China's domestic CPU FeiTeng-1000 has been installed in supercomputer Tianhe-1

[stax]

BEIJING, Oct. 28 (Xinhua) -- China's Tianhe-1 has overtaken Nebule to regain top spot as China's fastest computer according to a new list of China's Top 100 supercomputers released Thursday.

On the biannual world TOP 500 list published in June, China's Nebulae machine took the second spot only after the U.S.'s Jaguar system, while Tianhe-1 took seventh place.

Housed at the National Center for Supercomputing in northern port city of Tianjin, Tianhe-1, meaning Milky Way, has a sustained computing speed of 2,507 trillion calculations, or 2.507 petaflops, per second.

It has a theoretical speed of 4.7 petaflops per second, according to a R&D research member of Tianhe-1. A petaflop is equivalent to 1,000 trillion calculations.

Nebulae housed in Shenzhen is capable of sustained computing of 1.271 petaflop per second (PFlop/s) on the Linpack benchmark, a measure for ranking supercomputers in world Top 500 list.

The U.S. leads the world in supercomputing and is home to more than half of the top 500 supercomputers. The Jaguar system at Oak Ridge National Laboratory in Tennessee has a speed of 1.75 PFlop/s.

The enhanced Tianhe-1 has upgraded Intel CPUs, NVIDIA GPUs, and new domestically developed FeiTeng-1000 CPUs have been installed, the developer the National University of Defense Technology (NUDT) said.

Tianhe-1 has begun trial use among target clients including Tianjin Meteorological Bureau and the National Offshore Oil Corporation data center. "It can also serve the animation industry and bio-medical research," said Liu Guangming, director of the National Center for Supercomputing in Tianjin.

In September 2009, the NUDT created Tianhe-1 with a sustained computing speed of 0.5631 PFlop/s, the fastest supercomputer in China at that time.

The new technical data of Tianhe-1 has been submitted to the world Top 500 list and the next list will be released in November

Orignal Link:China's fastest supercomputer Tianhe-1 creates new speed record

 

[ChineseTiger1986]

I am sure that the next Supercomputer would use China's indigenous CPU and GPU.

 

[Nomenclature]

I am sure that the next Supercomputer would use China's indigenous CPU and GPU.

CPU maybe. GPU? very unlikely.

CPU designing has been around for a long time now and there's a huge amount of public knowledge available. The same can not be said for GPU designs.

FeiTeng-100 used in Tianhe-1, for example, utilizes Sun Microsystem's open source SPARC instruction set. There's no shame in using SPARC though, as Japan's next supercomputer will also use SPARC processors designed by Fujitsu.

On the other hand, I'm quite surprised by the rumor FeiTeng-100 was fabricated by TSMC. Coupled this with reports the next Loongsum will use TSMC's 32nm technology, it seems with warming cross-strait ties government-back projects on the mainland are opening up to the idea of using Taiwanese foundries.

I guess mainland CPU designers must be really disappointed by the slow progress of SMIC. But the government is not entirely giving up on SMIC yet as news came out yesterday SMIC got a fresh $500 million cash injection to expand its 65nm facilities in Beijing. I guess when SMIC's 65nm plants mature, NUDT will switch back to SMIC, IF they'll still be using 65nm for their next processor.

Anyway some spec for the FeiTeng-1000 CPU:
SPARC instruction set
65nm process
8 cores
8 simultaneous threads per core
running at 1GZ

 

[ChineseTiger1986]

CPU maybe. GPU? very unlikely.

CPU designing has been around for a long time now and there's a huge amount of public knowledge available. The same can not be said for GPU designs.

FeiTeng-100 used in Tianhe-1, for example, utilizes Sun Microsystem's open source SPARC instruction set. There's no shame in using SPARC though, as Japan's next supercomputer will also use SPARC processors designed by Fujitsu.

