Hierarchical Verification for Increasing Performance in Reliable Processors

ABSTRACT

Dynamic verification using the checker processor introduces severe degradation in performance unless the checker is as fast as the main processor core. Without widening the checker's bandwidth, we propose an active verification management (AVM) approach that utilizes a checker hierarchy. Before an instruction is verified at the checker processor, a filter checker marks a correctness non-criticality indicator (CNI) bit to indicate how likely its result is to be unimportant for reliability. AVM uses the CNI information to realize a congestion avoidance policy. Both reactive and proactive congestion avoidance policies are proposed to mitigate the performance degradation caused by the checker's congestion. Based on a simplified queueing model, we evaluate the proposed AVM analytically. Our experimental results show that AVM has the potential to solve the verification congestion problem when perfect fault coverage is not needed. With no AVM, congestion at the checker badly affects performance, to the tune of 57%, when compared to that of a non-fault-tolerant processor. With good marking by AVM, the performance of a reliable processor approaches 95% of that of a processor with no verification. Although instructions can be skipped on a random basis, such an approach reduces the fault coverage. A filter checker with a marking policy correlated with the correctness non-criticality metric, on the other hand, significantly reduces the soft error rate. Finally, we also present results showing the trade-off between performance and reliability.

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: Saugata Chatterjee , Chris Weaver , Todd Austin, Efficient checker processor design, Proceedings of the 33rd annual ACM/IEEE international symposium on Microarchitecture, p.87-97, December 2000, Monterey, California, United States [doi>10.1145/360128.360139]
• 3: M. Franklin, A study of time redundant fault tolerance techniques for superscalar processors, Proceedings of the IEEE International Workshop on Defect and Fault Tolerance in VLSI Systems, p.207, November 13-15, 1995
• 4: Mohamed A. Gomaa , T. N. Vijaykumar, Opportunistic Transient-Fault Detection, Proceedings of the 32nd annual international symposium on Computer Architecture, p.172-183, June 04-08, 2005
• 5: Kumar S, Aggarwal A (2006) Reducing resource redundancy for concurrent error detection techniques in high performance microprocessors. In: Proceedings of the 12th international symposium on high-performance computer architecture, Feb.
• 6: A. Mahmood , E. J. McCluskey, Concurrent Error Detection Using Watchdog Processors-A Survey, IEEE Transactions on Computers, v.37 n.2, p.160-174, February 1988 [doi>10.1109/12.2145]
• 7: Shubhendu S. Mukherjee , Michael Kontz , Steven K. Reinhardt, Detailed design and evaluation of redundant multithreading alternatives, Proceedings of the 29th annual international symposium on Computer architecture, May 25-29, 2002, Anchorage, Alaska
• 8: Shubhendu S. Mukherjee , Christopher Weaver , Joel Emer , Steven K. Reinhardt , Todd Austin, A Systematic Methodology to Compute the Architectural Vulnerability Factors for a High-Performance Microprocessor, Proceedings of the 36th annual IEEE/ACM International Symposium on Microarchitecture, p.29, December 03-05, 2003
• 9: Joydeep Ray , James C. Hoe , Babak Falsafi, Dual use of superscalar datapath for transient-fault detection and recovery, Proceedings of the 34th annual ACM/IEEE international symposium on Microarchitecture, December 01-05, 2001, Austin, Texas
• 10: Reinhardt SK (2005) Using the m5 simulator. ISCA tutorials and workshops, Jun.
• 11: Steven K. Reinhardt , Shubhendu S. Mukherjee, Transient fault detection via simultaneous multithreading, Proceedings of the 27th annual international symposium on Computer architecture, p.25-36, June 2000, Vancouver, British Columbia, Canada
• 12: Rotenberg E (1999) Slipstream processors: improving both performance and fault tolerance. In: Proceedings of the 33rd international symposium on microarchitecture, Jun.
• 13: Michael A. Schuette , John Paul Shen, Processor Control Flow Monitoring Using Signatured Instruction Streams, IEEE Transactions on Computers, v.36 n.3, p.264-276, March 1987 [doi>10.1109/TC.1987.1676899]
• 14: Kevin Skadron , Mircea R. Stan , Wei Huang , Sivakumar Velusamy , Karthik Sankaranarayanan , David Tarjan, Temperature-aware microarchitecture, Proceedings of the 30th annual international symposium on Computer architecture, June 09-11, 2003, San Diego, California
• 15: Jared C. Smolens , Jangwoo Kim , James C. Hoe , Babak Falsafi, Efficient Resource Sharing in Concurrent Error Detecting Superscalar Microarchitectures, Proceedings of the 37th annual IEEE/ACM International Symposium on Microarchitecture, p.257-268, December 04-08, 2004, Portland, Oregon [doi>10.1109/MICRO.2004.19]
• 16: Sundaramoorthy K, Purser Z, Rotenberg E (2000) Slip-stream processors: improving both performance and fault tolerance. In: Proceedings of the 33rd international symposium on microarchitecture, Dec.
• 17: J S Upadhyaya , K K Saluja, A watchdog processor based general rollback technique with multiple retries, IEEE Transactions on Software Engineering, v.12 n.1, p.87-95, Jan. 1986
• 18: T. N. Vijaykumar , Irith Pomeranz , Karl Cheng, Transient-fault recovery using simultaneous multithreading, Proceedings of the 29th annual international symposium on Computer architecture, May 25-29, 2002, Anchorage, Alaska
• 19: Weaver C, Emer J, Mukherjee SS, Reinhardt SK (2004) Characterizing the effects of transient faults on a high-performance processor pipeline. In: Proceedings of the international conference on dependable systems and networks, Jun.
• 20: Joonhyuk Yoo , Manoj Franklin, The Filter Checker: An Active Verification Management Approach, Proceedings of the 21st IEEE International Symposium on on Defect and Fault-Tolerance in VLSI Systems, p.516-524, October 04-06, 2006 [doi>10.1109/DFT.2006.64]

INDEX TERMS

Primary Classification:
  B. Hardware
  B.8 Performance and Reliability
      B.8.1 Reliability, Testing, and Fault-Tolerance

Additional Classification:
  B. Hardware
  B.7 INTEGRATED CIRCUITS
      B.7.1 Types and Design Styles
          Subjects: Microprocessors and microcomputers

  C. Computer Systems Organization
  C.4 PERFORMANCE OF SYSTEMS

General Terms:
Design, Performance, Reliability, Verification

Keywords:
Active verification management, Correctness non-critically, Fault tolerance, Filter checker, Hierarchical verification, Performance