ + *pSrcB++, 8);
  83. /* Decrement loop counter */
  84. blkCnt--;
  85. }
  86. }
  87. /**
  88. @} end of BasicAdd group
  89. */