Amd Officially Benches Bulldozer

[Pestilence]

Still, 980x is the best multi-threaded CPU available in the market.

Most people would gladly take a 2600K for 700 less and live with the multithreaded hit

[qcmadness]

Most people would gladly take a 2600K for 700 less and live with the multithreaded hit

But the fact that 980X is the best multi-threaded CPU will not change whenever the price changes.

[bamtan2]

Benching a new chip against a chip that came out in 1Q of 2010.... Yeah that makes sense.

I don't know man, do you buy dates, or chips? chips have price tags on them, not dates. you compare performance, not dates.

[Glow9]

I don't know man, do you buy dates, or chips? chips have price tags on them, not dates. you compare performance, not dates.

Moore's law? But when I see something brand new top of the line, I want it compared to something brand new top of the line.
Dates are a downfall with AMD I guess, If I want a modern quad I know intel has 2011 technology I can go to the store and buy, I also know AMD has 2009 technology I can go to the store and buy. I really hope these BD Quads are something special, I want to turn my current rig into a HTPC.

[Lanek]

The only games I want to see a comparison of are ARMA II (OA) and Total War: Shogun II . Those games crush processors.

DCS A10C Warthog.. But Simulator are not really common ...

[Megacharge]

980X should never even be considered for gaming when the 2500K trounces it. The 8150s price is rumored to be 229.99 so all tests should be compared against a 2500K not a 980X. Wonder if intel plans on dropping the 2500Ks price to counter Amds strategy. 189 dollar 2500K would be a hell of a bargin.

I thought this was the pricing structure

FX-8150: 8 core, 3.6GHz (4.2GHz Turbo) - $266.28
FX-8120: 8 core, 3.1GHz (4GHz Turbo) - $221.73
FX-6100: 6 core, 3.3GHz (3.9GHz Turbo) - $188.32

AMD changed it?

[looncraz]

well said and I agree. Actually I think it's unfair to compare it to a 980X, 2500K and 2600K is more reasonable


Well, if it holds it's own against a 980X that sort of speaks volumes as to how it will do against a 2500k or 2600K yes?

In Dirt 3, the 980x outperforms the Sandy Bridge CPUs (heck, even the i7 920 does...).

This means that the showing from Bulldozer is actually more impressive against the 980X than against a Sandy Bridge CPU...

However, Phenom II does extremely well in the game as well, but not as well as the 980X.

On the Handbrake side, however, most seem to not realize that six-core 3.3GHz phenom II cores lose quite heavily against even the lowly i5 2400. Given the Bulldozer architecture, I'd expect POOR multi-threaded scaling in comparison to the phenom II X6.

Bulldozer's behavior changes under duress:
1. Clock will be at the low end (3.1GHz vs the ~3.6/7 turbo)
2. Internal module overhead and contention will cost around 7~12% *per core* on integer workloads
3. FlexFPU will likely perform poorly in unoptimized code

These design sacrifices should mean that an 8 core Bulldozer is more like a 6.8-7 core phenom II when under heavy load, which is actually about the performance we see... except we still must have some improved IPC to make up the difference... but only about 10-13% or so, which is not making me happy... I hope the i5 was a 2500, that would make it 15-18% (since phenom II loses by a good chunk in Handbrake vs the 2500). That means IPC for the Bulldozer is "only" about 15-20% lower than Sandy Bridge

Well, at least it is faster than phenom II

With turbo running, though, we see a nice boost - the system should run as well as the i5 in the comparison in single threaded tasks, and will be about 20% faster in heavily multi-threaded tasks, and faster STILL when TDP allows turbo to keep things going and thread-balancing between the modules completely removes the module overhead.

So, interestingly, a quad-core load will be about equal between the two, single-threaded loads should be equal, and the Bulldozer should win in multi-threaded work loads, though the margin by which it wins will diminish the heavier the load becomes (big-time diminishing returns in the Bulldozer design ).

This seems to fit the pricing policy perfectly as well, fits the official benchmarks, and conforms with the known design details of Bulldozer.

I will not be surprised to see Bulldozer pulling some upset wins vs Sandy Bridge in single/lightly threaded tasks beyond what would be plainly expected. The performance characteristics will take some time to figure out for a "LOT" of people... Shop by price, and I think AMD has a winner... and a great starting point for improvements!

That said, though, the design is EXTREMELY beneficial to the server environment. There, the work-loads are light, you normally have good process control so you can set affinity to keep threads which share data on the same module, TDP values can be set to self-manage policy between low/high latency, tasks can be sent to separate modules to optimize throughput, clock scales to the TDP so you can get the best performance/$$, you can concurrently execute a thread per CPU thread at the same rate, and much much more design advantages for Bulldozer.

And, some of those same benefits should make the desktop experience much smoother - once the software catches up to it (I believe there will be a Windows driver for Bulldozer to effect the scheduling for optimal behavior depending on policy [max perf / energy savings / etc...]).

God I want to get my hands on one...

