Breaking News
News & Analysis

Intel unveils 1 TFLOP/s Knight's Corner

11/16/2011 06:51 AM EST
23 comments
NO RATINGS
More Related Links
View Comments: Threaded | Newest First | Oldest First
bobbytsai
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
bobbytsai   11/16/2011 4:15:42 PM
NO RATINGS
so intel finally made it to 1 Tflops. been able to buy this level of perforance for 2 or 3 years in a single slot pcie card. what is the flops/watt, flops/$ installed (floor space / cooling ...), memory bandwidth, max concurrent threds ?

askubel
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
askubel   11/16/2011 7:20:55 PM
NO RATINGS
Not a fair comparison. Knight's Corner achieves 1 TFLOP running x86 instructions.

bobbytsai
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
bobbytsai   11/16/2011 10:20:29 PM
NO RATINGS
who care anymore what instruction set is used in HPC. when programming in C / C++ / cuda / opencl / java / perl / and a few hundered programming languages ... all that is abstracted away. code will have to be ported in either case (from intel single thread to intel multi-thread, MIC or OPENCL/CUDA). if you are going to go through the effort of porting, ISA is not that important a factor. install cost, operating cost, tools availabity, feature support, perf/$$ are more improtant. don't buy the intel hype. MIC is still just a research project @ intel. You can actually buy AMD and NVIDIA products with 3rd party tools support.

drewm1980
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
drewm1980   11/16/2011 11:39:49 PM
NO RATINGS
For HPC, very little has been "abstracted away" since C was invented. Only the first four languages you list (plus Fortran) are actually used for HPC. Intel is promising the ability to use one (mature!) language/compiler/toolchain for both CPU and GPU/MIC code. This wouldn't be practical if the hardware wasn't x86(ish) ISA.

wilber_xbox
User Rank
Manager
re: Intel unveils 1 TFLOP/s Knight's Corner
wilber_xbox   11/16/2011 6:47:29 PM
NO RATINGS
this is really a success for the 3D tri-gate technology. It just opens up real possibilities for lower nodes than 22nm.

p_g
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
p_g   11/17/2011 12:03:05 AM
NO RATINGS
Agreed. This is a good milestone establishing yieldable silicon on such a great size as well as bringing 3D transistor to production worthy silicon.

goafrit
User Rank
Manager
re: Intel unveils 1 TFLOP/s Knight's Corner
goafrit   11/17/2011 12:30:21 AM
NO RATINGS
It simply means Intel owns the next decade. Too bad for AMD.

wilber_xbox
User Rank
Manager
re: Intel unveils 1 TFLOP/s Knight's Corner
wilber_xbox   11/17/2011 12:15:01 PM
NO RATINGS
Intel might face some competition but in my opinion they have just gone too far to catch in terms of the technology. Now the question is how they would capture the imagination of the consumers to gain control of the tablet/ultrabook segments.

resistion
User Rank
CEO
re: Intel unveils 1 TFLOP/s Knight's Corner
resistion   11/17/2011 1:21:32 PM
NO RATINGS
I think such high performance is not really targeted for consumers, but for enterprise servers. And since power was not remarked, I expect it to be typical ~200 W.

Mxv
User Rank
CEO
re: Intel unveils 1 TFLOP/s Knight's Corner
Mxv   11/17/2011 12:24:55 AM
NO RATINGS
These are old Pentium III cores. No instruction level parallelism, no out of order execution, etc. Only I/O interface is PCIe. Only advantage this has is the tool chain and that you can prototype your code on normal multicore x86 workstations and move to MIC later. Plus, the cores can work independently. GPU cores can't really work on separate processes. They are too interconnected.

resistion
User Rank
CEO
re: Intel unveils 1 TFLOP/s Knight's Corner
resistion   11/17/2011 12:44:00 AM
NO RATINGS
"within a 20MW power envelope" per chip? No thanks.

jaybus0
User Rank
CEO
re: Intel unveils 1 TFLOP/s Knight's Corner
jaybus0   11/17/2011 1:30:12 PM
NO RATINGS
I think you misunderstood the statement. He meant racks of servers using many chips, not a single chip. Their goal is a machine with exaflop, (ie. 1 million teraflop), performace.

resistion
User Rank
CEO
re: Intel unveils 1 TFLOP/s Knight's Corner
resistion   11/17/2011 1:38:34 PM
NO RATINGS
Of course, it has to be lots of hot chips requiring lots of cooling. I mentioned a reference of ~200 W/chip just a while ago.

