Book Volume 1808 2001

Compiler Optimizations for Scalable Parallel Systems

Languages, Compilation Techniques, and Run Time Systems

Editors:

ISBN: 978-3-540-41945-7 (Print) 978-3-540-45403-8 (Online)

Table of contents (21 chapters)

previous Page of 2
  1. Front Matter

    Pages I-XIX

  2. Languages

    1. No Access

      Chapter

      Pages 3-43

      High Performance Fortran 2.0

    2. No Access

      Chapter

      Pages 45-72

      The Sisal Project: Real World Functional Programming

    3. No Access

      Chapter

      Pages 73-107

      HPC++ and the HPC++Lib Toolkit

    4. No Access

      Chapter

      Pages 109-137

      A Concurrency Abstraction Model for Avoiding Inheritance Anomaly in Object-Oriented Programs

  3. Analysis

    1. No Access

      Chapter

      Pages 141-171

      Loop Parallelization Algorithms

    2. No Access

      Chapter

      Pages 173-219

      Array Dataflow Analysis

    3. No Access

      Chapter

      Pages 221-246

      Interprocedural Analysis Based on Guarded Array Regions

    4. No Access

      Chapter

      Pages 247-281

      Automatic Array Privatization

  4. Communication Optimizations

    1. No Access

      Chapter

      Pages 285-338

      Optimal Tiling for Minimizing Communication in Distributed Shared-Memory Multiprocessors

    2. No Access

      Chapter

      Pages 339-383

      Communication-Free Partitioning of Nested Loops

    3. No Access

      Chapter

      Pages 385-411

      Solving Alignment Using Elementary Linear Algebra

    4. No Access

      Chapter

      Pages 413-443

      A Compilation Method for Communication-Efficient Partitioning of DOALL Loops

    5. No Access

      Chapter

      Pages 445-484

      Compiler Optimization of Dynamic Data Distributions for Distributed-Memory Multicomputers

    6. No Access

      Chapter

      Pages 485-524

      A Framework for Global Communication Analysis and Optimizations

    7. No Access

      Chapter

      Pages 525-549

      Tolerating Communication Latency through Dynamic Thread Invocation in a Multithreaded Architecture

  5. Code Generation

    1. No Access

      Chapter

      Pages 553-596

      Advanced Code Generation for High Performance Fortran

    2. No Access

      Chapter

      Pages 597-645

      Integer Lattice Based Methods for Local Address Generation for Block-Cyclic Distributions

  6. Task Parallelism, Dynamic Data Structures and Run Time Systems

    1. No Access

      Chapter

      Pages 649-682

      A Duplication Based Compile Time Scheduling Method for Task Parallelism

    2. No Access

      Chapter

      Pages 683-708

      SPMD Execution in the Presence of Dynamic Data Structures

    3. No Access

      Chapter

      Pages 709-749

      Supporting Dynamic Data Structures with Olden

previous Page of 2