Skip to Main content Skip to Navigation
Poster communications

EEA-Aware For Large-Scale Scientific Applications On Heterogeneous Architectures

Abstract : Heterogeneous parallel programming has two main problems on large computation systems: the first is the increase of power consumption on supercomputers in proportion to the number of computational resources used to obtain high performance, the second one is the underuse of these resources by scientific applications with improper distribution of tasks. Select the optimal computational resources and make a good mapping of task granularity is the fundamental challenge for the next generation of Exascale Systems. This research proposes an integrated energy-aware scheme called efficiently energetic acceleration (EEA) for large-scale scientific applications running on heterogeneous architectures. The EEA scheme uses statistical techniques to get GPU power levels to create a GPU power cost function and obtains the computational resource set that maximizes energy efficiency for a provided workload. The programmer or load balancing framework can use the computational resources obtained to schedule the map parallel task granularity in static time.
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download
Contributor : John Anderson Garcia Henao <>
Submitted on : Wednesday, March 21, 2018 - 11:01:41 AM
Last modification on : Thursday, March 5, 2020 - 12:20:47 PM
Document(s) archivé(s) le : Thursday, September 13, 2018 - 11:03:59 AM


  • HAL Id : hal-01739585, version 1



John Anderson Garcia Henao, Esteban Hernandez, Philippe Navaux, Carlos Jaime Barrios-Hernandez. EEA-Aware For Large-Scale Scientific Applications On Heterogeneous Architectures. ACM Student Research Competition at Supercomputing. The International Conference for High Performance Computing, Networking, Storage and Analysis, Nov 2016, Salt Lake City, Utah, United States. ⟨hal-01739585⟩



Record views


Files downloads