• Accelerating x‐ray tracing for...

Treffer: Accelerating x‐ray tracing for exascale systems using Kokkos

Title:
Accelerating x‐ray tracing for exascale systems using Kokkos
Authors:
Wittwer, Felix, Sauter, Nicholas K, Mendez, Derek, Poon, Billy K, Brewster, Aaron S, Holton, James M, Wall, Michael E, Hart, William E, Bard, Deborah J, Blaschke, Johannes P
Source:
Concurrency and Computation Practice and Experience, vol 36, iss 5
Publisher Information:
eScholarship, University of California
Publication Year:
2024
Collection:
University of California: eScholarship
Subject Terms:
46 Information and Computing Sciences (for-2020), 4608 Human-Centred Computing (for-2020), AMD GPU, cross compilation, code optimization, Kokkos, Nvidia GPU, 0801 Artificial Intelligence and Image Processing (for), 0803 Computer Software (for), 0805 Distributed Computing (for), Distributed Computing (science-metrix)
Document Type:
Fachzeitschrift article in journal/newspaper
File Description:
application/pdf
Language:
unknown
Relation:
qt38v3k44n; https://escholarship.org/uc/item/38v3k44n; https://escholarship.org/content/qt38v3k44n/qt38v3k44n.pdf
DOI:
10.1002/cpe.7944
Availability:
https://escholarship.org/uc/item/38v3k44n
https://escholarship.org/content/qt38v3k44n/qt38v3k44n.pdf
https://doi.org/10.1002/cpe.7944
Rights:
CC-BY-NC
Accession Number:
edsbas.57A77724
Database:
BASE

Weitere Informationen

Summary The upcoming exascale computing systems Frontier and Aurora will draw much of their computing power from GPU accelerators. The hardware for these systems will be provided by AMD and Intel, respectively, each supporting their own GPU programming model. The challenge for applications that harness one of these exascale systems will be to avoid lock‐in and to preserve performance portability. We report here on our results of using Kokkos to accelerate a real‐world application on NERSC's Perlmutter Phase 1 (using NVIDIA A100 accelerators) and Crusher, the testbed system for OLCF's Frontier (using AMD MI250X). By porting to Kokkos, we successfully ran the same X‐ray tracing code on both systems and achieved speed‐ups between 13 % and 66 % compared to the original CUDA code. These results are a highly encouraging demonstration of using Kokkos to accelerate production science code.