12 Commits

Author	SHA1	Message	Date
Gabriele Gristina	f8ceb8785e	CUDA Backend: moved functions to ext_cuda.c/ext_nvrtc.c and includes to ext_cuda.h/ext_nvrtc.h	2022-01-03 16:29:15 +01:00
Jukka Ojanen	cdf27a1cb3	Implement async run_cuda_kernel_memset() and run_cuda_kernel_memset32()	2021-07-27 18:56:59 +03:00
Jukka Ojanen	a642f7b233	Remove synchronous GPU memory copy functions	2021-07-26 15:36:42 +03:00
Jukka Ojanen	4263cafdcf	Add async CUDA memcpy functions: hc_cuMemcpyDtoDAsync(), hc_cuMemcpyDtoHAsync() and hc_cuMemcpyHtoDAsync(). Implement partially async CUDA memset and bzero kernels.	2021-07-20 12:23:39 +03:00
Jens Steube	66ae5125ce	Cache cubin instead of PTX to decrease startup time	2020-01-29 15:56:36 +01:00
Jens Steube	33028314f0	Add hc_cuCtxSetCacheConfig()	2019-05-09 00:04:05 +02:00
Jens Steube	ec9925f3b1	Warnings self-check and autotune with CUDA	2019-05-04 21:52:00 +02:00
Jens Steube	a6fa7a2749	Add support for some first CUDA module loader	2019-05-02 14:58:52 +02:00
Jens Steube	4b986de5fb	Prepare native CUDA hybrid integration	2019-04-25 14:45:17 +02:00
jsteube	378258d789	Fix caching system for use with AMD and NV, drop BINARY_KERNEL define	2015-12-21 12:01:38 +01:00
jsteube	968265fffb	- Prepared for JIT use of hash-mode 1500, 8900 and 9300, works already on OpenCL (AMD) ... - Changed PROMPT	2015-12-07 21:37:12 +01:00
Jens Steube	5065474b4e	Initial commit	2015-12-04 15:47:52 +01:00