Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques (2004)
Antibes Juan-les-Pins, France
Sept. 29, 2004 to Oct. 3, 2004
Cristina Cifuentes , Sun Microsystems Labs, Mountain View, CA
Deepankar Bairagi , Sun Microsystems, Menlo Park, CA
Michael Ball , Sun Microsystems, Menlo Park, CA
Code partitioning is the problem of dividing sections of code among a set of processors for execution in parallel taking into account the communication overhead between the processors. Code partitioning of large amounts of code onto numerous processors requires variations to the classical partitioning algorithms, in part due to the memory and time requirements to partition a large set of data, but also due to the nature of the target machine and multiple constraints imposed by its architectural features.<div></div> In this paper we present our experience in the design of enhancements to the classical multi-level k-way partitioning algorithm to deal with large graphs of over 1 million nodes, 5 constraints, and nodes of irregular size. Our algorithm was implemented to produce code for a massively parallel machine of up to 40,000 processors, and forms part of a hardware description language compiler. The algorithm and the compiler were tested on RTL designs for a next generation SPARC(R) processor. We present perfomance results and comparisons for partitioning multi-processor hardware designs.
Cristina Cifuentes, Deepankar Bairagi, Michael Ball, "Partitioning of Code for a Massively Parallel Machine", Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques, vol. 00, no. , pp. 225-236, 2004, doi:10.1109/PACT.2004.10000