Fudzilla: Bulldozer performance figures are in

[AnandThenMan]

Wow, a 16 core chip being up to 40% faster than a 12 core chip?

Who would have thought!

You forgot a small detail.

 

[Davidh373]

Wow, a 16 core chip being up to 40% faster than a 12 core chip?

Who would have thought!

lol...

 

[Fox5]

Sorry, but this makes absolutely no sense. An A8-3850 with a Radeon HD 6850 is MUCH faster than with the Radeon HD 6550D IGP. That means the GPU is the bottleneck in the system with the A8-3850.

The fact that you stop getting performance increases at 1866MHz means that the IGP no longer needs any more bandwidth and can run optimally.

Or it means that the faster ram isn't providing more bandwidth. How so? Maybe you've already maxed the hyper transport bus, that can only provide what, a max of 21GB/s?

 

[bryanW1995]

It might be worthwhile if you want to get a 2011 rig together without dropping too much money at one time. Assuming that Intel doesn't retire it too soon, it should provide some room for future upgrades, perhaps to IB-E or something like that.

Yes, but I tried that with 1366 and it just doesn't make sense atm to drop $600 on a gulftown when SB is just as fast and you could get an entire SB system for not much more than that $600. If gulftowns are $600 right now, do you really expect sb-e or ib-e to be less than that after another year or two of intel pwnage? If anything they'll be more expensive, not less, and what is the market going to be for a used quadcore sb-e cpu?

Haha, I just realized another possible intel response to BD (other than the obvious 4ghz i7 2900k): introduce a $300 gulftown sku. THAT would be brutal, and would certainly convince many people to just skip BD.

 

[Tuna-Fish]

Or it means that the faster ram isn't providing more bandwidth. How so? Maybe you've already maxed the hyper transport bus, that can only provide what, a max of 21GB/s?

Ram accesses don't go across the HT. Only stuff that talks to the motherboard does.

 

[bryanW1995]

Everyone is speculating left and right without any facts. They could have discovered a bug in the CPU and didn't want the repeat of the TLB episode? Plenty of reasons why it is delayed: subpar performance, last minute bugs found, head engineer's dog got hit by a car and he became depressive and quit, cosmic rays messed up the wafers, etc ... Some more plausible than others for sure, but until we know from reputable sources (not some random guy on a random enthusiast board), it's still baseless speculation.

You got it all wrong: it's the antimatter!

An AMD exec claiming a 40% performance improvement.

I have a vague sense of deja vu, can't quite put my finger on it though....

Couldn't they have used 39% or 41% or, or, or ANYTHING else???

 

[soccerballtux]

someone pm me when we have hard numbers.
I'm staying out of CPUs & OCing until then.
I keep checking every day for news but there isn't any.

 

[Abwx]

someone pm me when we have hard numbers.
I'm staying out of CPUs & OCing until then.
I keep checking every day for news but there isn't any.

Only doubtfull benches are available...

A 4 threads optimised app supposed bench...

 

[LOL_Wut_Axel]

Or it means that the faster ram isn't providing more bandwidth. How so? Maybe you've already maxed the hyper transport bus, that can only provide what, a max of 21GB/s?

It's not bottlenecking it, but rather the platform. Even if we removed this limit, looking at the benchmarks it'd only gain 5-10% more performance. It's got little to go considering it's on DDR3 RAM.

 

[Idontcare]

Only doubtfull benches are available...

A 4 threads optimised app supposed bench...

Don't those guys know that if you are going to make up fake benches you are supposed to ensure that bulldozer goes to 11?

^ now that looks more like it :thumbsup:

 

[ieatdonuts]

Am I doing this right!?

 

[soccerballtux]

Am I doing this right!?

where'd you get this from, something doesn't look right about it...I call shens

 

[Davidh373]

"Blender?"

Is this time to render a single frame? Seems pretty vague...

 

[Idontcare]

Am I doing this right!?

Holy crap, you must be an eleet insider with access to ES bulldozers!

Somebody alert the xboxforum trolls, I has a feeling there's gonna be some more leaked screenies "from my friend who has an 8150P" tonight!

 

[podspi]

Everyone is speculating left and right without any facts. They could have discovered a bug in the CPU and didn't want the repeat of the TLB episode? Plenty of reasons why it is delayed: subpar performance, last minute bugs found, head engineer's dog got hit by a car and he became depressive and quit, cosmic rays messed up the wafers, etc ... Some more plausible than others for sure, but until we know from reputable sources (not some random guy on a random enthusiast board), it's still baseless speculation.

That's unlikely, given that AMD is claiming server isn't delayed. I would feel bad for the server people if they're given the buggy CPUs

Honestly I think that clocks and power usage are fine, and the respin is for OCing headroom. AMD pre-marketing for these is emphasizing OCing. What is the point of that if there is no headroom?

