Automatic Scoping of Variables in Parallel Regions of an OpenMP Program

Lin, Yaping; Terboven, Christian; Mey, Dieter an; Copty, Nawal

doi:10.1007/978-3-540-31832-3_8

Cited by 19 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have chosen to present the large number of private variables required, given the lack of a default(private) clause; we believe that such a clause would be beneficial for such codes. In our case, there are 56 private variables to be declared manually and given the presence of pointer variables and aliasing, automatic scoping of variables in parallel regions (as proposed in [6]) would be highly desirable although we are aware that it may be difficult for the compiler to perform.…”

Section: Fig 4 Compact Sequential Code Of Mos3load In Spice3mentioning

confidence: 99%

OpenMP Implementation of SPICE3 Circuit Simulator

Weng

Perng

Chapman

2007

Int J Parallel Prog

View full text Add to dashboard Cite

In this paper, we describe our experience of creating an OpenMP implementation of the SPICE3 circuit simulator program. Given the irregular patterns of access to dynamic data structures in the SPICE code, a parallelization using current standard OpenMP directives is impossible without major rewriting of the original program. The aim of this work is to present a case study showing the development of a shared memory parallel code with minimum effort. We present two implementations, one with minimal code modification and one without modification to the original SPICE3 program using Intel's taskq construct. We also discuss the results of the case study in terms of what future compiler tools may be needed to help OpenMP application developers with similar porting goals. Our experiments using SPICE3, based on SRAM model simulation, were compiled by the SUN compiler running on a SunFire V880 UltraSPARC-III 750 MHz and by the Intel icc compiler running on both an IBM Itanium with four CPUs and Intel Xeon of two processors machines. The results are promising.

show abstract

Section: Fig 4 Compact Sequential Code Of Mos3load In Spice3mentioning

confidence: 99%

OpenMP Implementation of SPICE3 Circuit Simulator

Weng

Perng

Chapman

2007

Int J Parallel Prog

View full text Add to dashboard Cite

show abstract

“…Recent work on autoscoping of data in OpenMP programs [13] proposes alternative approaches to accomplish this. Our work has also benefited from recent efforts to further elucidate the OpenMP memory consistency specifications [14] and to formalize the OpenMP memory model [15].…”

Section: Related Workmentioning

confidence: 99%

Incorporation of OpenMP Memory Consistency into Conventional Dataflow Analysis

Basumallik

Eigenmann

2008

OpenMP in a New Era of Parallelism

View full text Add to dashboard Cite

Abstract. Current OpenMP compilers are often limited in their analysis and optimization of OpenMP programs by the challenge of incorporating OpenMP memory consistency semantics into conventional data flow algorithms. An important reason for this is that data flow analysis within current compilers traverse the program's control-flow graph (CFG) and the CFG does not accurately model the memory consistency specifications of OpenMP. In this paper, we present techniques to incorporate memory consistency semantics into conventional dataflow analysis by transforming the program's CFG into an OpenMP ProducerConsumer Flow Graph (PCFG), where a path exists from writes to reads of shared data if and only if a dependence is implied by the OpenMP memory consistency model. We present algorithms for these transformations, prove the correctness of these algorithms and discuss a case where this transformation is used.

show abstract

“…A static nonconcurrency analysis similar to the above has been implemented in Sun Studio TM 9 compilers. It serves as one of the analysis engines for the OpenMP autoscoping feature, which automatically detects the data sharing attributes of variables in an OpenMP application [6]. It also serves as an engine for the static OpenMP error detection feature provided in Sun compilers.…”

Section: Application: Static Race Detectionmentioning

confidence: 99%