You should see something like: $ /usr/local/cuda-10.0/samples/bin/x86_64/linux/release/matrixMulCUBLAS - Starting. You should see something like: $ /usr/local/cuda-10.0/samples/bin/x86_64/linux/release/deviceQuery /usr/local/cuda-10.0/samples/bin/x86_64/linux/release/deviceQuery Starting.CUDA Device Query (Runtime API) version (CUDART static linking) Detected 1 CUDA Capable device(s)Ģ.matrixMulCUBLAS /usr/local/cuda-10.0/samples/bin/x86_64/linux/release/matrixMulCUBLAS To do so, we enter these commands: cd /usr/local/cuda-10.0/samples sudo make Now, we need to confirm that our CUDA installation is complete. To apply this change, do: source ~/.bashrc Add these two lines to the bottom of your ~/.bashrc to complete post-installation configuration: # CUDA Config - ~/.bashrc export PATH=/usr/local/cuda-10.0/bin:/usr/local/cuda-10.0/NsightCompute-1.0$ This is strictly for Cuda 10.0.ĭownload the CUDA. Notice that installing Cuda 10.0 is very different from Cuda 9.0 and 9.2, so don’t use the same instructions for both of them.
0 kommentar(er)
