The MINC (Multistage Interconnection Network with Cache control mechanism) chip

Although bus connected multiprocessors have been widely used as high-end workstations or servers, the number of connected processors is strictly limited by the maximum bandwidth of the shared bus. Instead of them, a switch connected multiprocessor which uses a crossbar or Multistage Interconnection Networks (MINs) for connecting processors and memory modules is a hopeful candidate. However, in such a system, a snoop cache technique in bus connected multiprocessors cannot be used, and consistency problems must be solved for providing the cache memory between a processor and the switch. To address this problem, hardware approaches by making the best use of advanced VLSI technology have been proposed. However, traditional methods require a large memory outside the switching element and it causes not only a large additional hardware but also the extra latency by accessing the outside memory. Moreover, the complicated MIN with cache or directory must also treat data packet which should be transferred quickly. In order to solve these problems, we proposed the MINC (MIN with Cache control mechanism). In the MINC, the MIN which only transfers a part of the address and cache coherent messages is separated from the data transfer network, and pushed into an LSI chip called the MINC chip. The coherent control is done based on the directory using the reduced Hierarchical Bit-map Directory scheme (RHBD). In order to reduce unnecessary packets, the pruning cache which is a small cache enough to implement inside the chip is introduced in the MINC chip.

[1]  Hideharu Amano,et al.  An LSI implementation of the simple serial synchronized multistage interconnection network , 1997, Proceedings of ASP-DAC '97: Asia and South Pacific Design Automation Conference.

[2]  Hiroshi Nakashima,et al.  Overview of the JUMP-1, an MPP prototype for general-purpose parallel computations , 1994, Proceedings of the International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN).

[3]  Laxmi N. Bhuyan,et al.  Performance and Reliability of the Multistage Bus Network , 1994, 1994 International Conference on Parallel Processing Vol. 1.

[4]  Anoop Gupta,et al.  The Stanford FLASH Multiprocessor , 1994, ISCA.

[5]  P. Stenström,et al.  A cache consistency protocol for multiprocessors with multistage networks , 1989, ISCA.

[6]  Hideharu Amano,et al.  Hierarchical Bit-Map Directory Schemes on the RDT Interconnection Network for a Massively Parallel Processor JUMP-1 , 1995, ICPP.

[7]  Laxmi N. Bhuyan,et al.  Design and Analysis of Cache Coherent Multistage Interconnection Networks , 1993, IEEE Trans. Computers.

[8]  Anant Agarwal,et al.  Software-extended coherent shared memory: performance and cost , 1994, ISCA '94.

[9]  J. Robert Heath,et al.  Classification Categories and Historical Development of Circuit Switching Topologies , 1983, CSUR.

[10]  Kalidou Gaye,et al.  SSS (Simple Serial Synchronized)-MIN: A Novel Multi Stage Interconnection Architecture for Multiprocessors , 1992, IFIP Congress.

[11]  J. Zahorjan,et al.  Introducing memory into the switch elements of multiprocessor interconnection networks , 1989, ISCA '89.

[12]  Toshihiro Hanawa,et al.  MINC: Multistage Interconnection Network with Cache Control Mechanism , 1995 .

[13]  Stein Gjessing,et al.  Distributed-directory scheme: scalable coherent interface , 1990, Computer.

[14]  Alexander V. Veidenbaum,et al.  A cache coherence scheme with fast selective invalidation , 1988, ISCA '88.

[15]  Alexander V. Veidenbaum,et al.  A Compiler-Assisted Cache Coherence Solution for Multiprcessors , 1986, ICPP.

[16]  Anoop Gupta,et al.  The Stanford Dash multiprocessor , 1992, Computer.