C
Charles E. Leiserson
Researcher at Massachusetts Institute of Technology
Publications - 190
Citations - 50798
Charles E. Leiserson is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Cilk & Scheduling (computing). The author has an hindex of 65, co-authored 185 publications receiving 49312 citations. Previous affiliations of Charles E. Leiserson include Vassar College & Carnegie Mellon University.
Papers
More filters
Patent
Router for parallel computer including arrangement for redirecting messages
David C. Douglas,Charles E. Leiserson,Bradley C. Kuszmaul,Shaw-Wen Yang,W. Daniel Hillis,David S. Wells,Carl R. Feynman,Bruce J. Walker,Brewster Kahle +8 more
TL;DR: In this paper, a message generator performs an address translation operation in connection with the address data and the contents of the address translation table to generate updated address data which it uses data in relation with generating address information for the message.
A Layout for the Shuffle-Exchange Network.
Dan Hoey,Charles E. Leiserson +1 more
TL;DR: A technique for producing a VLSI layout of the shuffle-exchange graph based on the layout procedure which lays out a graph by bisecting the graph, recursively laying out the two halves, and then combining the two sublayouts is described.
Proceedings ArticleDOI
Memory models for open-nested transactions
TL;DR: A framework for defining and exploring the memory semantics of open nesting in a transactionl-memory setting is offered, which allows the traditional model of serializability and two new transactional-memory models, race freedom and prefix race freedom, to be defined.
VLSI theory and parallel supercomputing
TL;DR: How layout theory engendered the notion of area and volume-universal networks, such as fat-trees is discussed and these scalable networks offer a flexible alternative to the more common hypercube-based networks for inter-connecting the processors of large parallel supercomputers.
Proceedings ArticleDOI
An empirical evaluation of work stealing with parallelism feedback
TL;DR: Simulation studies confirm with simulation studies that A-STEAL performs well when scheduling adaptively parallel work-stealing jobs on large-scale multiprocessors and provide evidence that A.STEAL consistently provides higher utilization than ABP for a variety of job mixes.