M. Andrews, F. T. Leighton, P. T. Metaxas, and L. Zhang. Improved methods for hiding latency in high bandwidth networks. In Proc. of the 8th ACM Symp. on Parallel Algorithms and Architectures (SPAA), pages 52--61, 1996. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Data Management in Networks: Experimental.. - Krick, der Heide, .. (1999) (3 citations) (Correct)
....because improving communication bandwidth and latency is often more expensive or more difficult than increasing processor speed and memory capacity. But whereas several standard methods are known for hiding latency, e.g. pipelined routing (see, e.g. 14, 16] redundant computation (see, e.g. [3, 4, 21, 26, 27, 28]) or slackness (see, e.g. 32] the only way to bypass the bandwidth bottleneck is to reduce the communication overhead by exploiting locality. The theoretical analysis of the access tree strategy in [25] considers data management in a competitive model. It is shown that the access tree strategy ....
M. Andrews, F. T. Leighton, P. T. Metaxas, and L. Zhang. Improved methods for hiding latency in high bandwidth networks. In Proc. of the 8th ACM Symp. on Parallel Algorithms and Architectures (SPAA), pages 52--61, 1996.
Exploiting Locality for Data Management in Systems .. - Maggs, der Heide, .. (1997) (22 citations) (Correct)
....since improving communication bandwidth and latency is often more expensive or more difficult than increasing processor speed and memory capacity. But whereas several standard methods are known for hiding latency, e.g. pipelined routing (see, e.g. 7, 8] redundant computation (see, e.g. [1, 2, 15, 20, 21, 23]) or slackness (see, e.g. 29] the only way to bypass the bandwidth bottleneck is to reduce the communication load by exploiting locality. The principle of locality is already known from sequential computation. Two kinds of locality are usually distinguished: temporal and spatial locality (see, ....
M. Andrews, T. Leighton, P. T. Metaxas, and L. Zhang. Improved methods for hiding latency in high bandwidth networks. In Proc. of the 8th ACM Symp. on Parallel Algorithms and Architectures (SPAA), pages 52--61, 1996.
Exploiting Locality for Data Management in Systems .. - Maggs, der Heide, .. (1997) (22 citations) (Correct)
....since improving communication bandwidth and latency is often more expensive or more difficult than increasing processor speed and memory capacity. But whereas several standard methods are known for hiding latency, e.g. pipelined routing (see, e.g. 7, 8] redundant computation (see, e.g. [1, 2, 15, 21, 22, 24]) or slackness (see, e.g. 30] the only way to bypass the bandwidth bottleneck is to reduce the communication load by exploiting locality. The principle of locality is already known from sequential computation. Two kinds of locality are usually distinguished: temporal and spatial locality (see, ....
M. Andrews, T. Leighton, P. T. Metaxas, and L. Zhang. Improved methods for hiding latency in high bandwidth networks. In Proc. of the 8th ACM Symp. on Parallel Algorithms and Architectures (SPAA), pages 52--61, 1996.
Open Problems for Latency Hiding in Networks of.. - Andrews, Leighton.. Self-citation (Andrews Leighton Metaxas Zhang) (Correct)
....a program that will run with minimal degradation in performance on a network with potentially large and variable latencies, at least for certain classes of networks. 2 Previous Results Two papers that discuss how to design automatic methods for hiding latencies in high bandwidth networks, are [2] and [3] They study the problem under two different models of distributed computation, the dataflow model and the database model. In [2] the dataflow model is used. In that model, a step of the computation executed by processor g i depends solely on the results of the computation at the previous ....
....for certain classes of networks. 2 Previous Results Two papers that discuss how to design automatic methods for hiding latencies in high bandwidth networks, are [2] and [3] They study the problem under two different models of distributed computation, the dataflow model and the database model. In [2], the dataflow model is used. In that model, a step of the computation executed by processor g i depends solely on the results of the computation at the previous step by g i and its neighboring processors. We use a pebbling scheme to represent the computation, in which the computation performed by ....
[Article contains additional citation context not shown here]
M. Andrews, T. Leighton, P. T. Metaxas, and L. Zhang. Improved methods for hiding latency in high bandwidth networks. To appear in Proceedings of the 28th Annual ACM Symposium on Theory of Computing, 1996.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC