28719

Applying the Midas Touch of Reproducibility to High-Performance Computing

A. C. Minor, W. Feng
Dept. of Computer Science, Virginia Tech
IEEE High Performance Extreme Computing Conference (HPEC), 2022

@article{minor2022applying,

   title={Applying the Midas Touch of Reproducibility to High-Performance Computing},

   author={Minor, AC and Feng, W},

   year={2022}

}

Download Download (PDF)   View View   Source Source   

615

views

With the serial performance of CPUs improving exponentially through the 1980s and 1990s and then plateauing by the mid-2000s, the high-performance computing community has seen parallel computing become ubiquitous, which, in turn, has led to a proliferation of parallel programming models. This diversity in hardware platform and programming model has forced programmers to port their codes from one hardware platform to another (e.g., CUDA on Nvidia GPU to OpenCL on AMD GPU) and show reproducibility via ad-hoc testing. So, to validate reproducibility between codes, we propose Midas, a system to ensure that the results of the original code match the results of the ported code by leveraging snapshots to capture the state of a system before and after the execution of a kernel.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: