Is Tianhe-2 Overrated?

[C130]

Of course it's highly overrated.

A supercomputer that helped China develop advanced weapons, IT, machinery, oil exploration, medicines is extremely overrated.

now just post some evidence of this, and we have a debate finally.

 

[Azeri440]

it's been the fastest supercomputer in the world since it's debut in June 2013. running at a blistering speed of 33.86 Pflops, but this monster also consumes 17.6 MW of power (24MW including cooling) that's enough power to power 240,000 homes in the U.S


fast as it is, it's inefficient. coding for Tianhe-2 is a challenge , and the cost just to use it is insanely high.

World's fastest computer, Tianhe-2, might get very little use | South China Morning Post

wow, never realized supercomputers require so much power

 

[Kyusuibu Honbu]

No point in belittling a scientific endeavor, just because it is inefficient or not economical.
Today it may of little use, but years ahead will serve as a platform for future development.

For instance, anyone into space exploration knew space programs are expensive and would be long before we can colonize planets or exploit their natural resources. Yet, the space programs were pursued and people around the world benefit from its progress, in terms of satellite imagery, electronics, and computational progress etc.

 

[54ptu]

So China owns a kickass mustang which pulls out occasionally for a joy ride while Merica drives a honda civic to work everyday. Nice analogy!!

If the 天河-2 is such a show off, then why does Obama make an executive order to build a even faster one?

Not to mention his winning strategy seems to be sabotaging the 天河-2 by embargo the key component it needs to upgrade on.

 

[JSCh]

China planning new supercomputer
Source: Xinhua 2016-01-22 19:26:01

TIANJIN, Jan. 22 (Xinhua) -- China is planning a supercomputer 1,000 times more powerful than its groundbreaking Tianhe-1A as it faces rising demand for next-generation computing.

Meng Xiangfei, head of the applications department of the National Supercomputer Center, said on Friday that the center will release a prototype in 2017 or 2018 of an "exascale" computer -- one capable of at least a billion billion calculations per second

Exascale computing is considered the next frontier in the development of supercomputers.

Tianhe-1A was recognized as the world's fastest computing system in 2010. Though it has since been superseded by Tianhe-2, Tianhe-1A is being more widely used. Computer scientists are finding it challenging to run contemporary applications at their optimum on faster supercomputers.

With its uses including oil exploration data management, animation and video effects, biomedical data processing and high-end equipment manufacturing, Tianhe-1A's capacity is being stretched, said Meng.

It is carrying out more than 1,400 computing tasks and serving about 1,000 users per day.

The exascale computer will be wholly independently developed by the National Supercomputer Center, according to Meng.

About a seventh of Tianhe-1A's CPU chips are Chinese.

 

[gambit]

Anyway on topic- what are you guys using this supercomputer for right now?

To generate Internet forum insults against Americans.

 

[C130]

China planning new supercomputer
Source: Xinhua 2016-01-22 19:26:01

TIANJIN, Jan. 22 (Xinhua) -- China is planning a supercomputer 1,000 times more powerful than its groundbreaking Tianhe-1A as it faces rising demand for next-generation computing.

Meng Xiangfei, head of the applications department of the National Supercomputer Center, said on Friday that the center will release a prototype in 2017 or 2018 of an "exascale" computer -- one capable of at least a billion billion calculations per second

Exascale computing is considered the next frontier in the development of supercomputers.

Tianhe-1A was recognized as the world's fastest computing system in 2010. Though it has since been superseded by Tianhe-2, Tianhe-1A is being more widely used. Computer scientists are finding it challenging to run contemporary applications at their optimum on faster supercomputers.

With its uses including oil exploration data management, animation and video effects, biomedical data processing and high-end equipment manufacturing, Tianhe-1A's capacity is being stretched, said Meng.

It is carrying out more than 1,400 computing tasks and serving about 1,000 users per day.

The exascale computer will be wholly independently developed by the National Supercomputer Center, according to Meng.

About a seventh of Tianhe-1A's CPU chips are Chinese.

