Entries with tag fastest supercomputers.

Chinese Supercomputer Remains the World’s most Powerful

The Tianhe-2 supercomputer—based at China’s National University of Defense Technology—remains in first place in the Top500 list of the world’s most powerful high-performance machines. This is the fourth consecutive time the Tianhe-2—which performs 33.86 petaflops—has topped the semiannual list. Also for the fourth consecutive time, Titan, a Cray supercomputer housed at the US Oak Ridge National Laboratory, remained in second place with a performance of 17.59 petaflops; and IBM’s 17.17-petaflops Sequoia, at the US Lawrence Livermore National Lab, was in third place. The only new computer in the top 10 was an unnamed US government Cray machine in tenth place that runs 3.58 petaflops. Researchers from Lawrence Berkeley National Laboratory; the University of Tennessee; and Prometeus, a German company that runs high-performance computing conferences, update the Top500 list in June and November of each year. (re/Code)(HPC Wire)(Top500 Blog)(Top500)

Supercomputer Performance Improvements Are Slowing

Growth in the performance of the world’s most powerful computers, which has increased steadily for 20 years, is now slowing, according to the recently released Top500 list of the world’s fastest supercomputers. An international research team releases the list, released by in June and November of each year at major supercomputing conferences. The report released this month showed that the combined performance of all 500 ranked computers increased to 274 petaflops from 250 petaflops in November 2013. Researchers deemed this “a noticeable slowdown in growth.” The Tianhe-2 at the National Supercomputer Center in Guangzho, China, remains atop the list, as it has for three consecutive reports, with a speed of 33.86 petaflops. (CNET)(PC Mag)(Top500 – 1)(Top500 -- 2)

New Supercomputing Benchmark Planned

The benchmark used to test and rank supercomputer performance is outdated, prompting the creation of a new metric that will be used starting in November. Jack Dongarra, distinguished professor of computer science at the University of Tennessee and one of the compilers of the Top500 list of the world’s fastest supercomputers, says the Linpack benchmark, used for the past 20 years, is no longer a useful measurement of application performance. It measures linear equation calculations, while calculations with more complexity are now common. The latest iteration of the test was developed in 2008. It also means that those vendors constructing systems are building them to perform well on an outdated test rather than to perform current applications well. The new test, the High Performance Conjugate Gradient, uses complex calculations found in contemporary applications that require high bandwidth and low latency and that access data using irregular patterns. Dongarra developed the new test with Michael Heroux from Sandia National Laboratories at the request of the US Department of Energy, which was concerned about applying Linpack to exascale computer systems. The new test will be gradually adopted and will initially be used with Linpack. The new test will be introduced at the SC13 supercomputing conference in Denver this November, which is also when the next The Top500 list will be released. Tianhe-2, China’s National University of Defense Technology supercomputer, is currently the top-ranked system. (Computerworld)(ZDNet)(Inside HPC)(“Toward a New Metric for Ranking High Performance Computing Systems,” @ Sandia National Laboratories)
 

New Chinese Supercomputer Named World’s Fastest

A new Chinese supercomputer debuted atop a recently released list of the world’s most powerful computing systems. The Tianhe-2, which the government-run National University of Defense Technology developed, topped the latest Top500 list with a tested performance of 33.86 petaflops (one petaflops is 1015 flops). The second and formerly top-ranked system on the biannual list is the US’s Titan—housed at the Department of Energy’s Oak Ridge National Laboratory—which performs 17.59 petaflops. The US’s Sequoia computer ranked third, followed by the Japanese K and the US’s Mira. The Tianhe-2 uses Intel Ivy Bridge and Xeon Phi chips with 3,120,000 computing cores and has a theoretical peak performance of 54.9 petaflops. Most of the components are Chinese-made, including the Kylin Linux operating system. Of the systems on the Top500, the US has 252, China now has 66, Japan has 30, the UK has 29, and France has 23. Hans Meuer of the University of Mannheim, Erich Strohmaier and Horst Simon of the US Lawrence Berkeley National Laboratory, and Jack Dongarra of the University of Tennessee, Knoxville, compile the list. (BBC)(Top500 Supercomputer Sites) 

Showing 4 results.