On Sun, 29 Oct 2017, none wrote:
So is there an example ocaml code that can trigger the bug ?
Read the first referece (the INRIA ocaml bug report) throughoutly. It
has been public since day one.
And read all references in the updates I sent to that thread too, for
good measure. It is not
On 10/29/2017 01:17 AM, none wrote:
So is there an example ocaml code that can trigger the bug ?
Debian Linux reveals Intel Skylake and Kaby Lake processors have broken
hyper-threading
http://www.zdnet.com/article/debian-linux-reveals-intel-skylake-kaby-lake-processors-have-broken-hyper
On Sun, 29 Oct 2017, none wrote:
> So is there an example ocaml code that can trigger the bug ?
Read the first referece (the INRIA ocaml bug report) throughoutly. It
has been public since day one.
And read all references in the updates I sent to that thread too, for
good measure. It is not like
So is there an example ocaml code that can trigger the bug ?
Hi Henrique,
* Henrique de Moraes Holschuh [2017-07-23 14:56 -0300]:
> TL;DR: Intel has issued public microcode updates in 2017-07-07, fixing
> the hyper-threading errata on every affected processor. These updates
> have been included in the stable and oldstable point releases from
TL;DR: Intel has issued public microcode updates in 2017-07-07, fixing
the hyper-threading errata on every affected processor. These updates
have been included in the stable and oldstable point releases from
2017-07-22.
The microcode updates in the "intel-microcode" packages wit
John Elliot V wrote:
> KDE -> System Settings -> Multimedia (Hardware) -> Audio and Video ->
> Audio Hardware Setup
I was going to say - it is just KDE :D - crap
odels.
>
> Attached, you will find a perl script that can help detect if your
> system is affected or not. Many thanks to Uwe Kleine-König for
> suggesting, and writing this script.
Uwe Kleine-König was kind enough to update the perl script to fix the
broken hyper-threading detectio
odels.
>
> Attached, you will find a perl script that can help detect if your
> system is affected or not. Many thanks to Uwe Kleine-König for
> suggesting, and writing this script.
Uwe Kleine-König was kind enough to update the perl script to fix the
broken hyper-threading detectio
ion of the "7th gen. Core Family specification update" (which is
listed in the references section).
Please note that the "7th gen. Core i7 X-series processors" (Kaby
Lake-X) both support hyper-threading and share the processor signature
(family, model number and stepping) with
On 27/06/17 03:16, John Elliot V wrote:
> Hmm. I re-enabled hyper-threading (to test) and sound didn't come back.
After a number of false starts I was able to restore audio by:
KDE -> System Settings -> Multimedia (Hardware) -> Audio and Video ->
Audio Hardware Setup
HEDT), their related server processors (such as Xeon v5 and Xeon v6), as
well as select Intel Pentium processor models.
TL;DR: unfixed Skylake and Kaby Lake processors could, in some
situations, dangerously misbehave when hyper-threading is enabled.
Disable hyper-threading immediately in BIOS/UEFI to wor
On 27/06/17 02:47, John Elliot V wrote:
> I disabled hyper-threading in my BIOS in response to this advisory (I
> have an i7-7700K). Now I get weird graphical artifacts in drop-down
> lists in KDE (they flash between black and white background) and sound
> has stopped working on my
I disabled hyper-threading in my BIOS in response to this advisory (I
have an i7-7700K). Now I get weird graphical artifacts in drop-down
lists in KDE (they flash between black and white background) and sound
has stopped working on my system. Can anyone guess why that might be
happening? I might
Minor update on the issue:
The check command provided in the advisory to test for hyper-threading
doesn't work: it will always report hyper-theading as enabled. A better
command is provided below.
Note: this also means the perl script will give some false-positives.
I apologise fo
For the record: the email with the perl script doesn't contain malware.