On the other hand, I'm quite surprised by the rumor FeiTeng-100 was fabricated by TSMC. Coupled this with reports the next Loongsum will use TSMC's 32nm technology, it seems with warming cross-strait ties government-back projects on the mainland are opening up to the idea of using Taiwanese foundries.

I guess mainland CPU designers must be really disappointed by the slow progress of SMIC. But the government is not entirely giving up on SMIC yet as news came out yesterday SMIC got a fresh $500 million cash injection to expand its 65nm facilities in Beijing. I guess when SMIC's 65nm plants mature, NUDT will switch back to SMIC, IF they'll still be using 65nm for their next processor.

Anyway some spec for the FeiTeng-1000 CPU:
SPARC instruction set
65nm process
8 cores
8 simultaneous threads per core
running at 1GZ

Ops, i did reply too fast. Indeed China hasn't came with any powerhouse of graphic card, as our game industry isn't very developed like Japan and USA.

And it seems that USA has monopolized the technology of GPU.

And Sparc is actually a joint development between US and Japan, that's why they are the only two countries that currently monopolize the CPU technology.

 

[marshall]

HPCwire: China's Dark Horse Supercomputing Chip: FeiTeng


China's Dark Horse Supercomputing Chip: FeiTeng

Michael Feldman

Chinese development of domestic microprocessors for high performance computing seems to be ramping up. The Godson-3B and ShenWei SW1600 CPUs were the first out of the gate, with the latter chip powering a Chinese petascale supercomputer. Waiting in the wings is the FeiTeng processor, an architecture that could be the one that takes Chinese supercomputing into the exascale realm.

Although, there is not a lot of information publicly available on the latest FeiTeng chip, at one time it was being promoted as "the world's first 64-bit stream processor dedicated for high-performance science computing." The architecture, which is variously known as the FeiTeng, YinHe, the YinHe FeiTeng, and the FT64, has been developed at the National University of Defense Technology (NUDT) in Hunan Province. The design work culminated in its first implementation under the FT64 moniker in 2007.

According to a paper presented at the International Symposium on Computer Architecture in 2007 (ISCA 2007) and published by the ACM that year, the FT64 architecture and instruction set was specifically designed with high performance computing in mind. The instructions are of the VLIW persuasion and nearly half of them apply to 64-bit FP operations. Not surprisingly, about 36 percent of the die is devoted to arithmetic operations.

This first-generation FeiTeng was implemented on 130nm process technology and, at 500 MHz, delivered a peak performance of 16 gigaflops. While that's nothing to get too excited about today, keep in mind that the FT64 is nearly five years old. What's more impressive is that the chip consumed a mere 8.6 watts of power, which would yield an energy efficiency of about 1.8 gigaflops/watt. The current top of the line NVIDIA GPU in the Tesla M02090, built on 2011-era 40nm technology, delivers about 2.9 gigaflops/watt.

Like its GPGPU cousin, the FT64 was meant to run as a coprocessor, driven by a host CPU. The ACM paper describes an HPC system board that had one host driving eight FT64 and communicating with each coprocessor via an on-chip host interface. Like the GPU-CPU systems of today, FT64 memory and host memory are separate.

The FT64 designers also came up with a stream programming language called SF95, which extended FORTRAN95 with 10 compiler directives to exploit the architecture. The compiler was used to benchmark the FT64 against an Itanium 2 using nine science application kernels (FFT, EP, MG, Swim, CG, Laplace, Jacobi, GEMM, and NLAG-5). Except for the CG kernel where the FT64 had just a tenth of the Itanium's performance, the stream processor was between 1 and 2.5 times faster than the Itanium on the other kernels, and 8 time faster on FFT.

