Rambus XDR also on Graphic Cards?

[aaronspink]

I am talking about internal Latencys. And while they do vary the average is about right.

Hellbinder, I can confidently assert that you don't know what you are talking about in this case.

Aaron Spink
speaking for myself inc.

 

[aaronspink]

P4 has an off-die memory controller (right?), and it gets around 70-90ns with PC3200 DDR. A64 has an on-die controller (like video cards, right?), and it hits 40-50ns with PC3200 DDR. I'm thinking the A64's much lower latencies factors into its current [/quote]

As I have told Johan, the numbers he is reporting look suspect. None of those machines can really achieve those latency numbers without a significant effect of the prefetcher. This isn't a new issue.

Aaron Spink
speaking for myself inc.

 

[Maverick]

That said, I seem to remember that the major latency problem for RDRAM was due to the fact that only one chip on a RIMM is active at one time, for heat reasons. This is just an unfeasible scenario for graphics memory, as data is striped across all chips in such a way that they're really all active at the same time.

But if you're designing a GPU then couldn't you just, y'know, make it not do that?