Sign in with
Sign up | Sign in
Your question
Closed

AMD First to 22 Nm, Challenges Intel

Last response: in News comments
Share
August 18, 2008 11:19:42 PM

Cool nice article..
Score
2
August 18, 2008 11:22:19 PM

Major failure in the thread title, should be IBM not AMD reaches 22nm.
Score
-4
Related resources
Anonymous
August 18, 2008 11:35:25 PM

AMD needs to join up with IBM.
Score
-1
August 18, 2008 11:44:12 PM

spanner_razorMajor failure in the thread title, should be IBM not AMD reaches 22nm.

bobsmith1AMD needs to join up with IBM.

Lol,you guys are totally ignorant of the fact AMD works with IBM...
Score
10
Anonymous
August 18, 2008 11:46:05 PM

IBM is king

my dad works there :p 
Score
10
Anonymous
August 18, 2008 11:48:21 PM

IBM and AMD made a deal ages ago for the production of 22nm chips, so this is the culmination of it. They made the achievement together.
Score
8
August 18, 2008 11:54:53 PM

I wonder what the overclocking margins on such a small chip will be...
Score
0
August 19, 2008 12:11:03 AM

frozenleadI wonder what the overclocking margins on such a small chip will be...

depends on how good the actual process is...

I myself don't overclock,don't need more waste heat on my other parts
Score
1
August 19, 2008 12:13:25 AM

They should create 22nm processor next year ^_^
Score
0
August 19, 2008 12:27:30 AM

Im just wondering what kinda of clock speed increase can be expected from 22nm because we have seen very little average clock speed increases over the past 3 or 4 manurfacturing gereration (90-65-45) (although clock speed certainly is not everything when it comes to performance)

I guess this is the kinda manufacturing size that would be weel suited for the CPU/GPU intergrations that are on the horizons...


and..a few years down the track....
...maybe once CPU/GPU intergration kicks off, Physx(pun intended) will be once again sent back to the CPU for calculating allowing for single Vcard setups to make a comeback....
Score
0
August 19, 2008 12:51:38 AM

It always seems IBM anounces they made this or that break through... then its like 5 years before you can actually buy the tech.
Are they making 45nm Cell chips yet ?
Score
-5
August 19, 2008 1:29:18 AM

Incorrect title! Nice to attract more traffic though.
Score
-5
August 19, 2008 1:44:39 AM

Take a look at this:

I appears IBM also set the previous record for 32nm back in 2004. Have they released any 32nm processor? Not that I'm aware. I think the first 32nm CPU's will be shown at IDF.

I think the title is misleading on the major contributor and the implication of the finding.
Score
-5
August 19, 2008 1:49:39 AM

(repost with good link)
Take a look at this:

I appears IBM also set the previous record for 32nm back in 2004. Have they released any 32nm processor? Not that I'm aware. I think the first 32nm CPU's will be shown at IDF.

I think the title is misleading on the major contributor and the implication of the finding.
Score
-4
August 19, 2008 1:55:26 AM

Hell I would like to see AMD release a 45nm cpu........get your heads out of the future and into the present moment.
Score
0
Anonymous
August 19, 2008 4:39:17 AM

Well like Tom's said before IBM is a evil vampire that never die :p 
Score
-3
August 19, 2008 4:40:29 AM

Like Tom's said before IBM is vampire that never die.
Score
-3
August 19, 2008 5:01:14 AM

Nice title. Credibility = lost
Score
-4
August 19, 2008 6:18:27 AM

It's called planning ahead, it's kind of needed
Score
0
Anonymous
August 19, 2008 8:08:45 AM

Good to see some folks drinking the cool-aid. It is H2'2008, correct? Did I miss the 32nm node? Exactly when will 32nm go into production and then 22nm? 2011 seems a bit optimistic for IBM, yet alone AMD which hasn't even sold a SINGLE 45nm part yet! Help us out on this one... AMD 45nm end of the this year 2008... 32nm maybe mid-2010/late 2010... and then 22nm the following year?

"but IBM?s news is a good sign that chip manufacturer will be able to easily scale to this new level by the end of 2011"

If only we could fast forward 3 years! "EASILY SCALE"?!?!? Timeline?!? (are you trying to minimize the actual use of 45nm and 32nm capital equipment to throw it away as soon as possible?) This makes no economic or technical sense!

Finally consider READING the announcement - IBM demo'd/claimed a single SRAM cell (which is 6 transistors), not even an actual test chip (which is what you reference when discussing Intel). A 22nm SRAM cell does not mean a 22nm test chip, yet alone a yielding 22nm wafer. When you say Intel is not expected to show 22nm until next year you are no doubt referring to a TEST CHIP (containing 100's of millions, if not a billion transistors) as opposed to the IBM 6 transistor announcement... a wee bit (maybe 5 or 6 orders of magnitude?) different!

If you don't understand the technical details, which from the article it is clear that you don't, you shouldn't be making any analysis from it.
Score
0
Anonymous
August 19, 2008 8:25:05 AM

'According to IBM, the creation of the new cell was aided by factors including: "Band edge high-K metal gate stacks, transistors with less than 25nm gate lengths, thin spacers, novel co-implants, advanced activation techniques, extremely thin silicide, and damascene copper contacts".' (source - ZDNET)

A bit odd that they would say transistors less than 25nm gate lengths for a 22nm node (which by the way should have transistor gate lengths in the 19-20ish or smaller range)

I think what we have here is a typical IBM PR announcement which will be found to have several holes if the details are ever presented. Also of note, a working SRAM cell is not the same as a working SRAM chip, as Wolfgang somewhat implies in his commentary. From info on the web there is no IBM mention of an actual working SRAM test chip, just a 1 bit (byte?) cell.
Score
0
Anonymous
August 19, 2008 11:40:52 AM

