Slipstream processors: improving both performance and fault tolerance

Abstract

Processors execute the full dynamic instruction stream to arrive at the final output of a program, yet there exist shorter instruction streams that produce the same overall effect. We propose creating a shorter but otherwise equivalent version of the original program by removing ineffectual computation and computation related to highly-predictable control flow. The shortened program is run concurrently with the full program on a chip multiprocessor simultaneous multithreaded processor, with two key advantages:1) Improved single-program performance. The shorter program speculatively runs ahead of the full program and supplies the full program with control and data flow outcomes. The full program executes efficiently due to the communicated outcomes, at the same time validating the speculative, shorter program. The two programs combined run faster than the original program alone. Detailed simulations of an example implementation show an average improvement of 7% for the SPEC95 integer benchmarks.2) Fault tolerance. The shorter program is a subset of the full program and this partial-redundancy is transparently leveraged for detecting and recovering from transient hardware faults.

References

1. 1 H. Akkary and M. Driscoll. A Dynamic Multithreading Processor. 31st Int'l Symp. on Microarchitecture, Dec. 1998.
2. 2 T. Austin. DIVA: A Reliable Substrate for Deep Submicron Microarchitecture Design. 32nd Int'l Symp. on Microarchitecture, Nov. 1999.
3. 3 D. Burger, T. Austin, and S. Bennett. Evaluating Future Microprocessors: The Simplescalar Toolset. Technical Report CS-TR-96-1308, Computer Sciences Department, University of Wisconsin - Madison, July 1996.
4. 4 D. Burger, S. Kaxiras, and J. Goodman. DataScalar Architectures. 24th Int'l Symp. on Computer Architecture, June 1997.
5. 5 R. Chappell, J. Stark, S. Kim, S. Reinhardt, and Y. Patt. Simultaneous Subordinate Microthreading (SSMT). 26th Int'l Symp. on Computer Architecture, May 1999.
6. 6 D. Connors and W.-M. Hwu. Compiler-Directed Dynamic Computation Reuse: Rationale and Initial Results. 32nd Int'l Symp. on Microarchitecture,Nov. 1999.
7. 7 P. Dubey, K. O'Brien, K. M. O'Brien, and C. Barton. Single-Program Speculative Multithreading (SPSM) Architecture: Compiler-Assisted Fine-Grained Multithreading. Parallel Architectures and Compiler Techniques, June 1995
8. 8 A. Farcy, O. Temam, R. Espasa, and T. Juan. Dataflow Analysis of Branch Mispredictions and its Application to Early Resolution of Branch Outcomes. 31st Int'l Symp. on Microarchitecture, Dec. 1998.
9. 9 A. Gonzalez, J. Tubella, and C. Molina. Trace-Level Reuse. Int'l Conf. on Parallel Processing, Sep. 1999.
10. 10 J. Huang and D. Lilja. Exploiting Basic Block Value Locality with Block Reuse. 5th Int'l Symp. on High-Performance Computer Architecture, Jan. 1999.
11. 11 R. Iyer, A. Avizienis, D. Barron, D. Powell, H. Levendel, and J. Samson. Panel: Using COTS to Design Dependable Networked Systems. 29th Int'l Symp. on Fault-Tolerant Computing, June 1999.
12. 12 E. Jacobsen, E. Rotenberg, and J. Smith. Assigning Confidence to Conditional Branch Predictions. 29th Int'l Symp. on Microarchitecture, Dec. 1996.
13. 13 Q. Jacobson, E. Rotenberg, and J. Smith. Path- Based Next Trace Prediction. 30th Int'l Symp. on Microarchitecture, Dec. 1997.
14. 14 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. 31st Int'l Symp. on Microarchitecture, Nov. 1998.
15. 15 K. Lepak and M. Lipasti. On the Value Locality of Store Instructions. 27th Int'l Symp. on Computer Architecture, June 2000.
16. 16 M. Lipasti, C. Wilkerson, and J. Shen. Value Locality and Load Value Prediction. 7th Int'l Conf. on Architectural Support for Programming Languages and Operating Systems, Oct. 1996.
17. 17 M. Lipasti. Value Locality and Speculative Execution. Ph.D. Thesis, Carnegie Mellon University, April 1997.
18. 18 M. Martin, A. Roth, and C. Fischer. Exploiting Dead Value Information. 30th Int'l Symp. on Microarchitecture, Dec. 1997.
19. 19 C. Molina, A. Gonzalez, and J. Tubella. Reducing Memory Traffic via Redundant Store Instructions. HPCN Europe, 1999.
20. 20 K. Olukotun, B. Nayfeh, L. Hammond, K. Wilson, and K.-Y. Chang. The Case for a Single-Chip Multiprocessor. 7th Int'l Conf. on Architectural Support for Programming Languages and Operating Systems, Oct. 1996.