The "malware" alert came from an extremely badly configured system that
violates every best practice in the field: it sends email to every
original recipient (and not just to local users), and it FORGES its
headers to look lik
On Sun, 25 Jun 2017, Henrique de Moraes Holschuh wrote:
> This warning advisory is relevant for users of systems with the Intel
> processors code-named "Skylake" and "Kaby Lake". These are: the 6th and
> 7th generation Intel Core processors (desktop, embedded, mobile and
> HEDT), their related ser
f (/^$/) {
print "cpu $cpunum: ";
if ($vendor eq "GenuineIntel" and $family == 6) {
if ($model == 78 or $model == 94) {
if ($stepping eq "3") {
print "Your CPU is affected, ";
if (hex($microcoderev) >= 0xb9) {
print "but your mic
), as
well as select Intel Pentium processor models.
TL;DR: unfixed Skylake and Kaby Lake processors could, in some
situations, dangerously misbehave when hyper-threading is enabled.
Disable hyper-threading immediately in BIOS/UEFI to work around the
problem. Read this advisory for instruc
On 08/11/12 22:45, Martin Steigerwald wrote:
Am Donnerstag, 8. November 2012 schrieb Philip Ashmore:
So I think there is a bug in cpuid.
Reported as "cupid reports wrong hyper-threading count".
http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=692799
Regards,
Philip Ashmo
; > Regarding the subject of you mail:
> >
> > Thats in total 8 siblings.
> >
> > So you divide 8 / 4 and get 2 siblings per core. I never seen any
> > hyperthreading with more than 2 siblings per core so far.
> >
> > Ciao,
>
> I guess I wasn&#x
ring: " Intel(R) Core(TM) i7-2670QM CPU @ 2.20GHz"
CLFLUSH instruction cache line size: 8
Initial APIC ID: 3
Hyper threading siblings: 16
Feature flags bfebfbff:
FPUFloating Point Unit
VMEVirtual 8086 Mode Enhancements
DE Debugging Extensions
PSEPage Size Extensions
Am Donnerstag, 8. November 2012 schrieb Philip Ashmore:
> But cat /proc/cpuinfo says:
> ...
> processor : 0
> vendor_id : GenuineIntel
> cpu family : 6
> model : 42
> model name : Intel(R) Core(TM) i7-2670QM CPU @ 2.20GHz
> stepping: 7
> microcode : 0x2
Am Donnerstag, 8. November 2012 schrieb Philip Ashmore:
> But cat /proc/cpuinfo says:
> ...
> processor : 0
> vendor_id : GenuineIntel
> cpu family : 6
> model : 42
> model name : Intel(R) Core(TM) i7-2670QM CPU @ 2.20GHz
> stepping: 7
> microcode : 0x2
But cat /proc/cpuinfo says:
...
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 42
model name : Intel(R) Core(TM) i7-2670QM CPU @ 2.20GHz
stepping: 7
microcode : 0x28
cpu MHz : 2201.000
cache size : 6144 KB
physical id :
On Sun, 11 Jun 2006 07:00:55 -0500
Ron Johnson <[EMAIL PROTECTED]> wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Andy Smith wrote:
> > On Sat, Jun 10, 2006 at 10:14:41PM -0500, Ron Johnson wrote:
> >> Nate Bargmann wrote:
> [snip]
> > This
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Andy Smith wrote:
> On Sat, Jun 10, 2006 at 10:14:41PM -0500, Ron Johnson wrote:
>> Nate Bargmann wrote:
[snip]
> This is a bit simplistic. Hyper-Threading (or more correctly,
> simultaneous multithreading (SMT)) is almost always a wi
the HT-enabled CPU adds the overhead of trying
> to pretend it's 2 CPUs.
>
> Remember: the CPU only has X amount of processing power.
This is a bit simplistic. Hyper-Threading (or more correctly,
simultaneous multithreading (SMT)) is almost always a win because at
any given time a
On Wed, 28 Sep 2005, michael wrote:
> > user interface, and did not explain what I wanted to know (WTF are those
> > "hi" and "si" CPU statistics).
>
> May I redeem myself by pointing out they are h/w and s/w interrupts, resp
Thanks.
--
"One disk to rule them all, One disk to find them. One d
> On Tue, 27 Sep 2005, Clive Menzies wrote:
>> On (27/09/05 08:10), Henrique de Moraes Holschuh wrote:
>> > On Mon, 26 Sep 2005, Bob Proulx wrote:
>> > > Dick Davies wrote:
>> > > > Yup, use SMP. I get 2 cpus in cpuinfo that way (although top
>> doesn't
>> > > > see them for some reason).
