Re: [eigen] Status of AVX support |
[ Thread Index |
Date Index
| More lists.tuxfamily.org/eigen Archives
]
- To: eigen@xxxxxxxxxxxxxxxxxxx
- Subject: Re: [eigen] Status of AVX support
- From: Rohit Garg <rpg.314@xxxxxxxxx>
- Date: Wed, 7 Dec 2011 12:05:20 -0500
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :content-type; bh=ZZBDR+XpKbJTV2VHyKz3pRVSbnA4YwAtV+8GfPt+o0Y=; b=kXYApH7m+p+OXdp/9Rl5pZbC2lCyf0ckPMYMvDunlRxEKvnqXsccOxwJrj+gixK53V Ki2V14tX1+hNyvaw26Jm6mRXkCbb6D/QN27bdMu1iGoiutRVjF3gpp8jbEGMTvDoG1k+ O8B4Ao8VKr33CKB5pohps8/N4Be2SbLMsVWDc=
If you compile with -mavx, there will be no SSE code generated by GCC.
The SSE intrinsics will compile to corresponding AVX intrinsics. So
this penalty is not much of a bother.
On Wed, Dec 7, 2011 at 11:23 AM, Rhys Ulerich <rhys.ulerich@xxxxxxxxx> wrote:
>> W.r.t porting to AVX: Be aware that there might be some pitfalls with
>> AVX-performance:
>> http://www.agner.org/optimize/blog/read.php?i=142
>
> Interesting tidbit from that link "If the programmer inadvertently
> mixes AVX and non-AVX vector instructions in the same code then there
> is a penalty of 70 clock cycles for each transition between the two
> forms."
>
> Thank you for the pointer to the blog,
> Rhys
>
>
--
Rohit Garg
http://rpg-314.blogspot.com/
Graduate Student
Applied and Engineering Physics
Cornell University