[R-SIG-Mac] Performance Issues.
simon.urbanek at r-project.org
Wed May 17 04:55:25 CEST 2006
On May 16, 2006, at 8:34 PM, Byron Ellis wrote:
> Apparently somebody was having some performance issues
> fortunately, it got dugg and someone fixed it for us
> In an unsurprising turn of events it turns out to be malloc's fault.
> It also looks like the build isn't against an optimized BLAS?
We had a discussion about this earlier, it started with
What it boils down to is that ptATLAS can give you a good speed-up,
but it can also screw you up by calling malloc/free all the time - it
depends on the task. For single core CPUs it's definitely better to
use R's own BLAS. For Core Duos it depends on the size of the problem
- for bigger problems ptATLAS is better, for smaller problems
internal BLAS may be better.
In a quiet minute I'll try to run our benchmarks with Lea's allocator
and see if it would make sense to use it for OS X.
More information about the R-SIG-Mac