Re: 4x4 single-precision matrix product with SSE
Nicolas Bock <[email protected]> Wed, 5 Sep 2012 13:13:46 -0600
| Newsgroups | org.kernel.vger.linux-assembly |
|---|---|
| Message-ID | <CAPMKG4Co96j3bcFCL2qmB72FvYeGd+53Wxkx6x3nkDN7XHgmzQ@mail.gmail.com> |
Hi list, thanks to the many helpful comments and suggestions here I was able to write the 4x4x4 multiply and even get a somewhat performance out of the code. We have published our results on this here: http://arxiv.org/abs/1203.1692 Thanks again, nick