Or you know, maybe the flex-FPU thinks 2+2=5. Goodness knows the alleged ES performance was god-awful, even taking into account it was running at 1.8ghz.

 

[Vesku]

My friend Doc Brown gave me the un-tweaked original:

 

[Idontcare]

 

[Vesku]

Or you know, maybe the flex-FPU thinks 2+2=5. Goodness knows the alleged ES performance was god-awful, even taking into account it was running at 1.8ghz.

It's been said the B0 ES had extremely crippled cache and IMC, hope that was true hehe.

 

[Troll Trolling]

http://www.xboxmb.com/forum/93-pc-related/62252-fx-8150p-benchmarks.html

FX-8150P Benchmarks - prob fake?

3DMark 2011: P6265 points
Cinebench R10 (64-bit): 24 434 points
Fritz Chess Benchmark: 14 197 kilo nodes per second
PCMark 7: 3045 points
Super Pi 1M: 19.5 seconds
x264-Benchmark: 136.29fps 1 pass, 45.4fps 2 pass

Are all these guys just copying each others #s over the net?

http://www.xbitlabs.com/news/cpu/di...mbezi_8130P_Chips_Emerge_on_the_Internet.html

 

[Idontcare]

http://www.xbitlabs.com/news/cpu/di...mbezi_8130P_Chips_Emerge_on_the_Internet.html

Yep, and xbit labs got them from DonanimHaber who got them from OBR...the OBR of infamy around here...who later actually cleared the air and admitted the whole thing was a scam to show that DonanimHaber is full of crap and just steals everyone's fake benches to call their own.

So the answer is yes, its all BS, the people responsible for it have fessed up, and sadly it is literally the same BS that is being recycled over and over again in these rumors.

 

[Idontcare]

It's been said the B0 ES had extremely crippled cache and IMC, hope that was true hehe.

It's been said that BD heals the blind simply from the presence of its pure awesomeness.

And if we say that enough times the odds are in our favor it will be the top story on DonanimHaber tomorrow afternoon.

 

[Rifter]

it's been said that bd heals the blind simply from the presence of its pure awesomeness.

And if we say that enough times the odds are in our favor it will be the top story on donanimhaber tomorrow afternoon.

lmao

 

[ElFenix]

this is the same way camera rumors get started. someone makes an unsubstantiated post on dpreview forums, it gets posted around a bit, ends up on canonrumors as a CR1 rated post (lowest confidence tier), then gets posted on dpreview forums as the "OMG NEW CANON 70D SI 20MPIXELS and 50 cross AF points!," whence a big discussion ensues even after it's pointed out that the rumor originated 2 days prior on that same forum

 

[RussianSensation]

It's been said that BD heals the blind simply from the presence of its pure awesomeness.

And if we say that enough times the odds are in our favor it will be the top story on DonanimHaber tomorrow afternoon.

There have been 2 confirmed sightings of Bulldozer.

The 1st sighting involves an AMD employee staging Phase III testing of their FX-8000 B1 stepping model in the wild near main microprocessor manufacturing facilities, located in Dresden, Germany..... Unfortunately, it appears that the Intel 'special forces' were able to intercept the "Messiah" before reporters were able to gather any meaningful information:

More on that story Here.

Luckily, we have heard good news. Just 1 hour ago, Tom's Hardware gained possession of a next generation AMD Bulldozer FX-8000 series B2 stepping, which is rumored to sport much higher frequencies than the B1 stepping. This is a monumental scoop for a tech website--any news outlet would be thrilled to unveil such a coveted new device before AMD had a chance to do it themself. And while you're likely to read about this coup in mainstream news outlets across the globe in the upcoming days, feast your eyes:

Meanwhile, we are already starting to see fans gather themselves near AMD headquarters in Sunnyvale, California in preparation for the historic launch:

 

[Idontcare]

There have been 2 confirmed sightings of Bulldozer.

The 1st sighting involves an AMD employee staging Phase III testing of their FX-8000 B1 stepping model in the wild near main microprocessor manufacturing facilities, located in Dresden, Germany..... Unfortunately, it appears that the Intel 'special forces' were able to intercept the "Messiah" before reporters were able to gather any meaningful information:

More on that story Here.

Luckily, we have heard good news. Just 1 hour ago, Tom's Hardware gained possession of a next generation AMD Bulldozer FX-8000 series B2 stepping, which is rumored to sport much higher frequencies than the B1 stepping. This is a monumental scoop for a tech website--any news outlet would be thrilled to unveil such a coveted new device before AMD had a chance to do it themself. And while you're likely to read about this coup in mainstream news outlets across the globe in the upcoming days, feast your eyes:

Meanwhile, we are already starting to see fans gather themselves near AMD headquarters in Sunnyvale, California in preparation for the historic launch:

LMFAO veritable feast indeed