It may be that Amd also was demoing a very early revision. (hopes so:D )
We should now soon if AMD keep to its promise of Q2.
This summer will be great.
Printable View
It may be that Amd also was demoing a very early revision. (hopes so:D )
We should now soon if AMD keep to its promise of Q2.
This summer will be great.
AMD Quad flash ad
next gen after barcelona is 2008 :D mybe shanghai and montreal :up:
Nice thread (except for the intel fanboys posting here)....very usefull information here and thanks for sharing your news.
Without any chips in the computer and with similiar system its though to make any calls what testing means.
AMD are positive to its new k10 line which will offer a lot more than its previous gen.
Its also a quadcore designed to be one not 2 dualcore lumped togheter the used car seller way.
I just dont get why we need more cpu power, for me todays computer runs so well with the current tech.
I get that videoencoding, movierendering and other fields might benefit as serverside but for the common consumer it seems its enough as it is.
As I use the computer, games, some video its purely enough power without bottlenecks as it is today for me.
Even the new gen and tech the fps in games dont go up so much.
I am however looking forward AMD´s new design and if they lower powerconsumation with the same speed and more power for the user, that is very enviromental and something to consider.
I would like to see how much power todays computers draw with todays cpu and what would be if the powerconsumption if it was halved.
The idle power has to come down since it makes more sense if the workload would decide how much power the system would draw.
quadcore with each core has there own way of idle and lower power seems like a nice way of having chips doing work when needed and not all the time drawing full effect.
QFTQuote:
Originally Posted by LOE
we can all be happy about that fact:yepp:
Povray and detailed analysis on K10 scores can be find here:
http://abinstein.blogspot.com/2007/0...-and-amds.html
nice ;)
It's all good and all, but why don't they pick something Intel wont hawe and bench that as an advantage!?
Benching and claiming the same TDP is a hit below the belt attempt as intel will have the same ability (Harpertown), and will show it on Computex!
Why must they prove something only to be disproved weeks later?
The score explanation I don't have the attention span to grasp, so I hope someone will sumarise it.
I will add that my C2D@2.13 scores 920/467pps
while my friends X2 4200 scores 728/367pps I don't see that should be called optimised "more for c2d"
Some info on Barcelona's successor - Shanghai : (Sorry if repost).
(Translated from german by Google)
http://www.google.com/translate?u=http%3A%2F%2Fwww.computerbase.de%2Fnew s%2Fhardware%2Fprozessoren%2Famd%2F2007%2Fjuni%2Fa md_shanghai_barcelona-nachfolger%2F&langpair=de%7Cen&hl=en&ie=UTF8
[Click to enlarge]
http://www.Photo-Host.org/thumb/655903shang.png
http://www.Photo-Host.org/thumb/609824shang2.png
Ahh, thanks for that. Edited out and replaced.Quote:
Budapest aint successor. But the desktop/1S Opteron version of Barcelona
Budapest aint successor. But the desktop/1S Opteron version of Barcelona.
Shanghai = 45-nm Barcelona ?
yes, with some architectural improvements, more L3, more and faster HTT links and maybe more.Quote:
Originally Posted by frankR
Shanghai will be registered DDR2 (800 instead of 667)/DDR3, HT3.0, 45nm, and 4Mo or 6Mo of L3. :DQuote:
Originally Posted by gOJDO
sourceQuote:
The new "Stars" models receive new branding
On June 5th, AMD will launch its Athlon X2 BE-2350 and 2300 processors. The new Athlon X2 BE-series marks the debut of AMD’s new naming scheme. In addition to the Athlon X2 BE-series, AMD is to revamping its complete product lineup using the alphanumeric scheme.
The new naming scheme designates the first letter as the processor class. AMD currently has three processor classes for the new scheme – G, B and L. All G-class processors are designated as premium processors under the Phenom X4 and X2 names. The B-class processors slot below the G-class processors as an intermediate model. At the bottom of the AMD ladder is the L-class processors. L-class processors carry the AMD Athlon or Sempron names.
The second letter in the model designates thermal design power class. AMD P-class processors have TDPs greater than 65-watts; S-class processors have TDPs of approximately 65-watt while E-class processors have less than 65-watt TDPs.
