AMD Zambezi news, info, fans !

[Oliverda]

Nobody knows, but higher version numbers are always better. Someone with a BD CPU has to grab an AsRock board now and make some comparisons, or wait for his board for (beta) BIOS updates.

Why? Do ASRock mobos have the latest AGESA?

[dess]

It is actually slower by 15-20%,which goes against what we know about its FPU.

It depends. Each FMAC consists of an FADD and an FMUL, so the amount of FADDs and FMULs per core is the same as in K10. But, I wonder if the FADD and the FMUL in an FMAC were capable of working parallelly. AFAIK those in the K10 cores are capable of this. In SB cores they certainly do.

[duron]

Why? Do ASRock mobos have the latest AGESA?

I just updated my icafe870R2.0 bios was released Aug. 30, saying update CPU code

http://www.asrock.com/mb/download.as...%20R2.0&o=BIOS

i guess most mobo manu. has the latest Agesa by now

[Baam]

I hope its just a BIOS problem. Either way i am tied into getting a BD whether it stinks or not.

[Megacharge]

Interesting post by Phantom over at OCN: http://www.overclock.net/14972413-post5517.html

[Pestilence]

Interesting post by Phantom over at OCN: http://www.overclock.net/14972413-post5517.html

I forgot where that was posted but i believe it was in the news section last night.

If you're using programs that exploit all cores the 8150 is going to be a pretty amazing chip.

[Formula350]

I don't remember who mentioned it in the last few pages (lost the multi-quote I had going), but it was about making a 4M/4T chip and if AMD would do that... I don't know, it's unlikely, but about 1/2 way through the thread I was thinking how it'd be interesting for them to make one since it would give each core total access of all module resources. I think they'd make for pretty good gaming chips. Clock them at 4GHz with maybe a 4.5GHz 4C-Turbo, weee!

[informal]

Nordic Hardware got time with the Zambezi system:

CPU / Chipset | 17/09/2011 20:00 | Jacob Hugosson




AMD's processor architecture Bulldozers have been a long roller-coaster with delays and silence from AMD. AMD has not been able to offer other than silence, but in conversation with one of the employees of AMD confirmed that the FX series begun mass production and that the launch should not be too far away.

AMD was first to have launched its FX-series processors in the second quarter of this year, something that had to be postponed to a later date. Instead, they promised one within 60 - 90 days June 1, therefore, that by August something we all know did not occur. The next rumor was September, but we do not know will happen.

NordicHardware have now got hold of more concrete information on Bulldozers from one of its employees. We asked about what has actually been going in recent months with the FX series and why AMD has given us nothing but total silence. The answer was somewhat alarming, AMD has not even themselves know where they could launch the FX series, so they simply have not had anything to say to the media about it.

The situation remains very uncertain in AMD and you do not really know when the launch will take place, but mass production of AMD "Bulldozer" FX series has begun. As it stands today, hope AMD internally at a launch in 4-5 weeks. The latest rumors talk about a launch October 13 and in view of the 4 - 5 weeks we have heard directly from AMD, it may very well be true.

FX2 The test system with the FX 8150 AMD showed off

We also got the chance to briefly sit by a system equipped with 8-core processor, the FX-8150 with a clock speed of 3.6 GHz with a turbo mode at 4.2 GHz. Because of the very limited time period so we had time only to run the obsolete SuperPi 1.5 and wPrime 2:05. Unfortunately, the results far out to be something that represents the final product so take this information with a large pinch of salt.

In the obsolete SuperPi took 20.992 seconds to figure out a million decimal places. Given that Bulldozer is a completely new architecture, it is very possible that AMD has chosen not to do further optimization for x87 code. Then we should not forget that SuperPi is no longer a reliable indicator of performance, but it is much worse compared to previous AMD processors.


In the newer and more interesting wPrime 2:05 to get the CPU a final score of 15.815 seconds. We have reason to believe that this is not true, as Bulldozers in such cases would perform roughly equivalent to AMD A6-3650, according to our own tests .


The odd, or should we say really bad performance figures may be due to several different things. But something that is likely is that the processor has either an older stepping, or the BIOS, the computer had not arrived with the latest AGES code from AMD.

Although performance figures are not the most credible, we can confirm one thing: If all goes as planned with AMD is launching the new FX series within 4-5 weeks. We should also then get the green light in on the new flagship from AMD has been worth the long wait. AMD still say they expect the FX series is the world's fastest consumer processor.

As you can see, in his case FX 8150 has gotten some odd performance numbers in super pi and wprime. And this was system directly from AMD. This practically validates what JF-AMD said,don't trust anyone (with X files music in the background) .

