JC can you tell us if this is still Single Channel memory? what is the issue with triple channel?
Thanks for posting SS of Nehalem, more benchs would be awsome.
From a Yorktown this probably isn't much of an improvement, but from the older first gen Conroe's 2 generations of improvements leading to an on die mem controller is pretty nice.
On the memory front, it's reasonable to expect DDR3 to fall a bit more by the time mainstream Nehalem's are available (early '09). And the prices slightly below now will probably satisfy the first adopters who are going to be buying the premium priced cpu's anyway.
I agree with what you said for the most part, but a 20-30% improvement is a very good improvement and I want one.
Now, you said that Nehalem is evolution vs. revolution.
What then would be a revolution?
I see it as both ways. it's a revolution in the fact that it completely revamps Intel memory subsystem. XeonMP? Yeah, not much has changed when it comes to bandwith per core and anandtech said that each core would get maybe 600 MB/sec right now.
You move to a 4 socket Nehalem and each cpu has it's own memory controller and is connected to each other by more than a northbridge. I see that as a combination of evolution and revolution.
it's a revolution in that it's the stepping stone for what's to come.
With the rise of the GPU, I feel as if the way to go is not only adding more cores, but adding dumb cores that crank out FP. Intel said that Nehalem was a modular design, and unused QPI paths could be used for other applications such as FP boosts.
I think was Intel moves toward graphics that we might see some of those cores in CPUs. The role of the GPU is changing in the world. Back in the day, you gamed on your GPU and that's about it. Now that there's actual scientific research to the GPU, I wouldn't be surprised if we say future cpus with a Larrabee partially integrated.
So i feel l like it's both.
However, one thing that i'm wondering. The die size of Nehalem is relatively large for an Intel portfolio. Now they plan on increasing the cache size by 50% and adding two cores for Westmere.
How much cache is too much? Could we not just switch to a faster memory subsystem and rely less on cache. I think that's an important thing to consider. So yeah that's my ramble.
This extraction is not quite fair, nor correct. The entire memory sub-system for Nehalem has been reworked, you cannot look at the off-die DDR2-DDR3 comparision and make the assumption you are making.
In terms of marvels, who knows ... we have very little info to go by ... however, the hype machine of Geslinger compared the leap of Nehalem over Conroe to the magnitude of Conroe over Netburst, this indeed would be marvelous. My take on it is that it will be less overwhelming in single thread, but multithreaded situations will be impressive on this magnitude... Anand's preview data seems to indicate that this is indeed the potential... 30-50% gains depending on the app (multithreaded of course).
This will be even more impressive in server, where the mem BW issue is much much more pronounced... Kanter (RWT) seems to think Nehalem will be nothing short of a miracle. Time will tell.... however, initial indications are very positive that your downplay of Nehalem is probably not warranted.
Jack
One hundred years from now It won't matter
What kind of car I drove What kind of house I lived in
How much money I had in the bank Nor what my cloths looked like.... But The world may be a little better Because, I was important In the life of a child.
-- from "Within My Power" by Forest Witcraft
Crunch with us, the XS WCG team
The XS WCG team needs your support.
A good project with good goals.
Come join us,get that warm fuzzy feeling that you've done something good for mankind.
Absolutely agreed.
Core2 already provides a lot more computational power than the average user needs. Many games cannot fully utilize the power of a Penryn quad and most Microsoft/Adobe apps don't even come close. So unless you are working extensively with video and rendering or folding, Nehalem probably won't benefit you much.
It should turn out some pretty impressive memory benchmarks and I agree with Kanter that it will be a miracle on server loads, particularly multi-socket systems where the new QPI and IMC architecture can really shine.
Can't execute SisoftSandra too
...
===N/A===
PI32M
...
===N/A===
JC, do you have problem running other things. Or basicly just the HW detecting programs.
Crunching for Comrades and the Common good of the People.
informal, Jack summed it up well here:
This will be even more impressive in server, where the mem BW issue is much much more pronounced... Kanter (RWT) seems to think Nehalem will be nothing short of a miracle. Time will tell.... however, initial indications are very positive that your downplay of Nehalem is probably not warranted.
Jack
I don't think this Optimized Paralleled performance test will not make that much difference for most Desktop apps. This is what's expected with Hyperthreading 2. I'd much rather see what those poorly optimized and fewer threaded apps will do. I'm not worried about it clock speed or overclocking.
Last edited by Donnie27; 07-17-2008 at 01:00 PM.
Those Nehalem are really fast
Battlefield 3: Nachthymnen666
CINEBENCH10 Rendering xCPU
...
===N/A===
ROG Power PCs - Intel and AMD
CPUs:i9-7900X, i9-9900K, i7-6950X, i7-5960X, i7-8086K, i7-8700K, 4x i7-7700K, i3-7350K, 2x i7-6700K, i5-6600K, R7-2700X, 4x R5 2600X, R5 2400G, R3 1200, R7-1800X, R7-1700X, 3x AMD FX-9590, 1x AMD FX-9370, 4x AMD FX-8350,1x AMD FX-8320,1x AMD FX-8300, 2x AMD FX-6300,2x AMD FX-4300, 3x AMD FX-8150, 2x AMD FX-8120 125 and 95W, AMD X2 555 BE, AMD x4 965 BE C2 and C3, AMD X4 970 BE, AMD x4 975 BE, AMD x4 980 BE, AMD X6 1090T BE, AMD X6 1100T BE, A10-7870K, Athlon 845, Athlon 860K,AMD A10-7850K, AMD A10-6800K, A8-6600K, 2x AMD A10-5800K, AMD A10-5600K, AMD A8-3850, AMD A8-3870K, 2x AMD A64 3000+, AMD 64+ X2 4600+ EE, Intel i7-980X, Intel i7-2600K, Intel i7-3770K,2x i7-4770K, Intel i7-3930KAMD Cinebench R10 challenge AMD Cinebench R15 thread Intel Cinebench R15 thread
Bookmarks