Three extensions to register integration

ABSTRACT

Register integration (or just integration) is a register renaming discipline that implements instruction reuse via physical register sharing. Initially developed to perform squash reuse, the integration mechanism can exploit more reuse scenarios. Here, we describe three extensions to the original design that expand its applicability and boost its performance impact. First, we extend squash reuse to general reuse. Whereas squash reuse maintains the concept of an instruction instance "owning" its output register, we allow multiple instructions to simultaneously share a single register. Next, we replace the PC indexing scheme with an opcode-based indexing scheme that exposes more integration opportunities. Finally, we introduce an extension called reverse integration in which we speculatively create integration entries for the inverses of operations---for instance, when renaming an add, we create an entry for the inverse subtract. Reverse integration allows us to reuse operations that the program itself has not executed yet. We use reverse integration to implement speculative memory bypassing for stack-pointer based loads (register fills and restores).Our evaluation shows that these extensions increase the integration rate---the number of retired instructions that integrate older results and bypass the execution engine---to an average of 15% on the SPEC2000 integer benchmarks. On a 4-way superscalar processor with an aggressive memory system, this translates into an average IPC improvement of 7%. The fact that integrating instructions completely bypass the execution engine raises the possibility of using integration as a low-complexity substitute for execution bandwidth and issue buffering. Our experiments show that such a trade-off is possible, enabling a range of IPC/complexity designs.

REFERENCES

• 1: Todd M. Austin, DIVA: a reliable substrate for deep submicron microarchitecture design, Proceedings of the 32nd annual ACM/IEEE international symposium on Microarchitecture, p.196-207, November 16-18, 1999, Haifa, Israel
• 2: Yuan Chou , Jason Fung , John Paul Shen, Reducing branch misprediction penalties via dynamic control independence detection, Proceedings of the 13th international conference on Supercomputing, p.109-118, June 20-25, 1999, Rhodes, Greece [doi>10.1145/305138.305175]
• 3: Daniel Citron , Dror Feitelson , Larry Rudolph, Accelerating multi-media processing by implementing memoing in multiplication and division units, Proceedings of the eighth international conference on Architectural support for programming languages and operating systems, p.252-261, October 02-07, 1998, San Jose, California, United States
• 4: P. Glaskowsky. "Pentium 4 (Partially) Previewed." Microprocessor Report, 14(8), Aug. 2000.
• 5: S. Jourdan, R. Ronen, M. Bekerman, B. Shomar, and A. Yoaz. "A Novel Renaming Scheme to Exploit Value Temporal Locality Through Physical Register Reuse and Unification." MICRO-31, Dec. 1998.
• 6: R. E. Kessler, The Alpha 21264 Microprocessor, IEEE Micro, v.19 n.2, p.24-36, March 1999 [doi>10.1109/40.755465]
• 7: Hsien-Hsin S. Lee , Mikhail Smelyanskiy , Gary S. Tyson , Chris J. Newburn, Stack Value File: Custom Microarchitecture for the Stack, Proceedings of the 7th International Symposium on High-Performance Computer Architecture, p.5, January 20-24, 2001
• 8: Carlos Molina , Antonio González , Jordi Tubella, Dynamic removal of redundant computations, Proceedings of the 13th international conference on Supercomputing, p.474-481, June 20-25, 1999, Rhodes, Greece [doi>10.1145/305138.305239]
• 9: Andreas Moshovos , Gurindar S. Sohi, Streamlining inter-operation memory communication via data dependence prediction, Proceedings of the 30th annual ACM/IEEE international symposium on Microarchitecture, p.235-245, December 01-03, 1997, Research Triangle Park, North Carolina, United States
• 10: S. Onder and R. Gupta. "Load and Store Reuse using Register File Contents." ICS-15, Jan. 2001.
• 11: Amir Roth , Gurindar S. Sohi, Register integration: a simple and efficient implementation of squash reuse, Proceedings of the 33rd annual ACM/IEEE international symposium on Microarchitecture, p.223-234, December 2000, Monterey, California, United States [doi>10.1145/360128.360151]
• 12: Amir Roth , Gurindar S. Sohi, Speculative Data-Driven Multithreading, Proceedings of the 7th International Symposium on High-Performance Computer Architecture, p.37, January 20-24, 2001
• 13: A. Roth and G. Sohi. "Squash Reuse via a Simplified Implementation of Register Integration." JILP-4, 2002.
• 14: Avinash Sodani , Gurindar S. Sohi, Dynamic instruction reuse, 2000
• 15: Avinash Sodani , Gurindar S. Sohi, Dynamic instruction reuse, Proceedings of the 24th annual international symposium on Computer architecture, p.194-205, June 01-04, 1997, Denver, Colorado, United States
• 16: Gary S. Tyson , Todd M. Austin, Improving the accuracy and performance of memory communication through renaming, Proceedings of the 30th annual ACM/IEEE international symposium on Microarchitecture, p.218-227, December 01-03, 1997, Research Triangle Park, North Carolina, United States
• 17: Kenneth C. Yeager, The MIPS R10000 Superscalar Microprocessor, IEEE Micro, v.16 n.2, p.28-40, April 1996 [doi>10.1109/40.491460]

INDEX TERMS

Primary Classification:
  D. Software
  D.3 PROGRAMMING LANGUAGES
      D.3.4 Processors

Additional Classification:
  B. Hardware
  B.5 REGISTER-TRANSFER-LEVEL IMPLEMENTATION
      B.5.1 Design

  D. Software
  D.2 SOFTWARE ENGINEERING
        D.2.13 Reusable Software
            Subjects: Reuse models

General Terms:
Design, Performance