arm_cmplx_mult_cmplx_q31.c 4.0 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138
  1. /* ----------------------------------------------------------------------
  2. * Project: CMSIS DSP Library
  3. * Title: arm_cmplx_mult_cmplx_q31.c
  4. * Description: Q31 complex-by-complex multiplication
  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 groupCmplxMath
  31. */
  32. /**
  33. @addtogroup CmplxByCmplxMult
  34. @{
  35. */
  36. /**
  37. @brief Q31 complex-by-complex multiplication.
  38. @param[in] pSrcA points to first input vector
  39. @param[in] pSrcB points to second input vector
  40. @param[out] pDst points to output vector
  41. @param[in] numSamples number of samples in each vector
  42. @return none
  43. @par Scaling and Overflow Behavior
  44. The function implements 1.31 by 1.31 multiplications and finally output is converted into 3.29 format.
  45. Input down scaling is not required.
  46. */
  47. void arm_cmplx_mult_cmplx_q31(
  48. const q31_t * pSrcA,
  49. const q31_t * pSrcB,
  50. q31_t * pDst,
  51. uint32_t numSamples)
  52. {
  53. uint32_t blkCnt; /* Loop counter */
  54. q31_t a, b, c, d; /* Temporary variables */
  55. #if defined (ARM_MATH_LOOPUNROLL)
  56. /* Loop unrolling: Compute 4 outputs at a time */
  57. blkCnt = numSamples >> 2U;
  58. while (blkCnt > 0U)
  59. {
  60. /* C[2 * i ] = A[2 * i] * B[2 * i ] - A[2 * i + 1] * B[2 * i + 1]. */
  61. /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i ]. */
  62. a = *pSrcA++;
  63. b = *pSrcA++;
  64. c = *pSrcB++;
  65. d = *pSrcB++;
  66. /* store result in 3.29 format in destination buffer. */
  67. *pDst++ = (q31_t) ( (((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33) );
  68. *pDst++ = (q31_t) ( (((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33) );
  69. a = *pSrcA++;
  70. b = *pSrcA++;
  71. c = *pSrcB++;
  72. d = *pSrcB++;
  73. *pDst++ = (q31_t) ( (((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33) );
  74. *pDst++ = (q31_t) ( (((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33) );
  75. a = *pSrcA++;
  76. b = *pSrcA++;
  77. c = *pSrcB++;
  78. d = *pSrcB++;
  79. *pDst++ = (q31_t) ( (((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33) );
  80. *pDst++ = (q31_t) ( (((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33) );
  81. a = *pSrcA++;
  82. b = *pSrcA++;
  83. c = *pSrcB++;
  84. d = *pSrcB++;
  85. *pDst++ = (q31_t) ( (((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33) );
  86. *pDst++ = (q31_t) ( (((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33) );
  87. /* Decrement loop counter */
  88. blkCnt--;
  89. }
  90. /* Loop unrolling: Compute remaining outputs */
  91. blkCnt = numSamples % 0x4U;
  92. #else
  93. /* Initialize blkCnt with number of samples */
  94. blkCnt = numSamples;
  95. #endif /* #if defined (ARM_MATH_LOOPUNROLL) */
  96. while (blkCnt > 0U)
  97. {
  98. /* C[2 * i ] = A[2 * i] * B[2 * i ] - A[2 * i + 1] * B[2 * i + 1]. */
  99. /* C[2 * i + 1] = A[2 * i] * B[2 * i + 1] + A[2 * i + 1] * B[2 * i ]. */
  100. a = *pSrcA++;
  101. b = *pSrcA++;
  102. c = *pSrcB++;
  103. d = *pSrcB++;
  104. /* store result in 3.29 format in destination buffer. */
  105. *pDst++ = (q31_t) ( (((q63_t) a * c) >> 33) - (((q63_t) b * d) >> 33) );
  106. *pDst++ = (q31_t) ( (((q63_t) a * d) >> 33) + (((q63_t) b * c) >> 33) );
  107. /* Decrement loop counter */
  108. blkCnt--;
  109. }
  110. }
  111. /**
  112. @} end of CmplxByCmplxMult group
  113. */