FORGE® 90's Shared Memory Parallelizer (SMP) performs interprocedural analysis. Unlike parallelizing compilers that fail to parallelize the most important DO loops in your program, it can handle loops that call subroutines. SMP's strategy is to parallelize for high granularity by analyzing outermost loops first. It analyzes array and scalar dependencies across subprogram boundaries by tracing references through the database up and down the call tree. The result is a parallelized source code with compiler-specific directives inserted for scoping variables and for identifying Critical and Order regions of code.
John Levesque
President
Applied Parallel Research, Inc.
1723 Professional Drive
Sacramento, CA 95825
USA
916-481-9891
916-481-7924 (fax)
levesque@apri.com
For applications in related solution areas, see the following indices: Parallel Processing, Parallel Tools, the developer index for Applied Parallel Research, Inc. and the market segment index for Development Tools.
FORGE is a Registered Trademark of Applied Parallel Research, Inc.
