Jonathan,
This is now my fourth mail on this issue with no action. It is rather
rude to add a few lines at the bottom of a mail without removing the
context. To help you count the lines, and re-inforce the point, I will
manually number them below; please count them out loud with me:
1 On Thu, 2011-02-03 at 11:42 +0100, Jonathan Aquilina wrote:
2 On 2/2/11 10:01 PM, Kevin Hunter wrote:
3 > > At 3:31pm -0500 Wed, 02 Feb 2011, Michael Meeks wrote:
4 > >> On Wed, 2011-02-02 at 13:44 +0000, Wols Lists wrote:
5 > >>> Not quite sure what you mean by "legacy Intel", but if you're
6 > >>> referring to all single-processor CPUs, they still power most of
7 > >>> the budget brand new laptops!
8 > >>
9 > >> Surely those guys are hyper-threaded by now ? at least the Atom
10 > >> (which is cheap as chips [sic] ;-) is.
11 > >
12 > > I recognize this comment was in gest, but thought I'd chime in with a
13 > > tidbit. I believe that Intel removed HTT after the Pentium 4 chip.
14 > > Of note, as well, is that hyperthreading (HTT) is not as "universal"
15 > > an upgrade as true multi-core chips. In fact, the general practice in
16 > > the High Performance Computing (HPC) community is to turn off
17 > > hyperthreading because it degrades performance for most workloads.
18 > >
19 > > A further note is that there is some skepticism as to the security of
20 > > HTT, in terms of side-channel monitoring of in-core process data.
21 > >
22 > > Actually, now that I just wrote the above, I seem to recall a
23 > > discussion of HTT technology in the Nehalem chip. When I have time, I
24 > > might research that ...
25 > >
26 > > Cheers,
27 > >
28 > > Kevin
29 > > _______________________________________________
30 > > LibreOffice mailing list
31 > > LibreOffice@lists.freedesktop.org
32 > > http://lists.freedesktop.org/mailman/listinfo/libreoffice
Notice, not even removing the ML signature.
And then we have the two lines of content:
Kevin you are right the current i7's support HTT. It has come back with
a vengeance. the i5's and the i3's don't support hyper threading.
Then I read the content, and do the obligatory google search to see if
in fact what you are saying is reliable and useful (it is worth
researching what you say before saying it right ?). Intel's pages on
their current i5 and i3 processors (eg.
http://www.intel.com/consumer/products/processors/corei5.htm ) strongly
suggests the opposite.
I'm sorry if this seems harsh; but - I would like a lower noise level;
absent that - we'll move you to moderated posting until things
improve :-)
Thanks,
Michael.
--
michael.meeks@novell.com <><, Pseudo Engineer, itinerant idiot
Context
- [Libreoffice] [PUSHED] remove unused declaration - an unlikely fix for armel segfault in regcomp (continued)
Privacy Policy |
Impressum (Legal Info) |
Copyright information: Unless otherwise specified, all text and images
on this website are licensed under the
Creative Commons Attribution-Share Alike 3.0 License.
This does not include the source code of LibreOffice, which is
licensed under the Mozilla Public License (
MPLv2).
"LibreOffice" and "The Document Foundation" are
registered trademarks of their corresponding registered owners or are
in actual use as trademarks in one or more countries. Their respective
logos and icons are also subject to international copyright laws. Use
thereof is explained in our
trademark policy.