Bulldozer performance figures are in

An Exception · 11 Jul 2011 at 12:05

"The donanimhaber.com crew has run an engineering sample of AMD’s new FX-8130P through its paces and the results are very positive.

Although the chip fails to keep up with Intel cores in the SuperPI test, as we have already seen, it pulls ahead in other tests. For example, in x264 encoding tests, Bulldozer scores 136fps in the first pass and 45fps in the second pass, whereas the Core i7 2600K manages 100fps and 36fps respectively."

http://www.fudzilla.com/processors/item/23381-bulldozer-performance-figures-are-in

deusexlumina · 11 Jul 2011 at 12:07

as much as i'd love to believe this, its fudzilla.

Lelouch · 11 Jul 2011 at 12:16

It's all rumours until it's official actual release.

joeyjojo · 11 Jul 2011 at 13:05

As above, if that X264 comparison is right, I'm very excited.

DragonQ · 11 Jul 2011 at 13:34

Nice if it is true (not holding my breath). First-pass x264 isn't very multi-threaded so if Zambezi can outpace Sandy Bridge here, that'd be fantastic. No mention of clock speeds though so, really, these performance figures mean nothing.

Pickman · 11 Jul 2011 at 14:36

The wait is becoming painful.

drunkenmaster · 11 Jul 2011 at 15:06

I fancy boys said:
as much as i'd love to believe this, its fudzilla.

No, it isn't, can people really not read.

Cooper · 11 Jul 2011 at 15:14

"In Cinebench R10 AMD’s new flagship pulls off a score of 24434"

Hmmm, i hope thats at stock speeds, because i can get nearly 12,000 with just 3 cores on my unlocked Phenom II 550 @3.8Ghz...otherwise, with 8 cores, i'm not impressed

DragonQ · 11 Jul 2011 at 15:35

Cooper said:
"In Cinebench R10 AMD’s new flagship pulls off a score of 24434"

Hmmm, i hope thats at stock speeds, because i can get nearly 12,000 with just 3 cores on my unlocked Phenom II 550 @3.8Ghz...otherwise, with 8 cores, i'm not impressed

"Stock speeds" for an FX-81xx would be 4-4.2 GHz assuming Turbo Core is enabled.

Cooper · 11 Jul 2011 at 15:44

DragonQ said:
"Stock speeds" for an FX-81xx would be 4-4.2 GHz assuming Turbo Core is enabled.

If thats the case, then thats even worse...

, as when i meant 'stock speeds', i was thinkng 3.2Ghz...that has been said to be the stock speed.

http://www.techspot.com/news/44627-amds-bulldozer-based-fx-8130p-benchmarked-early.html

"The site managed to get their hands on an engineering sample of AMD's forthcoming FX-8130P and ran it through a range of tests. The 8-core chip features 3.2GHz clock speeds"

panyan · 11 Jul 2011 at 15:57

Cooper said:
If thats the case, then thats even worse..., as when i meant 'stock speeds', i was thinkng 3.2Ghz...that has been said to be the stock speed.

http://www.techspot.com/news/44627-amds-bulldozer-based-fx-8130p-benchmarked-early.html

"The site managed to get their hands on an engineering sample of AMD's forthcoming FX-8130P and ran it through a range of tests. The 8-core chip features 3.2GHz clock speeds"

i think "stock" in this case means the chip has not been fiddled with to get better performance, not as in turbo or not turbo

Combat squirrel · 11 Jul 2011 at 16:16

If it turns out to be between sandy and gulftown at less cost then I'll be happy. I was never expecting a miracle chip that was going to be 1000's of times faster.

as905 · 11 Jul 2011 at 17:11

Combat squirrel said:
I was never expecting a miracle chip that was going to be 1000's of times faster.

or even 1 times faster.

Martini1991 · 11 Jul 2011 at 17:12

I'm calling fake.
That Fritz benchmark, halfed would give you the 4 core result, as scaling is pretty 100% in Fritz, would give the 4 core a worse result than a Phenom II 955.

DragonQ · 11 Jul 2011 at 17:30

Cooper said:
If thats the case, then thats even worse..., as when i meant 'stock speeds', i was thinkng 3.2Ghz...that has been said to be the stock speed.

http://www.techspot.com/news/44627-amds-bulldozer-based-fx-8130p-benchmarked-early.html

"The site managed to get their hands on an engineering sample of AMD's forthcoming FX-8130P and ran it through a range of tests. The 8-core chip features 3.2GHz clock speeds"

Ah well maybe it was 3.2 GHz then. Engineering samples are often at lower clock speeds than the final result.

Owenb · 11 Jul 2011 at 17:32

Martini1991 said:
I'm calling fake.
That Fritz benchmark, halfed would give you the 4 core result, as scaling is pretty 100% in Fritz, would give the 4 core a worse result than a Phenom II 955.

2 BD cores share fetch&decode hardware so depending on the app they will take a hit if both cores on a single module are active.

MrElve · 11 Jul 2011 at 17:32

186W TDP? Blimey.

Owenb · 11 Jul 2011 at 17:35

MrElve said:
186W TDP? Blimey.

That's just an error with CPU-Z. 125W TDP is the max for the highest BD CPU.

nalla · 11 Jul 2011 at 18:31

Although the chip fails to keep up with Intel cores in the SuperPI test, as we have already seen, it pulls ahead in other tests. For example, in x264 encoding tests, Bulldozer scores 136fps in the first pass and 45fps in the second pass, whereas the Core i7 2600K manages 100fps and 36fps respectively."

9 fps more on the second pass, isnt that much really being as it has twice as many cores, would have to be cheap to compete.

Jokester · 11 Jul 2011 at 18:47

So it's a 1/3 faster give or take than a 2600K in the multithreaded stuff, now the 2600K runs 8 threads with HT which very roughly equates to a 50% boost over 4 threads only. So it's roughly the same speed thread per (non HT) thread on the 2600K. If the BD is running 4.2GHz and the SB presumably 3.8GHz it's not that far away clock for clock for single threaded performance.