Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

Pipelining allows processors to exploit parallelism. Unfortunately, critical loops---pieces of logic that must evaluate in a single cycle to meet IPC (Instructions Per Cycle) goals---prevent deeper pipelining. In today's processors, one of these loops is the instruction scheduling (wakeup and select) logic [10]. This paper describes a technique that pipelines this loop by breaking it into two smaller loops: a critical, single-cycle loop for wakeup; and a non-critical, potentially multi-cycle, loop for select. For the 12 SPECint*2000 benchmarks, a machine with two-cycle select logic (i. e., three-cycle scheduling logic) using this technique has an average IPC 15% greater than a machine with three-cycle pipelined conventional scheduling logic, and an IPC within 3% of a machine of the same pipeline depth and one-cycle (ideal) scheduling logic. Since select accounts for more than half the scheduling latency [10], this technique could significantly increase clock frequency while having minimal impact on IPC.

REFERENCES

• 1: Ramon Canal , Antonio González, A low-complexity issue logic, Proceedings of the 14th international conference on Supercomputing, p.327-335, May 08-11, 2000, Santa Fe, New Mexico, United States [doi>10.1145/335231.335263]
• 2: Anantha P. Chandrakasan , William J. Bowhill , Frank Fox, Design of High-Performance Microprocessor Circuits, Wiley-IEEE Press, 2000
• 3: J. A. Farrell and T. C. Fischer. Issue logic for a 600-MHz Out-of-Order execution microprocessor. IEEE Journal of Solid-State Circuits, 33(5), 1998.
• 4: Dana S. Henry , Bradley C. Kuszmaul , Gabriel H. Loh , Rahul Sami, Circuits for wide-window superscalar processors, Proceedings of the 27th annual international symposium on Computer architecture, p.236-247, June 2000, Vancouver, British Columbia, Canada
• 5: G. Hinton, D. Sager, M. Upton, D. Boggs, D. Carmean, A. Kyker, and P. Roussel. The microarchitecture of the Pentium 4 processor. Intel Technical Journal, Feb. 2001. Q1 2001 Issue.
• 6: Intel Corporation. IA-32 Intel Architecture Software Developer's Manual Volume 1: Basic Architecture, 2001.
• 7: Pierre Michaud , André Seznec, Data-Flow Prescheduling for Large Instruction Windows in Out-of-Order Processors, Proceedings of the 7th International Symposium on High-Performance Computer Architecture, p.27, January 20-24, 2001
• 8: Enric Morancho , José María Llabería , Àngel Olivé, Recovery Mechanism for Latency Misprediction, Proceedings of the 2001 International Conference on Parallel Architectures and Compilation Techniques, p.118, September 08-12, 2001
• 9: S. Önder , R. Gupta, Superscalar Execution with Direct Data Forwarding, Proceedings of the 1998 International Conference on Parallel Architectures and Compilation Techniques, p.130, October 12-18, 1998
• 10: Subbarao Palacharla , Norman P. Jouppi , J. E. Smith, Complexity-effective superscalar processors, Proceedings of the 24th annual international symposium on Computer architecture, p.206-218, June 01-04, 1997, Denver, Colorado, United States
• 11: Jared Stark , Mary D. Brown , Yale N. Patt, On pipelining dynamic instruction scheduling logic, Proceedings of the 33rd annual ACM/IEEE international symposium on Microarchitecture, p.57-66, December 2000, Monterey, California, United States [doi>10.1145/360128.360136]
• 12: S. Weiss and J. E. Smith. Instruction issue logic in pipelined supercomputers. IEEE Transactions on Computers, C-33(11):1013-1022, Nov. 1984.
• 13: Kenneth C. Yeager, The MIPS R10000 Superscalar Microprocessor, IEEE Micro, v.16 n.2, p.28-40, April 1996 [doi>10.1109/40.491460]