arm_power_f32.c 4.6 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143
  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_power_f32.c
  9. *
  10. * Description: Sum of the squares of the elements of a floating-point vector.
  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 groupStats
  43. */
  44. /**
  45. * @defgroup power Power
  46. *
  47. * Calculates the sum of the squares of the elements in the input vector.
  48. * The underlying algorithm is used:
  49. *
  50. * <pre>
  51. * Result = pSrc[0] * pSrc[0] + pSrc[1] * pSrc[1] + pSrc[2] * pSrc[2] + ... + pSrc[blockSize-1] * pSrc[blockSize-1];
  52. * </pre>
  53. *
  54. * There are separate functions for floating point, Q31, Q15, and Q7 data types.
  55. */
  56. /**
  57. * @addtogroup power
  58. * @{
  59. */
  60. /**
  61. * @brief Sum of the squares of the elements of a floating-point vector.
  62. * @param[in] *pSrc points to the input vector
  63. * @param[in] blockSize length of the input vector
  64. * @param[out] *pResult sum of the squares value returned here
  65. * @return none.
  66. *
  67. */
  68. void arm_power_f32(
  69. float32_t * pSrc,
  70. uint32_t blockSize,
  71. float32_t * pResult)
  72. {
  73. float32_t sum = 0.0f; /* accumulator */
  74. float32_t in; /* Temporary variable to store input value */
  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] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
  85. /* Compute Power and then store the result in a temporary variable, sum. */
  86. in = *pSrc++;
  87. sum += in * in;
  88. in = *pSrc++;
  89. sum += in * in;
  90. in = *pSrc++;
  91. sum += in * in;
  92. in = *pSrc++;
  93. sum += in * in;
  94. /* Decrement the loop counter */
  95. blkCnt--;
  96. }
  97. /* If the blockSize is not a multiple of 4, compute any remaining output samples here.
  98. ** No loop unrolling is used. */
  99. blkCnt = blockSize % 0x4u;
  100. #else
  101. /* Run the below code for Cortex-M0 */
  102. /* Loop over blockSize number of values */
  103. blkCnt = blockSize;
  104. #endif /* #ifndef ARM_MATH_CM0_FAMILY */
  105. while(blkCnt > 0u)
  106. {
  107. /* C = A[0] * A[0] + A[1] * A[1] + A[2] * A[2] + ... + A[blockSize-1] * A[blockSize-1] */
  108. /* compute power and then store the result in a temporary variable, sum. */
  109. in = *pSrc++;
  110. sum += in * in;
  111. /* Decrement the loop counter */
  112. blkCnt--;
  113. }
  114. /* Store the result to the destination */
  115. *pResult = sum;
  116. }
  117. /**
  118. * @} end of power group
  119. */