This paper describes two new ideas by which an HPF compiler can deal with irregular computations effectively. The first mechanism invokes a user-specified parallel mapping procedure via a set of compiler directives. The directives allow use of program arrays to describe graph connectivity, spatial location of array elements and computational load. The second mechanism is a simple conservative method that in many cases enables a compiler to recognize that it is possible to reuse previously computed information from inspectors (e.g. communication schedules, loop iteration partitions, information that associates off-processor data copies with on-processor buffer locations). We present performance results for these mechanisms from a Fortran 90D...
This paper describes a compilation approach for a Fortran 90D/HPF compiler, a source-to-source paral...
We developed a dataflow framework which provides a basis for rigorously defining strategies to make ...
In the data parallel programming style the user usually specifies the data parallelism explicitly so...
This paper describes two new ideas by which an HPF compiler can deal with irregular computations eff...
In this paper, we describe two new ideas by which HPF compiler can deal with irregular computations ...
In recent years, distributed memory parallel machines have been widely recognized as the most likely...
Fortran 90D/HPF is a data parallel language with special directives to enable users to specify data ...
This paper presents methods that make it possible to efficiently support irregular problems using da...
This work was also published as a Rice University thesis/dissertation: http://hdl.handle.net/1911/16...
Data-parallel languages, such as H scIGH P scERFORMANCE F scORTRAN or F scORTRAN D, provide a machin...
This paper describes the design of the Fortran90D/HPF compiler, a source-to-source parallel compiler...
Fortran 90D/HPF is a data parallel language with special directives to enable users to specify data ...
Fortran 90D/HPF is a data parallel language with special directives to enable users to specify data ...
This paper describes the design of a compiler which can translate ont-of-core programs written in a ...
Languages such as Fortran D provide irregular distribution schemes that can efficiently support irre...
This paper describes a compilation approach for a Fortran 90D/HPF compiler, a source-to-source paral...
We developed a dataflow framework which provides a basis for rigorously defining strategies to make ...
In the data parallel programming style the user usually specifies the data parallelism explicitly so...
This paper describes two new ideas by which an HPF compiler can deal with irregular computations eff...
In this paper, we describe two new ideas by which HPF compiler can deal with irregular computations ...
In recent years, distributed memory parallel machines have been widely recognized as the most likely...
Fortran 90D/HPF is a data parallel language with special directives to enable users to specify data ...
This paper presents methods that make it possible to efficiently support irregular problems using da...
This work was also published as a Rice University thesis/dissertation: http://hdl.handle.net/1911/16...
Data-parallel languages, such as H scIGH P scERFORMANCE F scORTRAN or F scORTRAN D, provide a machin...
This paper describes the design of the Fortran90D/HPF compiler, a source-to-source parallel compiler...
Fortran 90D/HPF is a data parallel language with special directives to enable users to specify data ...
Fortran 90D/HPF is a data parallel language with special directives to enable users to specify data ...
This paper describes the design of a compiler which can translate ont-of-core programs written in a ...
Languages such as Fortran D provide irregular distribution schemes that can efficiently support irre...
This paper describes a compilation approach for a Fortran 90D/HPF compiler, a source-to-source paral...
We developed a dataflow framework which provides a basis for rigorously defining strategies to make ...
In the data parallel programming style the user usually specifies the data parallelism explicitly so...