Go Back   AnandTech Forums > Hardware and Technology > Video Cards and Graphics

Forums
· Hardware and Technology
· CPUs and Overclocking
· Motherboards
· Video Cards and Graphics
· Memory and Storage
· Power Supplies
· Cases & Cooling
· SFF, Notebooks, Pre-Built/Barebones PCs
· Networking
· Peripherals
· General Hardware
· Highly Technical
· Computer Help
· Home Theater PCs
· Consumer Electronics
· Digital and Video Cameras
· Mobile Devices & Gadgets
· Audio/Video & Home Theater
· Software
· Software for Windows
· All Things Apple
· *nix Software
· Operating Systems
· Programming
· PC Gaming
· Console Gaming
· Distributed Computing
· Security
· Social
· Off Topic
· Politics and News
· Discussion Club
· Love and Relationships
· The Garage
· Health and Fitness
· Home and Garden
· Merchandise and Shopping
· For Sale/Trade
· Hot Deals with Free Stuff/Contests
· Black Friday 2014
· Forum Issues
· Technical Forum Issues
· Personal Forum Issues
· Suggestion Box
· Moderator Resources
· Moderator Discussions
   

Reply
 
Thread Tools
Old 11-03-2012, 02:03 AM   #1
blastingcap
Diamond Member
 
blastingcap's Avatar
 
Join Date: Sep 2010
Posts: 5,884
Default [SemiAccurate] Tesla K20 specs: 13 SMX, GeForce probably 12-13 SMX

http://semiaccurate.com/2012/11/02/n...t-28nm-yields/
__________________
Quote:
Originally Posted by BoFox View Post
We had to suffer polygonal boobs for a decade because of selfish corporate reasons.
Main: 3570K + R9 290 + 16GB 1866 + AsRock Extreme4 Z77 + Eyefinity 5760x1080 eIPS
blastingcap is offline   Reply With Quote
Old 11-03-2012, 02:11 AM   #2
3DVagabond
Diamond Member
 
Join Date: Aug 2009
Location: Christchurch, NZ
Posts: 8,546
Default

Charlie's scenario is only one possibility. Another is they fused them off purely for power usage, nothing at all to do with yields. The clocks being so low would also point to that.
3DVagabond is offline   Reply With Quote
Old 11-03-2012, 02:13 AM   #3
Jaydip
Diamond Member
 
Jaydip's Avatar
 
Join Date: Mar 2010
Posts: 3,299
Default

So he is at it again
__________________
Windows 7 Home Premium 64 bit || i7 4770K @ 4.2 with CM V6-GT || MSI Z87 GD 65||MSI Gaming N780 TF 3GD5/OC GeForce GTX 780|| Corsair Vengeance 16GB 1600 || WD Cavier Black 1TB FAEX X2|| HAF-X || Corsair TX750 V2 ||AL MX 5021E || DELL U2713HM||SideWinder X4||Razer DA
Jaydip is offline   Reply With Quote
Old 11-03-2012, 02:18 AM   #4
3DVagabond
Diamond Member
 
Join Date: Aug 2009
Location: Christchurch, NZ
Posts: 8,546
Default

Charlie is "usually" right when he is quoting his own sources. This is him just reading an article and drawing conclusions based off of it.
3DVagabond is offline   Reply With Quote
Old 11-03-2012, 02:47 AM   #5
blastingcap
Diamond Member
 
blastingcap's Avatar
 
Join Date: Sep 2010
Posts: 5,884
Default

If they relieve the memory bandwidth constraints and allow GeForce to be somewhat less power efficient = higher voltages and clocks than Tesla, then we're looking at ~35% more performance than a GTX 680. Considering that HD8970 is supposed to be less than 20% faster than HD7970, it seems that NV is about to reclaim the single-GPU crown.
__________________
Quote:
Originally Posted by BoFox View Post
We had to suffer polygonal boobs for a decade because of selfish corporate reasons.
Main: 3570K + R9 290 + 16GB 1866 + AsRock Extreme4 Z77 + Eyefinity 5760x1080 eIPS
blastingcap is offline   Reply With Quote
Old 11-03-2012, 03:18 AM   #6
Plimogz
Senior Member
 
Plimogz's Avatar
 
Join Date: Oct 2009
Location: Off Topic
Posts: 609
Default

so, if I'm getting this straight, NV would've delivered 18K+ 14/15 SMX to ORNL, but yields would bad enough to only market a 13/15 SMX part as the professional market compute part and slot in below that a 12 or 13 (uncertainty per the article) SMX part for the consumer graphics market?

