• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Nocona review.

Opty got pawned in 3D rendering. Now the question is: "What idiot would play games on a server?!"
 
still pissed off. The performance would have been better if the bus architecture was better.
 
M4d-K10wN said:
Opty got pawned in 3D rendering. Now the question is: "What idiot would play games on a server?!"

I wouldn't say "pawned." Xeon got clobbered badly in Maya but edged ahead in 3DSMax. Opty DID take a heavy beating in Photoshop and FlashMX tho.

Not sure WTF happened with HyperThreading in Maya. :confused: I thought Intel had ironed out HT performance regressions...but then again, adding a bunch of pipeline stages and other tweaks might have wrinkled it all up again.

As far as Xeon bus architecture, that should get a boost with Twin Castle.

EDIT: what I REALLY wanted to see, though...I want to see EM64T in action. GamePC supposedly had an EM64T-compatible build of Win64, so I don't know what held them back. I haven't heard good things about EM64T so far, but I figure maybe it will surprise me.
 
Kelledin said:
I wouldn't say "pawned." Xeon got clobbered badly in Maya but edged ahead in 3DSMax. Opty DID take a heavy beating in Photoshop and FlashMX tho.

Not sure WTF happened with HyperThreading in Maya. :confused: I thought Intel had ironed out HT performance regressions...but then again, adding a bunch of pipeline stages and other tweaks might have wrinkled it all up again.

As far as Xeon bus architecture, that should get a boost with Twin Castle.

EDIT: what I REALLY wanted to see, though...I want to see EM64T in action. GamePC supposedly had an EM64T-compatible build of Win64, so I don't know what held them back. I haven't heard good things about EM64T so far, but I figure maybe it will surprise me.
It will be depressing to say the least. The INQ did an article and said that a software tester said that the Nonaca extensions sucked. Talk about being nice. The Xeon needs more bandwith. It boils down to that. I still dont think the Xeons have a 31 stage pipeline. We'll wait for AceHardware to review it and see what happens. Intel should use a 128 bit XDR RAM memory controller when it comes out or a 128/256 Bit memory controller. The Xeons need that boost in bandwith.
 
Kelledin said:
EDIT: what I REALLY wanted to see, though...I want to see EM64T in action. GamePC supposedly had an EM64T-compatible build of Win64, so I don't know what held them back. I haven't heard good things about EM64T so far, but I figure maybe it will surprise me.


im not sure what you mean but they did testing in WindowsXP 64 bit
 
kronchev said:
im not sure what you mean but they did testing in WindowsXP 64 bit

Well, yes, but I would have liked to see more extended analysis--like testing each processor running SPEC compiled in both 32-bit and 64-bit mode, and seeing what performance gain/loss there was on Xeon vs Opteron. Maybe some custom-coded benchmarks as well, to analyze the impact of using 64-bit pointers/integers vs 32-bit.

I'm hearing some pretty ugly rumors/details about EM64T performance; it would be nice if those rumors could be confirmed or debunked once and for all.
 
It seems that a few of the tests didn't really take advantage of multiple CPUs (for example, the LAME test).

Of course, you can't expect a site called "Games PC" to do much in the way of server tests.
 
Back
Top