I'm been out of the loop for quite a while now, and I'm looking at build a new rig. Back when I first started doing GPU folding a couple years ago, the performance was CPU-limited. Is that still the case, or has the client improved enough that the CPU is no longer the bottleneck?
I guess my question comes down to this: if I get a $50 CPU/MB combo from Fry's (typically something like a Sempron LE1640), will it bottleneck a modern GPU?
I guess my question comes down to this: if I get a $50 CPU/MB combo from Fry's (typically something like a Sempron LE1640), will it bottleneck a modern GPU?