37 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
André R. Brodtkorb	58f281d724	Added more efficient function to read data from global memory!	2018-09-04 15:23:47 +02:00
André R. Brodtkorb	a1902a1330	Updated writeblock also	2018-08-24 15:44:51 +02:00
André R. Brodtkorb	92fba5dc4f	Refactoring readBlock	2018-08-24 14:11:29 +02:00
André R. Brodtkorb	daa175ef32	Checkpoint	2018-08-24 11:48:30 +02:00
André R. Brodtkorb	918d22b257	Refactoring CudaArray and ArakawaA grid	2018-08-23 21:12:48 +02:00
André R. Brodtkorb	5668e28f99	Updated domain size benchmark in autotuning	2018-08-23 16:05:23 +02:00
André R. Brodtkorb	803ce8ab70	Working prototype of autotuning	2018-08-23 11:47:18 +02:00
André R. Brodtkorb	f60ceaa316	Added autotuning notebook to get best block size	2018-08-15 08:08:43 +02:00
André R. Brodtkorb	e48a408a7c	Added no extern c as default	2018-08-13 16:10:25 +02:00
André R. Brodtkorb	8bda93e565	Changed from print to logging	2018-08-13 16:04:46 +02:00
André R. Brodtkorb	9592a09d36	Added logging instead of print	2018-08-13 14:01:38 +02:00
André R. Brodtkorb	8614ba96cd	Updated passing of arguments from python to cuda	2018-08-13 09:02:44 +02:00
André R. Brodtkorb	8ccc0d57a0	Added disk caching of kernels	2018-08-13 08:37:36 +02:00
André R. Brodtkorb	9c20930c11	Templetized LxF kernel	2018-08-10 15:26:48 +02:00
André R. Brodtkorb	3e401e3fe1	Renamed macro and added iPython magic	2018-08-10 13:59:52 +02:00
André R. Brodtkorb	426b8dba5c	Updated way to get kernel	2018-08-09 16:46:00 +02:00
André R. Brodtkorb	4da6fd043d	Added superclass	2018-08-09 15:14:50 +02:00
André R. Brodtkorb	8863f654be	Cleaned up include structure for kernels	2018-08-09 10:16:05 +02:00
André R. Brodtkorb	e01cdb3c19	Updates to convergence plots	2018-08-08 16:10:31 +02:00
André R. Brodtkorb	01174dbae7	Updated 1d smooth notebook - should have nice figures now	2018-08-07 09:17:06 +02:00
André R. Brodtkorb	2e0dac3919	Addressed bug in WAF	2018-08-03 16:01:34 +02:00
André R. Brodtkorb	27a7ee4154	Merge pull request #2 from babrodtk/opencl_to_cuda ... Removed old reference files	2018-08-01 11:10:05 +02:00
André R. Brodtkorb	3fa4aab0fc	Removed old reference files	2018-08-01 11:09:13 +02:00
André R. Brodtkorb	ed48305953	Merge pull request #1 from babrodtk/opencl_to_cuda ... Opencl to cuda	2018-08-01 11:08:08 +02:00
André R. Brodtkorb	4f0a73db33	Updated cuda context handling	2018-08-01 11:03:00 +02:00
André R. Brodtkorb	8c431d2a7d	Removed get_local_size	2018-07-25 16:40:49 +02:00
André R. Brodtkorb	a0f429148c	Fixed WAF	2018-07-25 16:39:50 +02:00
André R. Brodtkorb	d94daeae7e	Fixed KP07 dimensionally split	2018-07-25 16:12:23 +02:00
André R. Brodtkorb	cbb1bdb839	Fixed KP07	2018-07-25 15:52:31 +02:00
André R. Brodtkorb	c6758b477b	Updated compilation of kernels etc	2018-07-25 15:06:56 +02:00
André R. Brodtkorb	7cecd23e59	Fixed HLL	2018-07-25 12:42:36 +02:00
André R. Brodtkorb	dd88d44162	Updates, hll doesnt work yet	2018-07-25 09:39:17 +02:00
André R. Brodtkorb	fcc1d0db1c	Ported FORCE to CUDA	2018-07-25 08:48:43 +02:00
André R. Brodtkorb	bc086865de	LxF appears to work somewhat with CUDA	2018-07-24 15:44:49 +02:00
André R. Brodtkorb	e5200cd200	Updated to python 3, and took a look at WAF	2018-07-20 16:02:41 +02:00
André R. Brodtkorb	c5dc865c48	Added initial version of SW code	2018-06-14 10:35:01 +02:00
André R. Brodtkorb	3767b121df	Initial commit	2018-06-01 12:34:57 +02:00