On 17 May 2013 05:19, "Christopher Jordan-Squire" wrote:
>
> I'd been under the impression that the easiest way to get SSE support
> was to have numpy use an optimized blas/lapack. Is that not the case?
Apples and oranges. That's the easiest (only) way to get SSE support for
operations that go th
I'd been under the impression that the easiest way to get SSE support
was to have numpy use an optimized blas/lapack. Is that not the case?
On Thu, May 16, 2013 at 10:42 AM, Julian Taylor
wrote:
> Hi,
> I have been experimenting a bit with how applicable SSE vectorization is
> to NumPy.
> In prin
Hi,
I have been experimenting a bit with how applicable SSE vectorization is
to NumPy.
In principle the core of NumPy mostly deals with memory bound
operations, but it turns out on modern machines with large caches you
can still get decent speed ups.
The experiments are available on this fork:
htt
