Tianhe-2 (Milky Way-2), a system developed by China’s National University of Defense Technology (NUDT) and deployed at the National Supercomputer Center in Guangzho, China remains the No. 1 system with 33.86 petaflop/s (Pflop/s) on the Linpack benchmark. The system currently has 16,000 nodes, each with two Intel Xeon Ivy Bridge processors and three Xeon Phi processors for a combined total of 3,120,000 computing cores. It features a number of Chinese-developed components, including the TH Express-2 interconnect network, front-end processors, operating system and software tools. The Tianhe-2 uses the Kylin Linux operating system. The power consumption of Tianhe-2 while running Linpack was 17.8 MW.
Highlights from the Top 10
Titan, a Cray XK7 system installed at the Department of Energy’s (DOE) Oak Ridge National Laboratory remains the No. 2 system. It achieved 17.59 Pflop/s on the Linpack benchmark using 261,632 of its NVIDIA K20x accelerator cores. Titan is one of the most energy efficient systems on the list consuming a total of 8.21 MW and delivering 2.143 Gflops/W.
Sequoia, an IBM BlueGene/Q system installed at DOE’s Lawrence Livermore National Laboratory, is again the No. 3 system. It was first delivered in 2011 and has achieved 17.17 Pflop/s on the Linpack benchmark using 1,572,864 cores.
Fujitsu’s K computer installed at the RIKEN Advanced Institute for Computational Science (AICS) in Kobe, Japan, is the No. 4 system with 10.51 Pflop/s on the Linpack benchmark using 705,024 SPARC64 processing cores.
Mira, a BlueGene/Q system installed at DOE’s Argonne National Laboratory, is No. 5 with 8.59 Pflop/s on the Linpack benchmark using 786,432 cores.
Trinity, a Cray X40 system installed at DOE/NNSA/LANL/SNL joins the TOP 10 with 8.1 Pflops/s and 301,056 cores.
At No. 7 is Piz Daint, a Cray XC30 system installed at the Swiss National Supercomputing Centre (CSCS) in Lugano, Switzerland and the most powerful system in Europe. Piz Daint achieved 6.27 Pflop/s on the Linpack benchmark using 73,808 NVIDIA K20x accelerator cores. Piz Daint is also the most energy efficient systems in the TOP10 consuming a total of 2.33 MW and delivering 2.7 Gflops/W.
Shaheen II, a Cray XC40 system installed at King Abdullah University of Science and Technology (KAUST) is a second time in the TOP 10 at No. 9 with 5.536 PFlop/s on the Linpack benchmark using 196,608 Intel Xeon E5-2698v3 cores.
Stampede, a Dell PowerEdge C8220 system installed at the Texas Advanced Computing Center of the University of Texas, Austin, is now at No. 8. It also uses Intel Xeon Phi processors (previously known as MIC) to achieve its 5.17 Pflop/s.
Systems #6, #8, and #9 systems are the only Top 10 system installed or upgraded in 2015. The #1 system the only system installed in 2013. The remaining 6 systems have been installed in 2012 or 2011. This age of the population in the Top 10 is unprecedented.
Highlights from the Overall List
The overall list-by-list growth rates of performance recovers after historical low values in the last 3 years.
The performance of the last system on the list (#500) has systematically continued to lag behind historical trends for the last 6 years and now clearly continues to run on a different growth trajectory than before. From 1994 to 2008 it grew by 90% per year. Since 2008 it only grows by 55% per year.
The growth of the average performance of all systems in the list has slowed since 2013 as well and has also dropped to about 55% per years
There are 81 systems with performance greater than a Pflop/s on the list, up from 68 six months ago.
In the Top 10, 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, the No. 7 system Piz Daint is using NVIDIA GPUs to accelerate computation.
A total of 104 systems on the list are using accelerator/co-processor technology, up from 90 on June 2015. Sixty-six (66) of these use NVIDIA chips, three use ATI Radeon, and there are now 27 systems with Intel Xeon Phi technology. Four systems use a combination of Nvidia and Intel Xeon Phi accelerators/co-processors.
The average number of accelerator cores for these 104 systems is 68,138 cores/system.
Intel continues to provide the processors for the largest share (89 percent) of TOP500 systems.
Ninety-eight (96.8) percent of the systems use processors with six or more cores, eighty-eight (82.6) percent use eight or more cores, and forty-seven (52.4) percent ten or more cores.
Cray XC series is now the most popular system in the TOP 10 with four entries including the No. 6, 7, 8 and 9 systems. A Cray XK7 system remains at number 2 making Cray the dominant vendor in the TOP 10.
The number of systems installed in the USA declines sharply and is now at 199 system, down from from 233 in the previous list. This is the lowest number of systems installed in the US since the list has started.
The number of systems installed in China has increased dramatically to 109, compared to 37 on the last list. China is now at the No. 2 position as a user of HPC. China maintains the No. 2 position in the performance share as well.
General highlights from the TOP500 since the June 2015 edition
The entry level to the list moved up to the 206.3 Tflop/s mark on the Linpack benchmark, compared to 165.1 Tflop/s six months ago.
The last system on the newest list would have been listed at position 368 in the previous TOP500. This represents a slight recovery when compared to the last list.
Total combined performance of all 500 systems has grown to 420 Pflop/s, compared to 363 Pflop/s six months ago 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.
The entry point for the TOP100 increased in six months to 816 Tflop/s from 715 Tflop/s.
The average concurrency level in the TOP500 is 58,596 cores per system, up from 50,495 six months ago and 43,301 one year ago.
A total of 445 systems (89 percent) are now using Intel processors, slightly up from 86.2 percent six months ago.
The share of IBM Power processors is now at 26 systems, down from 38 systems six month ago.
The AMD Opteron family is used in 21 systems (4.2 percent), down from 4.4 percent on the previous list.
InfiniBand technology is now found on 235 systems, down from 257 systems, and is the most-used internal system interconnect technology. Gigabit Ethernet has risen to 182 systems up from 147 systems, in large part thanks to 120 systems now using 10G interfaces.
Following its acquisition of IBM’s x86 business last year, Lenovo now has 25 systems in list, up from 3 system six months ago.. Some systems that were previously listed as IBM are now labeled as both IBM/Lenovo (9 systems) and Lenovo/IBM (5 systems).
HP has the lead in systems and now has 155 systems (31.2 percent) followed by Cray with 69 systems. IBM now has 45 systems, down from 111 systems six month ago . HP had 178 systems six months ago. In the system category, Cray is now second with 13.8 percent (69 systems).
Sugon, a vendor from China is now ahead of IBM in the system category with 49 systems.
Cray emerges in this year as the clear leader in the TOP500 list in performance and has a considerable lead with a 25 percent share of installed total performance (up from 24 percent).
IBM takes the second spot with 14.9 percent share, down from 23 percent six months ago.
Thanks to Tianhe-2 and Tianhe-1A, NUDT contributes 9.2 percent of the total performance of the list, down from 10.9 percent.
HP is third with 12.9 percent, down from 14.2 percent six months ago.
The U.S. is clearly the leading consumer of HPC systems with 199 of the 500 systems (233 in June 2015) although its share has dropped sharply to an all time low in this list. The European share (107 systems compared to 141 last time) has fallen and is now lower than the Asian share of 173 systems., up from 107 in June 2015.
Dominant countries in Asia are China with 109 systems (up from 37) and Japan with 37 systems (down from 39).
In Europe, Germany is the clear leader with 32 systems followed by France and the UK at 18 systems each.
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 on to 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.