REVERSE Hyperthreading for AM2! - Page 9 - Techist - Tech Forum

Go Back   Techist - Tech Forum > Computer Hardware > New Systems | Building and Buying
Click Here to Login
Closed Thread
 
Thread Tools Display Modes
 
Old 06-22-2006, 03:10 PM   #81 (permalink)
Ultra Techie
 
Join Date: Feb 2005
Posts: 969
Default

Quote:
Originally posted by Orayn
RHT brings up a very interesting possibility. If it can, in fact, be used to create a virtual dual core on 4X4, AMD could really be on to something. Conroe killer? If the rumours are true, and the prices on AM2 drop enough, maybe.
Price. That is, in my mind, the only thing that is limiting AMD from beating Conroe. IF they can get 4x4 and RHT(if it's real) to a reasonable price like they have for years, then I believe they have a good chance.

Also, there were rumors going around about AMD acquiring ATI. This could keep AMD in the game. According to an article from www.theinquirer.net, it all makes sense. I will post the link to the article later when I can find it.
__________________

__________________
<br><br><font color=\"black\"><b>There's No Place Like </b></font><font color=\"red\"><b>127.0.0.1</b></font><br>
AnthraX is offline  
Old 06-22-2006, 03:46 PM   #82 (permalink)
Wizard Techie
 
Join Date: Dec 2004
Location: Canada
Posts: 3,790
Default

The only reason Intel is able to market the conroe cheaper than current RevE or RevF AMD64s is the fact that Intel is able to keep production costs lower as they've already switched their fabs to 65nm processes...you should expect to see a more balanced pricing scheme with AMD64 RevG cores are released which are also produced using a 65nm production process

Reverse hyperthreading is real, or at least, I assume AMD is working on developing it. It won't be around for a few years though and as I said by the time they've developed it it won't be very useful as most companies will have started writing programs with multiple threads
__________________

__________________
Intel C2D E6320 / AMD Athlon X2 3800+
Gigabyte 965P DS3 / DFI nF4 Ultra-D
2GB OCZ Gold PC2-6400 / 2GB OCZ Gold PC4000
eVGA 8800GTS 320MB / eVGA 6800GS 256MB
150GB Raptor / 74GB Raptor
2x500GB / 320GB
OCZ GameXStreme 850w / OCZ StealthXStream 600w
gaara is offline  
Old 06-22-2006, 05:20 PM   #83 (permalink)
Banned
 
Join Date: Jun 2006
Posts: 232
Default

What he said. ^

I'm sure its possible. Just don't see the practical application for it...anymore.

And yea, go ahead and run Dual FX-62s to try to beat the Conroe, but its going to cost you about 4 times the comparable Conroe. Which is called fanboyism.
Infomatic is offline  
Old 06-22-2006, 10:01 PM   #84 (permalink)
True Techie
 
Join Date: Feb 2006
Posts: 201
Send a message via AIM to Orayn
Default

Quote:
Originally posted by AnthraX
Price. That is, in my mind, the only thing that is limiting AMD from beating Conroe. IF they can get 4x4 and RHT(if it's real) to a reasonable price like they have for years, then I believe they have a good chance.

Also, there were rumors going around about AMD acquiring ATI. This could keep AMD in the game. According to an article from www.theinquirer.net, it all makes sense. I will post the link to the article later when I can find it.
Yes and no. If the AM2 X2 3800+ dropped to $150ish like people are saying it will, it wouldn't be a real stretch to get two and a 4x4 mobo. Even if the drop isn't huge, RHT could make it worth it. We'll need more solid evidence and benchmarks before making any judgements, though.
Orayn is offline  
Old 06-22-2006, 10:32 PM   #85 (permalink)
Wizard Techie
 
Join Date: Jan 2005
Location: Delaware
Posts: 3,475
Default

Quote:
Not to be outdone, AMD detailed how it built its fully-depleted Silicon-on-Insulator (FDSOI) technology. As previously reported the SOI technology is expected to create an ultra-fast PMOS (P-channel metal-oxide semiconductor) transistor -- 30 percent better than what is on the market now.
http://www.internetnews.com/infra/article.php/2221261
turtile is offline  
Old 06-22-2006, 11:13 PM   #86 (permalink)
Banned
 
Join Date: Jun 2006
Posts: 232
Default

Thank you Turtile.

