Skip to main content

Matrix Product (GEMM) Performance Data from GPUs

    Wayne Joubert | Oak Ridge National Laboratory
    Eric Palmer | Oak Ridge National Laboratory
Download Dataset on Globus

Description

Timing data for mixed precision GEMM matrix product operations on several GPU models, including NVIDIA V100 and A100, AMD MI100 and Intel P580. Also data from machine learning model training on this data using Scikit-learn.

Funding Information

DOE Contract Number

DE-AC05-00OR22725

Originating Research Organization

Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization

Office of Science (SC);Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)

Details

DOI

https://doi.org/10.13139/OLCF/1819195

Release Date

September 9, 2021

Subject

97 MATHEMATICS AND COMPUTING

Keywords

GEMM matrix product operations, computer system benchmarking, GPU Graphical Processing Units

Dataset

Dataset Type

ND Numeric Data

Software

gzip; tar

Cite This Dataset:

Joubert, W., Palmer, E. (2021). Matrix Product (GEMM) Performance Data from GPUs. Oak Ridge National Laboratory. https://doi.org/10.13139/OLCF/1819195.

Acknowledgements

This research used resources of the Oak Ridge Leadership Computing Facility at the Oak Ridge National Laboratory, which is supported by the Advanced Scientific Computing Research programs in the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.