Filters








71,778 Hits in 4.9 sec

Performance Analysis of Symbolic Analysis Techniques for Parallelizing Compilers [chapter]

Hansang Bae, Rudolf Eigenmann
2005 Lecture Notes in Computer Science  
In pursuit of this goal, we have measured the degree to which symbolic analysis techniques affect the behavior of current parallelizing compilers.  ...  We have chosen the Polaris parallelizing compiler and studied the techniques such as range analysis -which is the core symbolic analysis in the compiler -expression propagation, and symbolic expression  ...  Fahringer proposed symbolic analysis techniques to be used as part of a parallelizing compiler and a performance estimator for optimization of parallel programs [7] .  ... 
doi:10.1007/11596110_19 fatcat:odjangp2yfe5rnyrnmd5uo6tky

An Overview of Symbolic Analysis Techniques Needed for the Effective Parallelization of the Perfect Benchmarks

William Blume, Rudolf Eigenmann
1994 1994 International Conference on Parallel Processing (ICPP'94)  
We have identi ed symbolic analysis techniques that will improve the e ectiveness o f p arallelizing Fortran compilers, with emphasis upon data dependence analysis.  ...  We have done this by comparing the automatically and manually parallelized versions of the Perfect Benchmarks R .  ...  Except for FLO52, e v ery code required some sort of symbolic analysis technique to improve its performance. However, the distribution of these techniques was quite uneven.  ... 
doi:10.1109/icpp.1994.59 dblp:conf/icpp/BlumeE94 fatcat:dbo4n2zydzhjne2isjfabhsv2u

The Design of the PROMIS Compiler [chapter]

Hideki Saito, Nicholas Stavrakos, Steven Carroll, Constantine Polychronopoulos, Alex Nicolau
1999 Lecture Notes in Computer Science  
This information is used by other analysis and transformation passes to achieve highly optimized code. Symbolic analysis also helps statically quantify the effectiveness of transformations.  ...  This paper describes the organization and the major features of the PROMIS compiler.  ...  Ackknowledgements The authors are grateful to Peter Grun, Ashok Halambi, and Nick Savoiu of University of California at Irvine for their work on the trailblazing part of the backend and pointer analysis  ... 
doi:10.1007/978-3-540-49051-7_15 fatcat:pwro2nysuvdr3mxz4ic6lob7ma

Symbolic expression analysis for compiled communication

Shuyi Shao, Yu Zhang, Alex K. Jones, Rami Melhem
2008 Proceedings, International Parallel and Distributed Processing Symposium (IPDPS)  
In this paper we present symbolic expression analysis techniques in a MPI parallel compiler.  ...  Symbolic expression analysis allows the identification and representation the communication pattern and also assists in the determination of communication phases in MPI parallel applications at compile-time  ...  Several researchers studied symbolic analysis techniques in the context of parallel compilation for High Performance Fortran (HPF)-like programs [5, 13] .  ... 
doi:10.1109/ipdps.2008.4536344 dblp:conf/ipps/ShaoZJM08 fatcat:s7qkxg44svel7aoxx3sf55sgna

SYMBOLIC EXPRESSION ANALYSIS FOR COMPILED COMMUNICATION

ALEX K. JONES, SHUYI SHAO, YU ZHANG, RAMI MELHEM
2008 Parallel Processing Letters  
In this paper we present symbolic expression analysis techniques in a MPI parallel compiler.  ...  Symbolic expression analysis allows the identification and representation the communication pattern and also assists in the determination of communication phases in MPI parallel applications at compile-time  ...  Several researchers studied symbolic analysis techniques in the context of parallel compilation for High Performance Fortran (HPF)-like programs [5, 13] .  ... 
doi:10.1142/s0129626408003570 fatcat:fr4s4qf5zzguni7bdzjeo42iai

Interprocedural Symbolic Range Propagation for Optimizing Compilers [chapter]

Hansang Bae, Rudolf Eigenmann
2006 Lecture Notes in Computer Science  
It builds on our previous work of intraprocedural symbolic range analysis.  ...  Our algorithm contrasts with related work on interprocedural value range analysis in that it extends the ability to handle symbolic range expressions.  ...  We have developed and used such techniques in the past for our Polaris parallelizing compiler [2, 13, 4] .  ... 
doi:10.1007/978-3-540-69330-7_28 fatcat:yelfltgjpfcphbzyzjfjgihv34

Automatic Detection of Parallelism: A grand challenge for high performance computing

W. Blume, R. Eigenmann, J. Hoeflinger, D. Padua, P. Petersen, L. Rauchwerger, Perg Tu
1994 IEEE Parallel & Distributed Technology Systems & Applications  
Symbolic dependence analysis and array privatization, plus run-time versions of those techniques are shown to be important to the success of this e ort.  ...  The limited ability of compilers to nd the parallelism in programs is a signi cant barrier to the use of high performance computers.  ...  Techniques for dependence analysis, privatization, and symbolic analysis have all been mentioned as central to Fortran compilers for MPPs HKT92 .  ... 
doi:10.1109/m-pdt.1994.329796 fatcat:q4de46zaljaglertt6kjkofuwi

SCALA: A framework for performance evaluation of scalable computing [chapter]

