Adaptive, efficient, parallel execution of parallel programs
Tipus de documentText en actes de congrés
Data publicació2016-09-10
EditorBarcelona Supercomputing Center
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
Abstract
Future parallel processors will be heterogeneous, be increasingly less reliable, and operate in dynamically changing operating conditions. This will result in a constantly varying pool of hardware resources which can greatly complicate the task of efficiently exposing a program's parallelism onto these resources. Coupled with this uncertainty is the diverse set of efficiency metrics that users may desire.
This talk will describe Varuna, a system that dynamically, continuously, rapidly and transparently adapts a program's parallelism to best match the instantaneous capabilities of the hardware resources while satisfying different efficiency metrics. Varuna is applicable to both multithreaded and task-based programs and can be seamlessly inserted between the program and the operating system without needing to change the source code of either. The talk will also present results demonstrating Varuna's effectiveness in diverse execution environments using unaltered C/C++ parallel programs from various benchmark suites.
CitacióSohi, Guri. Adaptive, efficient, parallel execution of parallel programs. A: 2nd Severo Ochoa Research Seminar Lectures at BSC, Barcelona, 2015-2016. "Book of abstracts". Barcelona: Barcelona Supercomputing Center, 2016, p. 26-28.
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
23-24 2015-16 S ... n of Parallel Programs.pdf | 325,4Kb | Visualitza/Obre |