Official AMD Barcelona Thread

[red]

I don't think I said they were official. It is all guesses, as is this whole thread. But as you have said, compiler, configurations, etc. can greatly swing the results. It is unknown whether the scores provided are on the hopeful side or sandbagging.

K10 is way ahead of K8 in arch. improvements and it will be faster than 2 core and 4 core intel based systems(clock for clock ).You will see that when it gets reviewed, i can tell you that much.

And you have the nerve to call out my analysis If all you have is hype and no numbers, I could frankly care less. BTW, gl on AMD with their 1.6GHz dual/quads beating Intel's 1.6GHz dual/quads lol.

[GoThr3k]

And you have the nerve to call out my analysis If all you have is hype and no numbers, I could frankly care less. BTW, gl on AMD with their 1.6GHz dual/quads beating Intel's 1.6GHz dual/quads lol.

maybe its a bold statement, but if you look at the improvements, it should be better imo IPC <-> IPC

But we will have to wait for another few months to see the results, let's hope they're good so that AMD can breathe again

[mstp2009]

ummmm.... NO

yeah INT are probably the main recourse thats driving winamp and your web browser, but that are tasks that are fast enough already, they are not itme consuming tasks, heavy on calculations

I've said this before, and I'll say it again. Each and every app that demands more power, in order to get it's job done faster, is running FP code. Encoding, decoding, audio and video processing and post processing, image editing, 3d rending, scientific simulations... and so on

Actually, the new, "demanding" apps are running SSE code, not FP code.

And don't tell me they are the same, because they are very different. FP code has been left in to essentially support old applications that rely on it. It is notoriously hard to optimize in assembly language because the instructions for it have variable lengths.

This is one of the main reasons SSE/2/3/4 were developed. They have fixed length and can perform the same mathematical calculations with instructions that are all the same size. This is why it is so much easier to optimize SSE code for speed at the assembly level - all the instructions are the same length.

And since there already is a very large installed base of SSE code, this is where K10 is going to see the biggest improvement over K8.

[informal]

Here's what Johan from AnandTEch has to say about AMD's K10 perf. preview's that were reported in some "fast news" websites:
http://www.aceshardware.com/forums/r...3522&forumid=1

I am pretty sure someone could delve up evidence that Barcelona should have been with us in first half of 2007 or even earlier. So it seems like a remake of the opteron launch: pretty late.

However, the "fast news" press also did a "remake", publishing complete useless benchmark numbers like they did on the Opteron 800 and K7 500, on buggy hardware.

And no, I am not speculating or guessing :-)

So K10 is not even near those levels in retail version,it's much much better.

[LowRun]

What a useless thread it became

[Scimitar]

K10 has double the SSE throughput and it was quite obvious what I was talking about in my previous post.

K10 is the same speed as K8 for scalar SSE. It is only vectorized SSE that is faster.

[Shintai]

K10 has 2x the SSE units K8 has
dunno bout their speed...

No, it got the same SSE units, just twice as wide.

[red]

http://www.spec.org/cpu2006/CINT2006/
http://www.spec.org/cpu2006/CFP2006/

I frankly don't know what "int" or "fp" is, except that I can tell that according to the int and fp that AMD is talking too, the only thing remotely real world on the fp list is ray tracing and speech recognition

An as informal has just shown, AT and DT are seperate entities with different think tanks. So where is the AT hate coming from? BTW, I rather like the sloppy and dirty benches DT bring And I would hope that performance, and we can be hopeful with some s7 guy saying 10&#37; better same clock, metro.cl and cooper saying yay, http://www.theregister.co.uk/2007/03...ona/page2.html The Register hearing sources beating their chest, but recent evidence suggests it is hampered with bugs, delayed, not clocking high enough, soon to be fighting an early Penryn not Conroe, etc.

[red]

http://www.softlayer.com/servers_dpmc_compare.html
http://www.softlayer.com/downloads/SL_Opteron2000.pdf
http://www.softlayer.com/servers_dpmc.html

Opteron 2000 QC Series Available July 07
Speeds listed from 1.9-2.4.
Strange, 8 x 512k for 8 cores (dual socket system).

[informal]

They just didn't list the L3 cache..It's there.

[madcho]

http://www.softlayer.com/servers_dpmc_compare.html
http://www.softlayer.com/downloads/SL_Opteron2000.pdf
http://www.softlayer.com/servers_dpmc.html

Opteron 2000 QC Series Available July 07
Speeds listed from 1.9-2.4.
Strange, 8 x 512k for 8 cores (dual socket system).

Barcelona is coming

[PetNorth]

AMD: Barcelona still on track for a Q3 announcement

http://www.tgdaily.com/content/view/32533/135/

[red]

AMD: Barcelona still on track for a Q3 announcement

http://www.tgdaily.com/content/view/32533/135/

That is nothing new. Remember Hector's "late summer" launch and that September is still Q3 They've been "no delay" since rumors popped up during Computex. Of course the more optimistic were hoping something closer to "mid-2007", around May I'm sure and that's not how it has turned out.

[PetNorth]

I read from "expert analyst" a Q4 delay (at best) becuase Barcelona has a lot of bugs and yada yada yada

[madcho]

softlayer said july ...

