Journal of Shanghai University(Natural Science Edition) ›› 2014, Vol. 20 ›› Issue (2): 180-189.doi: 10.3969/j.issn.1007-2861.2013.07.001

• Computer Engineering and Science • Previous Articles     Next Articles

MPI Programming Based on Ternary Optical Computer in Supercomputer

ZHANG Qian1,2, JIN Yi1,2, SONG Kai1,2,3, GAO Huan1,2   

  1. 1. School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China;
    2. High Performance Computing Center, Shanghai University, Shanghai 200444, China;
    3. School of Information Engineering, East China Jiaotong University, Nanchang 330013, China
  • Online:2014-04-26 Published:2014-04-26

Abstract: An MPI method is proposed to make the ternary optical computer (TOC) node cooperate with other general compute nodes in a cluster supercomputer in an MPI program. The TOC nodes work as servers, running a process to wait for connections. Any MPI process running on CPU works as a client side, using a series of expand instructions with the prefix of SHDX to contact the TOC node. After the TOC node gets contact with the MPI process on the CPU nodes, MPI process sends an operation request and data to the TOC in a connection. Then, TOC exerts the advantages of its reconfigurable processor and high data-bit-width to process the data and sends the results back to the MPI process. This method realizes using TOC on the instruction level. At present, there can be at most 10 TOC nodes in a supercomputer system, and each TOC node opens 8 ports. Future versions may break these restrictions. Experimental results show feasibility and practicality of the method.

Key words: MPI program, supercomputer, ternary optical computer (TOC)

CLC Number: