TY  - GEN
AU  - Herten, Andreas
AU  - Pleiter, Dirk
AU  - Wagner, Mathias
AU  - Hagleitner, Christoph
AU  - Ravindar, Archana
AU  - Papatheodore, Tom
TI  - Application Porting and Optimization on GPU-Accelerated POWER Architectures
M1  - FZJ-2019-06785
PY  - 2019
AB  - The POWER processor has re-emerged as a technology for supercomputer architectures. One major reason is the tight integration of processor and GPU accelerator through the NVLink technology. Two major sites in the US, ORNL and LLNL, deployed their pre-exascale systems based on this new architecture (Summit and Sierra, respectively).This tutorial gives an opportunity to obtain in-depth knowledge and experience with GPU-accelerated POWER nodes. It focuses on porting applications to a single node and covers the topics architecture, compilers, performance analysis and tuning, and multi-GPU programming. The tutorial includes an overview of the NVLink-based node architectures, lectures on first-hand experience in porting to this architecture, and exercises using tools to focus on performance.
T2  - International Conference for High Performance Computing, Networking, Storage and Analysis (The Supercomputing Conference)
CY  - 18 Nov 2019 - 18 Nov 2019, Denver, CO (USA)
Y2  - 18 Nov 2019 - 18 Nov 2019
M2  - Denver, CO, USA
LB  - PUB:(DE-HGF)17
UR  - https://juser.fz-juelich.de/record/868213
ER  -