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