SPECint_rate2006 (outdated?) scores for Barcelona

[accord99]

And you know what are the scores of Clowerton @1.9 GHz? Please share them with us!

The best published scores for a 1.86GHz/1066MHz FSB E5320 is
SPECint2006 13.6
SPECfp2006 11.1

http://www.spec.org/cpu2006/results/...806-01697.html
http://www.spec.org/cpu2006/results/...514-01054.html

[TarTheDark]

Intel Xeon processor 3040, 1.86GHz:

SPECfp®2006 = 12.5

SPECfp_base2006 = 12.3

http://www.spec.org/cpu2006/results/...625-01332.html

Dual core, though.

[DoubleZero]

So when we stop using bandwidth/rates benches. K10 suddenly drops behind...how funny...and how predictable.

And when we stop using benches that fit in the cache C2D suddenly drops behind... it's also funny...and predictable:


Look how L7345 beats the crap out of the E7320 despite being 200mhz slower... if that isn't funnier then any result K10 can produce i don't know what is.

But i guess it's ok to use cache, but completely wrong to use bandwidth... go figure.

[Shintai]

And when we stop using benches that fit in the cache C2D suddenly drops behind... it's also funny...and predictable:


Look how L7345 beats the crap out of the E7320 despite being 200mhz slower... if that isn't funnier then any result K10 can produce i don't know what is.

But i guess it's ok to use cache, but completely wrong to use bandwidth... go figure.

Since there is only 4MB DC Xeons and 8MB Quad Xeons..go figure it out. There is no 4MB quad Xeon. Its a wrong posting.

http://processorfinder.intel.com/det...px?sSpec=SLA69

But I would guess they use a single Quad there. And rest is dual.

[dave_graham]

again, (as i've said ad naseum), unless folks are using the production stepping vs. the B1 stepping tomorrow, you're going to see some pretty interesting results.

ask a lot of questions and try to understand what they're testing on. I've got no doubts that AMD wants the reviews to be positive, but given the huge populace of idiots in the reviewing world, someone's going to fubar it.

dave

[DoubleZero]

Since there is only 4MB DC Xeons and 8MB Quad Xeons..go figure it out. There is no 4MB quad Xeon. Its a wrong posting.

http://processorfinder.intel.com/det...px?sSpec=SLA69

But I would guess they use a single Quad there. And rest is dual.

That's a typo, E7320 is only 4mb.
http://www.hardwareschotte.de/hardwa...0+BX80565E7320

Don't you think the score is a bit high for a single Quadcore?

[JumpingJack]

again, (as i've said ad naseum), unless folks are using the production stepping vs. the B1 stepping tomorrow, you're going to see some pretty interesting results.

ask a lot of questions and try to understand what they're testing on. I've got no doubts that AMD wants the reviews to be positive, but given the huge populace of idiots in the reviewing world, someone's going to fubar it.

dave

You mean run something other than SpecFP2006? Sorry... couldn't help it... this is going to be the bench people focus on.

[JumpingJack]

And you know what are the scores of Clowerton @1.9 GHz? Please share them with us!

Clovertown 1.86 GHz best scores
http://www.spec.org/cpu2006/results/...0611-01262.pdf
http://www.spec.org/cpu2006/results/...0305-00613.pdf


SpecINT2006 peak 14.2, base 12.9
SpecFP2006 Peak 10.9, base 10.8

If you like, take the 2.0 clovertown results to
http://www.spec.org/cpu2006/results/...0806-01673.pdf
http://www.spec.org/cpu2006/results/...0301-00593.pdf

SpecINT2006 peak 15.5, base 14.0
SpecFP2006 Peak 14.0, base 13.6

[Shintai]

That's a typo, E7320 is only 4mb.
http://www.hardwareschotte.de/hardwa...0+BX80565E7320

Don't you think the score is a bit high for a single Quadcore?

Arh you are right. Ye could be so. Cache would have a large impact on the rates. Specially in 4 sockets.

[Motiv]

Clovertown 1.86 GHz best scores
http://www.spec.org/cpu2006/results/...0611-01262.pdf
http://www.spec.org/cpu2006/results/...0305-00613.pdf


SpecINT2006 peak 14.2, base 12.9
SpecFP2006 Peak 10.9, base 10.8

If you like, take the 2.0 clovertown results to
http://www.spec.org/cpu2006/results/...0806-01673.pdf
http://www.spec.org/cpu2006/results/...0301-00593.pdf

SpecINT2006 peak 15.5, base 14.0
SpecFP2006 Peak 14.0, base 13.6

Don't want to knock the results but why is the libquantum results so high? I didn't realise there was that kind of architecture improvement in clovertown?