KB3001
User Rank
CEO
re: Intel unveils 1 TFLOP/s Knight's Corner
KB3001   11/17/2011 1:46:58 PM
NO RATINGS
And what's the performance per $ and performance per watt? Intel can't keep banking on x86 forever!

snowboard9
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
snowboard9   11/18/2011 2:34:39 PM
NO RATINGS
They can , they have and they should.

palf
User Rank
Manager
re: Intel unveils 1 TFLOP/s Knight's Corner
palf   12/14/2011 8:10:03 PM
NO RATINGS
My engineering career began in 1970 and I was using the 8086 in 1976. It's always somewhat of an odd feeling to still see the x86 label being referenced. I would never have imagined it back then. Kudos to Intel for sustaining the product line.

timemerchant
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
timemerchant   11/18/2011 12:18:10 AM
NO RATINGS
Impressed with the wine rack in the background. Is this in a restaurant or a nicely fitted out exec's office? Seeing a chip in the air with a silkscreened logo but no decent specs is like deciding which bottle to pull from the rack without reading a label. I suppose "actual silicon with specs to follow" is better than "two years of specs with silicon to follow" from Xilinx, Altera etc. At least the wine will improve by the time it hits mainstream. Initial specs are impressive, even this sceptic must admit. Well done Intel, particularly on that tired x86 architecture. Heat dissipation? Must be less than what can be pulled out through a heatsink to prevent solder reflow, so to the 20MW per chip quip above, unlikely. Even 200 Watts, look at those city nightlines and switch off two light bulbs, then get back to work.

SylvieBarak
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
SylvieBarak   11/18/2011 1:09:21 AM
NO RATINGS
wow, good eye, TimeMerchant! Not his office, no, it was the wine cellar of a restaurant in Seattle where the briefing was being held. He wouldn't give out any details about the wattage per chip, but it certainly wasn't 20MW! That is the theoretical aim for an exascale system running these chips.... He also wasn't specific on the number of cores, sticking to the "more than 50" party line... but my bet is 64 cores with some being deactivated in order to improve yields.

resistion
User Rank
CEO
re: Intel unveils 1 TFLOP/s Knight's Corner
resistion   11/18/2011 2:05:27 AM
NO RATINGS
If they need a million such chips to achieve the ultimate goal anyway, it really takes away from the meaning of replacing ~10000 old processors with a single new one.

snowboard9
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
snowboard9   11/18/2011 2:37:05 PM
NO RATINGS
Here Tuesday's and Thursday's?

TFCSD
User Rank
CEO
re: Intel unveils 1 TFLOP/s Knight's Corner
TFCSD   11/18/2011 4:33:40 AM
NO RATINGS
I can't wait to see how this will improve solitaire on my wintel box! Exaflop is now within reach, sweet. I worked on weather forecasting software and can use the JIT forecasting this will allow.

Charles.Desassure
User Rank
Manager
re: Intel unveils 1 TFLOP/s Knight's Corner
Charles.Desassure   11/20/2011 3:07:30 PM
NO RATINGS
Hats off to you Intel...another success story.

Lee Harrison
User Rank
Rookie
re: Intel unveils 1 TFLOP/s Knight's Corner
Lee Harrison   11/22/2011 2:00:42 AM
NO RATINGS
The ratio of brand advocacy to informed commentary seems extraordinarily high in many of the sentiments above. Knights Corner gets most of those flops from a very wide SIMD micro-architecture. I happen to really LIKE SIMD micro-arches, and have done quite a lot of programming for them, and from what I see of the nLRBI (that's what the instruction set was called when the device was "Larrabee") it appears to be a very-well thought out SIMD ISA, far better than SSE. But the claim that ordinary "scalar" procedural programs written in C, Fortran etc are automatically going to be accelerated to Tflops ... simply isn't so. If you can't exploit the SIMD width efficiently ... its a 2-issue x86 core which isn't all that different from Atom. It's the SIMD extensions that make this design "powerful." Auto-vectorizing compilers haven't lived up to the hype so far (for any microarch ... GPGPUs included). AMD advocacy is misplaced here, because so far as I know, AMD isn't trying to compete in specialized HPC processors and/or adjunct accelerators. The competition is IBM with its spectrum of Cell/Power7/BlueGeneQ processors, and to some extent the nVidia Kepler+ARM initiative. It's going to be an interesting competition ... I wouldn't make any predictions of success. Folks should remember that both Cell and Power7 have successively not "conquered the HPC world," and for those thinking that Intel has avoided such experiences .. remember Itanium? Or for that matter that Knight's Corner is an updated Larrabee?

Radio
NEXT UPCOMING BROADCAST
EE Times Senior Technical Editor Martin Rowe will interview EMC engineer Kenneth Wyatt.
Top Comments of the Week
Like Us on Facebook

Datasheets.com Parts Search

185 million searchable parts
(please enter a part number or hit search to begin)
EE Times on Twitter
EE Times Twitter Feed
Flash Poll