SUIF-Adapt: An Integrated Compiler/Run-Time System for Global and Dynamic Data Distributions
نویسندگان
چکیده
Distributing data is one of the key problems in implementing efficient distributed-memory parallel programs. The problem is especially difficult in programs where (1) data redistribution between computational phases is considered or (2) the participating processors (nodes) executing a parallel application are not dedicated. In either case, the commonly used BLOCK and CYCLIC distributions no longer suffice. We have investigated this problem in the context of a software distributed shared memory (SDSM) system. We have developed integrated compileand run-time analysis for SDSM systems to support both singleand multi-phase applications on potentially non-dedicated workstation clusters. Our system, SUIF-Adapt, selects an effective initial distribution per phase, finds an effective global data distribution, and adapts to changes in the underlying computing environment, including dynamic removal and addition of nodes. Each of these features contributes to good performance; in particular, SUIF-Adapt performs significantly better than both hand-coded static distributions and many dynamic distributions.
منابع مشابه
An Integrated Compiler/Run-Time System for Global Data Distribution in Distributed Shared Memory Systems∗
A software distributed shared memory (DSM) provides the illusion of shared memory on a distributed-memory machine; communication occurs implicitly via page faults. For efficient execution of DSM programs, the threads and their implicitly associated data must be distributed to the nodes to balance the computational workload and minimize communication due to page faults. The focus of this paper i...
متن کاملA SUIF Java Compiler
To compete with optimized C, object-oriented languages need classical optimizations as well as speci c object-oriented optimizations. Therefore, a compiler infrastructure that enables object-oriented compiler research is of great interest for the research community. The SUIF compiler system with the OSUIF extension o ers such a research environment. SUIF de nes an intermediate representation fo...
متن کاملPath Splitting: A Technique for Improving Data-Flow Analysis
The eeectiveness of traditional global optimizations is limited by the quality of data-ow information available to the compiler. The rich control structure of many programs hinders global optimizations by polluting data-ow information and forcing the compiler to make worst-case assumptions during data-ow analysis. Path splitting is a new technique for improving the amount of data-ow information...
متن کاملLanguage and Run-Time Support for Network Parallel Computing
Network parallel computing is the use of diverse computing resources interconnected by general purpose networks to run parallel applications. This paper describes NetFx, an extension of the Fx compiler system which uses the Fx model of task parallelism to distribute and manage computations across the sequential and parallel machines of a network. A central problem in network parallel computing ...
متن کاملAdaptive parallelism in compiler-parallelized code
As moderate-scale multiprocessors become widely used, we foresee an increased demand for eeective compiler parallelization and eecient management of parallelism. While parallelizing compilers are achieving success at identifying parallelism, they are less adept at predetermining the degree of parallelism in diierent program phases. Thus, a compiler-parallelized application may execute on more p...
متن کامل