--The loon

[PerryR]

But Simulator are not really common ...

Not anymore at least....Those bastards!

[Movieman]

Were they all gaming benches?

nope..

[Lanek]

Stop the tease lol ..

[Dresdenboy]

Where did they claim victory? They just put two machines next to each other.

Seems, some people have a sixth sense for what hasn't been said

[Movieman]

Stop the tease lol ..

[Lanek]

Not anymore at least....Those bastards!

Yeah, and ask ED ( DCS ) how much it is difficult to find a distributor for this type of "game" ( specially in US ). anyway this make some months their products are on Steam ( KA50 Black Shark and the A10C).

[Pestilence]

I thought this was the pricing structure

FX-8150: 8 core, 3.6GHz (4.2GHz Turbo) - $266.28
FX-8120: 8 core, 3.1GHz (4GHz Turbo) - $221.73
FX-6100: 6 core, 3.3GHz (3.9GHz Turbo) - $188.32

AMD changed it?

Those are marked up prices on bottom line telecommunications. The newegg price for the 8150 should be ballpark with the 2500Ks

[boxleitnerb]

In Dirt 3, the 980x outperforms the Sandy Bridge CPUs (heck, even the i7 920 does...).

This means that the showing from Bulldozer is actually more impressive against the 980X than against a Sandy Bridge CPU...

However, Phenom II does extremely well in the game as well, but not as well as the 980X.

This benchmark is flawed. A i7-920 cannot beat 2500/2600K. Every test in the web agrees with that. SB has more IPC and higher clocks and you guys actually believe these results? Also, it makes no sense whatsoever to benchmark CPUs in or near the GPU limit. You simply don't bench CPUs in highres with AA. This mainly taxes the graphics card and distorts the test field. This benchmark is completely useless.

[Mats]

Seems, some people have a sixth sense for what hasn't been said

Indeed, they could fill up a whole subforum all by themselves..
I'd like to see all far off predictions collected in one place after the launch, just to see how many Nostradamus we've actually got here.

[Spectrobozo]

On the Handbrake side, however, most seem to not realize that six-core 3.3GHz phenom II cores lose quite heavily against even the lowly i5 2400. Given the Bulldozer architecture, I'd expect POOR multi-threaded scaling in comparison to the phenom II X6.

I wouldn't be so sure,

here I see something very interesting


look at the X4 vs X6, this seems like a good scaling (probably you can find other reviews with different results, I suppose it can be explained by difference version and settings, but still, it always seems like the software scales relative well with more "threads")
so it seems AMD handpicked a 4 core SB when more cores or HT can do a good difference, vs their 8 threads CPU, why not use the 980x here to, if this is their target to beat?

on the other hand they choose to compare on a game clearly GPU limited to the 980x, while probably a Phenom II X4 could achieve the same 80fps, as a i5 2300, or maybe a i3 2100


anyway, I found another Dirt 3 CPU test
http://translate.google.com/translat...669005_5.shtml

[FlanK3r]

it depends of version,setings input and output....

[radaja]

this is what JF said about these tests

If it came from AMD, then there would be some blog at AMD with the results. I haven't seen anything from AMD, just people saying it came from AMD. Something doesn't sound right.

[Mechromancer]

DCS A10C Warthog.. But Simulator are not really common ...

I'm building a new system around this game and BF3. Only a few thousand of us actually play flight sims now, unlike the old days.

[ga1ve1an]

I am leaning towards Movieman knowing these new BD's are probably leading now. He seems pretty confident, and also this was just posted by xbit-labs spilling the beans. They obviously have the chips under testing and seem to confirm that AMD has the leadership with Bulldozer but for only a short while. So guess that is it. Bulldozer will be overall faster or at the minimum equal to what intel has out. Great news!!!

http://www.xbitlabs.com/articles/cpu...011-idf_5.html

Under the Final Remarks paragraph..

Anything to say about this Movieman?

P.S. they even mention that intel may push Sandy E up sooner... hmmmm

[highoctane]

Even without seeing any benchmark the price will generally match average performance relative to the competition.
But if BD can't pull off some benchmark wins with 8 fully functional cores they set the bar way too low.

[Apokalipse]

I hate these "cherry picked" benchmarks...why they don't have the balls to show some serious wprime or pifast or whatever really matters for benchers? also they compare a highly multi-threaded benchmark 8 vs. 4 cores....how stupid is that?

I think it's logical to compare one BD module (two cores) to one core + HT.
I think AMD have simply come up with a solution superior to hyperthreading.

These design sacrifices should mean that an 8 core Bulldozer is more like a 6.8-7 core phenom II when under heavy load

You're expecting it to have lower IPC than K10.5?
I don't think so....

[duron]

...will Stores have them on Monday?

[-=DVS=-]

I think it's logical to compare one BD module (two cores) to one core + HT.
I think AMD have simply come up with a solution superior to hyperthreading.

I disagree , logical is to compare threads vs threads. That is what you get at the end of the day. And price.