>> > >
>>
On Tue, 27 Sep 2005, Clive Menzies wrote:
> On (27/09/05 08:10), Henrique de Moraes Holschuh wrote:
> > On Mon, 26 Sep 2005, Bob Proulx wrote:
> > > Dick Davies wrote:
> > > > Yup, use SMP. I get 2 cpus in cpuinfo that way (although top doesn't
> > > > see them for some reason).
> > >
> > > Have y
On Tue, 27 Sep 2005, michael wrote:
> On Tue, 2005-09-27 at 13:19 +0100, Dick Davies wrote:
> > On 27/09/05, michael <[EMAIL PROTECTED]> wrote:
> > > On Tue, 2005-09-27 at 08:10 -0300, Henrique de Moraes Holschuh wrote:
> > > > On Mon, 26 Sep 2005, Bob Proulx wrote:
> > > > > Dick Davies wrote:
> >
On Tue, 27 Sep 2005, michael wrote:
> On Tue, 2005-09-27 at 08:10 -0300, Henrique de Moraes Holschuh wrote:
> > On Mon, 26 Sep 2005, Bob Proulx wrote:
> > > Dick Davies wrote:
> > > > Yup, use SMP. I get 2 cpus in cpuinfo that way (although top doesn't
> > > > see them for some reason).
>
> cpuinf
Henrique de Moraes Holschuh wrote:
> Bob Proulx wrote:
> > Dick Davies wrote:
> > > Yup, use SMP. I get 2 cpus in cpuinfo that way (although top doesn't
> > > see them for some reason).
> >
> > Have you ever run a top that lists individual processors on a 64
> > processor machine? I have and top
On Tue, 2005-09-27 at 13:19 +0100, Dick Davies wrote:
> On 27/09/05, michael <[EMAIL PROTECTED]> wrote:
> > On Tue, 2005-09-27 at 08:10 -0300, Henrique de Moraes Holschuh wrote:
> > > On Mon, 26 Sep 2005, Bob Proulx wrote:
> > > > Dick Davies wrote:
> > > > > Yup, use SMP. I get 2 cpus in cpuinfo t
On 27/09/05, michael <[EMAIL PROTECTED]> wrote:
> On Tue, 2005-09-27 at 08:10 -0300, Henrique de Moraes Holschuh wrote:
> > On Mon, 26 Sep 2005, Bob Proulx wrote:
> > > Dick Davies wrote:
> > > > Yup, use SMP. I get 2 cpus in cpuinfo that way (although top doesn't
> > > > see them for some reason).
On (27/09/05 08:10), Henrique de Moraes Holschuh wrote:
> On Mon, 26 Sep 2005, Bob Proulx wrote:
> > Dick Davies wrote:
> > > Yup, use SMP. I get 2 cpus in cpuinfo that way (although top doesn't
> > > see them for some reason).
> >
> > Have you ever run a top that lists individual processors on a
On Tue, 2005-09-27 at 08:10 -0300, Henrique de Moraes Holschuh wrote:
> On Mon, 26 Sep 2005, Bob Proulx wrote:
> > Dick Davies wrote:
> > > Yup, use SMP. I get 2 cpus in cpuinfo that way (although top doesn't
> > > see them for some reason).
cpuinfo will tell you about the logical CPUs; top will t
On Mon, 26 Sep 2005, Bob Proulx wrote:
> Dick Davies wrote:
> > Yup, use SMP. I get 2 cpus in cpuinfo that way (although top doesn't
> > see them for some reason).
>
> Have you ever run a top that lists individual processors on a 64
> processor machine? I have and top is quite useless there with
Dick Davies wrote:
> Yup, use SMP. I get 2 cpus in cpuinfo that way (although top doesn't
> see them for some reason).
Have you ever run a top that lists individual processors on a 64
processor machine? I have and top is quite useless there with
all of the screen being taken up by the cpu listing
On Mon, 26 Sep 2005, michael wrote:
> On Mon, 2005-09-26 at 14:01 -0300, Henrique de Moraes Holschuh wrote:
> > On Sun, 25 Sep 2005, James He wrote:
> > > Should one CPU(Hyper-Threading) machine use SMP kernel, or stick to a
> > > regular kernel?
