When I run the following sample program X10RT_ACCELS=CUDA0 ./CUDAKernelTest I get this error
X10RT fatal initialization error: CUDA reports 0 devices, you cannot use device 0.
Aborted (core dumped)
But I have a GPU, and I can use it with CUDA C, but X10 doesn't use it when doing X10RT_ACCELS=ALL.
--- General Information for device 0 ---
Name: NVIDIA GeForce GTX 1050
Compute capability: 6.1
Clock rate: 1493000
Device copy overlap: Enabled
Kernel execition timeout: Enabled
--- Memory Information for device 0 ---
Total global mem: 4236115968
Total constant mem: 65536
Max mem pitch: 2147483647
Texture Alignment: 512
--- MP Information for device 0 ---
Multiprocessor count: 5
Shared mem per mp: 49152
Registers per mp: 65536
Threads in warp: 32
Max threads per block: 1024
Max thread dimensions: (1024, 1024, 64)
Max grid dimensions: (2147483647, 65535, 65535)
When I run the following sample program
X10RT_ACCELS=CUDA0 ./CUDAKernelTestI get this errorBut I have a GPU, and I can use it with CUDA C, but X10 doesn't use it when doing
X10RT_ACCELS=ALL.