21. 21 J. Oplinger, D. Heine, S.-W. Liao, B. Nayfeh, M. Lam, and K. Olukotun. Software and Hardware for Exploiting Speculative Parallelism in Multiprocessors. CSL-TR-97-715, Stanford University, Feb. 1997.
22. 22 S. Reinhardt and S. Mukherjee. Transient Fault Detection via Simultaneous Multithreading. 27th Int'l Symp. on Computer Architecture, June 2000.
23. 23 D. Ronfeldt. Social Science at 190 MPH on NASCAR's Biggest Superspeedways. First Monday Journal (on-line), Vol. 5 No. 2, Feb. 7, 2000.
24. 24 E. Rotenberg. AR-SMT: A Microarchitectural Approach to Fault Tolerance in Microprocessors. 29th Int'l Symp. on Fault-Tolerant Computing, June 1999.
25. 25 E. Rotenberg. Exploiting Large Ineffectual Instruction Sequences. Technical Report, Department of Electrical and Computer Engineering, North Carolina State University, Nov. 1999.
26. 26 A. Roth, A. Moshovos, and G. Sohi. Dependence Based Prefetching for Linked Data Structures. 8th Int'l Conf. on Architectural Support for Programming Languages and Operating Systems, Oct. 1998.
27. 27 A. Roth and G. Sohi. Speculative Data Driven Sequencing for Imperative Programs. Technical Report CS-TR-2000-1411, Computer Sciences Department, University of Wisconsin - Madison, Feb. 2000.
28. 28 A. Roth and G. Sohi. Speculative Data-Driven Multithreading. Technical Report CS-TR-2000-1414, Computer Sciences Department, University of Wisconsin - Madison, April 2000.
29. 29 P. Rubinfeld. Virtual Roundtable on the Challenges and Trends in Processor Design: Managing Problems at High Speeds. Computer, 31(1):47-48, Jan. 1998.
30. 30 Y. Sazeides and J. E. Smith. Modeling Program Predictability. 25th Int'l Symp. on Computer Architecture, June 1998.
31. 31 A. Sodani and G. S. Sohi. Dynamic Instruction Reuse. 24th Int'l Symp. on Computer Architecture, June 1997.
32. 32 A. Sodani and G. S. Sohi. An Empirical Analysis of Instruction Repetition. 8th Int'l Conf. on Architectural Support for Programming Languages and Operating Systems, Oct. 1998.
33. 33 G. Sohi, S. Breach, and T. N. Vijaykumar. Multiscalar Processors. 22nd Int'l Symp. on Computer Architecture, June 1995.
34. 34 J. Steffan and T. Mowry. The Potential for Using Thread-Level Data Speculation to Facilitate Automatic Parallelization. 4th Int'l Symp. on High-Performance Computer Architecture, Feb. 1998.
35. 35 J.-Y. Tsai and P.-C. Yew. The Superthreaded Architecture: Thread Pipelining with Run-time Data Dependence Checking and Control Speculation. Parallel Architectures and Compiler Techniques, 1996.
36. 36 D. Tullsen, S. Eggers, and H. Levy. Simultaneous Multithreading: Maximizing On-Chip Parallelism. 22nd Int'l Symp. on Computer Architecture, June 1995.
37. 37 D. Tullsen, S. Eggers, J. Emer, H. Levy, J. Lo, and R. Stamm. Exploiting Choice: Instruction Fetch and Issue on an Implementable Simultaneous Multithreading Processor. 23rd Int'l Symp. on Computer Architecture, May 1996.
38. 38 D. Tullsen and J. Seng. Storageless Value Prediction Using Prior Register Values. 26th Int'l Symp. on Computer Architecture, May 1999.
39. 39 W. Yamamoto and M. Nemirovsky. Increasing Superscalar Performance through Multistreaming. Parallel Architectures and Compilation Techniques, June 1995.
40. 40 C. Zilles, J. Emer, and G. Sohi. The Use of Multithreading for Exception Handling. 32nd Int'l Symp. on Microarchitecture, Nov. 1999.
41. 41 C. Zilles and G. Sohi. Understanding the Backward Slices of Performance Degrading Instructions. 27th Int'l Symp. on Computer Architecture, June 2000.

Index Terms

• Computer systems organization

  • Architectures

    • Parallel architectures

      • Very long instruction word

    • Serial architectures

      • Complex instruction set computing

      • Reduced instruction set computing

  • Dependable and fault-tolerant systems and networks

• Computing methodologies

  • Modeling and simulation

    • Model development and analysis

      • Model verification and validation

    • Simulation evaluation

    • Simulation support systems

      • Simulation environments

• General and reference

  • Cross-computing tools and techniques

    • Evaluation

    • Metrics

    • Performance

• Networks

  • Network performance evaluation

• Social and professional topics

  • Professional topics

    • Management of computing and information systems

      • Project and people management

        • Systems analysis and design

• Software and its engineering

  • Software organization and properties

    • Extra-functional properties

      • Software fault tolerance