CELLE, Germany; BERKELEY, Calif.; and KNOXVILLE, Tenn.— For the sixth consecutive time, Tianhe-2, a supercomputer developed by China’s National University of Defense Technology, has retained its position as the world’s No. 1 system, according to the 46th edition of the twice-yearly TOP500 list of the world’s most powerful supercomputers. Overall, change at the top of the list is again minor, with only two new systems in the Top 10 -- the Trinity supercomputer built by Cray and jointly deployed by the Department of Energy’s (DOE) Los Alamos and Sandia national laboratories, and the Hazel-Hen system built by Cray and installed at the HLRS - Höchstleistungsrechenzentrum Stuttgart in Germany.
In the bigger picture, China nearly tripled the number of systems on the latest list, while the number of systems in the United States has fallen to the lowest point since the TOP500 list was created in 1993. China is also carving out a bigger share as a manufacturer of high performance computers with multiple Chinese manufacturers becoming more active in this field.
Tianhe-2, which means Milky Way-2, led the list with a performance of 33.86 petaflop/s (quadrillions of calculations per second or Pflop/s) on the Linpack benchmark. Keeping its hold on the No. 2 spot is Titan, a Cray XK7 system installed at DOE’s Oak Ridge National Laboratory. Titan, the top system in the United States and one of the most energy-efficient systems on the list, achieved 17.59 petaflop/s on the Linpack benchmark.
The only new entries in the Top 10 supercomputers on the latest list are Trinity at No. 6 and Hazel-Hen at No. 8. Trinity is a Cray XC system which has 301,056 cores and achieved 8.1 Pflops/s. Trinity is managed and operated by Los Alamos National Laboratory and Sandia National Laboratories under the Alliance for Computing at Extreme Scale (ACES) partnership. Hazel-Hen is also a Cray XC system installed in Germany at the HLRS - Höchstleistungsrechenzentrum Stuttgart -- and features 185,088 cores and achieved 5.6 Pflop/s.
Six of the Top 10 systems were installed in 2011 or 2012, Tianhe-2 in 2013 and only Trinity, Hazel-Hen, and Shaheen II in Saudi Arabia were installed in 2015. This low level of turnover among the top supercomputers reflects a slowing trend that began in 2008.
A detailed analysis of the latest TOP500 list will be presented Tuesday, Nov. 17, at the SC15 conference on high performance computing and networking in Austin, Texas. At that time, the full list will also be published at TOP500.org.
Among the significant changes to this list from the July 2015 list is the sharp decline in the number of systems in the United States, now at 200. This down from 231 in July and is the lowest number of systems installed in the U.S. since the list was started in 1993.
The European share has fallen to 108 systems compared to 141 on the last list and is now lower than the Asian share, which has risen to 173 systems, up from 107 last time.
In Asia, China made a great leap to 109 systems, nearly three times the 37 the country had on the previous list. Japan’s share dropped slightly to 36 systems, compared to 40 last time.
China’s role in high performance computing is also increasing in the manufacturing arena, with Lenovo now being counted among the vendors of systems on the TOP500 list. Following its acquisition of IBM’s x86 business last year, Lenovo now has 25 systems in list, up from just three systems on the July 2015 list. Some systems that were previously listed as IBM are now labeled as both IBM/Lenovo (nine systems) and Lenovo/IBM (five systems). Sugon, a vendor from China, has overtaken IBM in the system category with 49 systems.
At the same time, Cray Inc., a company long associated with supercomputers, is on a resurgence and emerges in the latest list as the clear leader in performance, claiming a 24.9 percent share of installed total performance (up from 24 percent). IBM takes the second spot with a 14.9 percent share, down from 23 percent last July. Hewlett Packard is third with 12.9 percent, down from 14.2 percent six months ago. Thanks to three system from China’s National University for Defense Technology (Tianhe-2, Tianhe-2 LvLiang, and Tianhe-1A), China now contributes 9.2 percent of the total performance of the list, down from 10.9 percent.
Slowing trend in performance growth
Since its inception in June 1993, the TOP500 list has served as a consistent measure of the performance growth of supercomputers, since all systems are ranked according to performance running the same Linpack benchmark application. As noted at the release of the 44th list in November 2014, the overall list-by-list growth rates of performance continues to be at historically low values for the last two years.
The performance of the last system on the list (#500) has systematically continued to lag behind historical trends for the last six years and now clearly continues to run on a different growth trajectory than before. From 1994 to 2008 it grew by 90 percent per year, but since then has grown by just 55 percent per year.
This lag in the overall average performance of all 500 systems is noticeably influenced by the low turnover among very large systems at the top of the list. Recent installations of very large systems – up to June 2013 – have counteracted the reduced growth rate at the bottom of the list, but with few new systems at the top of the past few lists, the overall growth rate is now slowing. This offers an indication that the market for the very largest systems might currently behave differently from the market of mid-sized and smaller supercomputers.
On the latest edition of the list, the No. 500 system recorded a performance of 204.3 teraflops (trillions of calculations per second), compared to 164 teraflop/s in July. The last system on the newest list was listed at position 369 in the previous TOP500.
Other highlights from the 46th list
Total combined performance of all 500 systems has grown to 420 Pflop/s, compared to 361 Pflop/s last November and 309 Pflop/s one year ago. This increase in installed performance also exhibits a noticeable slowdown in growth compared to the previous long-term trend.
There are 80 systems with performance greater than 1 petaflop/s on the list, up from 67 last July.
The No. 1 system, Tianhe-2, and the No. 10 system, Stampede, use Intel Xeon Phi processors to speed up their computational rate. The No. 2 system, Titan, and the No. 7 system, Piz Daint, use NVIDIA GPUs to accelerate computation.
A total of 104 systems on the list are using accelerator/co-processor technology, up from 90 in July 2015. Sixty-six of these use NVIDIA chips, three use ATI Radeon, and there are now 27 systems with Intel’s Xeon Phi processors. Four systems use a combination of Nvidia and Intel Xeon Phi accelerators/co-processors.
Ninety-eight percent of the systems use processors with six or more cores, 88 percent use eight or more cores, and 47 percent ten or more cores.
About the TOP500 List
The first version of what became today’s TOP500 list started as an exercise for a small conference in Germany in June 1993. Out of curiosity, the authors decided to revisit the list in November 1993 to see how things had changed. About that time they realized they might be onto something and decided to continue compiling the list, which is now a much-anticipated, much-watched and much-debated twice-yearly event.
The TOP500 list is compiled by Erich Strohmaier and Horst Simon of Lawrence Berkeley National Laboratory; Jack Dongarra of the University of Tennessee, Knoxville; and Martin Meuer of ISC Group, Germany.