The proceedings contain 49 papers. The special focus in this conference is on europeandistributedmemorycomputing. The topics include: The new age of supercomputing;the next generation transputers and beyond;a distr...
ISBN:
(纸本)9783540539513
The proceedings contain 49 papers. The special focus in this conference is on europeandistributedmemorycomputing. The topics include: The new age of supercomputing;the next generation transputers and beyond;a distributed implementation of shared virtual memory with strong and weak coherence;store coherency in a parallel distributed-memory machine;using a weak coherency model for a parallel lisp;flexible user-definable memory coherence scheme in distributed shared memory of GALAXY;parallelization of multigrid programs in SUPERB;mapping graphs onto a partially reconfigurable architecture;a performance evaluation tool environment for parallel anddistributed systems;interleaving partitions of systolic algorithms for programming distributedmemory multiprocessors;partial ordering of synchronization events for distributed debugging in tightly-coupled multiprocessor systems;a development environment for distributed systems;monitor-supported analysis of a communication system for transputer-networks;an integrated environment for programming distributedmemory multiprocessors;optimal multinode broadcast on a mesh connected graph with reduced bufferization;adaptive irregular multiple grids on a distributedmemory multiprocessor;an object-oriented interface for parallel programming of loosely-coupled multiprocessor systems;on automatic loop data-mapping for distributed-memory a scalable communication processor design supporting systolic communication;multiprocessors;efficient and scalable logical busses for message-passing interconnection networks;performance benefits from locally adaptive interval routing in dynamically switched interconnection networks;an optimal structure that accommodates both a ring and a binary tree;on the design of deadlock-free adaptive routing algorithms for multicomputers and parallelization of lee's routing algorithm on a hypercube multicomputer.
作者：
HAMMER, CHENTIES, TSiemens AG
ZFE IS SOF 22 Corporate Research and Development Otto-Hahn-Ring 6 Munich 83 D-8000 Germany
The parallel language EDS Lisp has been designed for distributedmemory machines. In this respect, it presupposes only a minimal required coherency in the storage view of parallel processes. This paper describes the c...
详细信息
The implementation of a large finite element program used for nonlinear industrial applications on an iPSC/2 Hypercube is described in this paper. Two strategies for the solution of the linearized system of equations ...
详细信息
We describe a tool that supports data-parallel programming on a distributedmemory multiprocessor. Load balancing, based on an evolution algorithm, is integrated into this environment. Timing results for balanced Jaco...
详细信息
In this paper we have described a user-definable memory coherence scheme for distributed shared memory that is flexible enough to meet the varying needs of a wide variety of user applications. We believe that the conc...
详细信息
The Peace distributed operating system makes massively parallel systems fit for use. This paper describes the Peace incremental loading scheme, encompassing two aspects. First, it provides capabilities for starting an...
详细信息
暂无评论