While I expect that even such a fraction of their monster 7.1 billion xtor part would be formidable in itself, I can't remember when gamers ever received a part so crippled in lieu of a high end chip.
Weird.
__________________
2500K/P67A-UD5/HCP-850/2xTF3 7950/4x4GB RipjawsX 1600/120GB Vertex3/1TB Caviar Black/3x2TB Caviar Green ...
Plimogz is offline   Reply With Quote
Old 11-03-2012, 03:30 AM   #7
boxleitnerb
Platinum Member
 
Join Date: Nov 2011
Posts: 2,531
Default

Quote:
Originally Posted by blastingcap View Post
Charlie purposefully left out that K20 at ORNL is 14 SMX, his other stuff is pure speculation to make Nvidia look bad. Nothing new in the west.
boxleitnerb is offline   Reply With Quote
Old 11-03-2012, 03:36 AM   #8
Silverforce11
Diamond Member
 
Silverforce11's Avatar
 
Join Date: Feb 2009
Location: Australia
Posts: 4,858
Default

He is incorrect one a major point, the reason for the fused part and low clocks = to fit the 225W TDP. Because these K20s are going to be used as a upgrade, replacing Fermi, which was also a 225W TDP HPC part. Massive sever upgrades would not risk replacing the infrastructure, especially the water cooling units and aircond for the facility. TDP being the same is critical.

I expect yields to be low, but it seems shipping 18,000 units in a few months points to TSMC either a) starting the ramp a long long time ago (possible, but unlikely due to 28nm constraints on every other part, ie. mobile), or b) yields are not so bad! (more likely)
__________________

Rig 1: 3570K | Z77 E4 | Crossfire R290 | 840 250GB + 840EVO 250GB | 8GB G.Skill Ares 2133 | OCZ 850W Gold+ | Nanoxia DS1 | Ghetto Water
Hobby: Mobile Game Dev & Cryptocoin day-trader
Silverforce11 is offline   Reply With Quote
Old 11-03-2012, 04:25 AM   #9
VulgarDisplay
Diamond Member
 
Join Date: Apr 2009
Location: Chicago
Posts: 5,926
Default

Quote:
Originally Posted by blastingcap View Post
If they relieve the memory bandwidth constraints and allow GeForce to be somewhat less power efficient = higher voltages and clocks than Tesla, then we're looking at ~35% more performance than a GTX 680. Considering that HD8970 is supposed to be less than 20% faster than HD7970, it seems that NV is about to reclaim the single-GPU crown.
You need to remember that the 7970 itself can be 20% faster than the 7970 through fairly reasonable overclocking. I don't think this refresh is going to be that negative for AMD.
VulgarDisplay is offline   Reply With Quote
Old 11-03-2012, 04:32 AM   #10
boxleitnerb
Platinum Member
 
Join Date: Nov 2011
Posts: 2,531
Default

The reason for selling 14SMX parts in K20 for ORNL is not only TDP. Obviously, yields on the full parts are always lower, so that means you need more wafers and more time to produce a certain amount. AMD and Intel are beginning to invade the HPC market with their own solution, so it is only logical to fulfill the contracts as quickly as possible. 5% more or less performance is irrelevant when you can supply 3 times as many cards.
boxleitnerb is offline   Reply With Quote
Old 11-03-2012, 05:15 AM   #11
sontin
Platinum Member
 
Join Date: Sep 2011
Posts: 2,245
Default

Good old Charlie.

With the w9000 AMD is selling a 28 SIMD GCN chip in the server market. SO i guess there is no full GCN on the market right now?
sontin is offline   Reply With Quote
Old 11-03-2012, 05:19 AM   #12
HurleyBird
Golden Member
 
Join Date: Apr 2003
Posts: 1,092
Default

Quote:
Originally Posted by Silverforce11 View Post
He is incorrect one a major point, the reason for the fused part and low clocks = to fit the 225W TDP. Because these K20s are going to be used as a upgrade, replacing Fermi, which was also a 225W TDP HPC part. Massive sever upgrades would not risk replacing the infrastructure, especially the water cooling units and aircond for the facility. TDP being the same is critical.
Quote:
Originally Posted by 3DVagabond View Post
Charlie's scenario is only one possibility. Another is they fused them off purely for power usage, nothing at all to do with yields. The clocks being so low would also point to that.
Wishful thinking. I thought the two of you would know better.