> >
> > I
James He wrote:
Hi Marco,
I didn't notice it that there is no "ht" sign in the flags info below
until you pointed it out. I'm sorry. But I do have another machine with
one hyper-threading CPU, so never mind.
Hi James,
no problem! If you own a PIV CPU with HT you sho
On Mon, 2005-09-26 at 14:01 -0300, Henrique de Moraes Holschuh wrote:
> On Sun, 25 Sep 2005, James He wrote:
> > Should one CPU(Hyper-Threading) machine use SMP kernel, or stick to a
> > regular kernel?
>
> It depends:
> - If it is a 2.4 kernel, don't bother. Us
On Sun, 25 Sep 2005, James He wrote:
> Should one CPU(Hyper-Threading) machine use SMP kernel, or stick to a
> regular kernel?
It depends:
- If it is a 2.4 kernel, don't bother. Use an UP kernel.
- If it is a recent 2.6 kernel, it depends on the workload. Try it,
and do some m
Hi Marco,
I didn't notice it that there is no "ht" sign in the flags info below
until you pointed it out. I'm sorry. But I do have another machine with
one hyper-threading CPU, so never mind.
Thanks for all. :-)
$ cat /proc/cpuinfo
flags : fpu vme de pse tsc msr m
On Mon, 2005-09-26 at 10:37 +0100, michael wrote:
> On Mon, 2005-09-26 at 10:03 +0100, Dick Davies wrote:
> > On 25 Sep 2005 23:23:48 -0700, James He <[EMAIL PROTECTED]> wrote:
> >
> > > Should one CPU(Hyper-Threading) machine use SMP kernel, or stick to a
> >
On Mon, 2005-09-26 at 10:03 +0100, Dick Davies wrote:
> On 25 Sep 2005 23:23:48 -0700, James He <[EMAIL PROTECTED]> wrote:
>
> > Should one CPU(Hyper-Threading) machine use SMP kernel, or stick to a
> > regular kernel?
>
> Yup, use SMP. I get 2 cpus in cpuinfo
James He wrote:
$ cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 13
model name : Intel(R) Pentium(R) M processor 1.60GHz
stepping: 8
cpu MHz : 1600.096
cache size : 2048 KB
Hi James,
your CPU does not
On 25 Sep 2005 23:23:48 -0700, James He <[EMAIL PROTECTED]> wrote:
> Should one CPU(Hyper-Threading) machine use SMP kernel, or stick to a
> regular kernel?
Yup, use SMP. I get 2 cpus in cpuinfo that way (although top doesn't
see them for
some reason).
--
Rasputin :: Jack of Al
Hi,
Should one CPU(Hyper-Threading) machine use SMP kernel, or stick to a
regular kernel?
I know it's a dumb question. Please do help me. Thanks a lot! :-)
$ cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 13
model name : In
On Tue, 2003-11-04 at 14:32, Marco Cecconi wrote:
> >
> >Karsten M. Self wrote:
> >
> >
> >>Marco Cecconi wrote:
[snip]
> Thank you for the very thorough answer, although I meant another thing,
> every time i install debian, the date gets screwed up (the time stays
> ok). When I go back to wind
on Tue, Nov 04, 2003 at 09:32:50PM +0100, Marco Cecconi ([EMAIL PROTECTED]) wrote:
>
> >
> >Karsten M. Self wrote:
> >
> >
> >>Marco Cecconi wrote:
> >>
> >>
> >>>It's actually Debian's fault! Every time I install it, it reads and
> >>>writes the clock wrongly... Dammit!
> >>>:-)
> >> apt-
On Tue, Nov 04, 2003, at 11:07 -0700, Bob Proulx wrote:
> Karsten M. Self wrote:
> > Marco Cecconi wrote:
> > > It's actually Debian's fault! Every time I install it, it reads
> > > and writes the clock wrongly... Dammit!
> > > :-)
> >
> > apt-get install ntp
>
> apt-get install ntp ntpda
Karsten M. Self wrote:
Marco Cecconi wrote:
It's actually Debian's fault! Every time I install it, it reads and
writes the clock wrongly... Dammit!
