Skip to Main content Skip to Navigation
New interface
Journal articles

Composing multiple StarPU applications over heterogeneous machines: A supervised approach

Andra Hugo 1, 2 Abdou Guermouche 2, 3 Pierre-André Wacrenier 1, 2 Raymond Namyst 1, 2 
1 RUNTIME - Efficient runtime systems for parallel architectures
Inria Bordeaux - Sud-Ouest, UB - Université de Bordeaux, CNRS - Centre National de la Recherche Scientifique : UMR5800
3 HiePACS - High-End Parallel Algorithms for Challenging Numerical Simulations
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest
Abstract : Enabling HPC applications to perform efficiently when invoking multiple parallel libraries simultaneously is a great chal-lenge. Even if a uniform runtime system is used underneath, scheduling tasks or threads coming from different libraries over the same set of hardware resources introduces many issues, such as resource oversubscription, undesirable cache flushes and memory bus contention. This paper presents an extension of StarPU, a runtime system specifically designed for heterogeneous architectures, that allows multiple parallel codes to run concurrently with minimal interference. Such parallel codes run within schedul-ing contexts that provide confined execution environments which can be used to partition computing resources. Scheduling contexts can be dynamically resized to optimize the allocation of computing resources among concurrently running libraries. We introduce a hypervisor that automatically expands or shrinks contexts using feedback from the run-time system (e.g. resource utilization). We demonstrate the relevance of our approach using benchmarks invoking multi-ple high performance linear algebra kernels simultaneously on top of heterogeneous multicore machines. We show that our mechanism can dramatically improve the overall application run time (-34%), most notably by reducing the average cache miss ratio (-50%).
Complete list of metadata

Cited literature [29 references]  Display  Hide  Download
Contributor : Andra-Ecaterina Hugo Connect in order to contact the contributor
Submitted on : Friday, January 9, 2015 - 2:00:50 PM
Last modification on : Saturday, June 25, 2022 - 7:46:24 PM
Long-term archiving on: : Friday, September 11, 2015 - 1:35:19 AM


Files produced by the author(s)




Andra Hugo, Abdou Guermouche, Pierre-André Wacrenier, Raymond Namyst. Composing multiple StarPU applications over heterogeneous machines: A supervised approach. International Journal of High Performance Computing Applications, 2014, 28, pp.285 - 300. ⟨10.1177/1094342014527575⟩. ⟨hal-01101045⟩



Record views


Files downloads