The TOP500 project ranks and details the 500 most powerful (non-distributed) computer systems in the world. The project was started in 1993 and publishes an updated list of the supercomputers twice a year. The first of these updates always coincides with the International Supercomputing Conference in June, and the second one is presented in November at the ACM/IEEE Supercomputing Conference. The project aims to provide a reliable basis for tracking and detecting trends in high-performance computing and bases rankings on HPL, a portable implementation of the high-performance LINPACK benchmark written in Fortran for distributed-memory computers.
The TOP500 list is compiled by Jack Dongarra of the University of Tennessee, Knoxville, Erich Strohmaier and Horst Simon of NERSC/Lawrence Berkeley National Laboratory (and, from 1993 until his death in 2014, Hans Meuer of the University of Mannheim, Germany.)
- 1 History
- 2 Architecture and operating systems
- 3 Top 10 ranking
- 4 Other rankings
- 5 New developments in supercomputing
- 6 Large machines not on the list
- 7 See also
- 8 References
- 9 External links
In the early 1990s, a new definition of supercomputer was needed to produce meaningful statistics. After experimenting with metrics based on processor count in 1992, the idea was born at the University of Mannheim to use a detailed listing of installed systems as the basis. Early 1993 Jack Dongarra was persuaded to join the project with his LINPACK benchmark. A first test version was produced in May 1993, partially based on data available on the Internet, including the following sources:
- "List of the World's Most Powerful Computing Sites" maintained by Gunter Ahrendt
- David Kahaner, the director of the Asian Technology Information Program (ATIP), in 1992 had published a report titled "Kahaner Report on Supercomputer in Japan" which had an immense amount of data.
The information from those sources was used for the first two lists. Since June 1993, the TOP500 is produced bi-annually based on site and vendor submissions only.
Since 1993, performance of the #1 ranked position has steadily grown in agreement with Moore's law, doubling roughly every 14 months. As of November 2014, the fastest system, the Tianhe-2 with Rpeak of 54.9024 PFlop/s, is over 419,102 times faster than the fastest system in November 1993, the Connection Machine CM-5/1024 (1024 cores) with Rpeak of 131.0 GFlop/s.
Architecture and operating systems
As of November 2014[update], TOP500 supercomputers are only based on x86-64 CPUs (Intel EMT64 and AMD AMD64 instruction set architecture), with these few exceptions (all RISC-based), 39 supercomputers based on Power Architecture used by IBM POWER microprocessors, three SPARC (including two Fujitsu/SPARC-based, one of which surprisingly made the top in 2011 without a GPU, currently ranked fourth), and one ShenWei-based (ranked 11 in 2011, ranked 65th in November 2014) making up the remainder. Prior to the ascendance of 32-bit x86 and later 64-bit x86-64 in the early 2000s, a variety of RISC processor families made up the majority of TOP500 supercomputers, including RISC architectures such as SPARC, MIPS, PA-RISC and Alpha.
In recent years heterogeneous computing, mostly using Nvidia's graphics processing units (GPU) as coprocessors, has become a popular way to reach a better performance per watt ratio and higher absolute performance; almost required for good performance and to make the top (or top 10), with some exceptions, such as the mentioned SPARC computer without any coprocessors. Then an x86-based coprocessor, Xeon Phi, has also been used.
All the fastest supercomputers in the decade since the Earth Simulator supercomputer, have used a Linux-based operating system. As of November 2014[update], 485 or 97% of the world's fastest supercomputers use the Linux kernel Remaining 3% run some Unix variant (which is AIX for all of them except one), with one supercomputer running Windows and one with a "mixed" operating system. Within those 97% are the most powerful supercomputers including those ranking as the top ten.
Since November 2014, Windows Azure cloud computer is no longer on the list of fastest supercomputers (its best rank was 165 in 2012), leaving the Shanghai Supercomputer Center's "Magic Cube" as the only Windows-based supercomputer, running Windows HPC 2008 and ranked 360 (its best rank was 11 in 2008).
Top 10 ranking
- Rank – Position within the TOP500 ranking. In the TOP500 List table, the computers are ordered first by their Rmax value. In the case of equal performances (Rmax value) for different computers, the order is by Rpeak. For sites that have the same computer, the order is by memory size and then alphabetically.
- Rmax – The highest score measured using the LINPACK benchmark suite. This is the number that is used to rank the computers. Measured in quadrillions of floating point operations per second, i.e. petaflops.
- Rpeak – This is the theoretical peak performance of the system. Measured in Pflops.
- Name – Some supercomputers are unique, at least on its location, and are therefore christened by its owner.
- Computer – The computing platform as it is marketed.
