Fudzilla: Bulldozer performance figures are in

[AtenRa]

Sorry guys to bring that here but didnt want to start a new BD thread.

I was thinking about BDs die size and that 320mm wasn't looking ok for me.

AMD wanted to minimize die size with the CMT design and if BD is 320mm then it is bigger than Quad Core Phenom I (450M transistors @ 285mm, 65nm process) and from Quad Core Phenom II (758M transistors @ 258mm, 45nm process).

With 32nm process they would be able to double the transistor count of 45nm and maintain the same Die size, so if BD is at 1.5B transistors then it should be at 250-260mm and because of the CMT design even smaller 240mm ??

If the 320mm is correct, then how the CMT design helped in the Die Size ?? unless BD has more than 1.5B transistors i dont believe that the Die size will be bigger than Quad Core Phenom II.

Could it be that 320mm is in fact 220-230mm ??

I was wrong,



Edit: I was also right, ill let you know soon

 

[Vesku]

8MB of L2 and 8MB of L3 contribute to the die size considerably. Wish they could coax some better numbers out of their caches though to take full advantage.

 

[-Slacker-]

@garagisti That went right over my head, but it's about hyper threading issues in linux, from what little I can make out. Thanks :thumbsup:

 

[garagisti]

@garagisti That went right over my head, but it's about hyper threading issues in linux, from what little I can make out. Thanks :thumbsup:

Well, in short, real cores are real!

Also,
http://tinyxcc/r2qmv
kindly remove "x" and put "." instead

Juicy tidbit is that BD will see past 2600K in multi-threaded tests, but will stay close or under 980X

 

[soccerballtux]

As pointed by Dresdenboy , BD will need some compilers to optimize
for its architecture.

Otherwise , we ll keep on seeing things like this :

Anyone gonna address this, or is this normal?

they're on equal footing with respect to the compiler optimizations. IE no underhanded disabling of all optimizations if CPUID lacks "GenuineIntel"?

 

[Manoa]

there may still be hope for BD, the enterprise market likes cores, im thinking virtualization (when running many machines on one), http/sql servers. this is intel's idea with their..what was it's name.. larabee or something, where they tried to make a 64-core pentium-based cpu without a floating point unit, they tried to make a video card out of it and failed. although it seems that it's not especially good in that department at the moment, perhaps in the future they will have a version with more cores, so they will have a lead on intel in the number of cores department, they started small (with only twice more cores). this seems like a beta processor or a development version like larabee, an experimental approach, without any real target and the tests made so far indicate that if BD were to show up with 16 cores, it might have had some market, probably coupled with a few math cards from nvidia....or amd whatever gives the most floating point performance (some people like those @Home projects, might work out there) I wonder if there is anything that BD does significantly better....actually there maybe something, it's the new math instructions FMA4 or whatever it is called, maybe a market for that can be found. but people who need so much math probably already have a few math cards.

 

[tatertot]

http://tinyxcc/r2qmv
kindly remove "x" and put "." instead

Juicy tidbit is that BD will see past 2600K in multi-threaded tests, but will stay close or under 980X

That's some old super-overclocked result.

Reality tidbit is that BD will lose to the 2600K in virtually all multi-threaded tests (except for (yay!) winRAR), will tie/lose-to the 2500 in gaming, and will lose to the 2500K (maybe even the i3?) on single-threaded tests, and has lower IPC than Phenom II.

Sure you can overclock it. But then, you can overclock a 2600K or a 2500K as well, for a lot less power.

BD has it all.... 70% > CPU die area than SB, 33% more power usage, and it takes a lot more time to run benchmarks... what's not to love?

If only marketing slide decks and forum boasts could be plugged into a socket....

 

[BlueBlazer]

Well, in short, real cores are real!

Also,
http://tinyxcc/r2qmv
kindly remove "x" and put "." instead

Juicy tidbit is that BD will see past 2600K in multi-threaded tests, but will stay close or under 980X

@garagisti, you got punk'd. That's the old FAKE benchmarks from OBR that circulated around the forums months earlier.

 

[SickBeast]

That's some old super-overclocked result.

Reality tidbit is that BD will lose to the 2600K in virtually all multi-threaded tests (except for (yay!) winRAR), will tie/lose-to the 2500 in gaming, and will lose to the 2500K (maybe even the i3?) on single-threaded tests, and has lower IPC than Phenom II.

Sure you can overclock it. But then, you can overclock a 2600K or a 2500K as well, for a lot less power.

BD has it all.... 70% > CPU die area than SB, 33% more power usage, and it takes a lot more time to run benchmarks... what's not to love?

If only marketing slide decks and forum boasts could be plugged into a socket....

I don't know where you're getting your information from. BD looks to be very competitive with multithreaded apps. It looks like it will win at x264 encoding, WinRAR, and in several synthetic tests.

I have yet to see any leaked power consumption data.

Essentially what I want to say is that we don't know yet. We need a proper review.

It's only one more day until we find out...

 

[Olikan]

That's some old super-overclocked result.

Reality tidbit is that BD will lose to the 2600K in virtually all multi-threaded tests (except for (yay!) winRAR), will tie/lose-to the 2500 in gaming, and will lose to the 2500K (maybe even the i3?) on single-threaded tests, and has lower IPC than Phenom II.

Sure you can overclock it. But then, you can overclock a 2600K or a 2500K as well, for a lot less power.

BD has it all.... 70% > CPU die area than SB, 33% more power usage, and it takes a lot more time to run benchmarks... what's not to love?

now look at phenom II x6

 

[videoclone]

I would say its a very big FAIL of a CPU, they really should have just shrunk the Phenom II X6 1100T to 32nm and with the power saving boost up the tdp to bump up the core clock .
a Phenom II X6 1100T at say 4.2Ghz would of been competative with intel's current lineup much more so then this bulldozer POS that cant even compete with the Phenom II X6 1100T

 

[nenforcer]

I would say its a very big FAIL of a CPU, they really should have just shrunk the Phenom II X6 1100T to 32nm and with the power saving boost up the tdp to bump up the core clock .
a Phenom II X6 1100T at say 4.2Ghz would of been competative with intel's current lineup much more so then this bulldozer POS that cant even compete with the Phenom II X6 1100T

 

[ViRGE]

Alright guys, we're rolling this into the Official Review Thread. Please continue there.