Under the new naming scheme, upcoming Stars-family dual and quad-core processors will carry the AMD Phenom X2 GS-6xxx and Phenom X4 GP-7xxx names. Value-priced AMD Athlon and Sempron processors will carry the Athlon X2 LS-2xxx and Sempron LE-1xxx names.
AMD Phenom FX processors will not follow the new class designations; however, AMD is undecided on the model numbers.
:clap:
@madcho
Don't get too excited about AMD announcements. Athlon 64 BE are a dualcore K8's with 45W TDP, clocked at 1.9GHz and 2.1GHz(2300 and 2350 respectively).
i'm exited about Agena, i don't care about K8 :D
So any news on K10 benchmarks on computex? It's going to happen?
I'm really curious, i'm inclining to AMD pulling another R600 with K10 unfortunelly, at least in desktop.
@madcho
What is so exciting about it?:confused:
No info, no numbers, no benchmarks, no release date...:down:
According to Computex website, it doesn't start until tomorrow. It is still June 4th(8 PM) in TaiwanQuote:
Originally Posted by DoubleZero
follow the link, now we know how AMD will name the K10 :up:Quote:
Originally Posted by gOJDO
Does any one really cares about the name?:rolleyes:
We still don't know when we will be able to buy it and what performance/$ it will offer. :shrug:
TDP in the name is very interesting for evrybody. ;)Quote:
Originally Posted by gOJDO
Can't wait to once again be able to be free of the hassles familiar with a FSB and other RAM-related nighmares.
yeah well looking forward to it :)Quote:
Originally Posted by largon
I've waited so I don't have to deal with it. :D
:mad:Quote:
Originally Posted by frankR
SInce that K10 thread got closed,I will post my reply to Vapor here :) :
Yes you can compare it per core.Read again what i wrote.Quote:
Originally Posted by Vapor
Scaling is 1.85 for dual core K8.
K10,1.6Ghz ,4core - 814.
K10,1.6Ghz,2 core - 440(with scaling of 1.85x from 2 to 4 cores)
K8,1.6Ghz,2 cores(1MB of L2)- 445!!!
So by this we get that K10 is supposedly slower than K8 per core in this test.And test was done on AM2 mobo!
This tells me that that was some early buggy revision with who knows what deactivated trough bios,with sole purpose of demonstrating the performance/watt claims AMD made in the pas(Double the cores ,keep the same total system consumption and double the performance
It is possible that many of new features in this Barcelona sample was not working/broken.
Cinebench itself was ran in 32bit mode under 64bit OS.. how strange.
My old X2 3800 clocked@2550MHz was getting 874 points under 64bit OS/test.
This test proves that CPU is 'working' not only in Task Manager, but I wont be judging my opinion based on just one benchmark with preproduction sample run under unknown circumstances.
i think cinebench was writed for K8. 440-445 about the same. Barcelona can run DDR2-800-ECC, it was 666. maybe this could slow it.Quote:
Originally Posted by informal
And maybe K8 apps can't be faster on K10. :rolleyes: ( or it's dual X2 :mad: )
It can't. The highest it can run is DDR2-667.Quote:
Originally Posted by madcho
It's like saying single-core K8 AM2 can't run DDR2-800...Quote:
Originally Posted by gOJDO
Officially only dual cores can work with DDR2-800 and single cores max is DDR2-667... but why on earth I have working option DDR2-800 in BIOS???
Official support for it, yes but it can run DDR2-800 & DDR2-1066 if you wanted it to.Quote:
Originally Posted by gOJDO
Since when is OC the norm on server chips ?Quote:
Originally Posted by DeathReborn
TrueQuote:
Originally Posted by savantu
But the big question here is how effective the Barcelona Memory controller is?
For all we know Ddr2 667 10,7gbs may give Barcelona more than enough Bandwitch.
Also keep in mind that Amd may bump up ddr2 support when their processors are released.
Since everyone started using opterons for OC ?Quote:
Originally Posted by savantu
I think he's talking about server chips actually used in servers. :)Quote:
Originally Posted by Ubermann
Here is my 25 seconds on my FX60...
