X-bit labs

Started by: Joz | Date 03/04/08

Comments: 30 | Last Comment:  03/11/08

[1-19]

1. 3ghz? HAAA HAAAAAA

VIA for life

2. I suppose it is a small step in the right direction for AMD - I hope AMD has learnt the harsh lessons of recent

3. Badonkadonk

4. Second half 2008 = December, presumably ...

December, engineering samples are shipped to reviewers.
Fully available first half of 2009. My bonbon prediction.

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.

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.

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.

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.

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.

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...

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.

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.

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.

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...

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.

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.

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.

8. My bad... saw the screens. Is CPUZ showing the correct core voltage? 1.648V is awfully high!

9. I only hope AMD can drastically reduce the power draw under load and @ idle

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.

11. Amazing... AMD is comming back..

12. Run AMD, run!

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.

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.

15. Just enough to be still alive AMD? certainly nothing special about these chips...

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.

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.

18. ROFLMAO@Cuervo #6

19. Finally!

[1-19]