These screenshots are real. Tamas told me that Everest can read L3 on AMD, and the cpuid is correct.Quote:
Originally Posted by tictac
Well done Fuad :up:
Printable View
These screenshots are real. Tamas told me that Everest can read L3 on AMD, and the cpuid is correct.Quote:
Originally Posted by tictac
Well done Fuad :up:
Does that mean that L3 is activate?
Do you know why Everest is saying that 512KB Cache L2 i asynchronous??Quote:
Originally Posted by cpuz
http://www.fudzilla.com/images/stori...celonak10a.jpg
I found the machine above as well, it had a stress test running on all four cores but the way they set it up you couldnt tell what was going on, the screens would flash too fast to make anything of what was going on.
I plugged in a mouse and stopped the stress test, I went into everest for screens.
The plaque on the side said it was an Opteron 2200
nemrod> remember previous screenshots of cpuz showing a L3. As I mentionned, cpuz does not look for L3 on AMD, so this information was wrong. Everest does look for L3, and therefore there is nothing irrelevant in displaying one. A latency test would tell if L3 is really activated (and what its latency is).
Lightman> Asynchronous refers to a cache design. AFAIK, K8 also uses an asynch L2.
That definitely validates these screenshots.Quote:
Originally Posted by FUGGER
yes the side of virtualization and efficiency.Quote:
Originally Posted by dinos22
I'm confused...Quote:
Originally Posted by cpuz
Asynchronous for me means clocked differently than core, but in K8 L2 cache is clocked @ core speeds.
Maybe it might be clocked with different speeds like caches from first K7 Slot CPUs??
Anyone to enlighten me...
EDIT:
After 20 minutes of thinking and digging....
Look at this and compare to QC screen:
Attachment 60327
On my machine Everest 4.xxx.xxx is showing L2 cahce as 'Full speed'.
This lead me to theory that L2 cache in K8 really is asynchronous and AMD can change it's multiplier. This also can answer why Everest picture of QC part is showing L2 cache as Asynchronous... simply it's not Full speed, it's clocked at different than 1.6GHz clock (probably 1/2 or 2/3 of core speed).
This theory is in conjunction with what Groo and some other people was saying... Demoed K10 is cripped... It's not fully working part!
AMD noted that the memory controler will be clocked a lil' higher than the core it self. That may have something to do with it.
Yes, but memory controller is connected with L3 cache (same power plane), not L2...Quote:
Originally Posted by TigeriS
Wierd, cause exactly one month ago Groo was reporting that the B0 stepping had come back and resulted in a "massive gain in frequency", that as a result we could expect 2.9 GHz quads at launch, and that they were 'dancing in the aisles' over at AMD.Quote:
Originally Posted by Lightman
Now Groo says that same B0 is "so broken" and so full of "bugs and more bugs" that any benchies taken of it should be disregarded as worthless. Methinks he needs to go back to AMD marketing and tell them to straighten out what story he's going to be peddling next week.
No need in any theory - it is known that those were engineering parts.Quote:
Originally Posted by Lightman
It even could not be other way.
The Barcelona servers at Computex are all running engineering samples of the chip that were provided to help server makers build their systems.
http://www.theinquirer.net/default.aspx?article=40181
AMD puts out Phenom teaser
Anyone know anything that is happening on June 10th in Montreal?
---
I didn't get the hint from the INQ the first time, apparently Formula 1 racing. Why not May 13th in Barcelona though :D
sounds like the quad phenoms are going to be very pricey.... right around when intel drops prices on their quads... i do hope amd builds a reasonably and competitively priced quad chip.
As I said in the news thread for the teaser, if Barcelona launches Sunday, then AMD has been sandbagging Barcelona all along. Which means there is no problem with the chips :) (if they were having problems why would they launch it Sunday?)Quote:
Originally Posted by red
Yepp.... :yepp:Quote:
Originally Posted by cpuz
Check this out: :up:
http://xtremesystems.org/forums/show...6&postcount=36
Perhaps we should wait before speculate... if they were having no problems why they miss the computex for an obscur launch 3 days latter? This few day difference would have allow to intel to developp a new architecture in response?Quote:
Originally Posted by Zytek_Fan
AMD want make big shows, they want to be the only one on the spot ligts, in the computex show evrey body is under spot lights.Quote:
Originally Posted by nemrod
maybe a idf like at montreal sunday with Barcelona. I'm asking myself why AMD cut the opteron prices if K10 is not on time ? :confused:
maybe it's a soft lunch and the cpu will be available on jully :shrug:
The software could easily be wrong.Quote:
Originally Posted by Lightman
Has AMD ever sandbagged before (like at K8 launch)?
It's just wishful thinking (even on my part :() to expect K10 desktop to make an appearance before Christmas...
Suman
Just wondered, if 1.6gz is doing the rounds. How would that translate to the POV results?
Wouldn't that translate quite well?
All speculation ofc.
The POV results were ran at the same current vs Barcelona generation Opterons speed (i.e. Opty @ 1.6 and barcelona @ 1.6 or both @ 2.0 - doesn't matter which one, it still puts the barcelona in the slower-than-K8 ranks).
well one would assume after 3 years and one of the worlds best design teams, they would be able to improve performance atleast slightlyQuote:
Originally Posted by alfaunits
Barcelona is not delayed, AMD lunatic information formally, Barcelona is for this summer.
source ( french )