E
Edgar A. León
Researcher at Lawrence Livermore National Laboratory
Publications - 28
Citations - 276
Edgar A. León is an academic researcher from Lawrence Livermore National Laboratory. The author has contributed to research in topics: Supercomputer & Cache. The author has an hindex of 10, co-authored 28 publications receiving 254 citations. Previous affiliations of Edgar A. León include University of New Mexico & IBM.
Papers
More filters
Proceedings ArticleDOI
Instruction-level simulation of a cluster at scale
TL;DR: A scalable simulator that couples a cycle-accurate node simulator with a supercomputer network model and shows its suitability for architecture research by evaluating the impact of cache injection on parallel application performance.
Proceedings ArticleDOI
HpMC: An Energy-aware Management System of Multi-level Memory Architectures
Chun-Yi Su,David G. Roberts,Edgar A. León,Kirk W. Cameron,Bronis R. de Supinski,Gabriel H. Loh,Dimitrios S. Nikolopoulos +6 more
TL;DR: This work proposes HpMC, a new memory controller design that combines the best aspects of existing management policies to improve performance and energy, and creates HMsim, an infrastructure that enables n-level, heterogeneous memory studies by leveraging existing memory simulators.
Proceedings ArticleDOI
Predicting the performance impact of different fat-tree configurations
Nikhil Jain,Abhinav Bhatele,Louis H. Howell,David Böhme,Ian Karlin,Edgar A. León,Misbah Mubarak,Noah Wolfe,Todd Gamblin,Matthew L. Leininger +9 more
TL;DR: This paper showcases the use of simulations to compare the impact of design options on representative production HPC applications, libraries, and multi-job workloads and presents advances in the TraceR-CODES simulation framework that enable this analysis and evaluates its prediction accuracy against experiments on a production fat-tree network.
Proceedings ArticleDOI
Characterizing parallel scientific applications on commodity clusters: an empirical study of a tapered fat-tree
Edgar A. León,Ian Karlin,Abhinav Bhatele,Steven H. Langer,Chris Chambreau,Louis H. Howell,Trent D'Hooge,Matthew L. Leininger +7 more
TL;DR: A systematic study that characterizes applications with an emphasis on communication requirements, identifying a representative set of applications from a U.S. Department of Energy laboratory, and characterizing their communication requirements provided key insights into the procurement of next generation commodity systems.
Proceedings ArticleDOI
Reducing the Impact of the MemoryWall for I/O Using Cache Injection
TL;DR: It is shown that cache injection provides significant advantages over data prefetching by reducing the pressure on the memory controller by up to 96% and injection policies to determine when and where to inject data are proposed.