Re: The performance increase of the K8 relative to the K7. Most of it came from the IMC, as AMD says.
That's not even what AMD says, you bleating fool.
"it's well known that the latency to first memory access is a first-order effect on the performance of processors. So we've attacked that problem very directly by putting the memory controller directly on the processor."
"So when we come in and reduce memory latency, it always does give a boost—it's just a question of how much that boost is. It's very significant in a lot of cases, though; you can see a 20% performance boost for having the memory controller on-chip on very many crucial applications."
Look past the spin, Doug. The ambiguity here is staggering. They set the stage by admitting that there is a question of how large the boost might be, and then they pick a high number, 20%, and claim it *can* be the case in many "crucial" apps.
They never say how they define crucial, or how many is "a lot", or what the range could be in apps that don't see the 20%. For all you know, they could have tested using some memory latency kernels and a few low level benchmarks and they could have been able to claim all of the above as true.
Of course, that never stopped you before from believing what they want to believe.
Market Data 
Markets 
AI