2850 mhz.. 285 TCCD
K10 fails hard, it cant even beat K8.
http://www.sspmustang.com/OT/ggseanpwntby2850tccd.JPG
Either Barcelona is having serious problems, or AMD is intentionally showing us junk. I'm losing any confidence I had left with AMD pulling off the upset against Intel with K10. At this point I think AMD will be lucky to repeat Barcelona like R600.:(
Amd fx 60
Maybe that is the ipc performance is just the same as K8, but it'll clock higher like the Netburst Intels.
Maybe. But most likely L3 cache was disabled in bios "in purpose" to show or it was pre-release sample with disabled L3
don't you just love how much FUD that Intel seems to love pumping out lately?
If I got a Nickel for every bit of FUD that came out about K10, I'd have a :banana::banana::banana::banana:load of nickels
Intel demoed the dissapointing POVray and Cinebench tests? :rolleyes:
kinda like how nVidia demoed the disappointing x1800xt scores that later turned out to be an overclocked x850xtQuote:
Originally Posted by red
What's really disappointing is the kind of shrill coming from Anandtech. Anand used to be a balanced guy, comparing AMD and Intel, but ever since Conroe he's been decidedly pessimistic and negative on AMD. The moment I saw his review being quoted and plastered all over the "official" Intel slides, I knew his time of being an impartial reviewer was over.Quote:
Originally Posted by nn_step
Kinda sad, since Anandtech was a reasonably good place for reviews in a time when THG was the #1 Intel fanboy site. However, THG has since toned it down considerably, and Anandtech has instead taken that #1 spot.
K10 doesn't run CPU-Z ? :shrug:
http://www.fudzilla.com/index.php?op...=1342&Itemid=1
Quote:
Originally Posted by nn_step
Exactly !Quote:
Originally Posted by Mav451
i don't know why go attack anandtech
they are probably one of the most reliable review sites out there. if it hurts you that Wes and Gary tell it like it is because you are a fanboy of the brand that gets plastered that is entirely your problem and you should not blame them
i know that nn_step is clearly one sided much like the Iraqi Minister for Information :rolleyes: but it seems that he's not alone here
What is wrong with being pessimistic and negative towards AMD? What positive do they have to...be positive about?
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 )
looks sexy! :)Quote:
Originally Posted by tictac
There is still something, I don't understand... What is Budapest?
Is it a specific version for cray? Or is it the desktop version of the barcelona?
Quote:
Barcelona is a strategically important chip for AMD, as it tries to regain market share lost to Intel's newer Core 2-based Xeon server processors, the dual-core 5100 and the quad-core 5300.
However, Budapest shipments to Cray slipped. "Specific to Cray, we did have a change in our schedule, as far as when Cray gets Budapest parts," Hughes said, declining to share further specifics.
Barcelona is designed for systems with two or more processor sockets, but Budapest is for single-socket systems.
Budapest is single socket with HT3.
it's opteron K10 for AM2+ with HT3. Budapest is used by cray ;)Quote:
Originally Posted by nemrod
I still find it wierd that Cray want to buy single socket Opterons and not MP sockets.
maybe budapest is mutli P able, and cray want HT3 :confused:Quote:
Originally Posted by Shintai
And the barcelona hasn't HT3?
Why MP are ready and single socket not? I would have think that MP processors are more difficult to realize?
They are same ;)Quote:
Originally Posted by nemrod
Hint as of when NDA on Barcelona will be lifted!
SourceQuote:
At the CTO Summit, AMD laid out a fully finished 300mm wafer to touch and photograph, and we were shown specifics on the fab rollout schedule for AMD’s 45nm process. We got an advance look at new AMD/ATI chip-set technology as well, along with a completely new and radical AMD CPU, the nondisclosures on which lift this month. AMD is not running behind Intel. It is simply not practicing reactive engineering, and if you pay attention, you’ll see that AMD’s take on 45nm process, 300mm wafers, desktop chip sets, and dual-core mobile architecture are more than mere snapshots of the marketed leading edge, which is a coat of gloss on the present. AMD, through its partnership with IBM, defines the leading edge. Watch.
nice :D
This is "May 16, 2007"... "the nondisclosures on which lift this month"...
It's a joke... There is no "hint as of when NDA on Barcelona will be lifted!"
Quote:
Originally Posted by Lightman
...
Did you look at the date of the article? May 16, 2007.
So far, all AMD showed was how pathetic K10's FP performance improved over K8.
