7 Mar
2010
7 Mar
'10
8:34 p.m.
On 06/03/2010, at 03:10, stefan kersten wrote:
i'm still curious, though, why my three versions of direct convolution perform so differently (see attached file). in particular, i somehow expected conv_3 to be the slowest and conv_2 to perform similar to conv_1. any ideas? i haven't had a look at the core yet, mainly because i'm lacking the expertise ...
Hmm, one problem is that the current definition of reverse is suboptimal to say the least. I'll fix that. Could you perhaps send me your complete benchmark? Roman