[Daveburt714]

Thanks informal... I think people are getting too hung up on benchmarks from the 90's.

SPi lost any relevance back when the A64 came out. Slowly but surely info is leaking and personally, I don't think they look as bad as some folks would have us believe...
It may take a little time for OS's/compilers to take advantage of what BD has to offer, but I don't doubt the performance will be there for modern software.

Now we just need them to be available for purchase!
I have the mobo and $$$ waiting! It's been a long time, but I'm getting excited...

If nothing else, it should end all this crazy speculation!!

[BeepBeep2]

SPi has never lost relevance Dave
SuperPi AMD vs AMD has always been comparable, Intel vs intel has been comparable.

That might change if it gets slower than Phenom II, people might not want to bench it anymore...but SuperPi is still benched for comparing single thread performance within a single architecture. I still find it fun to bench

[Daveburt714]

SPi has never lost relevance Dave
SuperPi AMD vs AMD has always been comparable, Intel vs intel has been comparable.

That might change if it gets slower than Phenom II, people might not want to bench it anymore...but SuperPi is still benched for comparing single thread performance within a single architecture. I still find it fun to bench

Ok Beep, I'll give you some amount of credit with this statement...
I know your a pup, but us old farts remember that P4's crushed A64's in Spi, but in everyday usage the P4 lost baddly!
I get the feeling BD is going to be the point where Spi totally looses relevance (x87 commands are so out dated it's ridiculous)...
No modern software uses x87 anymore!

Persoanally, I'll be a happy camper when folks don't even bother to run Spi anymore...
Hopefully this will be the chip that finally pushes it into obselesence (where it belongs)!

[Andi64]

I know how P4 crushed A64 in Super Pi, technically I've been overclocking since Pentium II (350 Mhz chip to 450, MSI motherboard caps leaked/blew) in 1999

Sorry for the OT, but it was the other way... K8 was faster than Netburst on SuperPi.

[Dumo]

SPi 1M will be benched till it goes to 1 second completion. Lol

Imo, 32m which required os tweaking for efficiency is why overclockers can't get enough of it

[FlawleZ]

Sorry for the OT, but it was the other way... K8 was faster than Netburst on SuperPi.

I was just about to post the same thing. The Netburst CPU's needed gigahertz higher frequencies to compete with the Athlon 64's. AMD was king of Super Pi until the legendary Conroe where Intel finally turned the tides.

[Oliverda]

fx 8150 has gotten some odd performance numbers in super pi and wprime. And this was system directly from amd. This practically validates what jf-amd said,don't trust anyone (with x files music in the background) .

Trust_No_One_2.jpg

[Smartidiot89]

Nordic Hardware got time with the Zambezi system:

As you can see, in his case FX 8150 has gotten some odd performance numbers in super pi and wprime. And this was system directly from AMD. This practically validates what JF-AMD said,don't trust anyone (with X files music in the background) .

The most important part isn't the benchmarks cause even I have a hard time believing them, but that we got confirmed that it should be launched within 4 - 5 weeks

[Frontl1ne]

but that we got confirmed that it should be launched within 4 - 5 weeks

It's not a confirmation unless they said "it will be launched within 4 - 5 weeks."

[Smartidiot89]

It's not a confirmation unless they said "it will be launched within 4 - 5 weeks."

Very true, but that evil "should" word was used unfortunately

[FlanK3r]

But what about wprime? 15.8s is not possible with 8 threads. How mayn threads do u used? Why this version of wprime (2500k cant be better than 1100T never in wprime! 1.55 version seems is better optimalized than newest versions...)

[Pestilence]

What is this ages code all about? I've seen it referenced but what is it.

[Alex-Ro]

Some kind of firmware,i think it's quite similar to Intel'S Management Engine.Somebody correct me if i am wrong

[TESKATLIPOKA]

Pestilence chew* already answered the same question page110

It's microcode injected into a bios.

For every cpu generation and or revision the microcode can be tuned/optimized and even without a silicon revision.

From there board partners can play around and "tweak" it even more via bios.

[Pestilence]

Some kind of firmware,i think it's quite similar to Intel'S Management Engine.Somebody correct me if i am wrong

So Amd needs to update the drivers?

Pestilence Alex-Ro chew* already answered the same question page110

Thank you Tesk. Must have missed it

[TESKATLIPOKA]

Pestilence No problem. Sometimes, you are not present for a day and no new comment is added but next time you must read at least 2 pages.

[Pestilence]

So BLT has pulled the listings for the 8150/8120/6100 from there site.. Hmmmm