The superblock: An effective technique for VLIW and superscalar compilation
| Autor: | Daniel M. Lavery, Richard E. Hank, William Y. Chen, Tokuzo Kiyohara, Grant Haab, John G. Holm, Wen-mei W. Hwu, Nancy J. Warter, Roland G. Ouellette, Scott Mahlke, Roger A. Bringmann, Pohua P. Chang |
|---|---|
| Rok vydání: | 1993 |
| Předmět: |
Computer science
Trace scheduling Speculative execution Optimizing compiler Parallel computing computer.software_genre Supercomputer Theoretical Computer Science Scheduling (computing) Computer architecture Hardware and Architecture Very long instruction word Superscalar Basic block Compiler Hardware_CONTROLSTRUCTURESANDMICROPROGRAMMING computer Software Information Systems |
| Zdroj: | The Journal of Supercomputing. 7:229-248 |
| ISSN: | 1573-0484 0920-8542 |
| DOI: | 10.1007/bf01205185 |
| Popis: | A compiler for VLIW and superscalar processors must expose sufficient instruction-level parallelism (ILP) to effectively utilize the parallel hardware. However, ILP within basic blocks is extremely limited for control-intensive programs. We have developed a set of techniques for exploiting ILP across basic block boundaries. These techniques are based on a novel structure called the superblock. The superblock enables the optimizer and scheduler to extract more ILP along the important execution paths by systematically removing constraints due to the unimportant paths. Superblock optimization and scheduling have been implemented in the IMPACT-I compiler. This implementation gives us a unique opportunity to fully understand the issues involved in incorporating these techniques into a real compiler. Superblock optimizations and scheduling are shown to be useful while taking into account a variety of architectural features. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink