π has been abaliable since 6 May, 2016 - 9:00
News & Notices
Introduction of π

The CHPC’s supercomputer, which is currently the fastest supercomputer among the universities in China, is named π. π, with a peak performance of 263 TFLOPS, ranked 158th of the TOP500 supercomputers in June 2013.

Why “π”?

  • π means parallelism in Greek;
  • π is an infinite non-repeating decimal, signifying the start of humans exploring the infiniteness;
  • The accurate calculation of π is a classic example of humans solving scientific problems with computers;
  • π can be visually regarded as a combination of J and T, which is the abbreviation of Shanghai Jiao Tong University.

Here is a brief look at the facilities.

Performance 196/263 Tflops
CPU 830 Intel SandyBridge E5-2670
GPU 100 Nvidia Kepler K20
MIC 10 Intel Xeon Phi 5110P
Interconnection Mellanox IB FDR 56Gbps
Parallel File Storage DDN SFA12K 720TB with Lustre
SSD 80 Intel SSD 400G
Cooling System Rittal Liquid

π utilizes a “CPU+GPU+MIC+FAT” hybrid architecture, with 332 CPU nodes, 50 GPU nodes, 5 MIC nodes and 20 FAT nodes. In comparison with pure CPU computing architecture, hybrid architecture is much more energy-efficient and can provide greater computational capabilities in some applications. π is also supported by a high-speed Infiniband 56G FDR network and 720TB shared storage system, which enable the carriage of data-intensive applications.