Hardware system of the earth simulator

  • Authors:
  • Shinichi Habata;Kazuhiko Umezawa;Mitsuo Yokokawa;Shigemune Kitawaki

  • Affiliations:
  • 4th Engineering Department, Computers Division, NEC Corporation, 1st Computers Operations Unit, 1-10, Nisshin-cho, Fuchu, Tokyo 183-8501, Japan;4th Engineering Department, Computers Division, NEC Corporation, 1st Computers Operations Unit, 1-10, Nisshin-cho, Fuchu, Tokyo 183-8501, Japan;Grid Technology Research Center, National Institute Advanced Industrial Science and Technology, Umezono 1-1-1, Tsukuba 304-3568, Japan;Earth Simulator Center, Japan Agency for Marine-Earth Science and Technology, 3173-25, Showa-machi, Kanazawa-ku. Yokohama 236-60001, Japan

  • Venue:
  • Parallel Computing
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

The Earth Simulator (ES), developed under the Japanese government's initiative "Earth Simulator project", is a highly parallel vector supercomputer system. In this paper, an overview of ES, its architectural features, hardware technology and the result of performance evaluation are described.In May 2002, the ES was acknowledged to be the most powerful computer in the world: 35.86 teraflop/s for the LINPACK HPC benchmark and 26.58 teraflop/s for an atmospheric general circulation code (AFES). Such a remarkable performance may be attributed to the following three architectural features; vector processor, shared-memory and high-bandwidth non-blocking interconnection crossbar network.The ES consists of 640 processor nodes (PN) and an interconnection network (IN), which are housed in 320 PN cabinets and 65 IN cabinets. The ES is installed in a specially designed building, 65m long, 50m wide and 17m high. In order to accomplish this advanced system, many kinds of hardware technologies have been developed, such as a high-density and high-frequency LSI, a high-frequency signal transmission, a high-density packaging, and a high-efficiency cooling and power supply system with low noise so as to reduce whole volume of the ES and total power consumption.For highly parallel processing, a special synchronization means connecting all nodes, Global Barrier Counter (GBC), has been introduced.