The fastest model, the AK, featured two Piledriver modules operating at 4. The Bulldozer based FX had a 3. Thomas Ryan Author at SemiAccurate. I believe you may have inadvertently included turbo-scaling losses in with your calculations for CMT scaling losses. If you have a hardware performance question or an interesting data set Thomas has you covered. Starting with Cinebench we can see that Piledriver offers an eight percent advantage in the single threaded test and a smaller six percent advantage in the multi-threaded test. You can use these HTML tags.

Uploader: Nikoramar
Date Added: 13 January 2014
File Size: 62.35 Mb
Operating Systems: Windows NT/2000/XP/2003/2003/7/8/10 MacOS 10/X
Downloads: 92840
Price: Free* [*Free Regsitration Required]

AMD Bulldozer/Piledriver Modules and Hyper-Threading « Blog

This performance metric is quite easy to measure, and answers the question: All of the above really just boils down to re-running my earlier Hyper-Threading Performance tests again on AMD systems. Our final test, Chalkboard, shows a seven percent advantage in favor of Piledriver. But all of this may be a moot point. Ideal speedup is 2 for replicated CPU cores.

The FX has a five percent clock speed advantage over the FX, in addition to a six percent average in per clock performance improvement.

Piledriver (microarchitecture) – Wikipedia

Does Piledriver deliver where Bulldozer fell short? Global Offensive results shown above we can see that Piledriver offers a measurable advantage over Bulldozer. As configured see above tablethe AMD wmd already consume more power. Throughput does not increase beyond 8 bulldozer because the OS is time-slicing threads onto 8 hardware thread contexts, and time-slicing offers no performance improvement to CPU-bound tasks. If I gave the system two independent threads rather than one, how much performance will it give me in return for my effort?


Poorly threaded web based tests like the Bullrozer and Chalkboard benchmarks showed much larger gains than well threaded tests like our wPrime and Truecrypt benchmarks.

Username or Email Address Password. Retrieved 10 February Six percent is the average advantage that Piledriver offers over Bulldozer when both are in an eight core configuration, and clocked at 4Ghz.

That explains their current financial situation…. Retrieved 23 March Thomas Ryan is a freelance technology writer and photographer from Seattle, living in Austin. Intel Lynnfield Core i, MHz.

Look at this cost comparison for machines for similar price: Now this 10 to 15 percent figure is a combination of two kinds of enhancements. NET benchmark, Piledriver is once again ahead by eight percent.

To find out we dusted off an old FX and warmed up the testing platform from our recent Oe review. I tested four microarchitectures: This newsletter may contain advertising, deals, or affiliate links. Steamroller – Family 15h 3rd-gen.


AMD’s FX-8350 analyzed: Does Piledriver deliver where Bulldozer fell short?

Email will not be published required. Furthermore I replaced bc with wcalc on my script. If it was really floating-point, the runtime would approximately not depend on ir size of the numbers. Retrieved 22 March The Bulldozer based FX had a 3. The changes over Bulldozer are incremental.

Yep, performance scaling with SMT is dependent on the workload.

Piledriver (microarchitecture)

Now I know bulldozeer is working with floating point because I needed to increase the exponent a lot for each calculation to take a measurable amount of time. Look at this cost comparison for machines for similar price:. What benchmark are you running, and which part of the processor is the bottleneck?