Conference Presentation (After Call)

FZJ-2023-05322

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Advancing the Distributed Multi-GPU ChASE Library through Algorithm Optimization and NCCL Library

Di Napoli, E. (Corresponding author)FZJ* ; Wu, X. (Corresponding author)FZJ*

2023

Abstract: As supercomputers become larger with powerful Graphics Processing Unit (GPU), traditional direct eigensolvers struggle to keep up with the hardware evolution and scale efficiently due to communication and synchronization demands. Subspace eigensolvers, like the Chebyshev Accelerated Subspace Eigensolver (ChASE), have a simpler structure and can overcome communication and synchronization bottlenecks. ChASE is a modern subspace eigensolver that uses Chebyshev polynomials to accelerate the computation of extremal eigenpairs of dense Hermitian eigenproblems. In this work we show how we have modified ChASE by rethinking its memory layout, introducing a novel parallelization scheme, switching to a more performing communication-avoiding algorithm for one of its inner module, and substituting MPI library by vendor-optimized NCCL library. The resulting library can tackle dense problems with size up to N=O(10^6), and scales effortlessly up to the full 900 nodes---each one powered by 4xA100 NVIDIA GPUs---of the JUWELS Booster hosted at the Jülich Supercomputing Centre.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)
2. Center for Advanced Simulation and Analytics (CASA)

Research Program(s):

1. 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) (POF4-511)
2. Simulation and Data Laboratory Quantum Materials (SDLQM) (SDLQM) (SDLQM)

Appears in the scientific report 2023

---