Xian-He Sun, Mario Pantano, Thomas Fahringer, Zhaohua Zhan
1999 Lecture Notes in Computer Science  
These technologies, together with a new approach of scalability analysis, enable SCALA to provide the user with a higher and more intuitive level of performance analysis.  ...  Conventional performance environments are based on pro ling and event instrumentation. It becomes problematic as parallel systems scale to hundreds of nodes and beyond.  ...  SCALA combines symbolic and static analysis of the parallelized code with dynamic performance data.  ... 
doi:10.1007/bfb0097887 fatcat:rzu7nkaxvzd3tofatlevbkwidi

Automatic Loop Transformations and Parallelization for Java

P Artigas
2001 Parallel Processing Letters  
This transformation, combined with other techniques that we have developed, enables the compiler to perform high order loop transformations (for better data locality) and parallelization completely automatically  ...  This paper describes a prototype Java compiler which demonstrates that it is possible to achieve performance levels approaching those of current state-of-the-art C, C++ and Fortran compilers on numerical  ...  Acknowledgments The technique of creating new symbols to provide more precise alias information was jointly developed with the TPO group of the IBM Toronto Lab.  ... 
doi:10.1016/s0129-6264(00)00016-0 fatcat:rvxbu4qu2jfizg6e6u2qpwuoga

Automatic loop transformations and parallelization for Java

Pedro V. Artigas, Manish Gupta, Samuel P. Midkiff, José E. Moreira
2000 Proceedings of the 14th international conference on Supercomputing - ICS '00  
This transformation, combined with other techniques that we have developed, enables the compiler to perform high order loop transformations (for better data locality) and parallelization completely automatically  ...  This paper describes a prototype Java compiler which demonstrates that it is possible to achieve performance levels approaching those of current state-of-the-art C, C++ and Fortran compilers on numerical  ...  Acknowledgments The technique of creating new symbols to provide more precise alias information was jointly developed with the TPO group of the IBM Toronto Lab.  ... 
doi:10.1145/335231.335232 dblp:conf/ics/ArtigasGMM00 fatcat:pxsttcbmkrgnjgz7ijukipiks4

Challenges in the automatic parallelization of large-scale computational applications

Brian Armstrong, Rudolf Eigenmann, Howard J. Siegel
2001 Commercial Applications for High-Performance Computing  
We h a ve found ve c hallenges faced by an automatic parallelizing compiler when dealing with full applications: modularity, legacy optimizations, symbolic analysis, array reshaping, and issues arising  ...  In this paper, we reveal some of the hurdles that must be crossed in order to enable these compilers to apply parallelization techniques to large-scale codes.  ...  Our codes emphasize the importance of such symbolic analysis techniques. The code in Figure 5 shows another example.  ... 
doi:10.1117/12.434876 fatcat:k6sw446ysbh25jd63mubdlxcr4

Commutativity analysis: a new analysis technique for parallelizing compilers

Martin C. Rinard, Pedro C. Diniz
1997 ACM Transactions on Programming Languages and Systems  
If all of the operations required to perform a given computation commute, the compiler can automatically generate parallel code.  ...  This article presents a new analysis technique, commutativity analysis, for automatically parallelizing computations that manipulate dynamic, pointer-based data structures.  ...  ACKNOWLEDGMENTS We wish to thank the anonymous referees for their many useful comments and suggestions.  ... 
doi:10.1145/267959.269969 fatcat:b35qnogek5gqbafkemtvtsqlam

Scala: A Performance System for Scalable Computing

Xian-He Sun, Thomas Fahringer, Mario Pantano
2002 The international journal of high performance computing applications  
These technologies, together with a new approach of scalability analysis, enable SCALA to provide the user with a more intuitive level of performance analysis for scalable computing.  ...  SCALA assumes the availability of modern compiler technology, adopts statistical and symbolic methodologies, and has the support of browser interface.  ...  His main research interests include performance measurement, modeling and analysis of parallel programs, scalability analysis, tools and run-time systems for parallel program instrumentation and measurements  ... 
doi:10.1177/109434200201600401 fatcat:yvl5x2ke5vakthwqbny2p3appa

Issues in Implementation of Parallel Parsing on Multi-Core Machines

Amit Barve, Brijendra Kumar Joshi
2014 International Journal of Computer Science Engineering and Information Technology  
Parallel compilation is the area which still needs significant improvement by the use of this architecture. Recent research has shown some improvement in lexical analysis phase.  ...  The advent of multi-core architecture has highly influenced the area of high performance computing.  ...  Their approach is to divide the source code into number of blocks and perform lexical analysis on individual blocks. Their approach was good for parallel lexical analysis.  ... 
doi:10.5121/ijcseit.2014.4505 fatcat:t42btn7mt5ak7dmjgga3l7m52q

Symbolic performance modeling of parallel systems

A.J.C. van Gemund
2003 IEEE Transactions on Parallel and Distributed Systems  
Apart from simulation, PAMELA features a symbolic analysis technique that enables PAMELA models to be compiled into symbolic performance models that trade prediction accuracy for the lowest possible solution  ...  For programs expressed in a high-level, structured programming model, such as data-parallel programs, symbolic performance modeling can be entirely automated.  ...  Apart from simulation, PAMELA features a performance analysis technique that enables PAMELA models to be compiled into symbolic performance models that trade prediction accuracy for the lowest possible  ... 
doi:10.1109/tpds.2003.1178879 fatcat:d4cx6cbtgrhzdokckilikta7jy
« Previous Showing results 1 — 15 out of 71,778 results