AMD FX-8150 Bulldozer finally tested

[jimbo75]

16801060 and 1920.1080 and aa8 lol

Would you rather see 1024x768 0xAA and 400fps on the intel cpu and 300 fps on the AMD cpu?

[eXa]

Yes, because that actually says something. (all settings maxed ofc)

[Maxforces]

I would like to see the cpu test and not gpu built-in benchmark

[looncraz]

I suppose there is also a small chance that all the final BIOS updates for the BD won't be released until the day of the launch.
They still could have disabled a few things to see who is breaking the NDA...
If AMD is doing this, then, they really got some devious people there.

I was thinking the same thing, but JF-AMD stated outright (to me, IIRC) that no such thing was happening, but that the BIOS updates could make a considerable performance difference do to the CPU initialization code. Also, Windows and Linux need kernel scheduler changes and memory alignment changes due to the share L1 cache causing excessive cross invalidations and subsequent reloads.

The cache memory has significantly more latency, but about a third more reading performance. Writes are also slower, which explains the presence of an L2 WCC (write coalescing cache). The very existence of the WCC and the cache details made available long ago made me wary... 18-20 cycle access times vs 12 cycles on Phenom II seemed like a BAD idea... that, and they kept the specialization of the ALUs instead of making them more capable, then removed one... but added an extra pipeline... that didn't seem too bright either, unless you can use the ALUs across the whole module to make a fat core (which should have been done before releasing this product).

If this is indicative of Bulldozer's performance, I will be building Intel machines almost across the board because the 1155 upgrade path is strong, but AM3+ is weak... a few of the lowest end machines will be AMD... but Athlon IIs.

My media machine upstairs is being prepped for an $800 upgrade and I was hoping Bulldozer would be the core, but it looks like an i2600k will be there instead - which sucks, because I have to pay a premium for the other features I need... but the performance is what matters for HD video.

--The loon

[gosh]

Well game benchmarks are fail.. they show exactly what many others and me where saying -> gpu limitation @ that high res... regardless what cpu is used all perform the same... a difference of 1-2fps is laughable... and yes the scailing in the graphs is also bad.. but well I just made the screen caps.. blame donanimhaber.

Dont think so, this is good for a cpu that focus on scaling. 2MB L2 cache and 8MB L3 cache 64 way set associative isn't as fast as cache on 2600K but it scales better

[Hornet331]

Dont think so, this is good for a cpu that focus on scaling. 2MB L2 cache and 8MB L3 cache 64 way set associative isn't as fast as cache on 2600K but it scales better

Yes a good thing we bench the gpu in a cpu review... and I have a very bad deja vu about a thread form 2008...

[-=DVS=-]

Some dude is doing live stream benching Bulldozer , with 8 threads he got 24 GFLOPs in LinX 0.6.4

[gosh]

bulldozer online: https://join.me/573-962-519

[eXa]

In what?

[Aberration]

Wow. I sure hope there is just something wrong in the BIOS, or maybe a new stepping is needed.

I was really hoping to change camps.

[jimbo75]

Yes, because that actually says something. (all settings maxed ofc)

Yes it would tell you how the chip handles gaming at settings you'll never play it.

In these 6 tests the BD cpu averaged 130 fps with AA. The i7 averaged 131.5 fps with AA.

Answer me this - if that BD chip was $50 would you even consider buying anything else for gaming? What about $100? How much is that 1.5 extra fps worth? This is the reality of enthusiast gaming, not ridiculous 600x480 resolutions.

[gosh]

Yes a good thing we bench the gpu in a cpu review... and I have a very bad deja vu about a thread form 2008...

No! It is important that it runs games at normal resolutions as fast as the fastest phenom as long as it wins in BF3. BF3 is the key because that is using new technology. It seems that it wins over phenom in all games and in some games it wins over 2600K, this is very good.

[Hornet331]

All credit geos to black96ws6 on Overclock.net
http://www.overclock.net/amd-general...s-benches.html

Screencaps so far:

Untitled20111010005620.jpglive stream cpuz.jpg

Cinebench1158120.jpg
bench9.jpg
bench8.jpg
bench7.jpg
Bench3.jpg
Bench4.jpg
bench6.jpg
bench_002.jpg

hes installing vantage now.

[richierich]

Why does the task manager not show 100% utilization?

[radaja]

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

[cold2010]

Would you rather see 1024x768 0xAA and 400fps on the intel cpu and 300 fps on the AMD cpu?

NO
1680x1080 without AA And AF

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

[Hornet331]

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

omg.. im laughing hard right now... damn you...

[Brice MJ]

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

Tragicomic.

[radaja]

omg.. im laughing hard right now... damn you...

Tragicomic.

i told you,its funny as hell whether your pro or anti amd,it is what it is,you just cant help to chuckle

[eXa]

Yes it would tell you how the chip handles gaming at settings you'll never play it.

In these 6 tests the BD cpu averaged 130 fps with AA. The i7 averaged 131.5 fps with AA.

Answer me this - if that BD chip was $50 would you even consider buying anything else for gaming? What about $100? How much is that 1.5 extra fps worth? This is the reality of enthusiast gaming, not ridiculous 600x480 resolutions.

Why are you arguing cpu performance with gpu performance?

The cpu does the same amount of work regardless of resolution (as long as all the other settings are the same)
Yes, a game wich has 3-400fps with 1024 resolution is rather pointless, since you obviously dont need much cpu performance for it to run great. But what if you get a game that runs with 100fps, or 50fps @ 1024?
Thoose 300 and 400fps would tell me SOMETHING about what to expect, while those 130 gpu limited fps you want to see wouldnt tell me a daam thing about cpu performance in that game.
All that 130fps shows me is that both cpu is enough for that game(but nothing about newer/more cpu dependant games).

[Hornet331]

Wait till the "hittler got told" stuff pops up...

Why are you arguing cpu performance with gpu performance?

The cpu does the same amount of work regardless of resolution (as long as all the other settings are the same)
Yes, a game wich has 3-400fps with 1024 resolution is rather pointless, since you obviously dont need much cpu performance for it to run great. But what if you get a game that runs with 100fps, or 50fps @ 1024?
Thoose 300 and 400fps would tell me SOMETHING about what to expect, while those 130 gpu limited fps you want to see wouldnt tell me a daam thing about cpu performance in that game.
All that 130fps shows me is that both cpu is enough for that game(but nothing about newer/more cpu dependant games).

Exactly, it just tells you right now the cpu is "good enough" what happens when you buy half a year later another gpu and run cf/sli, or when a game finnaly starts to be more cpu dependent (like SC2).

With lower res benches you see what potential the cpu has, with caped max res benches it all looks the same.

[Hondacity]

thats awesome

[Tha Last Meal]

dont forget this video someone made right after that FX-8120 CB run was done,its mean but funny as hell
http://youtu.be/CqTU4wVvZL0

LOL

[PerryR]

Indeed funny.

BTW, anyone know why the CPU is hardly strained in some of these CPU intensive benches?

[eXa]

hahahah, that clip made me laugh alot too