Log onto ssh.cs.miami.edu using your class credentials. This machine is on the same network of workstations, including those named,
Log onto one of those and check that the GPU device is working by running nvidia-smi.
@zizkaea:~$ nvidia-smi Wed Aug 28 19:35:09 2024 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 560.28.03 Driver Version: 560.28.03 CUDA Version: 12.6 | |-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA GeForce RTX 3070 Off | 00000000:01:00.0 Off | N/A | | 30% 28C P8 16W / 220W | 15MiB / 8192MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+
There is a single repo for all the projects, even for the 231 edition of this course.
The Makefiles should have the pathname to nvcc, the Nvidia compiler needed to compile CUDA code. Note that files with Cuda code look like C, and have extension cu.
If this is all correct, Make in the proj1 subdirectory should produce this output:
@zizkaea:~/accelerate/proj1$ make /usr/local/cuda/bin/nvcc hello.cu -o hello ./hello Hello World from CPU! Hello World from GPU! Hello World from GPU! Hello World from GPU! Hello World from GPU! Hello World from GPU! Hello World from GPU! Hello World from GPU! Hello World from GPU! Hello World from GPU! Hello World from GPU! @zizkaea:~/accelerate/proj1$
author: burton rosenberg
created: 28 aug 2022
update: 28 nov 2024