Data parallel languages like High Performance Fortran (HPF) are emerging as the architecture independent mode of programming distributed memory parallel machines. In this paper, we present the interprocedural optimizations required for compiling applications having irregular data access patterns, when coded in such data parallel languages. We have developed an Interprocedural Partial Redundancy...

Processing and analyzing large volumes of data plays an increasingly important role in many domains of scienti c research. Typical examples of very large scienti c datasets include long running simulations of time-dependent phenomena that periodically generate snapshots of their state, archives of raw and processed remote sensing data, and archives of medical images. High-level language and com...

In this paper we describe an approach to the compilation of data-parallel programming languages based on a formally deened intermediate language, called V-cal. The calculus V-cal was designed to represent the semantics of data management and control primitives found in data-parallel languages and allows to describe program transformations and optimizations as semantics preserving rewrite rules....

Integrated Circuits with over one million transistors are now common, and the current doubling of circuit density every two years seems likely to continue. Consequently, VLSI design has become a major bottleneck in new product development. SSI and MSI design methods are quite inadequate. The design of one 60,000-transistor chip took 15 technical experts three years and cost several million doll...

OBJECTIVE To compile available information - both hospital and community based--on the maternal mortality ratios (MMRs) and the causes of maternal deaths in Pakistan METHODS Data was collected from articles published in Medical Journals, in Proceedings of Conferences and of Workshops as well as from Newsletters of the National Committee for Maternal Health (NCMH). The data was then tabulated ...

Data-flow is a natural approach to parallelism. However, describing dependencies and control between finegrained data-flow tasks can be complex and present unwanted overheads. TALM (TALM is an Architecture and Language for Multi-threading) introduces a user-defined coarse-grained parallel data-flow model, where programmers identify code blocks, called superinstructions, to be run in parallel an...

Annotations are often added to mobile code to reduce the optimization burden of just-intime compilers. However, these annotations are not checked for correctness and must be trusted—incorrect or malicious annotations could lead to the generation of incorrect or insecure code. We present a timeand space efficient method for verifying the results of the large class of data flow optimizations. Thi...

This paper describes two new ideas by which an ttPF compiler can deal with irregular computations effectively. The first mechanism invokes a user specified 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 th...