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

Blume, William; Eigenmann, Rudolf

doi:10.1109/icpp.1994.59

Cited by 41 publications

(25 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, advanced analysis and transformation techniques exist today, which can optimize many programs to a degree close to that of manual parallelization. The ability of a compiler to manipulate and understand symbolic expressions is an important quality of this technology [1]. For instance, the accuracy of data dependence tests, array privatization, dead code elimination, and the detection of zero-trip loops increases if the techniques have knowledge of the value ranges assumed by certain variables.…”

Section: Introductionmentioning

confidence: 99%

“…Several research groups have developed symbolic analysis capabilities to make the most of program analysis techniques implemented in their compilers [1,[3][4][5][6][7][8]. The Polaris parallelizing compiler [2] has incorporated advanced symbolic analysis techniques in order to effectively detect privatizable arrays, to determine whether a certain loop is a zero-trip loop for induction variable substitution, and to solve data dependence problems that involve symbolic loop bounds and array subscripts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance Analysis of Symbolic Analysis Techniques for Parallelizing Compilers

Bae

Eigenmann

2005

Languages and Compilers for Parallel Computing

Self Cite

View full text Add to dashboard Cite

Abstract. Understanding symbolic expressions is an important capability of advanced program analysis techniques. Many current compiler techniques assume that coefficients of program expressions, such as array subscripts and loop bounds, are integer constants. Advanced symbolic handling capabilities could make these techniques amenable to real application programs. Symbolic analysis is also likely to play an important role in supporting higher-level programming languages and optimizations. For example, entire algorithms may be recognized and replaced by better variants. 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 manipulation. To measure the effect of a technique, we disabled it individually, and compared the performance of the resulting program with the original, fully-optimized program. We found that symbolic expression manipulation is important for most programs. Expression propagation and range analysis is important in few programs only, however they can affect these programs significantly. We also found that in all but one programs, a simpler form of range analysis -control range analysis -is sufficient.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Symbolic Analysis Techniques for Parallelizing Compilers

Bae

Eigenmann

2005

Languages and Compilers for Parallel Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…2 A topological ordering of a directed acyclic graph is an ordering such t h a t i f t h e r e i s a p a t h f r o m v ertex u to vertex v then u occurs before v in this ordering. 3 By de nition of SCCs, one can always topologically sort the SCCs of a graph in respect to each other. 4 Back-edges are edges in a graph, which if deleted would result in an acyclic graph.…”

Section: Determining a Replacement Ordermentioning

confidence: 99%

“…To e ectively parallelize real programs, parallelizing compilers need powerful symbolic analysis techniques 11,3 ]. One of most useful of these techniques is the ability to compare arbitrary symbolic expressions, using constraint information derived from the program 3].…”

Section: Introductionmentioning

confidence: 99%

Symbolic range propagation

Blume¹,

Eigenmann²

Proceedings of 9th International Parallel Processing Symposium

View full text Add to dashboard Cite

Many analyses and transformations in a parallelizing compiler can bene t from the ability t o compare arbitrary symbolic expressions. In this paper, we describe how one can compare expressions by using symbolic ranges of variables. A range is a lower and upper bound on a variable. We will also describe how these ranges can be e ciently computed from the program text. Symbolic range propagation has been implemented in Polaris, a parallelizing compiler being developed at the University of Illinois, and is used for symbolic dependence testing, detection of zero-trip loops, determining array sections possibly referenced by an access, and loop iteration-count estimation.

show abstract

“…Similar patterns have been discovered in the Perfect Benchmarks. 2 An example from subroutine TFTRI of SPECchem shows the propagated expression used to index an array i n loop DO 200: x14+i1+lhc+jj0**2+-55*j1+-11*jj0+25*j1**2 2+5*j1*jj0 = hij0 TFTRI deals with a triangular matrix where the subsequent jj , 1=2 elements of the work array are accessed in the next iteration. Variables j, jj0, and i1 are loop indices of a triply nested loop.…”

Section: Symbolic Analysismentioning

confidence: 99%

<title>Challenges in the automatic parallelization of large-scale computational applications</title>

Armstrong

Eigenmann

2001

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Application test suites used in the development of parallelizing compilers typically include single-le programs and algorithm kernels. The challenges posed by full-scale commercial applications are rarely addressed. It is often assumed that automatic parallelization is not feasible in the presence of large, realistic programs. 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. We use a benchmark suite that has been speci cally designed to exhibit the computing needs found in industry. The benchmarks are provided by the High Performance Group of the Standard Performance Evaluation Corporation SPEC. They consist of a seismic processing application and a quantum level molecular simulation. Both applications exist in a serial and a parallel variant. The parallel variants are hand-parallelized with shared-memory directives either at the largest level of granularity o r i n a h ybrid manner where MPI is used at the largest level of granularity and OpenMP directives are used at a lower level. In our studies we compare the parallel variants with the automatically parallelized, serial codes. We use the Polaris parallelizing compiler, which takes Fortran codes and inserts OpenMP directives around loops determined to be dependence-free. Polaris also reports the reasons why it assumes that a loop is parallel. 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 from input output operations. The results of this work will be used to equip parallelizing compilers with the necessary capabilities for handling commercially relevant science and engineering applications.

show abstract

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

Cited by 41 publications

References 15 publications

Performance Analysis of Symbolic Analysis Techniques for Parallelizing Compilers

Performance Analysis of Symbolic Analysis Techniques for Parallelizing Compilers

Symbolic range propagation

<title>Challenges in the automatic parallelization of large-scale computational applications</title>

Contact Info

Product

Resources

About