We present the top-down design of a new system which performs automatic parallelization of numerical Fortran 77 or C source programs for execution on distributed-memory message-passing multiprocessors such as e.g. the INTEL iPSC860 or the TMC CM-5. The key idea is a high-level pattern-matching approach which in some useful way permits partial restructuring of a wide class of numerical programs. With only a few hundred patterns, we will be able to completely match many important numerical algorithms. Together with mathematical background knowledge and parallel compiler engineering experience, this opens access to a new potential for automatic parallelization that has never been exploited before
Abstract—The need for processing power is constantly increas-ing as more processing-demanding and ti...
This paper studies howwell automatic parallelization techniques work on a collection of real codes w...
This paper studies the performance implications of architectural synchronization support for automat...
We describe the design of the PARAMAT system which will be able to automatically parallelize many nu...
This paper describes a knowledge-based system for automatic parallelization of a wide class of seque...
112 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1993.Numerical applications requir...
Scalable parallel numerical libraries and automatically parallelizing compilers seem to be contrary ...
iii Numerical applications require large amounts of computing power. Although shared memory multipro...
Modern heterogeneous multi-core architectures containing one or multiple GPU de- vices require exper...
Divide--and--conquer algorithms obtain the solution to a given problem by dividing it into subproble...
A significant amount of software research for developing programming environments for distributed--m...
This paper discusses the techniques used to hand-parallelize, for the Alliant FX/80, four Fortran pr...
Exploiting the full performance potential of distributed memory machines requires a careful distribu...
Shared-memory multiprocessor systems can achieve high performance levels when appropriate work paral...
Automatic parallelization is usually believed to be less effective at exploiting implicit parallelis...
Abstract—The need for processing power is constantly increas-ing as more processing-demanding and ti...
This paper studies howwell automatic parallelization techniques work on a collection of real codes w...
This paper studies the performance implications of architectural synchronization support for automat...
We describe the design of the PARAMAT system which will be able to automatically parallelize many nu...
This paper describes a knowledge-based system for automatic parallelization of a wide class of seque...
112 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1993.Numerical applications requir...
Scalable parallel numerical libraries and automatically parallelizing compilers seem to be contrary ...
iii Numerical applications require large amounts of computing power. Although shared memory multipro...
Modern heterogeneous multi-core architectures containing one or multiple GPU de- vices require exper...
Divide--and--conquer algorithms obtain the solution to a given problem by dividing it into subproble...
A significant amount of software research for developing programming environments for distributed--m...
This paper discusses the techniques used to hand-parallelize, for the Alliant FX/80, four Fortran pr...
Exploiting the full performance potential of distributed memory machines requires a careful distribu...
Shared-memory multiprocessor systems can achieve high performance levels when appropriate work paral...
Automatic parallelization is usually believed to be less effective at exploiting implicit parallelis...
Abstract—The need for processing power is constantly increas-ing as more processing-demanding and ti...
This paper studies howwell automatic parallelization techniques work on a collection of real codes w...
This paper studies the performance implications of architectural synchronization support for automat...