Make Home Page
Add to Favorites
1.
Hi Tim.
Nice article as always. Nothing like taking a solder tool to a new piece of HW!
"So, although the GeForce 6600 GT seems to be “misbalanced” in the characteristics (i.e. its performance is oftener limited by the memory bandwidth rather than by the GPU), I enjoyed more gains from GPU overclocking than from the memory speedup. The reason is simple: I managed to increase the GPU clock rate by 28%, while the memory clock rate grew by 10% only."
Also, by increasing GPU clock, the single front-end quad ROP speeds up relative to memory bandwidth, thus shifting the bottle-neck back to the memory subsystem. I would be interesting to see performance if it had half the ROPs of 6800 (ie 2 quads), what the effect would have been.
Nice article as always. Nothing like taking a solder tool to a new piece of HW!
"So, although the GeForce 6600 GT seems to be “misbalanced” in the characteristics (i.e. its performance is oftener limited by the memory bandwidth rather than by the GPU), I enjoyed more gains from GPU overclocking than from the memory speedup. The reason is simple: I managed to increase the GPU clock rate by 28%, while the memory clock rate grew by 10% only."
Also, by increasing GPU clock, the single front-end quad ROP speeds up relative to memory bandwidth, thus shifting the bottle-neck back to the memory subsystem. I would be interesting to see performance if it had half the ROPs of 6800 (ie 2 quads), what the effect would have been.
[Posted by: KazzaLite | Date: 09/08/04 05:43:14 AM]
