back to article China picks MIPS for super-duper super

The Chinese government burst onto the supercomputing scene in a big way last November when the Tianhe-1 massively parallel cluster at the National Supercomputer Center in Tianjin came in at number five on the global HPC ranking with a hybrid Intel Xeon-AMD Radeon GPU box. But it looks like the future of petaflops computing in …

COMMENTS

This topic is closed for new posts.

Another Chinese Me-too Project

Interesting but what a waste of good research talent! The hard reality is that any new processor that does not solve the parallel programming crisis is on a fast road to failure. No long march to victory in sight for the Loongson, sorry.

China should be trying to become a leader in this field, not just another me-too follower. There is an unprecedented opportunity to make a killing in the parallel processor industry in the years ahead. Intel may have cornered the market for now but they have an Achilles' heel: they are way too big and way too married to last century's flawed computing paradigms to change in time for the coming massively parallel computer revolution. Their x86 technology will be worthless when that happens. The trash bins of Silicon Valley will be filled with obsolete Intel chips.

Here's the problem. The computer industry is in a very serious crisis due to processor performance limitations and low programmer productivity. Going parallel is the right thing to do but the current multicore/multithreading approach to parallel computing is a disaster in the making. Using the erroneous Turing Machine-based paradigms of the last sixty years to solve this century's massive parallelism problem is pure folly. Intel knows this but they will never admit it because they've got too much invested in the old stuff. Too bad. They will lose the coming processor war. That's where China and Intel's competitors can excel if they play their cards right.

The truth is that the thread concept (on which the Loongson and Intel's processors are based) is the cause of the crisis, not the solution. There is an infinitely better way to build and program computers that does not involve threads at all. Sooner or later, an unknown startup will pop out of nowhere and blow everybody out of the water.

My advice to China, Intel, AMD and the other big dogs is this: first invest your resources into solving the parallel programming crisis. Only then will you know enough to properly tackle the embedded systems, supercomputing and cloud computing markets. Otherwise be prepared to lose a boatload of dough. When that happens, there shall be much weeping and gnashing of teeth but I'll be eating popcorn with a smirk on my face and saying "I told you so".

How to Solve the Parallel Programming Crisis:

http://rebelscience.blogspot.com/2008/07/how-to-solve-parallel-programming.html

0
0
Thumb Up

Good words well said but...

First they got to get themselves a decent parallel programming crisis first in which to solve.

I think they're doing a good thing. Anything not x86 these days I consider good.

I for one, welcome our asian chipzilla who is yet to come...Please give us an alternative!!!

0
0
Anonymous Coward

I hate to sound jingoistic

But absent some extremely credible and verifiable assurances that this system is not loaded with back-doors and "special features," nobody in their right mind is going to buy a supercomputer that is effectively designed and manufactured by the Chinese government.

0
0
Black Helicopters

MIPS re-emergence; Trade Decicit

MIPS has been pretty much considered dead - with the major advocates migrating to other processors - this is offers a good opportunity to employ more Chinese citizens, with their master & doctorate degrees, and really move an old technology (MIPS) forward again!

I do find this interesting, not that China may necessarily get into the system design & building business, to compete with Intel/AMD/SPARC/POWER- but because they can choose to spend the money on systems which they can design from the ground up, by their own citizens, and keep more of the money that is flowing into China and give less of it back to the West.

Keep in mind, China is a big market. If they standardize on MIPS with some level of recompilation to get Intel compatibility, they can choose to write their own ticket. They don't need to necessarily sell their ticket to the outside world.

0
0
Happy

MIPS cores are heavily used in consumer electronics

MIPS is certainly not dead. It is heavily used in consumer electronics.

See the list of devices that use MIPS-based cores

from the last Consumer Electronics Show in Las Vegas

http://money.cnn.com/news/newsfeeds/articles/globenewswire/182243.htm

You are also incorrect in calling MIPS "old technology". x86 is older (1978?), Power and Sparc were born at the same time as MIPS.

0
0
Boffin

Curious choice of architecture

MIPS died a death in the HPC world several years ago. The last MIPS processor from SGI was the R16000A which only just managed to hit 1 GHz round about 2004, but was pretty uncompetitive with x64, POWER, Itanic etc by then. Of course, being a fairly straightforward architecture, you might get quite a lot of cores onto the same die at 65nm..

0
0
Anonymous Coward

Ever hear of Sicortex?

The recently defunct company Sicortex was selling a super based on their own custom MIPS64 chip. I have a 72 700MHz MIPS node cluster on my desk that draws less that 300 watts of power. That includes an amd-64 head node. Sicortex systems scaled to over 5000 nodes. They were pushing the energy efficiency of the setup. The system runs very nicely with a custom Gentoo Linux and lots of dev tools.

I can understand their interest in MIPS after dealing with these systems. They are cheap, well understood and well supported in software. Add in some PathScale compilers like I have on my box and it could be a great little beast.

0
0
Thumb Up

x86 on MIPS

x86 on MIPS is good news. x86 on anything is good news and I expect ARM and others to develop emulators also. 30% reduction in speed is quite acceptable since, MIPS can offer twice the processing power per Wat. x86 is used only for office apps, where speed isn't critical. Sounds like a good move for the Chinese.

0
0
This topic is closed for new posts.

Forums