Opteron
2000 QC Series Available
July 07

Opteron 2258
Opteron 2260
Opteron 2262
Opteron 2264
Opteron 2266
Opteron 2268

[Shintai]

1.9 to 2.4Ghz if it holds.

http://www.softlayer.com/downloads/SL_Opteron2000.pdf

But here they say Q3 and with a *

[red]

http://www.theinquirer.net/default.aspx?article=40465

CHIP FIRM Advanced Micro Devices (AMD) has told its distributors and re-sellers to expect production quantities of its up-and-coming Barcelona chip in the middle of August.

That is the traditional time the channel gears up for its sales push although it is a generally quiet time for everyone else.

The long-toothed will remember that this er, phenomenon, has happened before. AMD makes a big push at Computex and then when all the fluff has settled, real chips start appearing in mid-August.

But it seems AMD fluffed its Computex launch a bit, and that caused a bit of a kerfuffle. &#181;

[terrace215]

1.9 to 2.4Ghz if it holds.

http://www.softlayer.com/downloads/SL_Opteron2000.pdf

But here they say Q3 and with a *

2.4GHz? That's 200MHz shy of their "simulated benchmark" PR.

Not gonna cut it... they'll lose to Clovertown on everything but fp_rate.

[red]

http://www.spec.org/cpu2006/results/...0528-01175.txt
Intel's new result already beats AMD's paper result if you don't care for clock for clock comparison. Of course to say that 2.4GHz isn't good enough is to assume that they can't boost spec scores +8.3%, which is reasonably attainable with different configurations (unless AMD really optimized for the 2.6Ghz scores).

[DoubleZero]

First he correlates Intel releasing Conroe on B2 and therefore hoping that AMD will, then guesstimates performance of K10, then tries to explain AMD's no show at Computex, so..was he trying to make a point or something Of course, I can see why you link him, him being an AMD propagandist, with nuts sprinkled on top and all

And were you trying to make a point, or you're just working on a low IQ?
Why didn't you point out were he was wrong, instead of making a post worthy of a 12 year old girl. Or point to another article, story, rumour that could be more accurate?

I can see why you link him, him being an AMD propagandist,

Excuse, do i know you? Maybe from another one of the many accounts you use to spread your Intel propaganda?
I didn't see any propaganda in that article, and i doubt anyone inteligent did... hell i doubt you even know the meaning of the word propaganda.

And please don't call me Scentia fanboy, or that reality will smack me in the face, or somenthing that dumb because, let me draw you a picture, just because i point out the redneck dumbasses that you are, that doesn't make me anything else.

The guy is Sharikou's twin brother , move along please.

Well at least the guy can make a blog, and write articles that are read and commented by many people (inclunding you, nice to see that spreading you usual crap is a full time job to you)
And that's a simple thing that i doubt even your grandchild will be able to do, let alone you.

[terrace215]

http://www.spec.org/cpu2006/results/...0528-01175.txt
Intel's new result already beats AMD's paper result if you don't care for clock for clock comparison. Of course to say that 2.4GHz isn't good enough is to assume that they can't boost spec scores +8.3%, which is reasonably attainable with different configurations (unless AMD really optimized for the 2.6Ghz scores).

Well... of course I don't care for clock-for-clock comparison... that's just silly.

AMD projected 102 for 2.6GHz. Assuming exact scaling with frequency, they'd get 94 with a 2.4GHz Barc...which means 3GHz Clovertown would be nearly 13% faster on 2P int_rate. Also much faster on int and faster on fp, with fp_rate left for Barc.

One thing is unclear: is the Intel 106 result using Seaburg? Or Blackford? If Blackford, there is room for improvement with Seaburg.

[red]

I think my point was clear, and that was that he didn't have a clear one So what was it again? I cannot point to a better article, story, rumor if I can't even understand what he is trying to get across.

I don't know you but if you are desperate to link to an AMD apologist with funny blogs like "Core 2 Duo -- The Embarassing Secrets", "Intel's Chipsets -- The Roots Of Monopoly", "Intel -- The Monopoly Under Siege", "Anandtech Melts Down", "Q4 06 Intel and AMD: Who Won?", "AMD Q4 Earnings -- Good Or Bad?", "The Dishonesty of Overclocking", "Intel's Bluff (Q3 06 Results)", "Tigerton or Kittenton? Memory Amnesia.", well yeah, that speaks for itself

And please don't call me Scentia fanboy, or that reality will smack me in the face, or somenthing that dumb because, let me draw you a picture, just because i point out the redneck dumbasses that you are, that doesn't make me anything else.

Calm down little boy

[terrace215]

1.9 to 2.4Ghz if it holds.

http://www.softlayer.com/downloads/SL_Opteron2000.pdf

But here they say Q3 and with a *

Anyone know how long they've had that up at that site? Could be based on an old AMD roadmap, like the early spring one... before the Computex troubles were revealed...

[red]

http://www.supermicro.com/products/m...00P/X7DB8+.cfm

It is Blackford I assume. The boost in scores is most linked to the new compiler I believe. Computex troubles, maybe it's AMD being funny again like in the past. Or not.

[informal]

Computex sandbagging is more like it.