The Network Architecture of the Connection Machine CM-5

Leiserson, Charles E.; Abuhamdeh, Zahi S.; Douglas, David C.; Feynman, Carl R.; Ganmukhi, Mahesh N.; Hill, Jeffrey V.; Hillis, W. Daniel; Kuszmaul, Bradley C.; Pierre, Margaret A. St.; Wells, David S.; Wong-Chan, Monica; Yang, Shaw-Wen; Zak, Robert

doi:10.1006/jpdc.1996.0033

Cited by 254 publications

(121 citation statements)

References 15 publications

Supporting

Mentioning

119

Contrasting

Unclassified

Order By: Relevance

“…The CM5 is a massively parallel computer based on 32MHz SPARC processors with a fat-tree interconnection network [32]. The Cilk runtime system on the CM5 performs communication among processors using the Strata [7] active-message library.…”

Section: Written By Chris Joerg Of Mit' S Laboratory For Computer Scimentioning

confidence: 99%

Cilk: An Efficient Multithreaded Runtime System

Blumofe¹,

Joerg²,

Kuszmaul³

et al. 1996

Journal of Parallel and Distributed Computing

Self Cite

943

924

View full text Add to dashboard Cite

Cilk (pronounced "silk") is a C-based runtime system for multithreaded parallel programming. In this paper, we document the efficiency of the Cilk work-stealing scheduler, both empirically and analytically. We show that on real and synthetic applications, the "work" and "critical-path length" of a Cilk computation can be used to model performance accurately. Consequently, a Cilk programmer can focus on reducing the computation' s work and critical-path length, insulated from load balancing and other runtime scheduling issues. We also prove that for the class of "fully strict" (well-structured) programs, the Cilk scheduler achieves space, time, and communication bounds all within a constant factor of optimal.The Cilk runtime system currently runs on the Connection Machine CM5 MPP, the Intel Paragon MPP, the Sun Sparcstation SMP, and the Cilk-NOW network of workstations. Applications written in Cilk include protein folding, graphic rendering, backtrack search, and the ?Socrates chess program, which won second prize in the 1995 World Computer Chess Championship.

show abstract

Section: Written By Chris Joerg Of Mit' S Laboratory For Computer Scimentioning

confidence: 99%

Cilk: An Efficient Multithreaded Runtime System

Blumofe¹,

Joerg²,

Kuszmaul³

et al. 1996

Journal of Parallel and Distributed Computing

Self Cite

943

924

View full text Add to dashboard Cite

show abstract

“…For traditional parallel programming on tightly coupled multiprocessors, barriers are commonly used to separate phases of computation within an execution and form natural synchronization points [Jordan 1978]. Given the importance of fast primitives for coordinating bulk synchronous SIMD applications, most massively parallel processors (MPPs) have hardware support for barriers [Leiserson et al 1996;Scott 1996]. Barriers also form a natural consistency point for software distributed shared memory systems, often signifying the point where data will be synchronized with remote hosts [Keleher et al 1994;Bershad et al 1993].…”

Section: Synchronizationmentioning

confidence: 99%

Distributed application configuration, management, and visualization with plush

Albrecht

Tuttle

Braud

et al. 2011

ACM Trans. Internet Technol.

View full text Add to dashboard Cite

Support for distributed application management in large-scale networked environments remains in its early stages. Although a number of solutions exist for subtasks of application deployment, monitoring, and maintenance in distributed environments, few tools provide a unified framework for application management. Many of the existing tools address the management needs of a single type of application or service that runs in a specific environment, and these tools are not adaptable enough to be used for other applications or platforms. To this end, we present the design and implementation of Plush, a fully configurable application management infrastructure designed to meet the general requirements of several different classes of distributed applications. Plush allows developers to specifically define the flow of control needed by their computations using application building blocks. Through an extensible resource management interface, Plush supports execution in a variety of environments, including both live deployment platforms and emulated clusters. Plush also uses relaxed synchronization primitives for improving fault tolerance and liveness in failure-prone environments. To gain an understanding of how Plush manages different classes of distributed applications, we take a closer look at specific applications and evaluate how Plush provides support for each.

show abstract

“…The k-ary n-tree network [8], also called fat tree, is commonly used to optimize this network design by combining the crossbars in the middle. Those networks have very similar properties to Clos networks, and k-ary n-tree networks can be built with full bisection bandwidth like Clos networks.…”

Section: Clos Topologymentioning

confidence: 99%