Javar-kai: Automatic parallelizing compiler

A Framework To Study Automatically Parallelized Programs

The eeectiveness of automatic parallelization could be enhanced if we take into account important factors such as cache utilization, memory delays, synchronization time etc. This would require a framework that ties up a parallelizing compiler with a simulator that models all parameters very eeectively. The gathered information could be used to tune the parallelizing compiler to get better perfo...

Parallelizing compiler pdf

An Empirical Study on DOACROSS Loops

Loop-iteration level parallelism is one of the most common forms of parallelism being exploited by optimizing compilers and parallel machines. In this study, we selected 6 large application programs and used an execution-driven simulation technique from MaxPar 5] to identify and to measure the eeectiveness of concurrent DOACROSS loops execution. It was found that executing DOACROSS loops serial...

Evaluation of Parallelizing Compilers

The recognition and exploitation of parallelism is a diicult problem for restructuring compilers. We present a method for evaluating the eeectiveness of parallelizing compilers in general and of speciic compiler techniques. We also report two groups of measurements that are the results of using this technique. One evaluates a commercially available parallelizer, KAP/Concurrent, and the other co...

Parallel loops - a test suite for parallelizing compilers: description and example results

Several multiprocessor systems are now commercially available, and advances in compiler technology provide automatic conversion of programs to run on such systems. However, no accepted measure of this parallel compiler ability exists. This paper presents a test suite of subroutines and loops, called Parallel Loops, designed to (1) measure the ability of parallelizing compilers to convert code t...