1 Parallel Architectures and Compilers. - 1. 1 Introduction. - 1. 2 Book Overview. - 1. 3 Vector and Parallel Machines. - 1. 4 Parallelism in Programs. - 1. 5 Basic Concepts and Definitions. - 2 Program restructuring for parallel execution. - 2. 1 Data Dependences. - 2. 2 Common Optimizations. - 2. 3 Transformations for Vector/Parallel Loops. - 2. 4 Cycle Shrinking. - 2. 5 Loop Spreading. - 2. 6 Loop Coalescing. - 2. 7 Run-Time Dependence Testing. - 2. 8 Subscript Blocking. - 2. 9 Future Directions. - 3 A Comprehensive Environment for Automatic Packaging and Scheduling of Parallelism. - 3. 1 Introduction. - 3. 2 A Comprehensive Approach to Scheduling. - 3. 3 Auto-Scheduling Compilers. - 4 Static and Dynamic Loop Scheduling. - 4. 1 Introduction. - 4. 2 The Guided Self-Scheduling (GSS(k)) Algorithm. - 4. 3 Simulation Results. - 4. 4 Static Loop Scheduling. - 5 Run-Time Overhead. - 5. 1 Introduction. - 5. 2 Bounds for Dynamic Loop Scheduling. - 5. 3 Overhead of Parallel Tasks. - 5. 4 Two Run-Time Overhead Models. - 5. 5 Deciding the Minimum Unit of Allocation. - 6 Static Program Partitioning. - 6. 1 Introduction. - 6. 2 Methods for Program Partitioning. - 6. 3 Optimal Task Composition for Chains. - 6. 4 Details of Interprocessor Communication. - 7 Static Task Scheduling. - 7. 1 Introduction. - 7. 2 Optimal Allocations for High Level Spreading. - 7. 3 Scheduling Independent Serial Tasks. - 7. 4 High Level Spreading for Complete Task Graphs. - 7. 5 Bounds for Static Scheduling. - 8 Speedup Bounds for Parallel Programs. - 8. 1 Introduction. - 8. 2 General Bounds on Speedup. - 8. 3 Speedup Measures for Task Graphs. - 8. 4 Speedup Measures for Doacr Loops. - 8. 5 Multiprocessors vs. Vector/Array Machines. - References. Language: English