Muhamed F. Mudawar
ABSTRACT
The cache hierarchy design in existing SMT and superscalar processors is optimized for latency, but not for band-width. The size of the L1 data cache did not scale over the past decade. Instead, larger unified L2 and L3 caches were introduced. This cache hierarchy has a high overhead due to the principle of containment. It also has a complex design to maintain cache coherence across all levels. Furthermore, this cache hierarchy is not suitable for future large-scale SMT processors, which will demand high bandwidth instruction and data caches with a large number of ports.This paper suggests the elimination of the cache hierarchy and replacing it with one-level caches for instruction and data. Multiple instruction caches can be used in parallel to scale the instruction fetch bandwidth and the overall cache capacity. A one-level data cache can be split into a number of block-interleaved cache banks to serve multiple memory requests in parallel. An interconnect is used to connect the data cache ports to the different cache banks, thus increasing the data cache access time. This paper shows that large-scale SMTs can tolerate long data cache hit times. It also shows that small line buffers can enhance the performance and reduce the required number of ports to the banked data cache memory.
- T. Austin and G. Sohi, "High-Bandwidth Address Translation for Multiple-Issue Processors", Proceedings of the 23rd Annual International Symposium on Computer Architecture, May 1996, pages 147--157. Google Scholar
Digital Library
- J. Edmondson et al, "Internal Organization of the Alpha 21164 a 300-MHz 64-bit Quad-issue CMOS RISC Microprocessor", Digital Technical Journal, Special 10th Anniversary Issue, Vol. 7, No. 1, 1995, pages 119--135. Google ScholarDigital Library
- "Hyper-Threading Technology", Intel Technical Journal, vol. 6, no. 1, February 2002.Google Scholar
- T. Juan, J. Navarro, and O. Temam, "Data Caches for Superscalar Processors", Proceedings of the 11th International Conference on Supercomputing, July 1997, pages 60--67. Google ScholarDigital Library
- R. Kessler, "The Alpha 21264 Microprocessor", IEEE Micro, March-April 1999, pages 24--36. Google ScholarDigital Library
- C. Kim, D. Burger, and S. Keckler, "An Adaptive, Non-Uniform Cache Structure for Wire-Dominated On-Chip Caches", Proceedings of the 10th International Conference on Architectural Support for programming Languages and Operating Systems, October 2002, pages 211--222. Google ScholarDigital Library
- D. Koufaty and D. Marr, "Hyperthreading Technology in the Netburst Microarchitecture", IEEE Micro, March-April 2003, pages 56--65. Google ScholarDigital Library
- L. Li, N. Vijaykrishnan, M. Kandemir, M. J. Irwin and I. Kadayif, "CCC: Crossbar Connected Caches for Reducing Energy Consumption of On-Chip Multiprocessors", Proceedings of the Euromicro Symposium on Digital System Design, September 2003, pages 41--48. Google ScholarDigital Library
- J. Lo, S. Eggers, J. Emer, H. Levy, R. Stamm, and D. Tullsen, "Converting Thread-Level Parallelism to Instruction-Level Parallelism via Simultaneous Multithreading", ACM Transactions on Computer Systems, vol.15, no.3, August 1997, pages 322--354. Google ScholarDigital Library
- M. D. Powell, A. Agarwal, T. N. Vijaykumar, B. Falsafi, and K. Roy, "Reducing Set-Associative Cache Energy via Way-Prediction and Selective Direct-Mapping", Proceedings of the 34th Annual International Symposium on Microarchitecture, December 2001, Austin, Texas, pages 54--65. Google ScholarDigital Library
- J. A. Rivers, G. S. Tyson, E. S. Davidson, and T. M. Austin "On High-Bandwidth Data Cache Design for Multi-Issue Processors", Proceedings of the 30th Annual International Symposium on Microarchitecture, December 1997, pages 46--56. Google ScholarDigital Library
- J. Tseng and K. Asanovic, "Banked Multiported Register Files for High-Frequency Superscalar Microprocessors", Proceedings of the 30th Annual International Symposium on Computer Architecture, June 2003, pages 62--71. Google ScholarDigital Library
- D. Tullsen and J. Brown, "Handling Long-Latency Loads in a Simultaneous Multithreading Processor", Proceedings of the 34th Annual International Symposium on Microarchitecture, December 2001, pages 318--327. Google ScholarDigital Library
- D. Tullsen, S. Eggers, J. Emer, H. Levy, J. Lo, and R. Stamm, "Exploiting Choice: Instruction Fetch and Issue on an Implementable Simultaneous Multithreading Processor", Proceedings of the 23rd Annual International Symposium on Computer Architecture, May 1996, pages 191--202. Google ScholarDigital Library
- D. Tullsen, S. Eggers, H. Levy, "Simultaneous Mutithreading: Maximizing On-Chip Parallelism", Proceedings of the 22nd Annual International Symposium on Computer Architecture, June 1995, pages 392--403. Google ScholarDigital Library
- K. Wilson, K. Olukotun, and M. Rosenblum, "Increasing Cache Port Efficiency for Dynamic Superscalar Processors", Proceedings of the 23rd Annual International Symposium on Computer Architecture, May 1996, pages 147--157. Google ScholarDigital Library
- K. Wilson and K. Olukotun, "Designing High Bandwidth On-Chip Caches", Proceedings of the 24th Annual International Symposium on Computer Architecture, June 1997, pages 121--132. Google ScholarDigital Library
Recommendations
An efficient cache design for scalable glueless shared-memory multiprocessors
CF '06: Proceedings of the 3rd conference on Computing frontiersTraditionally, cache coherence in large-scale shared-memory multiprocessors has been ensured by means of a distributed directory structure stored in main memory. In this way, the access to main memory to recover the sharing status of the block is ...
A composite and scalable cache coherence protocol for large scale CMPs
ICS '11: Proceedings of the international conference on SupercomputingThe number of on-chip cores of modern chip multiprocessors (CMPs) is growing fast with technology scaling. However, it remains a big challenge to efficiently support cache coherence for large scale CMPs. The conventional snoopy and directory coherence ...
Comments