This is kind of a continued discussion from this thread.
http://www.xtremesystems.org/forums/...d.php?t=147675
But man, if that article is true, then we (desktop users) won't see K10 until next year. Hopefully AMD can survive this with the revenue from the ATi chipset and video card sales.
Perkam closes this thread:
http://www.xtremesystems.org/forums/...d.php?t=147675
But if the first post was biased, the new article from Anandtech is interesting:Quote:
Originally Posted by perkam
http://www.anandtech.com/tradeshows/showdoc.aspx?i=3006
Obviously, there is still same kind of information about AMD not fully ready but there is too informations like
And this could a little bit invalidate the "quick and dirty benchmarks" result on cinebench.Quote:
We know that Barcelona works and runs benchmarks, as we saw back at AMD in May. But the demos that AMD ran were on its own motherboards, not on motherboards from its partners. AMD's partners just recently received their first Barcelona samples, and as expected, the boards require some heavy BIOS work before the new chips will even work.
The motherboard we tested on had minimal HT functionality and wouldn't run at memory speeds faster than DDR2-667; most video cards wouldn't even work in the motherboard. Memory performance was just atrocious on the system, but the motherboard manufacturer we were working with attributed this to a BIOS issue that it expects to be fixed in the very near future.
On an other hand, this give some questions about the "simply plug in AM2..."
Yeah but if it's just BIOS problems, that is no surprise right? I guess I assumed that AM2+ boards would still need BIOS update to run the new CPUs.Quote:
Originally Posted by nemrod
Big surprise a New CPU class requires new Bios..
The surprise is that apparently nobody was able to do a correct bios for those buggy devices... Memory issue? Is it really simply a bios problem? Where is the controler in the bios perhaps? Where are the bench on the AMD itself motherboard? A yes 4000 for the barcelona with 16 core when 8 K8 do 2000 and 8 core 2 do 5000... Play with that...Quote:
Originally Posted by nn_step
If it's a backward compatibility issue, why doesn't AMD just skip AM2+ and go to AM3. Then the motherboards can be designed to meet the cpu's needs.
http://www.anandtech.com/tradeshows/...spx?i=3006&p=5
Just in case anyone missed it, Anandtech..
Quote:
Oh yeah, after scouring several computer shops in the greater Taipei area we happened to find a pair of Barcelona chips available. Okay, maybe we broke into an engineering lab and ran off in the middle of the night with them but hey, nobody caught us. (Ed: and you thought all that time playing Ghost Recon was useless....) Once we get proper motherboard/BIOS support, we'll be ready to actually discuss performance.
I think AMD's very wise not to switch to DDR3 that soon.Quote:
Originally Posted by awdrifter
Wanna have AM2+ and a pair of DDR2 Rams!
Did you read about the new B2 Stepping? Think I heard that whole BS already about B0, but even fudzilla seems to become more pessimistic (or realistic?).
Because the "drop in upgrade" thing is a big marketing point for their server clients... and this is where they make the big bucks ;)Quote:
Originally Posted by awdrifter
A secret revision
SourceQuote:
Our sources have confirmed that a few Barcelona chips that the company demonstrated at Computex behind the closed doors are B0 revision.
We also learned that B0 can go faster than 1.6 GHz but that it was a very buggy revision. Now our sources are talking about B2 revision that is suppose to save the day and this one is expected any day now.
The same people also indicated that Barcelona will either be the best thing that even happened to AMD or it will be doomed to be the next Netburst. Unfortunately it looks more like the later one, at least from this perspective.
But that just meant it has to be compatible with socket F right? Not necessarily AM2.Quote:
Originally Posted by Sumanji
I think, the problem is the branch prediction, which didn't improve that much compared to other parts of the CPU. I measured 15% mispredicted branches for the povray benchmark on my X2. Standard code usually has ~5%. Then there is a branch about every 8 instructions. That's normal for a raytracer, which has to do a few calculations to find out, what to do next.Quote:
Originally Posted by nn_step
MSVC 8 also wasn't able to vectorize any calculations. So there are practically no 128 bit SSE instructions, which could make use of K10's improved FPU.
According to Prime95 benchmark, Willamette was much faster than Athlon and Northwood faster by 30% or more than Athlon 64.
All K10 chips will be compatible with current desktop/server platforms.Quote:
Originally Posted by awdrifter