Immediately?Quote:
Originally Posted by Olivon
Printable View
Immediately?Quote:
Originally Posted by Olivon
Yes, in corporate time. You know, few meetings, few responsibility dodges etc.Quote:
Originally Posted by gallag
Not true. Many companies in history have released inferior products to replace good ones. Happens all the time. It shouldn't, but it does, and sometimes on purpose.Quote:
Originally Posted by Alex-Ro
Anyone still remember brisbane ? Half the cache, higher lat, and lower clocks than it's predecessor, all this on a new node...Quote:
Originally Posted by Alex-Ro
And first Pentium 4 as well...
True but Brisbane was alot better at undervoltingQuote:
Originally Posted by Kuroimaho
Wow, come on... Hope that's pure luck, or easily hotfixable.Quote:
Originally Posted by duron
No suprise there... I really want to see how the opterons do... if there is a simillar picture it will be devastating for amd...
Quite shocking to look at those graphs, after all these years of waiting for Amd to be competitive...
lol by THOSE metrics, westmere is 50% more efficient than bulldozer, and sandy bridge is 50% more efficient than westmere
sandy bridge PAYS YOU to buy it over bulldozer. unless electricity is free
Is it posible for the adic who ownes gf to devalue amd by holding back there products with a crappy process only then to buy amd for a bargan price? I can see adic buying AMD at some point in the future then gf launching an amazing revision of there current process. wheres my tin foil hat lol.
This error was common with the original Phenom as well. If it wasn't a hot topic then, I don't see why it should be now other than to let people complain more about BD. Shogun players might have a legitimate beef.Quote:
Originally Posted by zalbard
AMD would lose the x86 license in the process, so no that's not what's happening here.Quote:
Originally Posted by gallag
this has got to be the worst possible way to show efficiency.Quote:
Originally Posted by Olivon
first you dont go with the biggest most power hungry motherboards if you want an efficient system
second you dont simply add up times together. some benchmarks took a few minutes, other took a portion of a second. horrible weighting factor and right there shows they are about as dumb as you can get.
third, you show efficiency per app since there are multiple ways to do stuff, and if you really care about power consumption, you pick the app and method that does it best for you.
and last, you might turn off turbo so that you loose a little bit of performance, but gain a huge power return of power savings.
we all knew that these things are power hungry when pushed hard, this is just trying to use shock value to get more hits rather than a proper test.
btw for a quick reference, i was able to increase efficiency on thuban by over 30% by simply dropping the voltage from 1.3 to ~1.1v at stock clocks, and thats with a chip already built around efficiency.
+1Quote:
Originally Posted by Hornet331
I'm looking to see the opteron 6220 vs 8120 FX.
looking to see how L3 cache impacts the cores/ modules.
I would expect the largest gain in the opterons will come from the much more aggressive clockspeed. The current gen tops out at 2.2ghz for the 12 core magny cours and 2.8ghz for the 6 core lisbon. So considering the 8 core parts top out at 3.5ghz (3ghz no turbo) and the 16 core parts top out at 2.8ghz (2.3ghz no turbo) AMD can probably expect some decent gains in integer computation. The weird thing is the FP seems to be much weaker than expected. I can't remember which review it was (i think it was for the 2700k actually) but the fx 8150 had no problems keeping up in integer computation but failed in float point, which is odd since fp had always been AMD's strong suit since the athlon days.
Though the power draw of BD is certainly disappointing, THG was a little sneaky by disabling the Intel on-chip HD graphics and using an HD6850.
That saved 20-30w right there.
Top 12C MC today is clocked at 2.5Ghz.Quote:
Originally Posted by AliG
Quote:
Originally Posted by AbortRetryFail?
That is probably done for fairness. When you can't match up specs exactly since they are different platforms, you still try to make it as similar as possible. The likely purpose of the test was to compare efficiency in a system for workloads(none gaming). Since Zambezi doesn't have integrated graphics, they have no choice but to use a videocard. Intel could run off of the integrated graphics if need be for the test desired.
What would be an unfair test would to have the amd processor use a dedicated, while the intel used its integrated. Since none of these benchmarks are gaming ones, Intel would have the clear advantage since using integrated would probably save more power than using the 6850.
That contradicts with many other test results like:Quote:
Originally Posted by Olivon
http://www.rage3d.com/reviews/cpu/am.../index.php?p=7
http://techreport.com/articles.x/21865
Quote:
These results couldn't be much more definitive. In every case but one, distributing the threads one per module, and thus avoiding sharing, produces roughly 10-20% higher performance than packing the threads together on two modules. (And that one case, the FDom function in picCOLOR, shows little difference between the three affinity options.) At least for this handful of workloads, the benefits of avoiding resource sharing between two cores on a module are pretty tangible. Even though the packed config enables a higher Turbo Core frequency of 4.2GHz, the shared config is faster.
Those results are big news!Quote:
Originally Posted by duron
Why didn't they tests any games ? Bulldozer needs appropriate software to get it ticking !! Dunno if Windows 8 will cut it out of the box...
This was known for some time. Two threads from same module yield only 160% speed increase from a single thread, because with one thread you don't share resources.