Abstract.
Simultaneous Multithreading (SMT) tolerates latency by executing instructions from multiple threads. If a thread is stalled, resources can be used by other threads. However, fetch stall conditions caused by multi-cycle branch predictors prevent SMT to achieve all its potential performance, since the flow of fetched instructions is halted.
This paper proposes and evaluates solutions to deal with the branch predictor delay on SMT. Our contribution is two-fold: we describe a decoupled implementation of the SMT fetch unit, and we propose an inter-thread pipelined branch predictor implementation. These techniques pro-ve to be effective for tolerating the branch predictor access latency.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Agarwal, V., Hrishikesh, M., Keckler, S., Burger, D.: Clock rate versus IPC: The end of the road for conventional microarchitectures. In: Procs. of the 27th Intl. Symp. on Computer Architecture (June 2000)
Ho, R., Mai, K., Horowitz, M.: The future of wires. In: Proceedings of the IEEE (April 2001)
Hrishikesh, M., Burger, D., Keckler, S., Shivakumar, P., Jouppi, N., Farkas, K.: The optimal logic depth per pipeline stage is 6 to 8 FO4 inverter delays. In: Procs. of the 29th Intl. Symp. on Computer Architecture (May 2002)
Jacobson, Q., Rottenberg, E., Smith, J.: Path-based next trace prediction. In: Procs. of the 30th Intl. Symp. on Microarchitecture (December 1997)
Jiménez, D., Keckler, S., Lin, C.: The impact of delay on the design of branch predictors. In: Procs. of the 33rd Intl. Symp. on Microarchitecture (December 2000)
Jiménez, D.: Reconsidering complex branch predictors. In: Procs. of the 9th Intl. Conf. on High Performance Computer Architecture (February 2003)
Michaud, P., Seznec, A., Uhlig, R.: Trading conflict and capacity aliasing in conditional branch predictors. In: Procs. of the 24th Intl. Symp. on Computer Architecture (June 1997)
Ramirez, A., Santana, O.J., Larriba-Pey, J.L., Valero, M.: Fetching instructions streams. In: Procs. of the 35th Intl. Symp. on Microarchitecture (November 2002)
Reinman, G., Calder, B., Austin, T.: Optimizations enabled by a decoupled front-end architecture. IEEE Trans. on Computers 50(4), 338–355 (2001)
Seznec, A., Fraboulet, A.: Effective ahead pipelining of instruction block address generation. In: Procs. of the 30th Intl. Symp. on Computer Architecture (June 2003)
Sherwood, T., Perelman, E., Calder, B.: Basic block distribution analysis to find periodic behavior and simulation points in applications. In: Procs. of the Intl. Conf. on Parallel Architectures and Compilation Techniques (September 2001)
Shivakumar, P., Jouppi, N.: CACTI 3.0, an integrated cache timing, power and area model. TR 2001/2, Compaq WRL (August 2001)
Tullsen, D.: Simulation and modeling of a simultaneous multithreading processor. In: 22nd Computer Measurement Group Conference (December 1996)
Tullsen, D., Eggers, S., Emer, J., Levy, H., Lo, J., Stamm, R.: Exploiting choice: Instruction fetch and issue on an implementable simultaneous multithreading processor. In: Procs. of the 23rd Intl. Symp. on Computer Architecture (May 1996)
Tullsen, D., Eggers, S., Levy, H.: Simultaneous multithreading: Maximizing onchip parallelism. In: Procs. of the 22nd Intl. Symp. on Computer Architecture (June 1995)
Yamamoto, W., Nemirovsky, M.: Increasing superscalar performance through multistreaming. In: Procs. of the Intl. Conf. on Parallel Architectures and Compilation Techniques (June 1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Falcón, A., Santana, O.J., Ramírez, A., Valero, M. (2003). Tolerating Branch Predictor Latency on SMT. In: Veidenbaum, A., Joe, K., Amano, H., Aiso, H. (eds) High Performance Computing. ISHPC 2003. Lecture Notes in Computer Science, vol 2858. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39707-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-39707-6_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20359-9
Online ISBN: 978-3-540-39707-6
eBook Packages: Springer Book Archive