Originally Posted by MrWhiteRX7
UPDATE: So I found my NB limit around 3000 no matter how many volts it just wouldn't post. Left it at 2680ish or whatever it is and got HT as high as 3300 and again my combined score went down and total score went down in Firestrike. Gpu score was down a little too. No clue why
A few years ago I tested my 1.st Intel Sandy Bridge proc. and compared the results by changing the speed / latency of DDR3 RAM.
I used Heaven Benchmark and the results were better with higher frequencies (1600/CL9 vs 1866/CL9), but even better with lower latency (1600/CL8).
Also, I've got some better results such as faster browser response and shorter home page load time.
In many games I have not received any fps increase.
Unfortunately I have not tested the online (MP) games or some such as a Batman...
The processoor itself also has a static memory latency, primary cache is L1, secondary cache is L2/L3.
Bulldozer/Piledriver has a bigger static memory latency than its Intel competitor :
What happens if we turn turbo on and peg the FX-8150 at 3.9GHz? Memory latency goes down!
Bulldozer Turbo frequency 3900 MHz (more than 4 cores) 4200 MHz (4 cores or less).
Piledriver vs Bulldozer ;
One of the most notable changes is a larger translation lookaside buffer for the L1 data cache, which grows from 32 entries to 64. Because the L2 TLB has fairly high 20-cycle latency, improving the hit rate in L1 can yield significant performance gains in workloads that touch large data structures.
Hardware prefetching into the L2 is improved as well. Minimum latency doesn’t change, which is why cache latency doesn’t look any better in our Sandra 2013 benchmark. However, as the prefetcher and L2 are used more effectively, average latency (much more difficult to measure with a diagnostic) should be expected to drop, AMD claims.
Because of this and other things I want you (or somebody else) to test with 4 active cores + OC. Good luck.