Sager NP5760 & Merom :-)

All tests were done with the 512MB GO 7900GTX. We will be updating this thread again with scores after a OC.

3D Mark 05 w/ Yonah = 8512
3D Mark 06 w/ Yonah = 4748

3D Mark 05 w/ Merom ES = 8633
3D Mark 06 w/ Merom ES = 4807

Photoshop 7.0 Bench

Some people are tired of seeing 3dmark and Pcmark and similar benchmarks, while these are visually attractive benchmarks they are not in many cases indicative of real world situations, this is not the case with photoshop. It is also a wonderful test of all round system performance, specifically memory bandwidth and CPU processing power. Massive files are also a good test of hard drive access performance as photoshop will rely heavily for its "paging file".

 

So if i'm reading that right... that's only about a 4% improvement.
Not as much as I would have thought...

 

The difference in the Photoshop tests is bigger in the first few tests, rather than the last few. Probably wouldn't have seen much of a difference in the 3DMark tests anyway.

Thanks for doing these tests Justin - nice to see.

 

Will the performance be better when we have a 64 bit OS or does that matter?

 

If the machine is running a true 64-bit application (not merely a 32-bit one with a 64-bit executable) on a 64-bit OS (necessary to run 64-bit apps), then yes, it would be faster generally speaking.

 

G the 'old' centrino looks so bad in those results.A few years ago it was the bomb,now it looks like its rowing a boat on a sunny sunday.

 

Indeed. However, keep in mind that those are multi-threaded benchmarks, so a single-core CPU doesn't stand a chance. In a single-threaded benchmark, it probably wouldn't look as bad.

 

Also notice that the Fujitsu running the single core is also only running with 512MB DDR1/333 PC2700 vs. 2GB DDR2/667 PC5300 memory and a 4,200RPM HDD instead of a 7,200RPM on the Sager. It isn't just the processor that makes it slower.

Nice tests Justin. I really like the real world tests much better than the synthetic benchmarks...they are far more meaningful

 

Thanks Donald, I agree.

Given the Fujitsu does have slower RAM, HD and the old Centrino; its amazing to see how much faster the Core Duo and Core 2 Duo are compared to it and how technology has evolved with the latest offerings.

 

Does 3dmark05/06 accurately simulate AI and physics code? Because if it doesn't your going to see a much bigger gain in performance in CPU limited game like Half-Life 2 with a Merom.

 

The CPU tests in 3DMark05 are completely useless, but 3DMark06 is very accurate - it is designed to simulate next-generation games and does quite a good job.

 

ummm , the PS7 test while a good idea aren't accurate .

Sure the Merom is much faster but PS7 is memory hungry and comparing a system with 512MB & 4200 rpm VS. 2GB & 7200 rpm isn't going to tell you much about the cpu upgrade .

 

is it me or that my super pi test on 1m ram faster than merom? I ran 30 seconds. Though i know 1 second isnt that big of a deal. But i got a 2.0ghz and that was a 2.16 merom. Um could someone test merom on 2m? btw i got 1 minute and 4 seconds

 

Uhh.. that's why he ran it on 3 different machines.
the third column is an identical config to the second with the only thing changed is the CPU...
You might need to scroll to the right to see it if your res is too low.