Follow us on Twitter
Follow us on FacebookChina lifts the lid on new supercomputer
@ 2013/06/05Details are emerging about a Chinese supercomputer that is headed to becoming the world's fastest.
The Chinese Tianhe-2 is being developed in the National Supercomputer Center in Guangzhou as the successor to the Tianhe-1A.
According to HPCwire, the Tianhe-1A was pretty fast. In its day it was number one and could drive its 14,336 Intel Xeon X5670 processors and 7,168 nVidia Tesla GPUs to a peak performance of 4.7 petaflops. Now it is the eighth fastest supercomputer, well behind the Titan, a Cray XK7 system installed at Oak Ridge National Laboratories with a peak performance of 20 petaflops, or 20,000 trillion calculations per second.
But the Tianhe-2 is supposed to deliver peak performance between 53 petaflops and 55 petaflops, with a LINPACK score for sustained performance of between 27 petaflops and 29 petaflops. It is supposed to eventually have a peak performance capability of more than 100 petaflops.
Most of the detail about Tianhe-2 came from a draft of a report on the system by Jack Dongarra, a researcher at Oak Ridge National Laboratories and founding member of the Top500 list organization.
Dongarra said that the Tianhe-2 runs a total of 3,120,000 processor cores divided among 16,000 nodes. Each node contains sockets for two Intel Ivy Bridge processors that serve as the CPU and three boards for co-processors, which use Intel's Xeon Phi processor.
This is probably the first commercial use of Chipzilla's Many Integrated Core Architecture, which can deliver as much as a teraflop per chipset.
Dongarra believes that the system is configured with a total of 1.404 petabytes of memory and a parallel storage system with 12.4 petabytes of space.
It managed to overcome scalability and performance problems by using a Chinese-developed network tool called the TH-Express 2, and a frontend system using 4,096 Galaxy FT-1500 CPUs–16-core processors developed by NUDT based on the Sparc-V9 chip, Dongarra said.
Each FT-1500 can manage 144 gigaflops a second, compared to 211 gigaflops from the Ivy Bridge processors.
As you might expects it takes a lot of electricity to power. At peak power consumption, the Tianhe-2 needs 17.6 megawatts plus another 6.4 megawatts for a closed-coupled water-cooling system, for a total of 24 megawatts.
As far as the software is concerned, it uses a NUDT-designed Linux distribution called Kylin Linux, which also runs on the Tianhe-1A.
The Chinese Tianhe-2 is being developed in the National Supercomputer Center in Guangzhou as the successor to the Tianhe-1A.
According to HPCwire, the Tianhe-1A was pretty fast. In its day it was number one and could drive its 14,336 Intel Xeon X5670 processors and 7,168 nVidia Tesla GPUs to a peak performance of 4.7 petaflops. Now it is the eighth fastest supercomputer, well behind the Titan, a Cray XK7 system installed at Oak Ridge National Laboratories with a peak performance of 20 petaflops, or 20,000 trillion calculations per second.
But the Tianhe-2 is supposed to deliver peak performance between 53 petaflops and 55 petaflops, with a LINPACK score for sustained performance of between 27 petaflops and 29 petaflops. It is supposed to eventually have a peak performance capability of more than 100 petaflops.
Most of the detail about Tianhe-2 came from a draft of a report on the system by Jack Dongarra, a researcher at Oak Ridge National Laboratories and founding member of the Top500 list organization.
Dongarra said that the Tianhe-2 runs a total of 3,120,000 processor cores divided among 16,000 nodes. Each node contains sockets for two Intel Ivy Bridge processors that serve as the CPU and three boards for co-processors, which use Intel's Xeon Phi processor.
This is probably the first commercial use of Chipzilla's Many Integrated Core Architecture, which can deliver as much as a teraflop per chipset.
Dongarra believes that the system is configured with a total of 1.404 petabytes of memory and a parallel storage system with 12.4 petabytes of space.
It managed to overcome scalability and performance problems by using a Chinese-developed network tool called the TH-Express 2, and a frontend system using 4,096 Galaxy FT-1500 CPUs–16-core processors developed by NUDT based on the Sparc-V9 chip, Dongarra said.
Each FT-1500 can manage 144 gigaflops a second, compared to 211 gigaflops from the Ivy Bridge processors.
As you might expects it takes a lot of electricity to power. At peak power consumption, the Tianhe-2 needs 17.6 megawatts plus another 6.4 megawatts for a closed-coupled water-cooling system, for a total of 24 megawatts.
As far as the software is concerned, it uses a NUDT-designed Linux distribution called Kylin Linux, which also runs on the Tianhe-1A.
