It defines Intel's cadence of process and design execution, but for AMD, "Tick - Tock" is beginning to sound like the countdown to its own dissolution. Every time Intel makes an announcement or a demo much like this week's IDF, AMD by comparison just looks more and more pitiful. It can't be said that AMD didn't bring this upon themselves. For the life of me I cannot comprehend why would AMD think that announcing plans to ship 3-core defects can be considered as stealing thunder while Intel talks about 4, 8 and 16 core CPUs.
Of course, the misery doesn't end there, while still trying to recover from its abysmal product launch, AMD is left with no choice but to look at their fluke 2.5Ghz Barcelona beaten to death by Harpertown, Intel’s soon to be launched, 45nm Xeons. The big difference is that the new Xeons with the 1600MHz bus has an official launch date and will be shipping in volume real soon.
The benchmarks confirms Intel's claim to floating point superiority, further increasing the performance gap with AMD. The only thing worse than stumbling is doing so while the competition executes efficiently.
From the TechReport:
Those new Opterons will certainly have their hands full with Intel's 45nm Xeons, though. The Xeon E5472 extends Intel's performance lead over the fastest quad-core Opteron we've seen yet, the 2.5GHz model 2360 SE. ...it looks like Intel will continue to lead in the server and workstation markets. The same may be true in other markets served by these same basic CPU designs, but only time will tell for sure.
9 comments:
A year of smoke and mirrors is what AMD furnished their investors with, so they'll get what they deserve: Massive restructuring in 2008 from the hands of Intel's massive 45-nm assault. It doesn't matter anymore if AMD can get K10 clocks up to 3.0 Ghz in Q1 08 or get Shanghai out by Q4, Intel's advantages in 2008 for clock, cost, and die size are too overwhelming. Since Penryn handily outperforms K10 per clock in the markets that matter for revenue, at much lower cost per unit performance, AMD have no hope of competing. It's over for AMD in their current form.
I'm impressed by the improvement in power consumption on the new Xeons. They still use more power than the Opterons, but AMD can't be happy to see them improve as much as they did, especially with the performance gains. It becomes harder to promote the 'performance-per-watt' metric when your competitor makes a more compelling case.
If AMD has any trouble at all getting Barcelona to 2.5GHz and higher and Intel is able to get Harpertown out on schedule and ramp up production quickly... it could make for two or three really bad quarters for AMD, just when they were hoping to start a slow turnaround.
Anonymous said...
I'm impressed by the improvement in power consumption on the new Xeons. They still use more power than the Opterons,
Actually the Xeons use less power than the Opteron, but the platform as a whole especially when it has a lot of FBDIMMs, uses more power. That's why Intel desktop and mobile system which base on the same architecture use less power than the AMD's.
There are almost nothing AMD can win at the desktop and laptop end now, except in mid to low end segment with pricing.
as of now, there are noly a few matrics that AMD marketing department would like you to know, the memory intensive stuff, and the MP server performance per watt (along with that, they won;t mention the MP, hoping the general public confused and take it as general).
Why i do not mention floating point? because the specfp_rate2006 result is more of memory intensive constraint, instead of the fp engine itself. That's why you see intel still won some fp benchmarks that is not memory intensive. While I do not disregard AMD's memory advantage on this, but i just stress out what it really won, and that doesn't represent the general fp power nor general application usage except certain server workload as well as some HPC application
Newegg has pulled the 1.7GHZ Barcy...lol
"Newegg has pulled the 1.7GHZ Barcy...lol"
There's a 1.7GHz? Huh I thought the slowest bin was 1.9... customers must have been really demanding lower clocked chips over these theoretically higher clocked chips which will come.
Was the 1.7GHz one of those cool new "native" tri-cores?
Was the 1.7GHz Barcelona the one that was listed for $790?
If so... ouch, LOL.
There's a 1.7GHz?
3-core... anyone else get the feeling AMD is going backwards?
"3-core... anyone else get the feeling AMD is going backwards?"
Roborat you clearly are a fool - don't you know AMD is releasing these products because customers are demanding it! We are talking "native" tri-core technology here, and ENERGY EFFICIENT CPU's.
There's a rumor floating around that AMD will be soon releasing the Uni-core (K10 quad with 3 cores "intentionally" disabled) - it operates at speeds near 1.1GHz, but it kicks butt on energy consumption!
[end sarcasm]
We are talking "native" tri-core technology here, and ENERGY EFFICIENT CPU's.
Correct mate.
Besides Intel can never make a tri-core out of a dual.
See the IBM Cell with 8 cores; they can disable as much cores as they need.
Intel version is very easy to do.
What they just have to do is create a new packing with 300mmx300mm and put as many cores that space can hold.
In fact what is Intel waiting for returning with SLOT processors? That would give them enough space to release 16 cores CPUs today!
Post a Comment