001019352 001__ 1019352
001019352 005__ 20231220201928.0
001019352 037__ $$aFZJ-2023-05322
001019352 041__ $$aEnglish
001019352 1001_ $$0P:(DE-Juel1)144723$$aDi Napoli, Edoardo$$b0$$eCorresponding author$$ufzj
001019352 1112_ $$a14th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Heterogeneous Systems$$cDenver$$d2023-11-12 - 2023-11-17$$gScalAH23$$wUSA
001019352 245__ $$aAdvancing the Distributed Multi-GPU ChASE Library through Algorithm Optimization and NCCL Library
001019352 260__ $$c2023
001019352 3367_ $$033$$2EndNote$$aConference Paper
001019352 3367_ $$2DataCite$$aOther
001019352 3367_ $$2BibTeX$$aINPROCEEDINGS
001019352 3367_ $$2DRIVER$$aconferenceObject
001019352 3367_ $$2ORCID$$aLECTURE_SPEECH
001019352 3367_ $$0PUB:(DE-HGF)6$$2PUB:(DE-HGF)$$aConference Presentation$$bconf$$mconf$$s1703049070_6181$$xAfter Call
001019352 520__ $$aAs supercomputers become larger with powerful Graphics Processing Unit (GPU), traditional direct eigensolvers struggle to keep up with the hardware evolution and scale efficiently due to communication and synchronization demands. Subspace eigensolvers, like the Chebyshev Accelerated Subspace Eigensolver (ChASE), have a simpler structure and can overcome communication and synchronization bottlenecks. ChASE is a modern subspace eigensolver that uses Chebyshev polynomials to accelerate the computation of extremal eigenpairs of dense Hermitian eigenproblems. In this work we show how we have modified ChASE by rethinking its memory layout, introducing a novel parallelization scheme, switching to a more performing communication-avoiding algorithm for one of its inner module, and substituting MPI library by vendor-optimized NCCL library. The resulting library can tackle dense problems with size up to N=O(10^6), and scales effortlessly up to the full 900 nodes---each one powered by 4xA100 NVIDIA GPUs---of the JUWELS Booster hosted at the Jülich Supercomputing Centre.
001019352 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001019352 536__ $$0G:(DE-Juel1)SDLQM$$aSimulation and Data Laboratory Quantum Materials (SDLQM) (SDLQM)$$cSDLQM$$fSimulation and Data Laboratory Quantum Materials (SDLQM)$$x1
001019352 7001_ $$0P:(DE-Juel1)178969$$aWu, Xinzhe$$b1$$eCorresponding author$$ufzj
001019352 8564_ $$uhttps://sc23.conference-program.com/presentation/?id=ws_scalah103&sess=sess445
001019352 909CO $$ooai:juser.fz-juelich.de:1019352$$pVDB
001019352 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)144723$$aForschungszentrum Jülich$$b0$$kFZJ
001019352 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)178969$$aForschungszentrum Jülich$$b1$$kFZJ
001019352 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001019352 9141_ $$y2023
001019352 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001019352 9201_ $$0I:(DE-Juel1)CASA-20230315$$kCASA$$lCenter for Advanced Simulation and Analytics$$x1
001019352 980__ $$aconf
001019352 980__ $$aVDB
001019352 980__ $$aI:(DE-Juel1)JSC-20090406
001019352 980__ $$aI:(DE-Juel1)CASA-20230315
001019352 980__ $$aUNRESTRICTED