Difference between revisions of "GPU Benchmarks"

From oldwiki.scinet.utoronto.ca
Jump to navigation Jump to search
m
 
(3 intermediate revisions by one other user not shown)
Line 1: Line 1:
Instructions:
+
{| style="border-spacing: 8px; width:100%"
 +
| valign="top" style="cellpadding:1em; padding:1em; border:2px solid; background-color:#f6f674; border-radius:5px"|
 +
'''WARNING: SciNet is in the process of replacing this wiki with a new documentation site. For current information, please go to [https://docs.scinet.utoronto.ca https://docs.scinet.utoronto.ca]'''
 +
|}
 +
 
 +
Instructions for running the Gromacs GPU Benchmark Single Node test case on Linux:  
  
 
1. Download [https://wiki.scinet.utoronto.ca/wiki/images/a/aa/GROMACS_GPU_BENCH.tar.gz Gromacs GPU Benchmark]
 
1. Download [https://wiki.scinet.utoronto.ca/wiki/images/a/aa/GROMACS_GPU_BENCH.tar.gz Gromacs GPU Benchmark]
Line 5: Line 10:
 
2. Tar and unzip
 
2. Tar and unzip
  
3. Run build script with either "OPENCL" or "CUDA"  
+
3. Run "build.sh" script with either "OPENCL" or "CUDA"  
  
4. ./run.sh
+
4. Run benchmark script run.sh
  
5. Report performance for each node type proposed.
+
5. Report performance of ns/day on a single node.

Latest revision as of 19:23, 31 August 2018

WARNING: SciNet is in the process of replacing this wiki with a new documentation site. For current information, please go to https://docs.scinet.utoronto.ca

Instructions for running the Gromacs GPU Benchmark Single Node test case on Linux:

1. Download Gromacs GPU Benchmark

2. Tar and unzip

3. Run "build.sh" script with either "OPENCL" or "CUDA"

4. Run benchmark script run.sh

5. Report performance of ns/day on a single node.