According to the most recent version of the Top500 list released this week, "Avoca," the 65,536-core IBM BlueGene/Q supercomputer owned by Australia's Victorian Life Sciences Computation Initiative, is still the fastest life science supercomputer in the world.
The system, which clocks in at 715.6 teraflops — up from 690.2 teraflops last year — is now No. 48 on the list of the world's fastest supercomputers, down from the No. 39 spot it held in the June version of the twice-yearly ranking.
Only one other life science system from the June list is still ranked. It's a 17,856-core, 125.8-teraflop Cray system named Beagle at the University of Chicago's Computation Institute. The system is now ranked at No. 455 down from No. 331 on the previous list.
Two other systems that were on the earlier list have been dropped as they did not meet the 117.8 Tflop/s entry requirement for November rankings. These include the 16,128-core, 100.6-teraflop Shirokane2 system at the University of Tokyo's Human Genome Center, ranked No. 468 on the June list; and Chinook, a 97.1-teraflop, 18,176-core HP cluster at Pacific Northwest National Laboratory’s Environmental Molecular Sciences Laboratory, listed at No. 492 earlier this year.
(see Table 1, below, for details of the life science systems on the list).
Supercomputing trends
China's Tianhe-2, or Milky Way-2, is still the fastest computer on the 42nd edition of the Top500 list — it held the same position on the June list after taking over the top spot from Titan, a Cray XK7 system installed at the US Department of Energy's Oak Ridge National Laboratory. The supercomputer, which was developed by China's National University of Defense Technology, achieved 33.86 petaflops on the Linpack benchmark used to assess the performance of the Top500 systems.
Tianhe-2, which will be deployed at the National Supercomputer Center in Guangzho, China, by the end of the year, has 16,000 nodes, each with two Intel Xeon IvyBridge processors and three Xeon Phi processors for a combined total of 3.12 million computing cores.
A total of 53 systems on the Top500 list used some sort of accelerator technology, down from 54 in June. The majority of these — 38 in total — use Nvida chips, two use ATI Radeon, and 13 systems use Intel MIC technology.
Furthermore, systems with multi-core processors continue to dominate the list, with 94 percent of systems in the current list using processors with six or more cores and 75 percent using processors with eight or more cores.
Intel continues to provide processors for most high-performance computing systems. Its chips are installed in about 82 percent of the current Top500 systems up from 80 percent of systems on this summer's list.
Meanwhile, HP has the most systems ranked in the current version of the list. It has 196 systems (39 percent) compared to 188 systems (38 percent) in June. IBM has 164 systems (33 percent) compared to 160 systems (32 percent) from six months ago. Cray remains third on the list with a little under 10 percent of systems.
(see Table 2, below, for details of manufacturer rankings)
The complete Top500 ranking is available here.
