Results: Euler 3D and 7-Zip
This is a benchmark version of a professional/academic simulation. This program models airflow over an airfoil, and is again nicely multi-threaded. It is very floating point heavy and does not adequately leverage the SSE capabilities of AMD processors (something the authors of the benchmark talk about due to them using a certain Intel compiler for their program).
These results are fascinating. No, seriously. With a single thread at stock speeds the X4 980 is the fastest of the bunch. Throw in another thread and the FX-6200 is the fastest. Take it to four threads and the FX-6200 falls behind the others again. At eight threads it is well behind the others. This of course changes around somewhat when the FX is overclocked, but at eight threads again it fails to overcome the lead held by the X6 1100T. I think the primary reason for this is the shared FP units on the modules. With one and two threads, the decode and execution units can easily handle the workload. Heading to 4 threads causes some issues with the scheduling of the three modules (though the FX-6200 could theoretically handle 6 x 128 bit double precision floating point instructions). At eight threads the contention is even worse, so much so that the native four core 980 is still outperforming the FX-6200. Even heavily overclocked, the eight thread test gives the X6 1100T a lead over the FX-6200. I honestly think the thread handling abilities of this architecture are still not up to snuff.
This free compression program has a nice benchmark that measures the theoretical MIPS of a processor when compressing/decompressing a file. I use the 32 MB dictionary setting for this particular benchmark and 1 through 6 threads.
When going single thread, the FX-6200 keeps up well with its older siblings. Once that goes above one thread, it seems to fall behind. At four and six threads it is well behind the X6 1100T. Only when overclocked does the FX-6200 catch up to the others.