lkml.org 
[lkml]   [2013]   [Dec]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] x86 idle: repair large-server 50-watt idle-power regression
On Thu, Dec 19, 2013 at 06:40:41AM -0800, H. Peter Anvin wrote:
> ... or just use static_cpu_has() maybe?

Right, if we can get the compiler to generate the shortest CLFLUSH of 3
bytes with register indirect addressing for the operand, then stomping
over those 3 bytes with the alternatives would be the fastest solution.

If, of course, three NOPs which get discarded in the front end are
cheaper than the near JMP from static_cpu_has.

--
Regards/Gruss,
Boris.

Sent from a fat crate under my desk. Formatting is fine.
--


\
 
 \ /
  Last update: 2013-12-19 18:21    [W:0.933 / U:0.712 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site