Abstract | ||
---|---|---|
The techniques of “load/store” memory reference modeling is based on deriving performance characteristics of the memory architecture of a computer by looking at the behavior of simple sequences of load, store and nop (null operation) instructions. The resulting data base can be used to match load/store templates against algorithm kernels to predict performance or as a source of data for testing analytical models of the architecture. In this paper we study the BBN GP1000 parallel processing system. We show how to build a subset of the load/store kernels needed to characterize the machine and illustrate the behavior of a simple model based on the data. |
Year | DOI | Venue |
---|---|---|
1990 | 10.1145/77726.255182 | international conference on supercomputing |
Keywords | DocType | Volume |
parallel algorithm,bbn gp1000,analytical model,data base,simple model,algorithm kernel,simple sequence,memory reference modeling,memory architecture,store template,performance evaluation,performance characteristic,reference model,parallel processing | Conference | 18 |
Issue | ISBN | Citations |
3 | 0-89791-369-8 | 17 |
PageRank | References | Authors |
2.28 | 2 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
François Bodin | 1 | 648 | 84.59 |
Daniel Windheiser | 2 | 129 | 24.82 |
William Jalby | 3 | 733 | 148.24 |
Daya Atapattu | 4 | 36 | 5.14 |
Mannho Lee | 5 | 129 | 12.18 |
Dennis Gannon | 6 | 2514 | 330.26 |