Matches in SemOpenAlex for { <https://semopenalex.org/work/W4321636633> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4321636633 abstract "The rise of machine learning (ML) applications and their use of mixed precision to perform interesting science are driving forces behind AI for science on HPC. The convergence of ML and HPC with mixed precision offers the possibility of transformational changes in computational science. The HPL-AI benchmark is designed to measure the performance of mixed precision arithmetic as opposed to the HPL benchmark which measures double precision performance. Pushing the limits of systems at extreme scale is nontrivial -little public literature explores optimization of mixed precision computations at this scale. In this work, we demonstrate how to scale up the HPL-AI benchmark on the pre-exascale Summit and exascale Frontier systems at the Oak Ridge Leadership Computing Facility (OLCF) with a cross-platform design. We present the implementation, performance results, and a guideline of optimization strategies employed for delivering portable performance on both AMD and NVIDIA GPUs at extreme scale." @default.
- W4321636633 created "2023-02-24" @default.
- W4321636633 creator A5011348166 @default.
- W4321636633 creator A5012951247 @default.
- W4321636633 creator A5026185056 @default.
- W4321636633 creator A5058248684 @default.
- W4321636633 creator A5062940770 @default.
- W4321636633 creator A5075702553 @default.
- W4321636633 date "2022-11-01" @default.
- W4321636633 modified "2023-10-16" @default.
- W4321636633 title "Climbing the Summit and Pushing the Frontier of Mixed Precision Benchmarks at Extreme Scale" @default.
- W4321636633 cites W1541682349 @default.
- W4321636633 cites W1947869163 @default.
- W4321636633 cites W1989165177 @default.
- W4321636633 cites W2006973305 @default.
- W4321636633 cites W2020804487 @default.
- W4321636633 cites W2054176560 @default.
- W4321636633 cites W2080038255 @default.
- W4321636633 cites W2131613942 @default.
- W4321636633 cites W2143119605 @default.
- W4321636633 cites W2151156597 @default.
- W4321636633 cites W2169631286 @default.
- W4321636633 cites W2791341782 @default.
- W4321636633 cites W2895305554 @default.
- W4321636633 cites W2972087877 @default.
- W4321636633 cites W2983126917 @default.
- W4321636633 cites W3108141724 @default.
- W4321636633 cites W3130650642 @default.
- W4321636633 cites W3133275763 @default.
- W4321636633 doi "https://doi.org/10.1109/sc41404.2022.00083" @default.
- W4321636633 hasPublicationYear "2022" @default.
- W4321636633 type Work @default.
- W4321636633 citedByCount "0" @default.
- W4321636633 crossrefType "proceedings-article" @default.
- W4321636633 hasAuthorship W4321636633A5011348166 @default.
- W4321636633 hasAuthorship W4321636633A5012951247 @default.
- W4321636633 hasAuthorship W4321636633A5026185056 @default.
- W4321636633 hasAuthorship W4321636633A5058248684 @default.
- W4321636633 hasAuthorship W4321636633A5062940770 @default.
- W4321636633 hasAuthorship W4321636633A5075702553 @default.
- W4321636633 hasConcept C100970517 @default.
- W4321636633 hasConcept C113775141 @default.
- W4321636633 hasConcept C11413529 @default.
- W4321636633 hasConcept C118524514 @default.
- W4321636633 hasConcept C121332964 @default.
- W4321636633 hasConcept C13280743 @default.
- W4321636633 hasConcept C162324750 @default.
- W4321636633 hasConcept C173608175 @default.
- W4321636633 hasConcept C185798385 @default.
- W4321636633 hasConcept C205649164 @default.
- W4321636633 hasConcept C2777303404 @default.
- W4321636633 hasConcept C2778755073 @default.
- W4321636633 hasConcept C2778837361 @default.
- W4321636633 hasConcept C2778848561 @default.
- W4321636633 hasConcept C41008148 @default.
- W4321636633 hasConcept C45374587 @default.
- W4321636633 hasConcept C459310 @default.
- W4321636633 hasConcept C50522688 @default.
- W4321636633 hasConcept C62520636 @default.
- W4321636633 hasConcept C83283714 @default.
- W4321636633 hasConceptScore W4321636633C100970517 @default.
- W4321636633 hasConceptScore W4321636633C113775141 @default.
- W4321636633 hasConceptScore W4321636633C11413529 @default.
- W4321636633 hasConceptScore W4321636633C118524514 @default.
- W4321636633 hasConceptScore W4321636633C121332964 @default.
- W4321636633 hasConceptScore W4321636633C13280743 @default.
- W4321636633 hasConceptScore W4321636633C162324750 @default.
- W4321636633 hasConceptScore W4321636633C173608175 @default.
- W4321636633 hasConceptScore W4321636633C185798385 @default.
- W4321636633 hasConceptScore W4321636633C205649164 @default.
- W4321636633 hasConceptScore W4321636633C2777303404 @default.
- W4321636633 hasConceptScore W4321636633C2778755073 @default.
- W4321636633 hasConceptScore W4321636633C2778837361 @default.
- W4321636633 hasConceptScore W4321636633C2778848561 @default.
- W4321636633 hasConceptScore W4321636633C41008148 @default.
- W4321636633 hasConceptScore W4321636633C45374587 @default.
- W4321636633 hasConceptScore W4321636633C459310 @default.
- W4321636633 hasConceptScore W4321636633C50522688 @default.
- W4321636633 hasConceptScore W4321636633C62520636 @default.
- W4321636633 hasConceptScore W4321636633C83283714 @default.
- W4321636633 hasFunder F4320306084 @default.
- W4321636633 hasLocation W43216366331 @default.
- W4321636633 hasOpenAccess W4321636633 @default.
- W4321636633 hasPrimaryLocation W43216366331 @default.
- W4321636633 hasRelatedWork W106125451 @default.
- W4321636633 hasRelatedWork W1262521223 @default.
- W4321636633 hasRelatedWork W1979781211 @default.
- W4321636633 hasRelatedWork W1992479880 @default.
- W4321636633 hasRelatedWork W1995481480 @default.
- W4321636633 hasRelatedWork W2073045545 @default.
- W4321636633 hasRelatedWork W2123643790 @default.
- W4321636633 hasRelatedWork W2385361820 @default.
- W4321636633 hasRelatedWork W2741639990 @default.
- W4321636633 hasRelatedWork W2900736724 @default.
- W4321636633 isParatext "false" @default.
- W4321636633 isRetracted "false" @default.
- W4321636633 workType "article" @default.