However, a somewhat different picture of the architecture emerged, based on a seminar delivered last month (December 2011) at the National University of Defense Technology. The seminar abstract is provided here:

YinHe FeiTeng (YHFT) series high-performance general-purpose CPUs, aimed for high-performance computing, are developed by school of computer, National University of Defense Technology. The first generation of the YHFT CPU adapts the EPIC (Explicitly Parallel Instruction Computing) architecture. Its ISA (Instruction Set Architecture) is fully compatible with Intel Itanium2. The second generation is based on the SoC (System-on-Chip) architecture. It is composed of a general-purpose CPU and a stream processor, which is the world's first 64-bit stream processor dedicated for high-performance science computing. The processor has been successfully used in the YinHe high-performance supercomputer system as an accelerator. The research results are published at ISCA 2007 and IEEE TPDS. The third generation of the YHFT CPU is a multi-core processor. Its ISA is fully compatible with SPARC. It supports floating-point SIMD (Single Instruction Multiple Data) and multi-chip interconnection to enhance parallel processing and constitute a SMP (Symmetric Multi-Processing) system directly. The first version of this multi-core processor has been used on the TH-1A PFLOPS supercomputer systems, and the ongoing upgraded version will be taped out in the next year and used in the next generation of the TH supercomputer system.

According to this, the FT64 was actually the second generation of the architecture and was deployed in some fashion in one of the YinHe (Galaxy) supercomputers in China -- presumably this one, although theoretically there could be an even lower-profile YinHe machine in existence somewhere else.

The third generation of the FeiTeng architecture sounds more like a conventional, standalone CPU, rather than a stream accelerator per se. The reference to this latest chip being used in the TianHe-1A supercomputer, with upgraded version due to be deployed in the next generation TH machine, is especially interesting. At 4.7 peak petaflops, the NUDT's TianHe-1A is currently China's most powerful machine, but is powered by Intel Xeon and NVIDIA Tesla parts.

It's not clear how big a role the upgraded FeiTeng chips will play in the next generation TH machine, but the NUDT has not been any more loyal to chip manufacturers, than its US counterparts. In 2010, the NUDT used Intel Xeon and AMD's Radeon GPUs for its first generation petascale machine, the TianHe-1. The following year they switched to NVIDIA GPUs for the TianHe-1A.

Given China's desire to develop and use indigenous microprocessors for its HPC sector, it wouldn't be too surprising to see FeiTeng processors replace both Intel and NVIDIA parts in a future NUDT supercomputer. Obviously, supercomputing centers in the country are experimenting a lot with microprocessors, although at this point are willing to use just about anything that maximizes performance. But it's almost certain that China would want its first exaflop machine to be entirely built with domestic technology, including, of course, the microprocessors.

 

[Bobshouse]

Ops, i did reply too fast. Indeed China hasn't came with any powerhouse of graphic card, as our game industry isn't very developed like Japan and USA.

And it seems that USA has monopolized the technology of GPU.

And Sparc is actually a joint development between US and Japan, that's why they are the only two countries that currently monopolize the CPU technology.

The opposite is actually true. CPU's are more advanced than GPU's. China has more chance in catching up with GPU designs rather than CPU's, Intel is currently about a generation and a half ahead of the next competitor.
How old is this article? Japan has had the fastest supercomputer since midway through last year.
I really hope China goes down the path of CPU fabrication, currently Intel has no competition. But silicon only has about 10 years to run before physical limitations are reached. China may be better off looking for the next step in computer evolution

 

[below_freezing]

The opposite is actually true. CPU's are more advanced than GPU's. China has more chance in catching up with GPU designs rather than CPU's, Intel is currently about a generation and a half ahead of the next competitor.
How old is this article? Japan has had the fastest supercomputer since midway through last year.
I really hope China goes down the path of CPU fabrication, currently Intel has no competition. But silicon only has about 10 years to run before physical limitations are reached. China may be better off looking for the next step in computer evolution

we are trying but there are many constraints on quantum computation, and in terms of cheapness, nothing will replace silicon - its abundant, while one of the best candidates for quantum computation, the nitrogen-vacancy in diamond, is... well, its a diamond =(

 

[Nishan_101]

Hoping that it will also reach pakistani Markets as well.

---------- Post added at 03:54 PM ---------- Previous post was at 03:53 PM ----------

Can we compare it to just Core i3? and to which extent?