- Processor cores – The number of active processor cores actively used running LINPACK. After this figure is the processor architecture of the cores named. If the interconnect between computing nodes is of interest, it's also included here.
- Vendor – The manufacturer of the platform and hardware.
- Site – The name of the facility operating the supercomputer.
- Country – The country in which the computer is situated.
- Year – The year of installation/last major update.
- Operating system – The operating system that the computer uses.
Numbers below represent the number of computers in the TOP500 that are in each of the listed countries.
|Country||Jun 2014||Nov 2013||Jun 2013||Nov 2012||Jun 2012||Nov 2011||Jun 2011||Nov 2010||Jun 2010||Nov 2009||Jun 2009||Nov 2008||Jun 2008||Nov 2007|
|United Arab Emirates||1|
Systems ranked #1 since 1993
- NUDT Tianhe-2A (National Supercomputing Center of Guangzhou China, June 2013 - present)
- Cray Titan (Oak Ridge National Laboratory United States, November 2012 - June 2013)
- IBM Sequoia Blue Gene/Q (Los Alamos National Laboratory United States, June 2012 – November 2012)
- Fujitsu K computer (RIKEN Advanced Institute for Computational Science Japan, June 2011 – June 2012)
- NUDT Tianhe-1A (National Supercomputing Center of Tianjin China, November 2010 – June 2011)
- Cray Jaguar (Oak Ridge National Laboratory United States, November 2009 – November 2010)
- IBM Roadrunner (Los Alamos National Laboratory United States, June 2008 – November 2009)
- IBM Blue Gene/L (Lawrence Livermore National Laboratory United States, November 2004 – June 2008)
- NEC Earth Simulator (Earth Simulator Center Japan, June 2002 – November 2004)
- IBM ASCI White (Lawrence Livermore National Laboratory United States, November 2000 – June 2002)
- Intel ASCI Red (Sandia National Laboratories United States, June 1997 – November 2000)
- Hitachi CP-PACS (University of Tsukuba Japan, November 1996 – June 1997)
- Hitachi SR2201 (University of Tokyo Japan, June 1996 – November 1996)
- Fujitsu Numerical Wind Tunnel (National Aerospace Laboratory of Japan Japan, November 1994 – June 1996)
- Intel Paragon XP/S140 (Sandia National Laboratories United States, June 1994 – November 1994)
- Fujitsu Numerical Wind Tunnel (National Aerospace Laboratory of Japan Japan, November 1993 – June 1994)
- TMC CM-5 (Los Alamos National Laboratory United States, June 1993 – November 1993)
Number of systems
By number of systems as of November 2014:
New developments in supercomputing
In November 2014, it was announced that the United States was developing two new supercomputers to dethrone China's Tianhe-2 from its position as world's fastest supercomputer. The two computers, Sierra and Summit, will each exceed Tianhe-2's 55 peak petaflops. Summit, the more powerful of the two, will deliver 150-300 peak petaflops.
Large machines not on the list
A few machines that have not been benchmarked are not eligible for the list: such as NCSA's Blue Waters. Additionally purpose-built machines that are not capable or do not run the benchmark were not included: such as RIKEN MDGRAPE-3.
Computers and architectures that drop off the list
IBM Roadrunner is no longer on the list (or any other using the Cell or the PowerXCell coprocessor), but it is an example of a computer that would easily be included if it had not been decommissioned as it is faster then the one ranked 500th.
Conversly a computer might drop off the list, such as the Windows Azure one, but may have been upgraded (or not) to be faster but not reported.
All Itanium based system (previously ranked second in 2004 and would still make the list) in any version and vector processors (NEC-based such as the Earth simulator that was fastest in 2002) are also off the list.
- Computer science
- HPC Challenge Benchmark
- Instructions per second
- Performance per watt
- AN INTERVIEW WITH JACK DONGARRA by Alan Beck, editor in chief HPCwire[dead link]
- Statistics on Manufacturers and Continents
- List of the World's Most Powerful Computing Sites
- Rpeak – This is the theoretical peak performance of the system. Measured in Pflops.
- TOP500 - Sublist Generator
- "Top500 - List Statistics - November 2014". Top500.org. Retrieved 17 November 2014.
- "Microsoft Windows Azure".
- "Magic Cube - Dawning 5000A, QC Opteron 1.9 GHz, Infiniband, Windows HPC 2008".
- TOP500 - List Statistics
- Balthasar, Felix. "US Government Funds $425 million to build two new Supercomputers". News Maine. Retrieved 16 November 2014.
- An Overview of High Performance Computing and Challenges for the Future on YouTube – Jack Dongarra discusses the TOP500 benchmark, its history and its trends.