Automatic Partitioning of Stencil Computations on Heterogeneous Systems

被引：4

作者：

Pereira, Alyson D. ^{[1
]}

Rocha, Rodrigo C. O. ^{[4
]}

Ramos, Luiz ^{[3
]}

Castro, Marcio ^{[1
]}

Goes, Luis F. W. ^{[2
]}

机构：

[1] Univ Fed Santa Catarina, Florianopolis, SC, Brazil

[2] Pontificia Univ Catolica Minas Gerais, Belo Horizonte, MG, Brazil

[3] Univ Estadual Campinas, Campinas, SP, Brazil

[4] Univ Edinburgh, Edinburgh, Midlothian, Scotland

来源：

2017 INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING WORKSHOPS (SBAC-PADW) | 2017年

关键词：

Stencil; Work Partitioning; Decision Tree Learning;

D O I：

10.1109/SBAC-PADW.2017.16

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

The stencil pattern is important in many scientific and engineering domains, spurring great interest from researchers and industry. In recent years, various optimizations have been proposed for parallel stencil applications running on GPUs. However, most of the runtime systems that execute those applications often fail to fully utilize the parallelism of modern heterogeneous systems. In this paper, we propose a mechanism based on machine learning that automatically partitions stencil computations across CPU and GPU. We implemented it into the PSkel framework and found that the mechanism can boost the performance of stencil applications on average by 17.9x compared to their sequential CPU-only counterparts, by 1.34x compared to a GPU-only version, and by 1.48x compared to a parallel CPU-only version.

引用

页码：43 / 48

页数：6

共 50 条

[1] Data Partitioning Strategies for Stencil Computations on NUMA Systems
Feinbube, Frank
Plauth, Max
Knaust, Marius
Polze, Andreas
[J]. EURO-PAR 2017: PARALLEL PROCESSING WORKSHOPS, 2018, 10659 : 597 - 609
[2] Effective Automatic Parallelization of Stencil Computations
Krishnamoorthy, Sriram
Baskaran, Muthu
Bondhugula, Uday
Ramanujam, J.
Rountev, Atanas
Sadayappan, P.
[J]. PLDI'07: PROCEEDINGS OF THE 2007 ACM SIGPLAN CONFERENCE ON PROGRAMMING LANGUAGE DESIGN AND IMPLEMENTATION, 2007, : 235 - 244
[3] Effective automatic parallelization of stencil computations
Krishnamoorthy, Sriram
Baskaran, Muthu
Bondhugula, Uday
Ramanujam, J.
Rountev, Atanas
Sadayappan, P.
[J]. ACM SIGPLAN NOTICES, 2007, 42 (06) : 235 - 244
[4] Automatic Adaptive Approximation for Stencil Computations
Schmitt, Maxime
Helluy, Philippe
Bastoul, Cedric
[J]. PROCEEDINGS OF THE 28TH INTERNATIONAL CONFERENCE ON COMPILER CONSTRUCTION (CC '19), 2019, : 170 - 181
[5] Automatic Performance Tuning of Stencil Computations on GPUs
Garvey, Joseph D.
Abdelrahman, Tarek S.
[J]. 2015 44TH INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING (ICPP), 2015, : 300 - 309
[6] TOAST: Automatic tiling for iterative stencil computations on GPUs
Rocha, Rodrigo C. O.
Pereira, Alyson D.
Ramos, Luiz
Goes, Luis F. W.
[J]. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE, 2017, 29 (08):
[7] A Strategy for Automatic Performance Tuning of Stencil Computations on GPUs
Garvey, Joseph D.
Abdelrahman, Tarek S.
[J]. SCIENTIFIC PROGRAMMING, 2018, 2018
[8] Unleashing the performance of ccNUMA multiprocessor architectures in heterogeneous stencil computations
Szustak, Lukasz
Halbiniak, Kamil
Wyrzykowski, Roman
Jakl, Ondrej
[J]. JOURNAL OF SUPERCOMPUTING, 2019, 75 (12): : 7765 - 7777
[9] Unleashing the performance of ccNUMA multiprocessor architectures in heterogeneous stencil computations
Lukasz Szustak
Kamil Halbiniak
Roman Wyrzykowski
Ondřej Jakl
[J]. The Journal of Supercomputing, 2019, 75 : 7765 - 7777
[10] A FRAMEWORK FOR PARTITIONING PARALLEL COMPUTATIONS IN HETEROGENEOUS ENVIRONMENTS
WEISSMAN, JB
GRIMSHAW, AS
[J]. CONCURRENCY-PRACTICE AND EXPERIENCE, 1995, 7 (05): : 455 - 478

← 1 2 3 4 5 →