Nehalem-EP......BLOOMFIELD

[JCornell]

damn would have been to good.

same with sisoft sandra?

Been a while not using sisoft, Will try it.

[savantu]

Been a while not using sisoft, Will try it.

Please do if you're not bound by any obligations.

CPU tests ( arithmetic , multimedia, multicore efficiency ) and memory BW+latency would be really nice.

[Donnie27]

Can't run everest, it crash while click the everest.exe

I did run CINEBENCH R10 : Rendering (xCPU)

Watching and waiting

[metro.cl]

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.

[Anemone]

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.

[Fuji]

Quadcore penryn is good enough to wait till 2H 2009 for 32nm shrink where price/performance ration against Penryn will be much better.Most probably octalcores will be available then.

People are expecting marvels from Nehalem but it will be more evolution than revolution.

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.

[JumpingJack]

http://www.anandtech.com/cpuchipsets...oc.aspx?i=2991
"In our recent DDR3 vs. DDR2 review we discovered a 16% to 18% improvement in memory bandwidth with the P35 chipset. This translated into a 2% to 5% increase in real world performance in some computer applications.

This bandwith will be only for overpriced Bloomfield Nehalem,Nehalems in lower price will come in 2H 2009 and will have only dual channel.I expect Bloomfield setup to be 100-150% more expensive than Penryn setup (Intel will position Bloomfield as high-end system and it will cost) with performance around 10-20% single thread ,20-40% multithread.New drivers and better mobos won't help more than 1-3%.

So until you really need new computer or you are into multithreaded apps upgrade to quadcore Nehalem does make sense.Otherwise you will pay 100% more for about 10-20% improvement - not worth IMO for typical user it's much wiser to upgrade GPU or wait for cheap SSDs.
Quadcore penryn is good enough to wait till 2H 2009 for 32nm shrink where price/performance ration against Penryn will be much better.Most probably octalcores will be available then.

People are expecting marvels from Nehalem but it will be more evolution than revolution.

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

[Movieman]

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

Very well said!

[therightway]

http://www.anandtech.com/cpuchipsets...oc.aspx?i=2991
"In our recent DDR3 vs. DDR2 review we discovered a 16% to 18% improvement in memory bandwidth with the P35 chipset. This translated into a 2% to 5% increase in real world performance in some computer applications.

This bandwith will be only for overpriced Bloomfield Nehalem,Nehalems in lower price will come in 2H 2009 and will have only dual channel.I expect Bloomfield setup to be 100-150% more expensive than Penryn setup (Intel will position Bloomfield as high-end system and it will cost) with performance around 10-20% single thread ,20-40% multithread.New drivers and better mobos won't help more than 1-3%.

So until you really need new computer or you are into multithreaded apps upgrade to quadcore Nehalem does make sense.Otherwise you will pay 100% more for about 10-20% improvement - not worth IMO for typical user it's much wiser to upgrade GPU or wait for cheap SSDs.
Quadcore penryn is good enough to wait till 2H 2009 for 32nm shrink where price/performance ration against Penryn will be much better.Most probably octalcores will be available then.

People are expecting marvels from Nehalem but it will be more evolution than revolution.

To expect a Core 2 Duo style beatdown for every processor launch would be asking too much. that said, Nehalem looks like a monster on top of a beast (Conroe).

[virtualrain]

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

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.

[JCornell]

Can't execute SisoftSandra too


...

[JCornell]

PI32M


...

[Shintai]

JC, do you have problem running other things. Or basicly just the HW detecting programs.

[Hornet331]

hmm, ok i know one last thing, can you try crystalmark?

[savantu]

Nehalem at 2.93GHz runs wPrime 32M with the speed of a QX9650 at ~ 4.4GHz.

That's 50% clock/clock advantage in this multithreaded test.

[Donnie27]

Shintai,Pinacolada summed it up well here:

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

[perkam]

informal, Jack summed it up well here:

Good stuff.

I had wished Nehalem would clock a tad higher on air, but then again, if it clocked the same as the quad cores with 8 cores, AMD would be a chip recycling plant by now

Perkam

[Donnie27]

Good stuff.

I had wished Nehalem would clock a tad higher on air, but then again, if it clocked the same as the quad cores with 8 cores, AMD would be a chip recycling plant by now

Perkam

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.

[nachthymnen]

Those Nehalem are really fast

[Neuuubeh]

I did run CINEBENCH R10 : Rendering (xCPU)

Post your CPU scores if you could please

[JCornell]

JC, do you have problem running other things. Or basicly just the HW detecting programs.

No problem at all, That's just simply HW & SW crash(can't detect the HW info).

[JCornell]

CINEBENCH10 Rendering xCPU


...

[FlanK3r]

Can't execute SisoftSandra too


...

try pls Wprime 1024M, thx

[JCornell]

try pls Wprime 1024M, thx

Thought you never ask


...

[JCornell]

Those Nehalem are really fast

WPrime scores, I did compared with your QX9650 @5.6~5.7G
Bloomfield platform with 2.93GHz + 1*2G DDR3-1066





...