launch in september.
dave
Printable View
"P" can be some as "premium" or "performance". Because all FX models are unclocked
ah, it will be premium package, because we seen special metal BOX for the top model...
Higher Turbo is my guess.
this is possible too, but metal BOX is next bonus :)....Im looking forward so :D
Any cpu fan will show those metal boxes with pride.
So now with some performance numbers and stock clocks somewhat known or guessed I think Im going to redesign my next computer build around these cpus. And I really want to see what the Crosshair V Extreme will have on it. At least I know my build will probably be less than building an Intel would be even with these boards and SLi.
I would say it depends on how you look at it. If I wanted to build an Intel system it would cost me more. Its also a new architectural and a manufacturing process. But that being said I say that they are doing extremely well. For bang for your buck AMD is the best. I personally have a limited fund of money as a college student.
First factor why i will be buying few of Zambezi FX-8xxxP chips is due that box, i want that metal box, one for candy, one for lollipops, one for screws and so on..!!
Second is Zambezi performance beating SB 2600K as well as i7 990x with ease.
Also i will be buying alot of Interlagos chips, by alot i mean 50+ for my servers, hopefully they will also come in that metal box so i will be lord of Bulldozer metal boxes.
Going to be rebuild of whole server farm and make my self AMD Bulldozer Metal Box computer case.
I'm not sure but i think the lighting in one of the Bulldozer metal box pic revealed a hole on one side, would be risky as a candy/screw box then.
I could put small plastic bag in those boxes, candy or screws would not get trough that hole :).
Think the hole is there because of protection from moisture.
I save up. Im currently saving to build a Bulldozer system but it wont be when they come out. Im still paying my CC bill for the C4E and am almost done with that. My GPUs have either been bought using EVGA stepup or when they were cheap on the egg. But yes this is a good setup and I would like the new stuff but saving up is what I do when I want a new piece of hardware because I like paying for it in full. Cant wait to see how you guys do with the BDs as far as clocks. Wont be buying under the top CPU again because my 1055 didnt clock like I would have liked.
Yeah, buying into intel is not cheap, but I give you points for attempted trolling.
i will be happy if top model use paper box and sell cheaper than metal box ....haha
Im waiting for 2x FX 8xxxx and 1x FX6xxx (in first state), I have 7 Phenoms CPU, so I must to have more FX than Phenoms :)
I'm very sad and thoughtfu because BD was "near" to launch, and now it has been delayed to no official date
I hoped almost to know something in June, even if BD was not launched. Just to see if we're waiting something special...
I dont know nothing for sure
- BD will work on some am3 motherboards like asus/msi said?
- BD how much will be better than phenom II, core vs core?
- BD 2 will be on another socket.. am3+ will be supported only 1 year?
I'm thinking of selling my CH IV and buy an am3+ motherboard, but I don't know if getting a "medium range" mainboard and save money or buying a CH V ...
a CH V will be too expensive IMHO if BD will not be almost +30% better than phenom II, core vs core, and if AMD will not support and develope am3+ cpus next year..
-> sorry for my poor english but itsnt my 1st language
Quick recap.Maybe im gonna be helpful.
Yes BD should work on selected AM3 boards, and will work for sure on am3+ boards using 7xx /8xx chipsets which are available for some time.
Performance is totally unknown.All theoretical estimations put it at least above 2600k in multithreaded and below in singlethreaded.However theres new instructions, AES/AVX/SSE4 .Improvement should be at least from small when using non optimized code, to big using new instructions.Its should destroy Phenom X6 no problem.
Yes BD2 will be on another socket, as for support longevity of Am3+ its unknown.However when in doubt always be pessimistic.
Youre right on the mainboard front.Its no use to buy now, most probably your board is going to be supported (there is bios already) and buying high end mobo with 990FX seems pointless for you as its the same chipset as 890FX.There are differences in mainbord itself, but am3+ is shortlived.Best advice, wait and see.If BD delivers performance and AMD commits somewhat to Am3+ than it might be a good idea, but not before that.
thank you for the reply, I agree with you.
but as you posted
-BD "should" work
- ts should destroy Phenom X6 no problem.
so nothing sure 100%.. I know, maybe I'm asking for something that I cannot know at the moment.
now, "to wait"is the answer.
