TY - GEN
T1 - DAGuE
T2 - 25th IEEE International Parallel and Distributed Processing Symposium, Workshops and Phd Forum, IPDPSW 2011
AU - Bosilca, George
AU - Bouteiller, Aurelien
AU - Danalis, Anthony
AU - Herault, Thomas
AU - Lemarinier, Pierre
AU - Dongarra, Jack
PY - 2011
Y1 - 2011
N2 - The frenetic development of the current architectures places a strain on the current state-of-the-art programming environments. Harnessing the full potential of such architectures has been a tremendous task for the whole scientific computing community. We present DAGuE a generic framework for architecture aware scheduling and management of micro-tasks on distributed many-core heterogeneous architectures. Applications we consider can be represented as a Direct Acyclic Graph of tasks with labeled edges designating data dependencies. DAGs are represented in a compact, problem-size independent format that can be queried on-demand to discover data dependencies, in a totally distributed fashion. DAGuE assigns computation threads to the cores, overlaps communications and computations and uses a dynamic, fully-distributed scheduler based on cache awareness, data-locality and task priority. We demonstrate the efficiency of our approach, using several micro-benchmarks to analyze the performance of different components of the framework, and a Linear Algebra factorization as a use case.
AB - The frenetic development of the current architectures places a strain on the current state-of-the-art programming environments. Harnessing the full potential of such architectures has been a tremendous task for the whole scientific computing community. We present DAGuE a generic framework for architecture aware scheduling and management of micro-tasks on distributed many-core heterogeneous architectures. Applications we consider can be represented as a Direct Acyclic Graph of tasks with labeled edges designating data dependencies. DAGs are represented in a compact, problem-size independent format that can be queried on-demand to discover data dependencies, in a totally distributed fashion. DAGuE assigns computation threads to the cores, overlaps communications and computations and uses a dynamic, fully-distributed scheduler based on cache awareness, data-locality and task priority. We demonstrate the efficiency of our approach, using several micro-benchmarks to analyze the performance of different components of the framework, and a Linear Algebra factorization as a use case.
UR - http://www.scopus.com/inward/record.url?scp=83455173186&partnerID=8YFLogxK
U2 - 10.1109/IPDPS.2011.281
DO - 10.1109/IPDPS.2011.281
M3 - Conference contribution
AN - SCOPUS:83455173186
SN - 9780769543857
T3 - IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum
SP - 1151
EP - 1158
BT - 2011 IEEE International Symposium on Parallel and Distributed Processing, Workshops and Phd Forum, IPDPSW 2011
Y2 - 16 May 2011 through 20 May 2011
ER -