[PDF][PDF] An optimized hardware architecture and communication protocol for scheduled communication

D Shoemaker - 1997 - dspace.mit.edu
Managing communications in parallel processing systems has proven to be one of the most
critical problems facing designers. As processor speeds continue to increase …

Numesh: An architecture optimized for scheduled communication

D Shoemaker, F Honore, C Metcalf, S Ward - The Journal of …, 1996 - Springer
The NuMesh system defines a high-speed communication substrate optimized for off-line
routing. By determining possible communication paths at compile time, highly efficient …

Communication optimization in Parsec: A parallel programming environment for multicomputers

SS Mulye - 1994 - open.library.ubc.ca
Multicomputer (distributed memory MIMD machines) have emerged as inexpensive, yet
powerful parallel computers that promise high computational performance. A parallel …

Do faster routers imply faster communication?

V Karamcheti, AA Chien - … Workshop on Parallel Computer Routing and …, 1994 - Springer
Despite significant improvements in network interfaces and software messaging layers,
software communication overhead still dominates the hardware routing cost in most parallel …

[PDF][PDF] Scheduling pipelined communication in distributed memory multiprocessors for real-time applications

SB Shukla, DP Agrawal - ACM SIGARCH Computer Architecture News, 1991 - dl.acm.org
This paper investigates communication in distributed memory multiprocessors to support
tasklevel parallelism for real-time applications. It is shown that wormhole routing, used in …

Contention-free communication scheduling on 2d meshes

A Eberhart, J Li - Proceedings of the 1996 ICPP Workshop on …, 1996 - ieeexplore.ieee.org
Spontaneous, unorchestrated communications on message-passing multicomputers can
cause collision, buffer overflow, and even deadlock, resulting in high communication …

[图书][B] A node interface for parallel processing

MR Hammes - 1989 - search.proquest.com
A multiprocessor communication scheme for large parallel systems is devised to offer total
interconnectivity which is software programmable. The system combines associated …

The NuMesh: A scalable, modular, 3D interconnect

SA Ward - Algorithms & Architectures: Proceedings of the …, 1993 - books.google.com
Over the past two decades, the backplane bus has dominated computer architectures as the
mechanism for intermodule communications. The reasons for this dominance are simple …

[PDF][PDF] ComPaSS: E cient communication services for scalable architectures,"

PK McKinley, H Xu, E Kalns, LM Ni - Proceedings of supercomputing, 1992 - Citeseer
In massively parallel computers (MPCs), e cient communication among processors is critical
to performance. This paper describes the initial implementation of the ComPaSS …

[图书][B] Customized message passing and scheduling for parallel and distributed applications

N Islam - 1994 - search.proquest.com
Replacing traditional operating systems communication and scheduling implementations
with customized implementations increases the performance of parallel and distributed …