I would like to wait but my problem is
- if I sell now my CH IV I can surely earn more money than I will earn if CH IV will not support BD or the support will be not good
- in the case that i sell now my ch iv and buy a medium mb am3+ with 990fx (worst than ch iv in phase power), I will be afraid if BD will work better on the CH IV ( It would have been better not sell my CH IV!)
so this is my problem, and I hoped to know something in this days but nothing..
liberato87, you can buy a mobo 990FX for about 120 euros like mine Gigabyte UD3 . It doesnt have to be a highend mobo.
Asus CIV might support BD, check in asus site. At least some old MSI and Asus mb support BD already. Better wait and see.
If I was you, I'd run the old mobo until next BD2 if the old mobo supports BD.
@Liberato87
Of course theres nothing 100% solid as of yet ;-) , were BEFORE launch, and AMD dicks around.
Well, that not fully true.
We know for SURE that ES samples of BD WORK on CH IV.And that they perform like crap :) but it isnt sockets fault.
thank you for the reply.
I'm considering buy the ud3 (or the ud5..i dont know what to buy I'm just getting mad) , and if BD will be great, I'll upgrade to CH V.
I would like ro rest with my CH IV, but I'm afraid that if the support will be not great (or if there will be no support on "final" cpu) , I've to sell it under cut price (now I can sell it at good price, I've to add only 10 euro for the ud5)..
sli is also appreciated..
It's a shame it's been pulled Q3 (I take you would hope August if possible). As a PR move I would of thought some special LN2 editions for the overclockers would have been in the pipeline, just to get the interest going before the mainstream hit the market.
Only a few more months of waiting, it's just a shame it's Q3 now.
He didnt ask if amd supported it.But if asus supported it.
EDIT .I may have misread you.If you were referring not to the compatibility but performance.This sample is crap on 990FX too.
As for the date, its even more granular, presentation on computex had 60-90days for PIB availability.
@BeepBeep.
I didnt tell otherwise, and from what i remember MSI had some models too with AM3 support.I may be wrong tho.And as for the chipsets ,there are AM3+ 7xx series mainboards out there.
-> http://www.gigabyte.pl/products/page...lmt-s2prev_31/
Double post ,pls del.
Boy i hate new forum software :/
The TWKR Ph2s were probably just leftovers of a run of non-standard chips AMD had run for other reasons. They didn't perform any better iirc.
You have to remember that TWKR's were C2 stepping, they were out before C3 hit.
I dont know many other C2's that hit nearly 6.8 Ghz:
http://www.xtremesystems.org/forums/...Z-amp-SPi1M-WR
http://www.hwbot.org/hardware/processor/phenom_ii_twkr/
beep has a point.
C2's NEVER HIT 6.8
i have a feeling we will see v2 of the TWKR, but in BD form
...there are a lot of C3's that wont do 6.8.
TWKR were defective leaky chips that wouldnt be suitable to sell in any form as they wouldn't fit TDP vs volts needed for stability, I bet otherwise they'd been scrapped.
TWKR is sort of a "performance at all cost" chip. It can tolerate higher volts and clocks high because it's a very leaky chip.
That also means high power consumption.
since amd is aiming to go towards a more multi purpose cpu/gpu combo i think your idea about lots of smaller cores coupled to a specialised core isnt so bad at all .... coupled with a next generation power-saving feature could mean goodness
thanks for your thought
@JF-AMD: can you confirm that amd is hosting a bulldozer demo of some sort on the 16th of july???
http://hardforum.com/showthread.php?...post1037335089
For anyone interested:
http://www.msi.com/news-media/news/1224.html
List is quite big and includes all recent amd chipsets.I think that companies like MSI and Asus deserve support for such actions :).
I know that when the time comes for a new MB i will be looking at them first.
I think, its right, because we had here 2 threads from Simon. One was "Los ANgeles" and second "Seattle". In LA was E3 and first show with BD
Just got it back from the shop, so it is time to burn off the vacation calories.
