Automatic BLAS Offloading on Unified Memory Architecture: A Study on NVIDIA Grace-Hopper

Junjie Li, Yinzhi Wang, Xiao Liang, Hang Liu
Texas Advanced Computing Center, The University of Texas at Austin, USA
arXiv:2404.13195 [cs.DC], (1 May 2024)


   title={Automatic BLAS Offloading on Unified Memory Architecture: A Study on NVIDIA Grace-Hopper},

   author={Junjie Li and Yinzhi Wang and Xiao Liang and Hang Liu},






Download Download (PDF)   View View   Source Source   



Porting codes to GPU often requires major efforts. While several tools exist for automatically offload numerical libraries such as BLAS and LAPACK, they often prove impractical due to the high cost of mandatory data transfer. The new unified memory architecture in NVIDIA Grace-Hopper allows high bandwidth cache-coherent memory access of all memory from both CPU and GPU, potentially eliminating bottleneck faced in conventional architecture. This breakthrough opens up new avenues for application development and porting strategies. In this study, we introduce a new tool for automatic BLAS offload, the tool leverages the high speed cache coherent NVLink C2C interconnect in Grace-Hopper, and enables performant GPU offload for BLAS heavy applications with no code changes or recompilation. The tool was tested on two quantum chemistry or physics codes, great performance benefits were observed.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: