Title :
Compiling global name-space parallel loops for distributed execution
Author :
Koelbel, Charles ; Mehrotra, Piyush
Author_Institution :
Center for Res. on Parallel Comput., Rice Univ., Houston, TX, USA
fDate :
10/1/1991 12:00:00 AM
Abstract :
Compiler support required to allow programmers to express their algorithms using a global name-space is discussed. A general method for the analysis of a high-level source program and its translation into a set of independently executing tasks that communicate using messages is presented. It is shown that if the compiler has enough information, the translation can be carried out at compile time; otherwise; run-time code is generated to implement the required data movement. The analysis required in both situations is described, and the performance of the generated code on the Intel iPSC/2 hypercube is presented
Keywords :
parallel programming; program compilers; Intel iPSC/2 hypercube; compiler; data movement; distributed execution; global name-space parallel loops; high-level source program; independently executing tasks; message communication; performance; run-time code; translation; Algorithm design and analysis; Costs; Data structures; Memory architecture; Message passing; NASA; Performance analysis; Program processors; Programming profession; Runtime;
Journal_Title :
Parallel and Distributed Systems, IEEE Transactions on
