Maximizing multiprocessor performance with the SUIF compiler

Hall, Mary; Anderson, Jennifer M.; Amarasinghe, Saman; Murphy, Brian R.; Liao, Shih-Wei; Bugnion, Edouard; Lam, Monica S.

doi:10.1109/2.546613

Cited by 425 publications

(201 citation statements)

References 7 publications

Supporting

Mentioning

196

Contrasting

Unclassified

Order By: Relevance

“…It combines a structured multistage evaluation layer built on top of C++ expression templates, with run-time generation and compilation, and with a transformation toolkit based on SUIF (1.3) [11] and/or ROSE [22]. It is not a language per se, but a set of C++ templates and classes associated with customizable source-to-source transformation capabilities.…”

Section: Related Workmentioning

confidence: 99%

A Language for the Compact Representation of Multiple Program Versions

Donadio

Brodman

Roeder

et al. 2006

Languages and Compilers for Parallel Computing

View full text Add to dashboard Cite

Abstract. As processor complexity increases compilers tend to deliver suboptimal performance. Library generators such as ATLAS, FFTW and SPIRAL overcome this issue by empirically searching in the space of possible program versions for the one that performs the best. Empirical search can also be applied by programmers, but because they lack a tool to automate the process, programmers need to manually re-write the application in terms of several parameters whose best value will be determined by the empirical search in the target machine. In this paper, we present the design of an annotation language, meant to be used either as an intermediate representation within library generators or directly by the programmer. This language that we call X represents parameterized programs in a compact and natural way. It provides an powerful optimization framework for high performance computing.

show abstract

Section: Related Workmentioning

confidence: 99%

A Language for the Compact Representation of Multiple Program Versions

Donadio

Brodman

Roeder

et al. 2006

Languages and Compilers for Parallel Computing

View full text Add to dashboard Cite

show abstract

“…We experimented with some applications from MediaBench [5]. We generated the dataflow graphs for these applications using SUIF compiler [19] and Machine-suif [17].…”

Section: Lemma 4 For a Given Instance Of The Edge Budgeting Problem mentioning

confidence: 99%

A Unified Theory of Timing Budget Management

Ghiasi¹,

Bozorgzadeh

Huang

et al. 2006

IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst.

View full text Add to dashboard Cite

show abstract

“…The Paraphrase-2 automatic parallelizing compiler [12] compiler uses the combination of a data dependence graph, control flow graph, and call graph to represent C and Fortran programs. The SUIF [9] research framework is targeted to imperative languages such as Fortran and C, providing an intermediate format and a set of common optimization passes. OSUIF [4] is an extension of SUIF2.0, introducing support for objectoriented optimizations.…”

Section: Related Workmentioning

confidence: 99%

“…Traditionally, this research focused on scientific applications that consist of loops and array references, typical of Fortran programs [6,9]. Regrettably, this focus has limited the widespread use of automatic parallelization in industry, where the majority of programs are written in C, C++, or more recently in Java.…”

Section: Introductionmentioning

confidence: 99%

A Compiler Infrastructure for High-Performance Java⋆

Brewster¹,

Abdelrahman

2001

High-Performance Computing and Networking

View full text Add to dashboard Cite

Abstract. This paper describes the zJava compiler infrastructure, a high-level framework for the analysis and transformation of Java programs. This framework provides a robust system, guaranteeing under transformations both the consistency of its internal structure and the syntactic correctness of the represented code. We address several challenges unique to Java, which have not been addressed by earlier frameworks. These include automatic maintenance of complex symbol scope information under transformations, insertion of implicit code to accurately model the source program, incorporation of compiled code into the representation, and representation of the complex control flow of exception handling constructs. We include support for the sharing of information between compiler passes, and a framework for interprocedural analysis. We believe that the features we introduce in the zJava compiler infrastructure will result in a means of rapidly prototyping new Java compiler analyses. We give a number of examples illustrating the use and utility of the infrastructure.

show abstract

Maximizing multiprocessor performance with the SUIF compiler

Cited by 425 publications

References 7 publications

A Language for the Compact Representation of Multiple Program Versions

A Language for the Compact Representation of Multiple Program Versions

A Unified Theory of Timing Budget Management

A Compiler Infrastructure for High-Performance Java⋆

Contact Info

Product

Resources

About