The World's Most Powerful Supercomputer

Tianhe-2 Supercomputer of China – World’s Most Powerful System

According to a biannual Top500 list of supercomputers, Tianhe-2 supercomputer of China has maintained its place as the most powerful system in the world for the sixth consecutive time. The Top500 list is considered to be one of the most authoritative rankings of the world’s supercomputers and has been compiled on the basis of the performance of the machines on the Linpack benchmark by experts from Germany and the US.

Tiahne-2 also known as the Milky Way-2 having a performance of 33.86 petaflops per second –Pflop/s had been invented by China’s National University of Defence Technology and organized at the National Supercomputer Centre in Guangzhou. It has held the title since June 2013.

According to the official media report, the Chinese system is said to be around twice as fast as the next on the list, Titan of the US Department of Energy that has a performance of 17.59 Pflop/s. In the latest edition of the closely watched list, no changes have come up regarding the ranking of the world’s top 5 supercomputers since June 2013.

China – Great Leap to 109 Systems

As per professor of the University of Tennessee and editor of the report, Jack Dongarra stated in an email to state-run Xinhua news agency that the top five computers are very expensive and powerful and it would take another year before a new system tends to enter the top five.From July 2015’s list some of the substantial changes to this list is the sharp decline in the number of systems in the US now at 201. It has been reported that in July, this is down from 231 and seems to be the lowest number of systems that have been connected in the US since the list had begun in 1993.

 In comparison, China had made a great leap to 109 systems. Dongarra had stated that China received a big enhancement from Sugon, Lenovo and Inspur. The large number of submissions had come from Sugon. As per the Top500 statement, Sugon had outdone IBM in the system category with 49 systems and Lenovo that had acquired IBM’s x86 server business last year had 25 systems in the list, up from three systems on the list of July 2015. Besides this, some systems which were earlier listed as IBM have now been labelled as IBM/Lenovo and Lenovo/IBM.

China Carving Bigger Share as Manufacturer

The third vendor from China, Inspur, now has about 15 systems on the list. The statement mentioned that China is carving out a bigger share as a manufacturer of great performance computer together with manifold Chinese manufacturers being very active in this arena.

Overall HP tends to lead the list with 156 systems followed by Cray with 69 systems with China’s Sugan with 49 systems. However, US intend to ultimately lead the world in supercomputer. Last fall IBM, had indicated that it would develop two new supercomputers named Summit and Sierra, for the Energy Department which would be still more powerful than China’s Tianhe-2 supercomputer but the same would not be ready till 2017.

President Obama had signed an executive order calling for the U.S. in July to develop the world’s most powerful supercomputer under the National Strategic Computing Initiative. The Energy Department as well as the National Science Foundation would be leading the push. There seems to be no deadline for the supercomputer’s completion though initiative members are expected to give yearly updates on its progress for the next five years.

Nvidia unveils Pascal, its next-gen GPU

Pascal a super computer module was unveiled by Jen Hsun Huang, CEO of Nvidia, at the annual conference of the company. This new architecture optimizes data transfer between the CPU and the GPU and uses a new type of memory arranged in three dimensions. According to NVidia, the module presented, which is one third the size of a PCIe graphics card brings the power of a supercomputer in the area occupied by two credit cards.

 NVidia, the manufacturer of graphics processors for computers and systems on a chip (SoC) that is found in tablets and Smartphones, held its annual conference this week (CWG 2014) in San Jose, California. This is an opportunity to unveil new graphics processor architecture for the next generation of chips, video games, mobile SoC devices and supercomputers. Pascal called in honor of the French scientist Blaise Pascal, this super computer is an important technical milestone with the introduction of several technologies that optimize the use of RAM and reduce bottlenecks for data transfer between the GPU and the central processor CPU.

The first of these is the new 3D memory, which consists of stacked DRAM cells arranged vertically and integrate all on the same semiconductor as the CPU. NVidia announces that the memory should be multiplied by 2.5 with a much larger bandwidth. This 3D architecture also allows you to place voltage regulators near the chip, which has the effect of optimizing the energy efficiency that would be four times higher than a GDDR5 memory solution. NVidia emphasizes that through this, the Pascal module will have one third of the size of a PCIe graphics card.

For its new processor architecture, NVIDIA opted for a RAM in 3D. The memory access is much faster while allowing a more compact design. Another key innovation is a new interconnected technology between the CPU and GPU named NVLink. It was co-developed with IBM with the goal to leverage the speed of data transfer between the two processors. According to NVidia , NVLink is 5-12 times faster than that can offer PCI Express bus third generation, because it leaves the GPU memory access the CPU at full bandwidth and vice versa.

The founder announced a bandwidth of 80 to 200 Gb / s, against 16 GB / s of PCIe 3.0. NVLink also renews the interconnection between the GPUs themselves, which will make creating clustering configurations that may include multiple GPUs. This new type of interconnects will greatly benefit applications that take advantage of hardware acceleration and massively for parallel computing. Through this system of unified memory, NVidia promises developers they will be released for optimizing problematic communication protocols.

IBM plans to integrate this technology into future versions of Power processors. Note that NVidia does not intend to abandon the PCIe bus. All transactions and configuration control initiated by the CPU go through a PCIe connection only. If a CPU is not NVLink supported, may interconnect between the GPU and function to improve the performance rise, or scaling. In other words, NVLink will somehow technical manufacturers of processors may or may not choose to adopt. The first chips from the architecture Pascal arrive in 2016.