Commit Graph

  • c41005fba6 add windows compiling instructions ... ugh ... master origin/master Dakota St. Laurent 2015-09-30 23:19:02 -04:00
  • 2891c9d6f5 - added out-of-place real transform to example05 - makefile now uses system-installed version of clFFT Dakota St. Laurent 2015-08-18 19:33:47 -04:00
  • bff9fd6443 - update Example05 to use FFTW to check the answer - update clFFT installation instructions Dakota St. Laurent 2015-08-12 16:34:10 -04:00
  • 3af7ec6c3b - added example05 for clfft real in-place transform - added readme to example04 for installing clfft Dakota St. Laurent 2015-08-03 18:38:14 -04:00
  • 14438e2355 added example04 for clfft inplace complex-interleaved transform Dakota St. Laurent 2015-08-03 16:01:08 -04:00
  • 3129ddfbf9 add example03 for using fp64 extension Dakota St. Laurent 2015-08-03 06:50:31 -04:00
  • c8179b88a7 added C version of example02 Dakota St. Laurent 2015-07-16 00:04:40 -04:00
  • 15d0ffaac2 use system header files instead of local ones Dakota St. Laurent 2015-07-07 17:14:07 -04:00
  • d954c321a0 added example 02 Dakota St. Laurent 2015-06-24 13:28:54 -04:00
  • eaef887f8e major update to example01 - old tests weren't really useful Dakota St. Laurent 2015-06-23 16:52:01 -04:00
  • 5c5a02b499 added fifth version, which gives very strange results... Dakota St. Laurent 2015-06-19 09:50:49 -04:00
  • de0533d168 lots of changes to example01: Dakota St. Laurent 2015-06-18 14:15:37 -04:00
  • 835c48d476 reorganize directory Dakota St. Laurent 2015-06-17 17:05:28 -04:00
  • bd11706eac update example01 with different number of global and local threads -- now first trial is slower... why Dakota St. Laurent 2015-06-16 18:49:02 -04:00
  • fd6b886c67 add configuration and compilation instructions; properly indent a function in example01 Dakota St. Laurent 2015-06-12 19:00:45 -04:00
  • 1ea82c8b76 added implementation of one thread per element for example01 - it's the fastest thus far Dakota St. Laurent 2015-06-11 18:00:51 -04:00
  • ef9df7f67c add code to 01 that repeatedly writes buffers to show overhead; change vector names in kernel code to v1,v2,v3 to show that they're not the same as A,B,C in the C++ code Dakota St. Laurent 2015-06-09 16:07:18 -04:00
  • ea3055fbc1 example 01 is compiling and running, and it's freaking fast ... I'm skeptical. Dakota St. Laurent 2015-06-05 19:36:32 -04:00
  • 07f78f6b3f init commit; example 00 is working, example 01 is not Dakota St. Laurent 2015-06-04 13:48:36 -04:00