Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- ArticleJune 1988
An approach to synchronization for parallel computing
ICS '88: Proceedings of the 2nd international conference on SupercomputingPages 573–581https://doi.org/10.1145/55364.55420This paper proposes an approach to minimally constrained synchronization for the parallel execution of imperative programs in a shared-memory environment. Anti-dependencies and output-dependencies arising from array references within loops are ...
- ArticleJune 1988
Code scheduling and register allocation in large basic blocks
ICS '88: Proceedings of the 2nd international conference on SupercomputingPages 442–452https://doi.org/10.1145/55364.55407We discuss the issues about the interdependency between code scheduling and register allocation. We present two methods as solutions: (1) an integrated code scheduling technique; and (2) a DAG-driven register allocator. The integrated code scheduling ...
- ArticleJune 1988
Pipelined data parallel algorithms—concept and modeling
ICS '88: Proceedings of the 2nd international conference on SupercomputingPages 385–395https://doi.org/10.1145/55364.55402A new style of efficient parallel algorithms on distributed-memory multiprocessors is introduced, which exploits parallelism through pipelined parallel computation, or large-grain pipelining. By using macro-pipelining between nodes in the system, large-...
- ArticleJune 1988
Optimul: An optional interconnect for multiprocessor systems
ICS '88: Proceedings of the 2nd international conference on SupercomputingPages 16–24https://doi.org/10.1145/55364.55367An optical interconnect is proposed for multiprocessor systems, of both the tightly and loosely coupled types. This interconnect solves the problem of contention for memory and interconnect in the tightly coupled case, and the problem of network ...
- ArticleJune 1988
Page table management in local/remote architectures
ICS '88: Proceedings of the 2nd international conference on SupercomputingPages 1–8https://doi.org/10.1145/55364.55365We conjecture that a paged memory with page migration by the operating system may be an effective system environment for a local/remote shared memory architecture executing a single parallel computation. Implementing a paged memory in such an ...
