[Date Prev][Date Next] [Thread Prev][Thread Next]
[Thread Index]
[Date Index]
[Author Index]
Re: Hypertreading faster myth or truth?
- From: George Washington Dunlap III <dunlapg umich edu>
- To: k dicec cl, For testers of Fedora Core development releases <fedora-test-list redhat com>
- Cc:
- Subject: Re: Hypertreading faster myth or truth?
- Date: Sat, 1 May 2004 10:23:01 -0400 (EDT)
On Fri, 30 Apr 2004, Christian B. Ellsworth Capo wrote:
> Intel says that a cpu with HT turned on is faster, but is that true for
> Linux? and for FC2 as well?, I have seen some @intel.com posts so a
> Intel Inside view could be very interesing.
It probably would be interesting, but I'd think an Intel employee would be
the last person to post something like that to a public list, unless it
had been vetted by PR first. :-)
I did some benchmarks on a kernel build awhile back, and "make -j4
bzImage" was about 20% faster with HT turned on; I believe this was a
linux 2.4.18 kernel.
-George
--
+-------------------+----------------------------------------
| dunlapg umich edu | http://www-personal.umich.edu/~dunlapg
+-------------------+----------------------------------------
| "An empty life of luxury is still an empty life"
| -- everybodyduck, "Walk the Plank"
+------------------------------------------------------------
| Outlaw Junk Email! Support HR 1748 (www.cauce.org)
[Date Prev][Date Next] [Thread Prev][Thread Next]
[Thread Index]
[Date Index]
[Author Index]