Scalable Instruction-Level Parallelism
This paper presents a model for instruction-level distributed computing that allows the implementation of scalable chip multiprocessors. Based on explicit microthreading it serves as a replacement for out-of-order instruction issue; it defines the model and explores implementations issues. The model results in a fully distributed implementation in which data is distributed to one register file per processor, which is scalable as the number of ports in each register file is constant. The only component with less than ideal scaling properties is the the switching network between processors.
KeywordsSwitching Network Dependency Distance Instruction Issue Main Thread Issue Width
Unable to display preview. Download preview PDF.
- 1.Peterson, R.P., et al.: Design of an 8-wide superscalar RISC microprocessor with simultaneous multithreading, ISSC Digest and Visuals Supplement (2002)Google Scholar
- 3.Par, I., Powell, M., Vijaykumar, T.: Reducing register ports for higher speed and lower energy. In: Proc. 35th annual ACM/IEEE international symposium on Microarchitecture, pp. 171–182. ACM, New York (2002) ISBN ISSN:1072-4451 , 0-7695-1859-1Google Scholar
- 6.Gwennap, L. (1997) DanSoft develops VLIWdesign. Microproc. Report, 11, 2, February 17 (1822)Google Scholar
- 7.Solihin, Y., Lee, J., Torrellas, J.: Correlation Prefetching with a User-Level Memory Thread. IEEE Trans. on Parallel and Distributed Systems 14(6) (2003)Google Scholar
- 8.Zilles, C., Sohi, G.: Execution-based prediction using speculative slices. In: Proc. Intl. Symposium on Computer Architecture (2001)Google Scholar
- 9.Burger, D., Goodman, J.R.: Billion-transistor architectures: there and back again. IEEE Computer 37(3), 22–28 (2004)Google Scholar
- 10.Jesshope, C.R.: Microthreading, a model for distributed instruction-level concurrency, submitted to Parallel Processing Letters, (2004), on-line at http://www2.dcs.hull.ac.uk/people/csscrj/papers.html