laplace2d.c 2.8 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879
  1. /* Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved.
  2. *
  3. * Redistribution and use in source and binary forms, with or without
  4. * modification, are permitted provided that the following conditions
  5. * are met:
  6. * * Redistributions of source code must retain the above copyright
  7. * notice, this list of conditions and the following disclaimer.
  8. * * Redistributions in binary form must reproduce the above copyright
  9. * notice, this list of conditions and the following disclaimer in the
  10. * documentation and/or other materials provided with the distribution.
  11. * * Neither the name of NVIDIA CORPORATION nor the names of its
  12. * contributors may be used to endorse or promote products derived
  13. * from this software without specific prior written permission.
  14. *
  15. * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AS IS'' AND ANY
  16. * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
  17. * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
  18. * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
  19. * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
  20. * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
  21. * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
  22. * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
  23. * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  24. * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  25. * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  26. */
  27. #include <math.h>
  28. #include <stdlib.h>
  29. #include <string.h>
  30. #define OFFSET(x, y, m) (((x)*(m)) + (y))
  31. void initialize(double *restrict A, double *restrict Anew, int m, int n)
  32. {
  33. memset(A, 0, n * m * sizeof(double));
  34. memset(Anew, 0, n * m * sizeof(double));
  35. for(int i = 0; i < m; i++){
  36. A[i] = 1.0;
  37. Anew[i] = 1.0;
  38. }
  39. }
  40. double calcNext(double *restrict A, double *restrict Anew, int m, int n)
  41. {
  42. double error = 0.0;
  43. #pragma acc parallel loop reduction(max:error) copyin(A[:n*m]) copyout(Anew[:n*m]) tile(32,4)
  44. for( int j = 1; j < n-1; j++)
  45. {
  46. for( int i = 1; i < m-1; i++ )
  47. {
  48. Anew[OFFSET(j, i, m)] = 0.25 * ( A[OFFSET(j, i+1, m)] + A[OFFSET(j, i-1, m)]
  49. + A[OFFSET(j-1, i, m)] + A[OFFSET(j+1, i, m)]);
  50. error = fmax( error, fabs(Anew[OFFSET(j, i, m)] - A[OFFSET(j, i , m)]));
  51. }
  52. }
  53. return error;
  54. }
  55. void swap(double *restrict A, double *restrict Anew, int m, int n)
  56. {
  57. #pragma acc parallel loop copyin(Anew[:n*m]) copyout(A[:n*m]) tile(32,4)
  58. for( int j = 1; j < n-1; j++)
  59. {
  60. for( int i = 1; i < m-1; i++ )
  61. {
  62. A[OFFSET(j, i, m)] = Anew[OFFSET(j, i, m)];
  63. }
  64. }
  65. }
  66. void deallocate(double *restrict A, double *restrict Anew)
  67. {
  68. free(A);
  69. free(Anew);
  70. }