Enabling all of the SMXes while lowering the clock rate and voltage further to compensate would allow for better power consumption at the same performance level, that's basic mathematics. Yields are the only possible reason for disabling SMXes. Given the size of GK110 this isn't at all surprising, and may have been expected by Nvidia from the onset. Expect a fully functional part six months to a year after big Kepler officially launches.

Last edited by HurleyBird; 11-03-2012 at 05:22 AM.
HurleyBird is offline   Reply With Quote
Old 11-03-2012, 09:35 AM   #13
Silverforce11
Diamond Member
 
Silverforce11's Avatar
 
Join Date: Feb 2009
Location: Australia
Posts: 4,858
Default

Quote:
Originally Posted by HurleyBird View Post
Wishful thinking. I thought the two of you would know better.

Enabling all of the SMXes while lowering the clock rate and voltage further to compensate would allow for better power consumption at the same performance level, that's basic mathematics. Yields are the only possible reason for disabling SMXes. Given the size of GK110 this isn't at all surprising, and may have been expected by Nvidia from the onset. Expect a fully functional part six months to a year after big Kepler officially launches.
Depends on the fusing techniques, they can effectively cut TDP by fusing if they need to fit a lower TDP mark.

You can bet a lot of their K20 sales will be for customers who are upgrading from Fermi. Slotting in an identical TDP card is easier.
__________________

Rig 1: 3570K | Z77 E4 | Crossfire R290 | 840 250GB + 840EVO 250GB | 8GB G.Skill Ares 2133 | OCZ 850W Gold+ | Nanoxia DS1 | Ghetto Water
Hobby: Mobile Game Dev & Cryptocoin day-trader
Silverforce11 is offline   Reply With Quote
Old 11-03-2012, 10:12 AM   #14
BenSkywalker
Elite Member
 
Join Date: Oct 1999
Posts: 8,955
Default

Quote:
Charlie is "usually" right when he is quoting his own sources.
If Charlie said the sun was going to come up tomorrow, I would be getting my wife and kids together to say goodbye.
BenSkywalker is offline   Reply With Quote
Old 11-03-2012, 10:48 AM   #15
tviceman
Diamond Member
 
Join Date: Mar 2008
Posts: 4,997
Default

Ryan Smith said that at 1.3 TF, the K20's in ORNL has to be 14 SMX's at 732mhz. About half way to two thirds down in the comments: http://www.anandtech.com/show/6421/i...cores?all=true I'll believe anandtech and hpcwire any day over Charlie anything. Especially when using real, mathematical figures and facts.

EDIT: The article discussion thread so far on semiaccurate pretty much has everyone telling him he is wrong too. http://semiaccurate.com/forums/showthread.php?t=6720

Last edited by tviceman; 11-03-2012 at 10:55 AM.
tviceman is offline   Reply With Quote
Old 11-03-2012, 10:54 AM   #16
Keysplayr
Elite Member
 
Keysplayr's Avatar
 
Join Date: Jan 2003
Posts: 20,000
Default

K20 could be 15 SMX with 1 disabled to meet the 225W power envelope they were looking for. With the last SMX enabled that might bring it up to 250W and multiply that by 18000+. Lot's O Watts.
__________________
Member of Nvidia Focus Group
NVIDIA Focus Group Members receive free software and/or hardware from NVIDIA from time to time
to facilitate the evaluation of NVIDIA products. However, the opinions expressed are solely those of the Members.

i5 2500K Asus P-Z68-V/Gen3 GTX980 SLI
Keysplayr is offline   Reply With Quote
Old 11-03-2012, 10:57 AM   #17
ShintaiDK
Lifer
 
ShintaiDK's Avatar
 
Join Date: Apr 2012
Location: Copenhagen
Posts: 11,354
Default

Why do people read that sensationalist site again?
__________________
Quote:
Originally Posted by Idontcare
Competition is good at driving the pace of innovation, but it is an inefficient mechanism (R&D expenditures summed across a given industry) for generating the innovation.
ShintaiDK is online now   Reply With Quote
Old 11-03-2012, 11:09 AM   #18
tviceman
Diamond Member
 
