At CeBit show that is currently on in Hanover, Germany, AMD for the first time demonstrated their quad-core processors with K10 micro-architecture manufactured with 45nm process. The processors were produced in Dresden, Germany, in AMD’s Fab 36 300mm manufacturing facility, using an advanced 45nm process co-developed with IBM. The first 45nm chips demonstrated by AMD include the “Shanghai” product for server and “Deneb” for desktop platforms.
This fact proves that AMD is on track to meet key production milestones, which support OEM and channel product delivery plans. AMD is ramping production of its first 45nm products in the first half of 2008 and expects 45nm products to be available in the second half of 2008.
Key innovations within AMD’s 45nm process are scheduled to include Immersion Lithography, Fourth-generation Strained Silicon, Ultra-low-k Dielectrics, and High-k/metal Gates. However, the initial 45 nm CPU generation will not use high-k dielectric metal gate technology. AMD believes that it can be “competitive” without high-k at this time, but high-k is an option to be introduced at a later stage of 45 nm production.
These enhancements are aimed primarily at improving AMD’s transistor designs and interconnect circuitry to enable sustained linear increases in processor and platform performance-per-watt, while also overcoming inherent challenges introduced from continued reduction of transistor size.
45nm Deneb and Shanghai processors are expected to have their shared L3 cache increased to 6MB. As a result of transition from 65nm to 45nm production technology, they should be able to drop processor TDP one step down. The top CPUs should have their maximum TDP reduced from 140W to 125W. More mainstream quad-core processor models should have their TDP dropped from 125W to 95W with the transition to 45nm process. They also expect the clock speed of the top CPU models to increase at least to 2.8-3.0GHz. All 45nm desktop AMD processors scheduled to be released this year will be designed for Socket AM2+ and will support DDR2-1066 SDRAM. Only in Q1 2009 we should see Socket AM3 processors that will also support DDR3-1333 in addition to their compatibility with DDR2 memory.
Comments currently: 31
Discussion started: 03/04/08 12:40:52 PM
Latest comment: 05/31/08 09:57:00 AM
Expand all threads |
Collapse all threads
[1-20]
1.
3ghz? HAAA HAAAAAA
VIA for life
[Posted by: Joz | Date: 03/04/08 12:40:52 PM]
2.
I suppose it is a small step in the right direction for AMD - I hope AMD has learnt the harsh lessons of recent
[Posted by: J-Hawke | Date: 03/04/08 01:04:10 PM]
3.
Badonkadonk
[Posted by: unclesharkey | Date: 03/04/08 01:16:07 PM]
4.
Second half 2008 = December, presumably ...
[Posted by: Cynic | Date: 03/04/08 01:26:10 PM]
+ expand thread (1 answer)
- collapse thread
December, engineering samples are shipped to reviewers.
Fully available first half of 2009. My bonbon prediction.
[Posted by: Mr. BonBon | Date: 03/04/08 01:36:25 PM]
5.
Well I guess they had to skip over 55nm. This is doubly good for AMD since they are likely to use 45nm in their GPUs as well. I think they will try out hi-k on their mainstream GPUs first before using that technology on their CPUs. Right now though I just want to see their quad core CPU's without the TLB bug.
[Posted by: Megamanx00 | Date: 03/04/08 01:47:57 PM]
+ expand thread (2 answers)
- collapse thread
Unlikely - the GPUs are still made by TSMC as they were when ATI was separate. I don't think they are made in the same fabs AMD uses for CPUs, so I would not expect any correlation between what technologies they deploy in CPU vs GPU.
[Posted by: jibbo | Date: 03/05/08 11:02:06 AM]
CPUs usually go by "full-node" process steps (130nm, 90nm, 65nm, 45nm) developed in-house by the manufacturer.
GPUs go with these and also "half-node" steps (110nm, 80nm, 55nm) mostly fabbed at TSMC. This is because of their faster product cycles, always pushing the envelope.
[Posted by: cheeseman | Date: 03/05/08 04:54:20 PM]
6.
Did they actually demo a System with a 45nm CPU or just show a wafer? That seems like a very big difference to me.
Regardless, good luck AMD with your shrinking. They don’t need much luck as they are experts at shrinking things; e,g.share price, profits, credibility.
[Posted by: Cuervo | Date: 03/04/08 03:34:57 PM]
+ expand thread (1 answer)
- collapse thread
lol, i used to be an amd fanboy, 80% of my 401k WAS in AMD,- thank god i saw the light before Dr. Ruiz w/ his degree from a cracker jack box stepped in.
[Posted by: suetonius | Date: 03/09/08 11:28:56 AM]
7.
What demo? All I find is an announcement. AMD, show us the real beef please...
Even with TLB fixed, ain't gonna be faster than current Intel's Core 2 Quads. Anyway, by the time their K10 is really ready, watch out for Nehalem. If the leaked Sun slides are anything to go by, and if true then Nehalem is truly a monster.
I guess Intel will be waiting to spring another coup again, or maybe not if 45nm K10 turns out to be a dud like Barcey...
[Posted by: Fluff Detector | Date: 03/04/08 04:11:01 PM]
+ expand thread (7 answers)
- collapse thread
Ace Hardware has some good estimates of FP/INT performance of Shanghai versus Nahalem. AMD can't see to catch a break these days. They finally get on track only to face a "tock" improvement from Intel.
