TY - GEN
T1 - Parallelism orchestration using DoPE
T2 - 32nd ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI'11
AU - Raman, Arun
AU - Kim, Hanjun
AU - Oh, Taewook
AU - Lee, Jae W.
AU - August, David I.
PY - 2011
Y1 - 2011
N2 - In writing parallel programs, programmers expose parallelism and optimize it to meet a particular performance goal on a single platform under an assumed set of workload characteristics. In the field, changing workload characteristics, new parallel platforms, and deployments with different performance goals make the programmer's development-time choices suboptimal. To address this problem, this paper presents the Degree of Parallelism Executive (DoPE), an API and run-time system that separates the concern of exposing parallelism from that of optimizing it. Using the DoPE API, the application developer expresses parallelism options. During program execution, DoPE's run-time system uses this information to dynamically optimize the parallelism options in response to the facts on the ground. We easily port several emerging parallel applications to DoPE's API and demonstrate the DoPE run-time system's effectiveness in dynamically optimizing the parallelism for a variety of performance goals.
AB - In writing parallel programs, programmers expose parallelism and optimize it to meet a particular performance goal on a single platform under an assumed set of workload characteristics. In the field, changing workload characteristics, new parallel platforms, and deployments with different performance goals make the programmer's development-time choices suboptimal. To address this problem, this paper presents the Degree of Parallelism Executive (DoPE), an API and run-time system that separates the concern of exposing parallelism from that of optimizing it. Using the DoPE API, the application developer expresses parallelism options. During program execution, DoPE's run-time system uses this information to dynamically optimize the parallelism options in response to the facts on the ground. We easily port several emerging parallel applications to DoPE's API and demonstrate the DoPE run-time system's effectiveness in dynamically optimizing the parallelism for a variety of performance goals.
UR - http://www.scopus.com/inward/record.url?scp=79959909380&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79959909380&partnerID=8YFLogxK
U2 - 10.1145/1993498.1993502
DO - 10.1145/1993498.1993502
M3 - Conference contribution
AN - SCOPUS:79959909380
SN - 9781450306638
T3 - Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI)
SP - 26
EP - 37
BT - PLDI'11 - Proceedings of the 2011 ACM Conference on Programming Language Design and Implementation
Y2 - 4 June 2011 through 8 June 2011
ER -