arm_dot_prod_f32.c 4.4 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135
  1. /* ----------------------------------------------------------------------
  2. * Copyright (C) 2010-2014 ARM Limited. All rights reserved.
  3. *
  4. * $Date: 12. March 2014
  5. * $Revision: V1.4.4
  6. *
  7. * Project: CMSIS DSP Library
  8. * Title: arm_dot_prod_f32.c
  9. *
  10. * Description: Floating-point dot product.
  11. *
  12. * Target Processor: Cortex-M4/Cortex-M3/Cortex-M0
  13. *
  14. * Redistribution and use in source and binary forms, with or without
  15. * modification, are permitted provided that the following conditions
  16. * are met:
  17. * - Redistributions of source code must retain the above copyright
  18. * notice, this list of conditions and the following disclaimer.
  19. * - Redistributions in binary form must reproduce the above copyright
  20. * notice, this list of conditions and the following disclaimer in
  21. * the documentation and/or other materials provided with the
  22. * distribution.
  23. * - Neither the name of ARM LIMITED nor the names of its contributors
  24. * may be used to endorse or promote products derived from this
  25. * software without specific prior written permission.
  26. *
  27. * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  28. * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  29. * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
  30. * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
  31. * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
  32. * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
  33. * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  34. * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  35. * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  36. * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
  37. * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  38. * POSSIBILITY OF SUCH DAMAGE.
  39. * ---------------------------------------------------------------------------- */
  40. #include "arm_math.h"
  41. /**
  42. * @ingroup groupMath
  43. */
  44. /**
  45. * @defgroup dot_prod Vector Dot Product
  46. *
  47. * Computes the dot product of two vectors.
  48. * The vectors are multiplied element-by-element and then summed.
  49. *
  50. * <pre>
  51. * sum = pSrcA[0]*pSrcB[0] + pSrcA[1]*pSrcB[1] + ... + pSrcA[blockSize-1]*pSrcB[blockSize-1]
  52. * </pre>
  53. *
  54. * There are separate functions for floating-point, Q7, Q15, and Q31 data types.
  55. */
  56. /**
  57. * @addtogroup dot_prod
  58. * @{
  59. */
  60. /**
  61. * @brief Dot product of floating-point vectors.
  62. * @param[in] *pSrcA points to the first input vector
  63. * @param[in] *pSrcB points to the second input vector
  64. * @param[in] blockSize number of samples in each vector
  65. * @param[out] *result output result returned here
  66. * @return none.
  67. */
  68. void arm_dot_prod_f32(
  69. float32_t * pSrcA,
  70. float32_t * pSrcB,
  71. uint32_t blockSize,
  72. float32_t * result)
  73. {
  74. float32_t sum = 0.0f; /* Temporary result storage */
  75. uint32_t blkCnt; /* loop counter */
  76. #ifndef ARM_MATH_CM0_FAMILY
  77. /* Run the below code for Cortex-M4 and Cortex-M3 */
  78. /*loop Unrolling */
  79. blkCnt = blockSize >> 2u;
  80. /* First part of the processing with loop unrolling. Compute 4 outputs at a time.
  81. ** a second loop below computes the remaining 1 to 3 samples. */
  82. while(blkCnt > 0u)
  83. {
  84. /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
  85. /* Calculate dot product and then store the result in a temporary buffer */
  86. sum += (*pSrcA++) * (*pSrcB++);
  87. sum += (*pSrcA++) * (*pSrcB++);
  88. sum += (*pSrcA++) * (*pSrcB++);
  89. sum += (*pSrcA++) * (*pSrcB++);
  90. /* Decrement the loop counter */
  91. blkCnt--;
  92. }
  93. /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
  94. ** No loop unrolling is used. */
  95. blkCnt = blockSize % 0x4u;
  96. #else
  97. /* Run the below code for Cortex-M0 */
  98. /* Initialize blkCnt with number of samples */
  99. blkCnt = blockSize;
  100. #endif /* #ifndef ARM_MATH_CM0_FAMILY */
  101. while(blkCnt > 0u)
  102. {
  103. /* C = A[0]* B[0] + A[1]* B[1] + A[2]* B[2] + .....+ A[blockSize-1]* B[blockSize-1] */
  104. /* Calculate dot product and then store the result in a temporary buffer. */
  105. sum += (*pSrcA++) * (*pSrcB++);
  106. /* Decrement the loop counter */
  107. blkCnt--;
  108. }
  109. /* Store the result back in the destination buffer */
  110. *result = sum;
  111. }
  112. /**
  113. * @} end of dot_prod group
  114. */