In this article, a hybrid optimization method has been proposed consisting of modified ant colony systems (ACSs) and constrained nonlinear programming (NLP) to solve the problems ...
This paper describes our early experiences with a preproduction Cray XMT system that implements a scalable shared memory architecture with hardware support for multithreading. Unl...
Networks of workstations are fast becoming the standard environment for parallel applications. However, the use of “found” resources as a platform for tightly-coupled runtime ...
Most shared memory systems maximize performance by unpredictably resolving memory races. Unpredictable memory races can lead to nondeterminism in parallel programs, which can suff...
Derek Hower, Polina Dudnik, Mark D. Hill, David A....
Evaluation of high performance parallel systems is a delicate issue, due to the difficulty of generating workloads that represent, with fidelity, those that will run on actual sys...