|
From: | Dmitri A. Sergatskov |
Subject: | Re: fastest way to element-by-element multiply matix by vector? |
Date: | Wed, 20 Jun 2007 11:00:26 -0500 |
On 6/20/07, David Bateman <address@hidden> wrote:
>
...
I get the reverse and the third option wins.. The third option also has a big memory advantage for large matrices..
... I wonder if this is CPU speed vs memory bandwidth thing. Opteron may perform differently vs Pentium/CoreDuo
D.
Dmitri. --
[Prev in Thread] | Current Thread | [Next in Thread] |