Abstract. Optimizing compilers typically limit the scope of their analyses and optimizations to individual modules. This has two drawbacks: rst, library code cannot be optimized to...
This paper presents reduction recognition and parallel code generationstrategies for distributed-memorymultiprocessors. We describe techniques to recognize a broad range of implic...
: The EM-4 is a supercomputer that offers very fast inter processor communication and support for multi threading. In this paper we demonstrate that the EM-4, Together with an auto...
Service-Oriented Architecture (SOA) plays an important role in the next generation computing models for scientific and commercial applications. But difficulties in the development...
The memory bandwidth largely determines the performance and energy cost of embedded systems. At the compiler level, several techniques improve the memory bandwidth at the scope of...