Improving Multiprocessor Performance with Coarse-Grain Coherence Tracking

To main coherence in conventional shared-memory multiprocessor systems, processors first check other proessors' caches before obtaining data from memory. This coherence checking adds latency to memory requests and leads to large amounts of interconnect traffic in broadcast-based systems. Our results for a set of commercial, scientific and multiprogrammed workloads show that on average 67% (and up to 94%) of broadcasts are unnecessary. Coarse-Grain Coherence Tracking is a new technique that supplements a conventional coherence mechanism and optimizes the performance of coherence enforcement. The Coarse-Grain Coherence mechanism monitors the coherence status of large regions of memory, and uses that information to avoid unnecessary broadcasts. Coarse-Grain Coherence Tracking is shown to eliminate 55-97% of the unnecessary broadcasts, and improve performance by 8.8% on average (and up to 21.7%).

[1]  Milo M. K. Martin,et al.  Timestamp snooping: an approach for extending SMPs , 2000, ASPLOS.

[2]  Jeffrey B. Rothman,et al.  The pool of subsectors cache design , 1999, ICS '99.

[3]  Balaram Sinharoy,et al.  POWER4 system microarchitecture , 2002, IBM J. Res. Dev..

[4]  Babak Falsafi,et al.  JETTY: filtering snoops for reduced energy consumption in SMP servers , 2001, Proceedings HPCA Seventh International Symposium on High-Performance Computer Architecture.

[5]  David A. Wood,et al.  Dynamic self-invalidation: reducing coherence overhead in shared-memory multiprocessors , 1995, Proceedings 22nd Annual International Symposium on Computer Architecture.

[6]  John S. Liptay,et al.  Structural Aspects of the System/360 Model 85 II: The Cache , 1968, IBM Syst. J..

[7]  Per Stenström,et al.  TLB and snoop energy-reduction using virtual caches in low-power chip-multiprocessors , 2002, ISLPED '02.

[8]  Cathy May,et al.  The PowerPC Architecture: A Specification for a New Family of RISC Processors , 1994 .

[9]  Milo M. K. Martin,et al.  Token Coherence: decoupling performance and correctness , 2003, 30th Annual International Symposium on Computer Architecture, 2003. Proceedings..

[10]  Paul F. Reynolds,et al.  Isotach Networks , 1997, IEEE Trans. Parallel Distributed Syst..

[11]  A. Charlesworth.  The Sun Fireplane System Interconnect , 2001, ACM/IEEE SC 2001 Conference (SC'01).

[12]  Alan Jay Smith,et al.  Experimental evaluation of on-chip microprocessor cache memories , 1984, ISCA 1984.

[13]  Mikko H. Lipasti,et al.  Power-Efficient Cache Coherence , 2004 .

[14]  A. Seznec,et al.  Decoupled sectored caches: conciliating low tag implementation cost and low miss ratio , 1994, Proceedings of 21 International Symposium on Computer Architecture.

[15]  Mikko H. Lipasti,et al.  Precise and Accurate Processor Simulation , 2002 .

[16]  André Seznec,et al.  Decoupled sectored caches: conciliating low tag implementation cost , 1994, ISCA '94.

[17]  Milo M. K. Martin,et al.  Using destination-set prediction to improve the latency/bandwidth tradeoff in shared-memory multiprocessors , 2003, ISCA '03.

[18]  Thomas J. LeBlanc,et al.  Adjustable block size coherent caches , 1992, ISCA '92.

[19]  Alan Jay Smith,et al.  A class of compatible cache consistency protocols and their support by the IEEE futurebus , 1986, ISCA '86.

[20]  Balaram Sinharoy,et al.  IBM Power5 chip: a dual-core multithreaded processor , 2004, IEEE Micro.

[21]  Laxmi N. Bhuyan,et al.  A dynamic cache sub-block design to reduce false sharing , 1995, Proceedings of ICCD '95 International Conference on Computer Design. VLSI in Computers and Processors.

[22]  Milo M. K. Martin,et al.  Simulating a $ 2 M Commercial Server on a $ 2 K PC T , 2001 .

[23]  Anoop Gupta,et al.  Two Techniques to Enhance the Performance of Memory Consistency Models , 1991, ICPP.

[24]  Andreas Moshovos.  RegionScout: Exploiting Coarse Grain Sharing in Snoop-Based Coherence , 2005, ISCA 2005.