UNDERSTANDING PORTABILITY OF A HIGH-LEVEL PROGRAMMING MODEL ON CONTEMPORARY HETEROGENEOUS ARCHITECTURES

被引：11

作者：

Sabne, Amit ^{[1
]}

Sakdhnagool, Putt ^{[1
]}

Lee, Seyong ^{[2
]}

Vetter, Jeffrey S. ^{[3
]}

机构：

[1] Purdue Univ, Sch Elect & Comp Engn, W Lafayette, IN 47907 USA

[2] Oak Ridge Natl Lab, Comp Sci & Math Div, Oak Ridge, TN USA

[3] Oak Ridge Natl Lab, Future Technol Grp, Oak Ridge, TN USA

来源：

IEEE MICRO | 2015年 / 35卷 / 04期

关键词：

Compilers; Heterogeneous (hybrid) systems; HeteroIR; Measurements; Remove Hybrid; Runtime environments;

D O I：

10.1109/MM.2015.73

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

HeteroIR is a high-level, architecture-independent intermediate representation for mapping high-level programming models to heterogeneous architectures. The authors present a compiler approach that translates OpenACC programs into HeteroIR and accelerator kernels to obtain OpenACC functional portability. They evaluate the performance portability obtained by OpenACC and study the effects of compiler optimizations and OpenACC program settings on various architectures to provide insights into the achieved performance portability.

引用

页码：48 / 58

页数：11

共 50 条

[41] Compiling high-level languages for vector architectures
Rickett, CD
Choi, SE
Chamberlain, BL
LANGUAGES AND COMPILERS FOR HIGH PERFORMANCE COMPUTING, 2005, 3602 : 224 - 237
[42] High-Level Synthesis for Designing Multimode Architectures
Andriamisaina, Caaliph
Coussy, Philippe
Casseau, Emmanuel
Chavet, Cyrille
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2010, 29 (11) : 1736 - 1749
[43] A High-Level Design Exploration of Heterogeneous Adders based on Mixed Integer Linear Programming
Sosa, J.
Montiel-Nelson, J. A.
Garcia-Montesdeoca, J. C.
Nooshabadi, Saeid
2011 IEEE 54TH INTERNATIONAL MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS (MWSCAS), 2011,
[44] Generation of heterogeneous distributed architectures for memory-intensive applications through high-level synthesis
Huang, Chao
Ravi, Srivaths
Raghunathan, Anand
Jha, Niraj K.
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2007, 15 (11) : 1191 - 1204
[45] Compiling a High-Level Directive-Based Programming Model for GPGPUs
Tian, Xiaonan
Xu, Rengan
Yan, Yonghong
Yun, Zhifeng
Chandrasekaran, Sunita
Chapman, Barbara
LANGUAGES AND COMPILERS FOR PARALLEL COMPUTING, LCPC 2013, 2014, 8664 : 105 - 120
[46] Stateful Dataflow Multigraphs: A Data-Centric Model for Performance Portability on Heterogeneous Architectures
Ben-Nun, Tal
Licht, Johannes de Fine
Ziogas, Alexandros N.
Schneider, Timo
Hoefler, Torsten
PROCEEDINGS OF SC19: THE INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS, 2019,
[47] Efficient High-Level Abstractions for Web Programming
Richard-Foy, Julien
Barais, Olivier
Jezequel, Jean-Marc
ACM SIGPLAN NOTICES, 2014, 49 (03) : 53 - 60
[48] High-Level Multicore Programming with XJava']Java
Otto, Frank
Pankratius, Victor
Tichy, Walter F.
2009 31ST INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, COMPANION VOLUME, 2009, : 319 - 322
[49] HIGH-LEVEL LANGUAGES EASE MICROCOMPUTER PROGRAMMING
SAUNDERS, JL
LEWIS, LE
ELECTRONICS, 1978, 51 (16): : 115 - 118
[50] ADDING GRAPHICS TO A HIGH-LEVEL PROGRAMMING LANGUAGE
JEFFERY, CL
GRISWOLD, RE
TOWNSEND, GM
SOFTWARE-PRACTICE & EXPERIENCE, 1995, 25 (06): : 637 - 655

← 1 2 3 4 5 →