Languages and Compilers for Parallel Computing: 7th International Workshop Ithaca, NY, USA, August 8–10, 1994 Proceedings [1 ed.]
354058868X, 9783540588689
This volume presents revised versions of the 32 papers accepted for the Seventh Annual Workshop on Languages and Compile
Table of contents : Fine-grain scheduling under resource constraints....Pages 1-15 Mutation scheduling: A unified approach to compiling for fine-grain parallelism....Pages 16-30 Compiler techniques for fine-grain execution on workstation clusters using PAPERS....Pages 31-45 Solving alignment using elementary linear algebra....Pages 46-60 Detecting and using affinity in an automatic data distribution tool....Pages 61-75 Array distribution in data-parallel programs....Pages 76-91 Communication-free parallelization via affine transformations....Pages 92-106 Finding legal reordering transformations using mappings....Pages 107-124 A new algorithm for global optimization for parallelism and locality....Pages 125-140 Polaris: Improving the effectiveness of parallelizing compilers....Pages 141-154 A formal approach to the compilation of data-parallel languages....Pages 155-169 The data partitioning graph: Extending data and control dependencies for data partitioning....Pages 170-185 Detecting value-based scalar dependence....Pages 186-200 Minimal data dependence abstractions for loop transformations....Pages 201-216 Differences in algorithmic parallelism in control flow and call multigraphs....Pages 217-233 Flow-insensitive interprocedural alias analysis in the presence of pointers....Pages 234-250 Incremental generation of index sets for array statement execution on distributed-memory machines....Pages 251-265 A unified data-flow framework for optimizing communication....Pages 266-282 Interprocedural communication optimizations for distributed memory compilation....Pages 283-299 Analysis of event synchronization in parallel programs....Pages 300-315 Computing communication sets for control parallel programs....Pages 316-330 Optimizing parallel SPMD programs....Pages 331-345 An overview of the Opus language and runtime system....Pages 346-360 SIMPLE performance results in ZPL....Pages 361-375 Cid : A parallel, “shared-memory” C for distributed-memory machines....Pages 376-390 EQ: Overview of a new language approach for prototyping scientific computation....Pages 391-405 Reshaping access patterns for generating sparse codes....Pages 406-420 Evaluating two loop transformations for reducing multiple-writer false sharing....Pages 421-437 Parallelizing tree algorithms: Overhead vs. parallelism....Pages 438-452 Autoscheduling in a distributed shared-memory environment....Pages 453-469 Optimizing array distributions in data-parallel programs....Pages 470-484 Automatic reduction tree generation for fine-grain parallel architectures when iteration count is unknown....Pages 485-496