Abstract | ||
---|---|---|
Data dependencies have become one of the main bottlenecks of current superscalar processors. Data speculation is gaining popularity as a mechanism to avoid the ordering imposed by data dependencies. Loads and stores are very good candidates for data speculation since their effective address has a regular behavior and then, they are highly predictable. In this paper we propose a mechanism called Address Prediction and Data Prefetching that allows load instructions to obtain their data at the decode stage. Besides, the effective address of load and store instructions is also predicted. These instructions and those dependent on them are speculatively executed. The technique has been evaluated for an out-of-order processor with a realistic configuration. The performance gain is about 19% in average and it is much higher for some benchmarks (up to 35%). |
Year | DOI | Venue |
---|---|---|
1997 | 10.1145/263580.263631 | International Conference on Supercomputing 2006 |
Keywords | Field | DocType |
speculative execution,address prediction,out of order,routing | Speculation,Computer science,Speculative execution,Parallel computing,Popularity,Speculative multithreading,Real-time computing,Superscalar | Conference |
ISBN | Citations | PageRank |
0-89791-902-5 | 78 | 5.88 |
References | Authors | |
19 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
José González | 1 | 526 | 35.85 |
Antonio González | 2 | 3178 | 229.66 |