AMD Bulldozer Dual-Interlagos Benchmarks On Linux

[phoronix]

Phoronix: AMD Bulldozer Dual-Interlagos Benchmarks On Linux

Lately we have been talking a lot about Intel's latest Sandy Bridge processors under Linux due to their very competitive performance and interesting graphics abilities, but on the AMD side there has not been too much to talk about. On the low-end there is the intriguing Fusion APUs, but on the high-end they don't have an answer to Sandy Bridge until delivering their new "Bulldozer" products closer to the summer. Fortunately, we have the first Linux scoop and performance benchmarks from engineering samples of their 16-core Interlagos server chip.

http://www.phoronix.com/vr.php?view=15816

[birdie]

"32 cores running at 1.8GHz indicates that its C-Ray time is a mere 25 seconds"

vs

4 cores Intel Core 2500K in astounding 61 seconds.



Now let's calculate per core efficiency:

1/(32*25) = 1/800 (32 cores bulldozer)

1/(61*4)  = 1/256 (4  cores SB)

1 / 800 vs 1 / 256 = SB is more than 3 times more efficient.

OK, Bulldozer runs at 2GHz, SB runs @ 3.2GHz, let's take it into account.

1 / 800 / 2 vs 1 / 256 / 3.2 -> SB is still 2(!) times more efficient.




I guess we'll have to see the desktop version of Bulldozer to draw any conclusions. I doubt any existing computational test today can scale to 32 cores without some major performance loss.

[Qaridarium]

"32 cores running at 1.8GHz indicates that its C-Ray time is a mere 25 seconds"
vs
4 cores Intel Core 2500K in astounding 61 seconds.
Now let's calculate per core efficiency:

1/(32*25) = 1/800 (32 cores bulldozer)
1/(61*4)  = 1/256 (4  cores SB)

1 / 800 vs 1 / 256 = SB is more than 3 times more efficient.
OK, Bulldozer runs at 2GHz, SB runs @ 3.2GHz, let's take it into account.
1 / 800 / 2 vs 1 / 256 / 3.2 -> SB is still 2(!) times more efficient.
I guess we'll have to see the desktop version of Bulldozer to draw any conclusions. I doubt any existing computational test today can scale to 32 cores without some major performance loss.

you calculate wrong because: an 16 core bulldozer do only have 8 real-full-featured-cores.

the OS only count 32cores in this test because its much better to use this 16 cores as a 32core.

[thalin]

Hey, awesome, you referenced one of my benchmark runs!

A Dell PowerEdge server that's packing four Intel Xeon X7550 CPUs that each have six-cores and Hyper Threading with a 2GHz base frequency with 2.4GHz Turbo Frequency and 18MB of L3 cache, is the current winner in that category as shown by doing this dynamic comparison.

That system is quite a beast.

[smitty3268]

32 core bulldozer = 32 integer cores, 16 fpu cores, and 16 "front-ends" dispatching instructions and everything.

So it's sort of a super-hyperthreading, that actually doubles some of the execution units instead of waiting for pipeline stalls.

AMD claims it gives all the benefits of an extra core with only 10% or so of the die space, but it remains to be seen how true that actually is in practice.

[frostwyrm333]

Core efficiency probably doesn't matter now because its hard to say what is a core.
I find the whole thing confusing, more bulldozer benchmarks would be great.

[cb88]

Indeed performance per watt is far more important...

[Sylarr]

compared to the Intel Core i5 2500K (quad-core + Hyper Threading; 3.3GHz + 3.7GHz Intel Turbo Boost)

The i5 does not have hyperthreading.

[Goderic]

32 core bulldozer = 32 integer cores, 16 fpu cores, and 16 "front-ends" dispatching instructions and everything.

So it's sort of a super-hyperthreading, that actually doubles some of the execution units instead of waiting for pipeline stalls.

AMD claims it gives all the benefits of an extra core with only 10% or so of the die space, but it remains to be seen how true that actually is in practice.

They claim +90% performance and +50% extra die space.
All the benefits of an extra core with only +10% extra die space is never going to happen.

[Raven3x7]

The i5 does not have hyperthreading.

It's a typo, the 2500k is a i7 not a i5.