• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

Just a thought (Regarding AMD vs Intel CPUs) and Benchmarks

U

undeclared

Senior member
Hello

Just a thought here, but aren't there quite a bit of benchmarks that will fit 100% in the cache of a core 2 duo, and will only fit half-way or less into an AMD x2 or Opty?

And if so, won't that give it a 20% advantage in speed at least?

I'm not saying C2D's aren't faster than X2s, but I think this is an important consideration when you look at benchmarks (and why AMD really needs to add bigger caches!)
 
Originally posted by: xtwells
Hello

Just a thought here, but aren't there quite a bit of benchmarks that will fit 100% in the cache of a core 2 duo, and will only fit half-way or less into an AMD x2 or Opty?

And if so, won't that give it a 20% advantage in speed at least?

I'm not saying C2D's aren't faster than X2s, but I think this is an important consideration when you look at benchmarks (and why AMD really needs to add bigger caches!)
Click to expand...

It's not our problem that AMD isn't able to throw bigger caches onto it's processors, that it's fault due to whatever design decisions it made.
 
From what I've learned, AMD CPU's are not as cache dependent as Intel CPU's, due to the memory controller being built into the processor.

Tha fact that they are slower is the architecture of the processor itself, not just the amount of cache.
 
Originally posted by: JustaGeek
From what I've learned, AMD CPU's are not as cache dependent as Intel CPU's, due to the memory controller being built into the processor.

Tha fact that they are slower is the architecture of the processor itself, not just the amount of cache.
Click to expand...

In the same sense K8 was superior ( more efficient ) to P4 ..

That said; programs and benchmarks can be written to run more efficiently on one architecture as opposed to the other ..
 
Originally posted by: xtwells
My point: if an entire benchmark can fit into the cache, will it not run faster?
Click to expand...

The more data you have closer to the processor the better is what I will say, different applications benefit in varying degrees.
 
You must log in or register to reply here.
Back
Top