cuda-samples
cuda-samples copied to clipboard
Samples for CUDA Developers which demonstrates features in CUDA Toolkit
Hi developer, Thanks to develop the great tools. I want to install the cudf cudatookit through mamba install -c rapidsai -c nvidia -c conda-forge cudf=0.19 python=3.8 cudatoolkit=11.0 cuda command into...
I am on Gentoo linux and am having odd problems with running built programs. There maybe other issues. I don't feel like going though every single Sample. upon running **simpleTexture**...
the Common directory is missing the header file **cuda_profiler_api.h**. So the make command files to run when building the asyncAPI package. I had to get the file from https://github.com/tpn/cuda-samples/tree/master/v12.0/include
When I run the "make test" command on the cuda-sample project on ARM64 platform. there are some testcases failed. After check the failed log, I found the follow several testcases...
Sample 5_Domain_Specific/stereoDisparity requires 90, which isn't available on older cuda versions.
I got a compilation error when building bandwidthTest_vs2022.sln in 1_Utilities using vs studio 2022. The nvcc -V output in cmd.exe is: > nvcc: NVIDIA (R) Cuda compiler driver Copyright (c)...
Maybe there is an error in Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy.cu?
As you can see, it shoule be `reinterpret_cast(&B[b + wB * threadIdx.y + t4x]);` obviously in line721. However, it is `reinterpret_cast(&B[a + wA * threadIdx.y + t4x]);` https://github.com/NVIDIA/cuda-samples/blob/e8568c417356f7e66bb9b7130d6be7e55324a519/Samples/3_CUDA_Features/globalToShmemAsyncCopy/globalToShmemAsyncCopy.cu#L225C1-L225C1 When matrixA.width...
I'm getting the following error when trying to run `make`: ``` make[1]: Entering directory '/mnt/c/Users/Drake/Development/cuda-samples/Samples/4_CUDA_Libraries/simpleCUFFT_callback' >>> GCC Version is greater or equal to 5.3.0
Fixes this error: ``` error: no operator "-" matches these operands operand types are: - const float2 ```