lkml.org 
[lkml]   [2008]   [Jan]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: CPA patchset
On Fri, 11 Jan 2008, Ingo Molnar wrote:

> * Andi Kleen <ak@suse.de> wrote:
>
> > Cached requires the cache line to be read first before you can write
> > it.
>
> nonsense, and you should know it. It is perfectly possible to construct
> fully written cachelines, without reading the cacheline first. MOVDQ is
> SSE1 so on basically in every CPU today - and it is 16 byte aligned and
> can generate full cacheline writes, _without_ filling in the cacheline
> first.

did you mean to write MOVNTPS above?


> Bulk ops (string ops, etc.) will do full cacheline writes too,
> without filling in the cacheline.

on intel with fast strings enabled yes. mind you intel gives hints in
the documentation these operations don't respect coherence... and i
asked about this when they posted their memory ordering paper but got no
response.

-dean


\
 
 \ /
  Last update: 2008-01-11 18:05    [W:0.112 / U:0.692 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site