Join Date: Mar 2008
Posts: 4,997
Default

Quote:
Originally Posted by ShintaiDK View Post
Why do people read that sensationalist site again?
It's good entertainment!
tviceman is offline   Reply With Quote
Old 11-03-2012, 11:15 AM   #19
Keysplayr
Elite Member
 
Keysplayr's Avatar
 
Join Date: Jan 2003
Posts: 20,000
Default

I blocked it at my router just in case I lose my head and click the link. No hits from me for Charlie. Ever. Not even by accident or redirected url.
__________________
Member of Nvidia Focus Group
NVIDIA Focus Group Members receive free software and/or hardware from NVIDIA from time to time
to facilitate the evaluation of NVIDIA products. However, the opinions expressed are solely those of the Members.

i5 2500K Asus P-Z68-V/Gen3 GTX980 SLI
Keysplayr is offline   Reply With Quote
Old 11-03-2012, 11:22 AM   #20
sontin
Platinum Member
 
Join Date: Sep 2011
Posts: 2,245
Default

Quote:
Originally Posted by tviceman View Post
It's good entertainment!
It was in the past. Now he is writing nothing new. It always the same with the same sentences and the same message.
sontin is offline   Reply With Quote
Old 11-03-2012, 12:00 PM   #21
SirPauly
Diamond Member
 
SirPauly's Avatar
 
Join Date: Apr 2009
Posts: 4,871
Default

Imho,

I don't mind Charlie and try to understand the subjective context: sensationalism, conjecture, speculation and the name of the site is semi-accurate --- not accurate. Seems to have an odd negative fetish for nVidia and sometimes his journalism suffers from this.

He was semi-accurate on the GK-104 - win in many important metrics and efficiency but off on some things as well.

Pretty tough to ignore HPC and AnandTech and what they offer -- Time will tell to see if nVidia offers a GeForce derivative and if they do - what the specs may be.
SirPauly is offline   Reply With Quote
Old 11-03-2012, 03:38 PM   #22
Silverforce11
Diamond Member
 
Silverforce11's Avatar
 
Join Date: Feb 2009
Location: Australia
Posts: 4,858
Default

I'm pretty sure reading into Charlie's previous sources, he has friends at MSI and ASUS.. other AIBs im not certain.

It's pretty clear he has no source inside NV itself. But then again, NV is really leak-free.

I really do hope GK110 for consumers will be a high TDP high perf part, none of this crippled rubbish to fit a certain power envelope.. $600 GPU who cares?!
__________________

Rig 1: 3570K | Z77 E4 | Crossfire R290 | 840 250GB + 840EVO 250GB | 8GB G.Skill Ares 2133 | OCZ 850W Gold+ | Nanoxia DS1 | Ghetto Water
Hobby: Mobile Game Dev & Cryptocoin day-trader
Silverforce11 is offline   Reply With Quote
Old 11-03-2012, 06:16 PM   #23
iMacmatician
Member
 
iMacmatician's Avatar
 
Join Date: Oct 2012
Location: United States of America
Posts: 88
Default

Charlie implies here that the 14 SMX K20s are "special" chips for ORNL (and maybe other supercomputers), and the 13 SMX K20 is the "real" version that will actually be available on the market.
iMacmatician is offline   Reply With Quote
Old 11-03-2012, 07:27 PM   #24
tviceman
Diamond Member
 
Join Date: Mar 2008
Posts: 4,997
Default

Quote:
Originally Posted by Silverforce11 View Post
I'm pretty sure reading into Charlie's previous sources, he has friends at MSI and ASUS.. other AIBs im not certain.

It's pretty clear he has no source inside NV itself. But then again, NV is really leak-free.

I really do hope GK110 for consumers will be a high TDP high perf part, none of this crippled rubbish to fit a certain power envelope.. $600 GPU who cares?!
I don't think we'll get a full on 15 SMX part at first. I think that won't come until the end of summer. Just my guess.
tviceman is offline   Reply With Quote
Old 11-03-2012, 07:29 PM   #25
sontin
Platinum Member
 
Join Date: Sep 2011
Posts: 2,245
Default

Until GF100 nVidia always released the full chip. There is no reason to believe that they will change their behavior.
sontin is offline   Reply With Quote
Reply

Thread Tools

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -5. The time now is 01:37 PM.


Powered by vBulletin® Version 3.8.7
Copyright ©2000 - 2014, vBulletin Solutions, Inc.