tags:

views:

60

answers:

3

AMD announced it's Fusion platform some time ago. Having read a bit about it I'm both excited and sceptic. For example it should make it possible that GPUs and CPUs share the same memory. (and the GPU and CPU are both in the same package) Now since GPUs have a much higher memory bandwidth (around 10x the bandwidth a CPU has) and that the way CPUs and GPUs use cache is fundamentally different, the question arises how the heck can they do this? I wonder if any details are known.

+1  A: 

CPUs and GPUs have been sharing memory for years. Fusion is no different, in fact it's far from the first instance of a GPU being integrated into a general-purpose CPU core.

Like all other such solutions, it'll be fine for casual use, but it'll be far from cutting-edge 3D acceleration.

Nicholas Knight
GPUs which use shared memory are usually dead slow.."Like all other such solutions, it'll be fine for casual use, but it'll be far from cutting-edge 3D acceleration."That's exactly the point, I thought AMD Fusion will be fast for graphics or scientific usage, which requires high memory bandwidth.
Nils
@Nils: msw's answer makes it sound like they might be going after a new hybrid strategy with GDDR5 (though his "AMD is happy to explain" comment is a bit disingenuous, since it just links to AMD's marketing hype), but I wouldn't expect it to close the gap. GDDR5 isn't magic, and every new shared-memory GPU has come out with marketing declarations of how wonderfully fast they are. I'll believe it when I see it.
Nicholas Knight
"I'll believe it when I see it." - Same here.
Nils
+1  A: 

I have also searched for some detailed info on how this APU technically works, but haven't found anything better than AMD's whitepaper on the subject, which, in a slightly marketing-wise tone, does present a lot of good info.

rubenvb
I quickly looked into it. It says that CPU and GPU share the bus, but not how. Nothing about CPU/GPU caching..
Nils
A: 

By using high-bandwidth dual ported RAM. AMD is happy to explain.

msw