9ab1bf24e2
Fix API inconsistency in cupp11.hpp
...
The function `CopyToAsync` has an optional event argument in the OpenCL version, which is used in CLBlast. This makes the code not compile at all if CUDA (through cupp11.hpp`) is used as backend. This issue was found by a CLBlast user and reported privately by email. This PR should fix that.
2022-05-23 12:45:22 +02:00
7709a7308b
Applied feedback from Cedric from first pull request
2018-07-14 19:50:47 -04:00
bd1715aff9
Fixes for CUDA version of CLBlast
2018-06-03 10:41:57 +02:00
ad1227c4f2
Added optional temp-buffer argument to C++ interface of GEMM
2017-12-30 18:45:06 +01:00
ca5dbcd2bd
Made the pre-processor run by default for ARM and Qualcomm GPUs
2017-12-09 15:16:53 +01:00
0f080bbc6e
Potentially fixed an MSVC 2013 issue with a copy-constructor not being generated
2017-11-20 20:54:18 +01:00
a3a8b44f59
Some fixed for the new auto-tuner to be compatible with the Python scripts
2017-11-19 16:31:08 +01:00
363568787e
Moved CUmodule code from Kernel to Program class to not require re-compilation every time
2017-10-18 18:17:30 +02:00
9d879c949a
Fix an incompatibility with CUDA's FP16 definition
2017-10-17 20:29:23 +02:00
0719f14486
Made all CUDA kernel launches synchronous; removed exception raising
2017-10-16 21:54:42 +02:00
71049e8d39
Added the SM-compute-arch version to the nv compile options
2017-10-15 17:41:44 +02:00
7408da174c
Various fixes to make the first CUDA examples work
2017-10-15 12:17:35 +02:00
54d0c440ce
Various fixes to make the host code and sample compile with the CUDA API
2017-10-14 11:43:57 +02:00
b901809345
Added first (untested) version of a CUDA API
2017-10-11 23:16:57 +02:00
Cedric Nugteren
Tyler Sorensen