tensor_opencl_kernel.cl 1.3 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051
  1. /* StarPU --- Runtime system for heterogeneous multicore architectures.
  2. *
  3. * Copyright (C) 2011,2012 Inria
  4. * Copyright (C) 2012,2015,2017 CNRS
  5. *
  6. * StarPU is free software; you can redistribute it and/or modify
  7. * it under the terms of the GNU Lesser General Public License as published by
  8. * the Free Software Foundation; either version 2.1 of the License, or (at
  9. * your option) any later version.
  10. *
  11. * StarPU is distributed in the hope that it will be useful, but
  12. * WITHOUT ANY WARRANTY; without even the implied warranty of
  13. * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
  14. *
  15. * See the GNU Lesser General Public License in COPYING.LGPL for more details.
  16. */
  17. __kernel void tensor_opencl(__global int *tensor,
  18. int nx, int ny, int nz, int nt,
  19. int ldy, int ldz, int ldt,
  20. int factor, __global int *err)
  21. {
  22. const int id = get_global_id(0);
  23. if (id > 0)
  24. return;
  25. unsigned int i, j, k, l;
  26. int val = 0;
  27. for (l = 0; l < nt; l++)
  28. {
  29. for (k = 0; k < nz; k++)
  30. {
  31. for (j = 0; j < ny; j++)
  32. {
  33. for (i = 0; i < nx; i++)
  34. {
  35. if (tensor[(k*ldz)+(j*ldy)+i] != factor * val)
  36. {
  37. *err = 1;
  38. return;
  39. }
  40. else
  41. {
  42. tensor[(k*ldz)+(j*ldy)+i] *= -1;
  43. val++;
  44. }
  45. }
  46. }
  47. }
  48. }
  49. }