The devices developed and manufactured by AMD, Freescale, IBM STMicroelectronics, Toshiba and the College of Nanoscale Science and Engineering (CNSE)Major failure in the thread title, should be IBM not AMD reaches 22nm. No you just fail at reading comprehension.
Score
2
August 19, 2008 11:53:26 AM

I "work" with alot of companies but I do the work and they dont get the credit. Seeing this title just pisses me off because it was purely IBM's R&D NOT AMD's. They could have put Sony is first to 22nm as well since Sony is a "partner" as well. AMD is bleeding to death and folks need to realize that. AMD still cant produce a above economic CPU to compete with Intel and this is after 2 YEARS since Core 2 came out. Intel isnt backing down, Core I7 is and will smash what AMD has out or even coming out in the next 2 years. Yes Intel was down with P4s but the original Bartons that AMD put out to compete with the P4 didnt exactly beat them.

The A64 beat the P4s in games but office it was the P4s domain. AMD puts out good chips, but they need to get back on track for competing or we all lose to 90's Intel pricing again.
Score
0
August 19, 2008 12:32:25 PM

.... Good job AMD........
Score
3
August 19, 2008 1:22:40 PM

I'm beginning to think some guys around here are paid to write good things about AMD.
Score
0
August 19, 2008 2:52:13 PM

Wow, misleading title.
Score
-3
August 19, 2008 4:40:43 PM

um, overclocking margins isn't a magic word that gets more magical when you microsize... they up the speeds accordingly when manufacturing the new parts see, or they'll just be the old parts made smaller (and indeed better for overclocking)..
the margin for overclocking remains forever the same :) 
Score
2
August 19, 2008 7:38:19 PM

My Money is on Intel... Unfortunately

AMD will be lucky if there producing processors come 2011
Score
0
August 19, 2008 8:24:18 PM

grieveMy Money is on Intel... UnfortunatelyAMD will be lucky if there producing processors come 2011


That's your mistake. ntel does not require your support; not do they care about you. They have hurt you and now you reward them? Additionally you do not need ntel. The other company is much more innovative - keep watching. Intel is following AMD.

Question the marketing machine - talk, misleading talk - you speak like you know because they have told you what to say. It is called training parrots. Wait for the releases and see the truth - beyond the biased carefully selected tests - one of the biggest bias areas is test conditions that can be easily adapted to illustrate through slight of hand. Anadtech is the worst for making ntel look good, and especially for making AMD look bad. The 2 are closer than you think. Not that 2, the other 2.
Score
-1
August 19, 2008 9:11:03 PM

Dudes chill ... consortium's always make announcements like this. Just be glad it is actually happening. Christ look at what competition recently yielded within the graphics segment, I can not if I choose to buy a 9800GTX for less than 200$ easy. I have even seen a few @ 150. Intel C2D's slowly track downward in price ... why is that? For the same reason NVIDIA never saw fit to grace us with a steep early discounts until the 4850 was released... lack of competition.

I am not sure why all the hate springs forth at any positive message towards AMD ... when in the end it is your and mine best interests to have healthy competition.
Score
1
August 20, 2008 8:52:50 PM

ZootyGrayThat's your mistake. ntel does not require your support; not do they care about you. They have hurt you and now you reward them? Additionally you do not need ntel. The other company is much more innovative - keep watching. Intel is following AMD. Question the marketing machine - talk, misleading talk - you speak like you know because they have told you what to say. It is called training parrots. Wait for the releases and see the truth - beyond the biased carefully selected tests - one of the biggest bias areas is test conditions that can be easily adapted to illustrate through slight of hand. Anadtech is the worst for making ntel look good, and especially for making AMD look bad. The 2 are closer than you think. Not that 2, the other 2.

...While innovating,their CPU's themselves aren't changing.Research and development please???
I'm tired of your spam of AMD fanboyism,it's really getting old,besides.Prove AMD is literally(NOT THEORITICALLY) better(right now,and when the new processors are released from both sides).I could give you a loan,perhaps ;) 
Score
0
August 20, 2008 8:54:56 PM

ZootyGrayThat's your mistake. ntel does not require your support; not do they care about you. They have hurt you and now you reward them? Additionally you do not need ntel. The other company is much more innovative - keep watching. Intel is following AMD. Question the marketing machine - talk, misleading talk - you speak like you know because they have told you what to say. It is called training parrots. Wait for the releases and see the truth - beyond the biased carefully selected tests - one of the biggest bias areas is test conditions that can be easily adapted to illustrate through slight of hand. Anadtech is the worst for making ntel look good, and especially for making AMD look bad. The 2 are closer than you think. Not that 2, the other 2.

Oh yeah,actually another note.Intel's stock.They have it.It's a good stock to invest in,unlike AMD.
Score
0
August 21, 2008 4:49:49 PM

jaragon13 said:
Lol,you guys are totally ignorant of the fact AMD works with IBM...

Ehh, it's more like AMD is a customer of IBM...
Score
0
August 22, 2008 1:02:42 AM

Amd should just skip 45nm and 30nm and focus on releasing in about two years because current architecture is crap compared to c2d. Is this a different architecture or just a die shrink?
Score
0
August 22, 2008 4:44:48 PM

^This has nothing to do with any specific processor, just a manufacturing node. Of course, AMD should have a new architecture out by the time they move to 22nm.
Score
0
September 12, 2008 1:22:08 PM

When processor get smaller thats will increase the performance
and make alto space for add more registry and the the cpu bus get smaller and faster .
because their is less lag in data transform

Score
0
October 16, 2008 10:16:27 PM

I thought that Intel used a High-K dielectric gate in all Core 2 Duo including 65 NM models?
Score
0
!