Complexity-effective superscalar processors

ABSTRACT

The performance tradeoff between hardware complexity and clock speed is studied. First, a generic superscalar pipeline is defined. Then the specific areas of register renaming, instruction window wakeup and selection logic, and operand bypassing are analyzed. Each is modeled and Spice simulated for feature sizes of 0.8µm, 0.35µm, and 0.18µm. Performance results and trends are expressed in terms of issue width and window size. Our analysis indicates that window wakeup and selection logic as well as operand bypass logic are likely to be the most critical in the future.A microarchitecture that simplifies wakeup and selection logic is proposed and discussed. This implementation puts chains of dependent instructions into queues, and issues instructions from multiple queues in parallel. Simulation shows little slowdown as compared with a completely flexible issue window when performance is measured in clock cycles. Furthermore, because only instructions at queue heads need to be awakened and selected, issue logic is simplified and the clock cycle is faster --- consequently overall performance is improved. By grouping dependent instructions together, the proposed microarchitecture will help minimize performance degradation due to slow bypasses in future wide-issue machines.

REFERENCES

• 1: Pritpal S. Ahuja , Douglas W. Clark , Anne Rogers, The performance impact of incomplete bypassing in processor pipelines, Proceedings of the 28th annual international symposium on Microarchitecture, p.36-45, November 29-December 01, 1995, Ann Arbor, Michigan, United States
• 2: C. Asato, R. Montoye, J. Gmuender, E. W. Simmons, A. Ike, and J. Zasio. A 14-port 3.Sns ll6-word 64b Read-Renaming Register F'de. In 1995 IEEE International Sold-State Circuits Conference Digest of Technical Papers, pages 104-105, February 1995.
• 3: Mark T. Bohr. Interconnect Sealing - The Real Limiter to High Performance ULSI. in 1995 International Electron Devices Meeting Technical Digest, pages 241-244, 1995.
• 4: Doug Burger, Todd M. Austin, and Steve Bennett. Evaluating Future Microprocessors: The Simplesealar Tool Set. Technical Report CS- TR-96-1308 (Available from http'.//www.cs.wisc.edtt/trs.html), University of Wisconsin-Madison, July 1996.
• 5: Michael Butler , Yale Patt, An investigation of the performance of various dynamic scheduling techniques, Proceedings of the 25th annual international symposium on Microarchitecture, p.1-9, December 01-04, 1992, Portland, Oregon, United States
• 6: Keith I. Farkas , Paul Chow , Norman P. Jouppi, Register File Design Considerations in Dynamically Scheduled Processors, Proceedings of the 2nd IEEE Symposium on High-Performance Computer Architecture, p.40, February 03-07, 1996
• 7: Linley Gwennap. Speed Kills? Not for RISe Processors, Micropro. cessor Report, 7(3):3, March 1993.
• 8: Linley Gwennap. HAL Reveals Multichip SPARC Processor, Micro. processor Report, 9(3), March 1995.
• 9: Linley Gwermap. Intel's P6 Uses Deeoupled Supersealar Design, Microprocessor Report, 9(2), February 1995.
• 10: Jim Keller. The 21264: A Supersealar Alpha Processor with Out-of- Order Execution, October 1996. 9th Annual Microprocessor Forum, San Jose, California.
• 11: Gregory A. Kemp and Manoj Franklin, PEWs: A Decentralized Dynamic Scheduler for ILP Processing. In Proceedings of the lnterna. tional Conference on Parallel Processing, volume I, pages 239-246, 1996.
• 12: Ashok Kumar. The HP-PA8000 RISC CPU: A High Performance Outof-Order Processor. In Proceedings of the Hot Chips VIII, pages 9-20, August 1996.
• 13: Scott MeFarling. Combining Branch Predictors. DEC WRL Technical Note TN-36, DEC Western Research Laboratory, 1993.
• 14: Meta-Software inc. HSpice User's Manual, June 1987,
• 15: Subbarao Palaeharla, Norman P. Jouppl, and James E. Smith, Quantifying the Complexity of Supersealar Processors. Technical Report CS- TR-96-1328 (Available from http'J/www.es.wise.edu/trs,html), University of Wisconsin-Madison, November 1996.
• 16: S. Peter Song , Marvin Denman , Joe Chang, The PowerPC 604 RISC microprocessor, IEEE Micro, v.14 n.5, p.8-17, October 1994 [doi>10.1109/MM.1994.363071]
• 17: N. Vasseghi et al. 200 MHz Supersealar RISC Processor Circuit Design Issues. in 1996 IEEE International Sold-State Circuits Conference Digest of Technical Papers, pages 356--357, February 1995,
• 18: Tomohisa Wada, Suresh Rajan, and Stevea A, Przybylski, An Analytical Access Tune Model for On-Chip Cache Memories. IEEE Journal of Solid.State Circuits, 27(8):1147-1156, August 1992,
• 19: Neil H. E. Weste , Kamran Eshraghian, Principles of CMOS VLSI design: a systems perspective, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1985
• 20: Nell C. Wilhelm. Why Wire Delays Will No Longer Scale for VLSI Chips. Technical Report SMI.,I TR-95-44, Sun Mierosystems Laboratories, August 1995.
• 21: Steven J. E. Wilton and Norman P. Jouppi. An Enhanced Access and Cycle Time Model for On-Chip Caches. Technical Report 93/5, DEC Western Research Laboratory, July 1994.
• 22: 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:
  F. Theory of Computation
  F.1 COMPUTATION BY ABSTRACT DEVICES
      F.1.2 Modes of Computation
          Subjects: Parallelism and concurrency

Additional Classification:
  C. Computer Systems Organization
  C.1 PROCESSOR ARCHITECTURES

General Terms:
Design, Measurement, Performance, Theory