Tony, <Why so slow?>
I don't know why. By the way, maybe now's a good time to correct my earlier statements. Celeron (Mendocino) has an 8 clock L2 latency. I don't know what the latency is for Dixon, or what it will be for Coppermine. I'm just using Celeron as a guideline.
In comparison, I do know that the Alpha 21364's on-die L2 cache, which is 1.5 MB large, will have a latency of 12 clocks, compared to 8 clocks for Intel's Celeron. Some of the reasons cited for Alpha's long latency (according to MPR) include power savings (a significant factor when the CPU already consumes 100 watts) and the unwillingness to modify the 21264 core design. I guess in the case of Celeron, Intel could have improved upon its L2 latency, but didn't because of time-to-market reasons.
Maybe Coppermine's L2 latency could be lower. MPR isn't very clear on what it will be. They say 6, but then again they consider Athlon's L2 latency to be 11, which is too small in my opinion. If you asked me, I would guess that Coppermine's L2 latency can't be any longer than Celeron's.
Tenchusatsu |
