Warning: You are not logged in. Your IP address will be publicly visible if you make any edits. If you log in or create an account, your edits will be attributed to your username, along with other benefits.
The edit can be undone.
Please check the comparison below to verify that this is what you want to do, and then save the changes below to finish undoing the edit.
Latest revision |
Your text |
Line 41: |
Line 41: |
| * [http://www.scl.ameslab.gov/netpipe/ NetPIPE] - One of the best network benchmarks. It tests a range of packet sizes and measures the time (bandwidth). It can use MPI as the message sending mechanism so it allows you to also test MPI implementations. | | * [http://www.scl.ameslab.gov/netpipe/ NetPIPE] - One of the best network benchmarks. It tests a range of packet sizes and measures the time (bandwidth). It can use MPI as the message sending mechanism so it allows you to also test MPI implementations. |
| * [http://www.netperf.org/netperf/ Netperf] - Another good networking benchmark that is used frequently. | | * [http://www.netperf.org/netperf/ Netperf] - Another good networking benchmark that is used frequently. |
− |
| |
− | '''GPU Benchmarks/Tests'''
| |
− | * [https://sourceforge.net/projects/cudagpumemtest CUDA GPU memtest] is a GPU memory test utility for NVIDIA and AMD GPUs using well established patterns from memtest86/memtest86+ as well as additional stress tests. The tests are designed to find hardware and soft errors. The code is written in CUDA and OpenCL.
| |
− | * [https://github.com/ihaque/memtestCL MemtestCL] is a program to test the memory and logic of OpenCL-enabled GPUs, CPUs, and accelerators for errors. It is an OpenCL port of our CUDA- based tester for NVIDIA GPUs, MemtestG80.
| |
− | * [https://launchpad.net/clamity Calamity] - is a testing framework that allows you test how your GPU is working, by running various tests. With its plugin system it can be expanded to test for more than just the core set.
| |
− | * [https://github.com/Microway/gpu-burn GPU-Burn] thoroughly exercises the math units on NVIDIA GPUs. It is capable of stressing both the single-precision (32-bit) and double-precision (64-bit) math units of any GPU with CUDA support. Generally-speaking, this means any NVIDIA Tesla, Quadro or GeForce GPU released after 2010. During startup, all GPUs in the system are discovered and tests are run on each. As the tool runs, the status of each GPU is output (including number of passes, number of errors encountered, and current GPU temperatures).
| |