But I guess that even though we are at 14+ days of 100F heat here in austin so far this year, some things are running cool:
http://www.theinquirer.net/inquirer/...lldozer-server
Now, one more meeting then I get to head out to ride tonight. 100F with a heat advisory means I can ride my bike, then drink beer - all while losing weight.
JF, enjoy the ride! My sister lives in Austin and has told me about the heat.
Uff, I hate heat for sport...Today its here about 28 C and its for me and sport too hot :(
It's winter down under.
Good for overclocking.
Try 100F with 80% humidity here in Houston. I can handle 100+ weather if the humidity is low, but along the Gulf Coast your sweat can't evaporate off your skin to cool you. Speaking of cooling, I can't wait to see what Zambezi under water can do.
in Singapore, it is 32C, with 79% humidity all year long...yay!!!!!
All you people talking about heat! Come feel the wrath of 45c
So do we know if the Zambezi on 900-series boards will be running with NB@2600MHz? I was getting excited about the 6.4MT/s (3200MHz) of 'Dozer, till I saw the new boards are only HT3.0 still :( Think they'll OC fine to 3200?
I dunno... I think with how big of deal was made that 890FX could do 2600Mhz (despite the PhII not defaulting to that), one would think the same would be again done with the 990FX. The only things I've seen are boards silkscreened with HT3.0, or like this ASRock Extreme4 (which as I found out over a month ago is just the 890FX Deluxe5) which just says FSB2.6GHz and HT3.0 :\ The Sabertooth nor the CVF mention HT version or the CPU-NB speed. MSI's 990FX-GD80 I didn't see mention it, but the GD65 says 3.0. I'm not going to check all the gigabyte models, but the two I did look at were absent of all mentioning, like ASUS
that's what you get when posting near midnight after spending hours working on the car..... parsons.... :D
^ Take results with a 10 tonne grain of salt
still its better than 4 GHz OC Thuban with 1866 RAM
http://img27.imageshack.us/img27/196...ban4ghz.th.jpg
Well, obr on his blog says he has two fresh samples, hes gonna test them with three new boards with 1866 ram.Thats one.
Second info from him is that they perform clock for clock near identically PHII, with two more cores a bit higher IPC and new instructions.
Results will be on weekend.He doesnt say for now what rev samples he has tho.
Oh, and he has some venom about flanker and xs there but i didnt understand from translator what he meant ;-)
yes, he folow us around the web :)...So, my talking in CZ forums discussion, some users here etc.
I think there is no point to jump to conclusions before we see test results. If he meant that 8 cores (4 modules) of Bulldozer perform in FPU-intense tasks 33% better than 6 Phenom cores (or one Bulldozer module is as fast as 2 Phenom cores), than it is big success for AMD.
repman: relax....this "bad" sample beating sb 2600k in rendering easily. Obr showed it a few weeks ago at blog. So, Sandy Bridge performance now sounds weird too? ,-)
The fact that he has ES chips is not debatable ;-) .As for the Core per Core IPC ,well i dont know, remember thats before Turbo, were talking Mhz per Mhz here.And Cores in Bd arent Full cores on their own.
Even if IPC core per core would be the same,you still have 33% more of them for multithreaded work.You have new instructions for specialised code (AES SSE4.1 4.2 etc) which will give biig boost for some parts of the code.And on top of that you have big turbo for single threaded works.All that at lower manufacturing costs than thubans.
Well ,i had hoped for more than that.But yea, all in all it wouldnt be bad chip still.
Taking best case scenario for BD tells us nothing about its general performance ;-)
please notice bd samples are likely crippled.. better wait for real info from 100% BD :D
Yes it is.
If you take a look at the architecture itself, it's not hard to see that BD's IPC will not merely match K10.
As far as core scaling goes, when both BD cores in each module are being used, AMD themselves said multi-threaded performance would increase by 80% (remember 80% more than 100% is 180%)
And that's not compared to K10. That's compared to doing one thread on one BD core.
AMD also said they got "50% more performance from 33% more cores"
Of course they didn't say what type of workload. But in that context I'd assume it means something that uses >=8 threads (still not THAT specific).