Tianhe-1A is better than Tianhe-2 if it's doing 1,400 computing tasks and serving 1,000 users a day


this is why I said Tianhe- 2 is overrated. all brawn and no brains

China's world-beating Tianhe-2 super has brawn, not brains • The Register



slower but easier to code supercomputers give it a run for it's money

Titan
Sequoia
Mira
Tianhe-1A

 

[xunzi]

I don't bash on China

quite the opposite to be honest. I have seen a lot of is anti-US threads coming from the Chinese members here.


and this thread is about whether Tianhe-2 is overrated.

If it is overrated, why are you trying to building an even more powerful than Tianhe2? LOL

 

[C130]

So China owns a kickass mustang which pulls out occasionally for a joy ride while Merica drives a honda civic to work everyday. Nice analogy!!

If the 天河-2 is such a show off, then why does Obama make an executive order to build a even faster one?

Not to mention his winning strategy seems to be sabotaging the 天河-2 by embargo the key component it needs to upgrade on.

Honda Civic are awesome, but I prefer Nissan Ultima.

 

[antonius123]

I am curious about IBM super computer utilization (comparing to Tianhe which is only 34%).

I think in spite of only 34% utilization, but if it is used for aerospace experiment, new weapons, nuclear energy and sort off, it can help China to reduce experiment & development cost

 

[C130]

If it is overrated, why are you trying to building an even more powerful than Tianhe2? LOL

yawn you didn't get my point

Tianhe-2 is the fastest supercomputer in the world (when running LINPACK) ...I am not disputing that. M y point was it doesn't use all that power because Chinese researchers are having a hard time programming code to unlock all that power. and the cost just to use it per day would set you back $60,000 to $100,000

U.S,Western, and Japanese have better software

and looking at all the parameters that make a supercomputer super Tianhe-2 ranks 6th

Brief Introduction | Graph 500


the Japanese Kei Supercomputer reigns supreme

@Nihonjin1051

 

[xunzi]

yawn you didn't get my point

Tianhe-2 is the fastest supercomputer in the world (when running LINPACK) ...I am not disputing that. M y point was it doesn't use all that power because Chinese researchers are having a hard time programming code to unlock all that power. and the cost just to use it per day would set you back $60,000 to $100,000

U.S,Western, and Japanese have better software

and looking at all the parameters that make a supercomputer super Tianhe-2 ranks 6th

Brief Introduction | Graph 500


the Japanese Kei Supercomputer reigns supreme

@Nihonjin1051

Not really. There has to be a purpose to write a software to compute all of its potential and currently there is nothing in this world that need that much computation power.

As we said before, Tianhe2 will aid us in simulation and testing on military and aerospace industry.

Btw, where is your Titan on that list? LOL

 

[C130]

I am curious about IBM super computer utilization (comparing to Tianhe which is only 34%).

I think in spite of only 34% utilization, but if it is used for aerospace experiment, new weapons, nuclear energy and sort off, it can help China to reduce experiment & development cost

if the Tianhe-2 was exclusively coded to run such things then yes it would help in those fields of research immensely.


which is why I brought up why didn't China just build three 10 to 15 Pflop supercomputers??

once could havefdone aerospace research, another nuclear energy/nuclear weapons research, and the third on whatever

Not really. There has to be a purpose to write a software to compute all of its potential and currently there is nothing in this world that need that much computation power.

As we said before, Tianhe2 will aid us in simulation and testing on military and aerospace industry.

Btw, where is your Titan on that list? LOL

this is to be seen. by the time China starts removing the dust Tianhe-2. you'll have built a 150 to 300 Pflops successor.


where is Titan.......that is a good question

 

[rcrmj]

now the ignorant and arrogant American start to constantly b*tching about China's technological achievements and military activities```, we gonna see more funny reacts from these jolly simpletons `

 

[xunzi]

this is to be seen. by the time China starts removing the dust from dust from Tianhe-2. you'll will have built a 150 to 300 Pflops successor.

where is Titan.......that is a good question

If you bother to look at that list,notice how many nodes and cores the top above Tianhe-2 were using. Right now, Tianhe-2 has the best computational power but it is not needed to use all because there is nothing needed for it to use all that power. It is that simple. In the future, we might need those power but right now we don't.

An analogy is like you used a Mustang vs a Honda Civic. If you are on a highway trying to escape a cop, you would certainly choose a Mustang over a Honda Civic but you are not in trouble, so you don't need a Mustang. It is always good to have it, just in case.