AMD FX-8350 Linux Performance-Per-Watt
Phoronix: AMD FX-8350 Linux Performance-Per-Watt
The latest Phoronix benchmarks to share of the AMD FX-8350 "Vishera" processor are performance-per-Watt results for the Piledriver eight-core processor compared to the previous-generation Bulldozer FX-8150. Tests were conducted when running at stock speeds as well as overclocked settings.
Ok, it's nice to see that the 8350 is a improvement over the 8150, but can we please get the same Bench in comparison with the Core i7 3770K, please? This would add real value to the article.
Yup, the onlt thing you can tell from this article is that the new architecture is a slight improvement over the old one. It would've benn rather puzzling if it weren't. But including the competition makes the whole thing pretty useless.
Originally Posted by Lynxeye
I agree. And performance/watt/price statistics for 5 years would be nice too.
Wow, 8 pages "Vishera" advertisement!
FXfirstname.lastname@example.org compiles Linux kernel in 72.98 seconds, consumes 207 Watts on average.
FXemail@example.com compiles Linux kernel in 79.25 seconds, consumes 235 Watts on average.
How is it possible for FXfirstname.lastname@example.org to have better performance-per-watt? Results in performance-per-watt graph seems to be wrong...
That also seemed strange to me. I think there's something wrong with the formula used to come up with those numbers. It's actually calculating how many watts are needed for each second, which obviously reverses the results. That formula works when more is better, but not when less is better. That's why all the graphs involving less is better are wrong.
Originally Posted by abacaba
Well it depends how much overvoltage is needed to get 4.6 ghz. If you need less vcore for the older cpu because it oc better then you see this. oc values are never compareable as those are single part specific.
It doesn't matter what voltage is set to run a core, what current does it takes etc. Even clock rate is not important. Only performance (here measured in seconds) and power consumption (in watts) do count. We can multiply time by power and get the number of joules required to do the job (compile kernel) with given setup, and that number will be better for email@example.com
Originally Posted by Kano
Very cool testing!
I agree to spice the test with some good Intel rival... However anyone can do this by running the test on own system and submitting. So please, if anyone has Ivy and time do this
Very cool CPU indeed! The 20% AMD has talked about do appear in tests!
Also, its scales like godlike so it could be good idea to overclock the CPU for serious tasks and to underclock it for daily tasks. This way the CPU will be as energy efficient as Intel for daily work and can be turned into a beast for serious load. Ofc, one needs to pull 24hr stability test on it, but the possibility to use ECC makes this feature even more tempting.. ))
Btw, 85 Watts idle and 150Watts load for vicera - compare to my Athlon II x4 630 - 90W idle and 140W full load when in stock - 80W idle and 120W when undervolted to 1.2v (runs at stock Hz, rocksolid).
This is great!