[Posted by: aka_evil_e | Date: 03/04/08 08:14:28 PM]
im going hold judgement on that, but sinds they are reintroducing Hyper-threading im going to take these numbers with a pinch of salt and wait for some realworld benchmarks.
hyper-treading had a way giving great results in synthetic benchmarks but then falling flat on its face in real world apps (often you where better off turning it off).
now ofcourse software is more threaded then in the p4 time but nehalem is also not a long-pipelined cpu anymore which was the reason for HT in the first place.
[Posted by: the_countess | Date: 03/05/08 01:18:30 AM]
They may be calling it HT again, but really the purpose will be somewhat different--much more akin to traditional SMT rather than the hack needed in the P4 due to the inaccessibility of deeply pipelined execution units. Processors nowadays have much more cache and much better memory latency figures than P4s did, so this iteration of HT should be a lot more effective at reducing thread switch latency and all the penalties that go along with that outside the execution pipeline itself.
[Posted by: MTX | Date: 03/05/08 05:45:45 AM]
Actually, I also meant to say: glad to see that L3 is going up to 6MB in the 45nm Phenom. Since it's not exactly a fast cache, at least it should be relatively large...
[Posted by: MTX | Date: 03/05/08 05:49:00 AM]
the more cache en lower latency ect only mean CPU's have less reason to use HT because they can keep their pipeline full without it.
[Posted by: the_countess | Date: 03/06/08 03:30:53 AM]
You're too hung up on P4, maybe because of the "HT" name. Keeping the pipeline full during normal execution isn't the issue any more (and never should have been)--SMT is all about thread switch latency, which can take several microseconds otherwise. True, it's still better to switch threads by flushing and refilling a second pipeline while keeping the execution units working on the contents of the first--but more importantly, the greater the number of threads that can be held ready to run on the processor, the less time the OS needs to spend in the scheduler and in context switches. The latter is what really takes the time.
[Posted by: MTX | Date: 03/06/08 06:41:19 AM]
actually shainghai is going to just inch out current core2's mhz for mhz and run at up to 3ghz. so they will be competitive clock for clock and in total performance. and, as always with AMD less expensive.
[Posted by: the_countess | Date: 03/05/08 01:24:50 AM]
8.
My bad... saw the screens. Is CPUZ showing the correct core voltage? 1.648V is awfully high!
[Posted by: Fluff Detector | Date: 03/04/08 05:06:52 PM]
9.
I only hope AMD can drastically reduce the power draw under load and @ idle
[Posted by: alpha0ne | Date: 03/05/08 12:59:34 AM]
10.
Bigger L3 Cache finally, but I hope they also improve the latency of this cache. I think that is one of the factors holding back Barcy.
[Posted by: Bill Gates | Date: 03/05/08 08:39:02 AM]
11.
Amazing... AMD is comming back..
[Posted by: Chris | Date: 03/05/08 09:16:24 AM]
12.
Run AMD, run!
[Posted by: BorgDrone | Date: 03/05/08 01:12:44 PM]
13.
This seems good for AMD. AMD should take a risk to have a maximum TDP of 95 watts for enthusiast processor models. Also spend time designing energy efficient motherboard chip sets. This will make sure if their processor does not come close to equal or overcome Intel's processor performance at the time of launch, they can still have a selling advantage.
I will like to see total energy consumption (motherboard, processor, and memory) be around 150 watts to 175 watts. Right now total energy consumption of both Intel and AMD systems are close to 300 watts.
[Posted by: linuxnerd | Date: 03/05/08 03:59:50 PM]
14.
Too late to help. Second half of 2008 probably means November-December. Remember the delays with Phenom? Even with the power consumption drop, they are still more power-hungry than Intel's offerings.
[Posted by: Kai | Date: 03/06/08 06:29:17 AM]
15.
Just enough to be still alive AMD? certainly nothing special about these chips...
[Posted by: muzzel Mo | Date: 03/06/08 05:31:01 PM]
16.
well i think this is good for AMD even if it got slightly lower performance than intel's product by then for the following reasons:
- 45nm will reduce the cost, reducing the price as well keeping AMD within the "lower performance (still very decent), cheaper prices" marketing strategy.
- i think there might be more to the package than just that, some feature, some SSE5 instructions improving multimedia performance .. etc.
- hopefully 3.0Ghz will reduce the huge gap between intel products and AMD products, i didn't see intel releasing anything above 3.2Ghz in their latest road map.
[Posted by: Me, expressing myself | Date: 03/07/08 12:02:19 AM]
17.
3 GHZ without IBM would have been a joke.
But with IBM's assistance this claim may have merit.
We'll see since they don't have much of a choice against Intel.
If they want to survive in the high end market that is.
[Posted by: xxx | Date: 03/07/08 06:25:31 AM]
18.
ROFLMAO@Cuervo #6
[Posted by: Chris | Date: 03/09/08 11:26:07 AM]
19.
Finally!
[Posted by: funkyu | Date: 03/11/08 07:26:32 AM]
20.
excellent news amd!i want a 45nm quad!!!
[Posted by: marius30 | Date: 05/31/08 09:57:00 AM]
[1-20]
Make Home Page
Add to Favorites
Print article
Send link to friend
Digg this
Post to del.icio.us
Post to Slashdot