Apokalipse; "Nickel Silicide." Quite different from "Silicon-Germanium." Please get your terms right and not make such an amateur mistake again.
Infomatic is offline  
Old 06-23-2006, 01:49 AM   #87 (permalink)
Techie Beyond Description
 
Apokalipse's Avatar
 
Join Date: Jun 2003
Location: Melbourne, Australia
Posts: 14,559
Default

no, I did mean silicon-germanium transistors. IBM and AMD are developing them together.
http://news.zdnet.com/2100-9584_22-5982887.html

although yes, AMD may use Nickel Silicide aswell (which I admit I didn't know before)

and please don't try and attack me. If I'm wrong, you can correct me without comments like these:
Quote:
Please get your terms right and not make such an amateur mistake again.
Quote:
Originally posted by Infomatic
Moving to a smaller production size does not improve efficiency...it simply allows for a bit higher clockability and less power consumption.
less power consumption. that's what I mean by efficiency.
plus there's the lower production costs.

Quote:
DDR2 won't show any performance increases.
can you say that for certain?
yes, current AM2 CPU's are not that great. but they are AMD's first chips to use DDR2. and their memory controller really needs improving.

Quote:
"Improving the architecture's efficiency." That is a result, not an action. You need to explain how they are accomplishing this, or else its nothing.
I don't know exactly how, since I don't work for AMD. but it will involve changing the architecture to process more instructions/clock cycle, like they did from K7 to K8. K8 chips don't need as high frequencies to get the same performance as K7 chips.

Quote:
As for the Silicon-Germanium transistors...where did you get that? I know those are the same ones used in that IBM chip, but where did you get that they're going to be using those in K8L? [/B]
I can't say for certain they will be used on K8L, but I'd say it's pretty likely IMO.

http://www.hi-techreviews.com/module...ticle&sid=7156
Quote:
So what can we expect from the first 65 nm parts off the line? Probably something that few folks actually expect. Let me delve into one of the more overlooked properties of transistor design (well, at least to laymen like me). Basically the more stages in a pipeline means that the propagation delay in a signal is cut down and overall clockspeed can be increased, but more stages means that more transistors are being used. AMD is working with several partners to make sure that its 65 nm process is world class. This process encompasses embedded SiGe with dual stress liner and stress memorization technology on silicon on insulator- or e-SiGe with DSL and SMT on SOI for those so inclined. AMD and IBM have stated publicly that this technology allows for a 40% faster switching transistor than from a standard 65 nm design without all the three letter acronyms (TLA’s). In a complex design like a CPU this could mean a theoretical 50% overall clockspeed increase going from AMD’s 90 nm process to AMD/IBM’s 65 nm process all the while staying within the same power envelope.
__________________
Apokalipse is offline  
Old 06-23-2006, 10:08 AM   #88 (permalink)
Lord Techie
 
Nitestick's Avatar
 
Join Date: May 2005
Location: смерти для спаме
Posts: 8,473
Default

Quote:
Thank you Turtile.

Apokalipse; "Nickel Silicide." Quite different from "Silicon-Germanium." Please get your terms right and not make such an amateur mistake again.
i am not a moderator but apokalipse is so tread carefully as you are on thin ice. don't presume to know what he means unless you state that it is just that: a presumption. other than that you've been far more constructive so far so welcome back i guess

i have not heard of nickel silicide for transistors, do you know anything else? SiGe does seen to be a good way to go but it won't really be viable until AMD drops to 65nm (don't think they had plans of implementing it before then anyway). seems it's quite costly making SiGe chips so it would be uneconomical to do it on 90nm. i think the big question about RHT is how the cores would handle switching between RHT tasks and regular multithreading. if that can't be handled correctly then they may as well ditch the project. whats the point in improving singlethreaded performance at the cost of multithreaded performance when multithreading is soon to be the norm?
Nitestick is offline  
Old 06-23-2006, 11:17 AM   #89 (permalink)
Wizard Techie
 
Join Date: Jan 2005
Location: Delaware
Posts: 3,475
Default

AMD will have SiGe eventually - they are working with IBM on it.

I just heard that Opteron AM2s will be out w/ RH and they will be cheaper.
turtile is offline  
Old 06-23-2006, 01:38 PM   #90 (permalink)
Ultra Techie
 
Join Date: Feb 2005
Posts: 969
Default

Quote:
Originally posted by turtile
AMD will have SiGe eventually - they are working with IBM on it.

I just heard that Opteron AM2s will be out w/ RH and they will be cheaper.
They are releasing Opterons on AM2?
__________________

__________________
<br><br><font color=\"black\"><b>There's No Place Like </b></font><font color=\"red\"><b>127.0.0.1</b></font><br>
AnthraX is offline  
Closed Thread

Thread Tools
Display Modes

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
Trackbacks are On
Pingbacks are On
Refbacks are Off




Copyright 2002- Social Knowledge, LLC All Rights Reserved.

All times are GMT -5. The time now is 07:09 PM.


Powered by vBulletin® Version 3.8.8 Beta 1
Copyright ©2000 - 2017, vBulletin Solutions, Inc.