cuda-samples
cuda-samples copied to clipboard
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
https://github.com/NVIDIA/cuda-samples/blob/b312abaa07ffdc1ba6e3d44a9bc1a8e89149c20b/Common/helper_cuda_drvapi.h#L239 this line should be `(unsigned long long)(multiProcessorCount) * sm_per_multiproc * clockRate;` Type convert after compute make no sense, and it has overflowed in case of RTX3080.
I try to using 'cudaMalloc' to alloc a gpu memory in the beginning of each loop and i using 'cudaFree' to destory it in the ending of each loop. (that...
Dear sir/madam: When I inference on a deep learning model (slowfast model), I'm facing a problem that my **python** program seems to take more inference time in cuda env compared...
How find the other version cuda? Do you have the link for all version list? Version: | 472.12 https://www.nvidia.com/Download/driverResults.aspx/180557
Bugfix #1: added missing cudaExternalMemoryDedicated flag on cudaExternalMemoryHandleDesc Bugfix #2: IsWindows8OrGreater queries return false on Windows 10. Always returning Windows 10 values now (might break on older Windows versions)
multiple definition of `cuda::__3::pipeline::__barrier_try_wait_parity(cuda::__3::barrier&, bool)'
Short: Fixed compilation errors relating Clang 13 with OpenMP and MPI examples Explanation: - Fixed clang 13 OpenMP bug in cudaOpenMP and UnifiedMemoryStreams: Check if we are running a clang...
even one element difference can lead to the difference of matrix
I am using V Tesla V100-PCIE gpu. I have a problem with memory allocation. when i call freeCuda to free memory, process did not return all of memory to OS,...
I am having ubuntu 20.04, here I installed CUDA and CudNN. How can I verify my CudNN version?