| Re: [eigen] Use of streaming loads in eigen |
[ Thread Index |
Date Index
| More lists.tuxfamily.org/eigen Archives
]
- To: eigen@xxxxxxxxxxxxxxxxxxx
- Subject: Re: [eigen] Use of streaming loads in eigen
- From: Rohit Garg <rpg.314@xxxxxxxxx>
- Date: Fri, 27 Mar 2009 21:15:54 +0530
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:in-reply-to:references :date:message-id:subject:from:to:content-type :content-transfer-encoding; bh=ok/EfkrCRbt7Rgi/NkmMvKv8LT1WAk4CHfQqUyNpHps=; b=Hn5Y6tQWiMFSudUZSHJxmlYg92N5iH6Sqq4QQTiqvKG+SHavAcsbnhWtS57Gi4GMfv /7bhaJlVfNwYA5J/21T8yCPlGuIihREBe+E0hq993AO/yJ2C5EnHBkx3eNLBTkEk5sxf xA/BmUl3reTWKBeB+B2mpZgt2KZTCpM826Gw4=
- Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :content-type:content-transfer-encoding; b=tUxtbndYtqN3q1vOpx2W3GfxppSFGcaqPeeDvwllJNn7x2Ghy1YF6ySJTMCaa2ntlg Lg3wGB0vayqUCUKteINxHADdfZlNcwm89vYkQdkXNKpPnADljfSAj00/QwACM2ZsxI6T BrGdKSMJ6LL7ozT3MXATYLCnlgBWuNXG5+rXQ=
for dynamic sized vectors, in blas 1 operations atleast, I am not sure
why their reuse can't be predicted. Lazy evaluation is the only case
where this might create an issue. But off had, even there I can't
think of one. Can you give me a test case?
On Fri, Mar 27, 2009 at 8:38 PM, Gael Guennebaud
<gael.guennebaud@xxxxxxxxx> wrote:
> On Fri, Mar 27, 2009 at 2:57 PM, Rohit Garg <rpg.314@xxxxxxxxx> wrote:
>> In the PacketMath.h file, the only eigen function to send the sse
>> registers back to memory is the _mm_store_ intrinsic. Has anybody
>> looked at using the _mm_stream intrinsics instead. They should help
>> atleast in BLAS 1 and BLAS 2 codes where the code is fundamentally
>> bandwidth bound. For a pseudo benchmark. look here
>>
>> http://humus.name/index.php?page=Comments&ID=244
>>
>> Even for BLAS 3 it should only help. However, for small sized stuff,
>> it will definitely not be helpful as one will want to have the item in
>> the cache as long as possible as it doesn't pollute the cache because
>> of it's small size.
>
> that's exactly why we cannot use it in Eigen: we cannot know if the
> data are going to reused soon or not, and even in the best case
> scenario the improvement would be pretty low...
>
>> --
>> Rohit Garg
>>
>> http://rpg-314.blogspot.com/
>>
>> Senior Undergraduate
>> Department of Physics
>> Indian Institute of Technology
>> Bombay
>>
>>
>>
>
>
>
--
Rohit Garg
http://rpg-314.blogspot.com/
Senior Undergraduate
Department of Physics
Indian Institute of Technology
Bombay