If I combine their two statements:
50% more performance from 33% more cores
When both cores in each module are used, you get 80% more perormance (180% OF single threaded performance)
and assuming perfect scaling when all four modules are active, I'd conclude single threaded performance to be
[1/(1.80/2)]*(1.5/1.33)~=1.253 (are these calculations right?)
i.e. single threaded performance is about 25% better in the particular type of workload AMD tested with... but becomes 90% as much as that when both cores in each module are used (unless there's some workload where sharing the cache can result in a performance benefit)
0.9*125%=112.5%
Although yes, that's taking AMD's statements at face value.
Don't forget 4 and 6 core versions of bulldozer, which would mean that the 6 core version would perform the same as Thuban (according to OBR that is), that's why I doubt AMD would invest so much into a new chip for the same performance they have now. IPC core per core should at least be 10% more for Bulldozer, but that's just me guessing ;)
Well yeah, it is debatable in that way that if you wont check it yourself you wont know for sure.However the guy is known for having its connections and getting ES stuff, while he is disliked by most guys here, no one "in the know" dismissed tha fact that he gets samples.They are even irritated because he breaks NDA`s and still gets samples.
Guy has pictures of samples, guy has sold one , he provided many screenshots.What more do you want ?
As for the scaling, as you said, its not relative performance to phenom II but to BD itself.So it doesnt give us any IPC indication, and besides that as ive said before, new instructions and turbo should give big boosts.We should know more in the weekend.
@repman, you also have 2,3,4 core phenoms now so i dont get your point.It still would be big move upwards ,4-6-8 higher clocked parts with new instructions cheaper to build instead of 2,3,4,6 slower bigger chips.Im not saying thats the case, im saying it would still make sense to produce them instead of phenoms.
wha Gigabyte Thailand reply me "900 series mobo may start selling in August 2011"
I'd want his statements about BD's performance to be more in line with what everything else hints.
In other words, measurably higher IPC than K10.5 (although exactly what IPC is compared to say SB is difficult to infer)
But some Gigabyte 900 series boards are already selling....
I even have a 990FXA-UD7 in my PC right now
If the results he shows this weekend are with shipping silicon and they're really crappy, what will people do? Still buy a crappy CPU or bail ship and switch camps? Just asking...
If we are going to draw conclusions on these leaks, then we must also recognize the price leaks. Which show it being same as SB. I think prices trump all "leaked data"
As far as i remember there is only one price leak, and its a simple excel chart,and not confirmed in any way at that...
What I'm trying to say is that OBR has said that core per core BD has same performance as Phenom II (if I understood that correctly), you compared a 4 module BD (8 cores) with a 6 core Phenom II and saying it has 33% more cores (If i read it correctly) but if you would compare a 6 core BD to a 6 core Phenom II (and according to OBR) they would have the same performance, since core per core performance is the same.
(sorry if I read anything incorrectly)
I think single thread performance needs to get better ( a lot better than Phenom II) for BD to compete on the market.
I agree but the first spins of this new arch will not really show where BD will be in 12 (or 24 for that matter) months.
Turbo'X' and additional SIMD compatibility will boost single-thread performance, but that may not reveal the underlying strength of the initial core/module design.
That comes with the Trinity APU 'SIMD Engine Array' in 2012, and further logic enhancements to the core/module concept.
AMD consistently 'builds' incremental performance on their base designs. The best analogy that comes to me now :shocked: is they step up to the plate and hit singles -- not necessarily home runs.
It's nice to smack a home run, and I hope they do with BD, but their limited resources tend to force them to be more incremental.
if by any chance bulldozer only perform like phenom II ... id call that an epic fail .... we didnt wait this long for what a rehash could have gave us far earlier
If it did then AMD would not be updating its APU line to Bulldozer cores in the future. They would just continue to shrink Stars.
Dont get me wrong, in a single thread, performance vs die space Stars is up there with sandy bridge. Unfortunately, that is a measure of performance vs die space.
OMG OMG.. we are discussing as it was fact
ROFL