:-)
apt-get install ntp
apt-get install ntp ntpdate
:-)
If the clock is very far off when ntp starts up then ntp won't be a
Karsten M. Self wrote:
> Marco Cecconi wrote:
> > It's actually Debian's fault! Every time I install it, it reads and
> > writes the clock wrongly... Dammit!
> > :-)
>
> apt-get install ntp
apt-get install ntp ntpdate
:-)
If the clock is very far off when ntp starts up then ntp won't be
on Mon, Nov 03, 2003 at 08:06:23AM +0100, Marco Cecconi ([EMAIL PROTECTED]) wrote:
> Scott C. Linnenbringer wrote:
> >On Mon, Nov 03, 2003, at 00:18 +0100, Werner Mahr wrote:
> >>Am Montag, 1. Dezember 2003 11:41 schrieb Marco Cecconi:
> >> ^
> >>Is my KMail broken?
> >
>
On Mon, Nov 03, 2003 at 08:12:50AM +0100, Marco Cecconi said
> Rob Weir wrote:
>
> >>Hello, which woody kernel supports Hyper Threading? I've read somewhere
> >>that 2.4+ kernels support this feature but how? Is a SMP build
> >>sufficient?
> >Yes, thou
On Mon, Nov 03, 2003 at 12:18:10AM +0100, Werner Mahr wrote:
> Am Montag, 1. Dezember 2003 11:41 schrieb Marco Cecconi:
>^
> Is my KMail broken?
Time moves more quickly on hyperthreaded systems! ;-)
--
To UNSUBSCRIBE, email to [EMAIL PROTECTED]
with a subject of "un
Rob Weir wrote:
Hello, which woody kernel supports Hyper Threading? I've read somewhere
that 2.4+ kernels support this feature but how? Is a SMP build
sufficient?
Yes, thought 2.6 will do smarter things with it. You also require APIC
and/or ACPI support, no doubt google has the details.
Wh
Scott C. Linnenbringer wrote:
On Mon, Nov 03, 2003, at 00:18 +0100, Werner Mahr wrote:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Am Montag, 1. Dezember 2003 11:41 schrieb Marco Cecconi:
^
Is my KMail broken?
Marco's clock is. ;)
His clock is set forward about one
On Mon, Nov 03, 2003, at 00:18 +0100, Werner Mahr wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Am Montag, 1. Dezember 2003 11:41 schrieb Marco Cecconi:
>^
> Is my KMail broken?
Marco's clock is. ;)
His clock is set forward about one month into the fu
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Am Montag, 1. Dezember 2003 11:41 schrieb Marco Cecconi:
^
Is my KMail broken?
- --
MfG usw
Werner Mahr
GPG-Key-ID 44B53C40
Registered-Linux-User: 303822 (http://counter.li.org)
ICQ-Nr. 317910541
-BEGIN PGP SIGNATURE-
On Mon, Dec 01, 2003 at 11:41:08AM +0100, Marco Cecconi wrote:
> Hello, which woody kernel supports Hyper Threading? I've read somewhere
> that 2.4+ kernels support this feature but how? Is a SMP build
> sufficient? How does linux support HT, dual processor style (like e.g.
ch woody kernel supports Hyper Threading? I've read somewhere
> that 2.4+ kernels support this feature but how? Is a SMP build
> sufficient?
Yes, thought 2.6 will do smarter things with it. You also require APIC
and/or ACPI support, no doubt google has the details.
> How does
Hello, which woody kernel supports Hyper Threading? I've read somewhere
that 2.4+ kernels support this feature but how? Is a SMP build
sufficient? How does linux support HT, dual processor style (like e.g.
Win2000) or natively (like e.g. WinXP)?
Thank you,
Marco
--
To UNSUBSCRIBE, ema
Hello, which woody kernel supports Hyper Threading? I've read somewhere
that 2.4+ kernels support this feature but how? Is a SMP build
sufficient? How does linux support HT, dual processor style (like e.g.
Win2000) or natively (like e.g. WinXP)?
Thank you,
Marco
--
To UNSUBSCRIBE, ema
EMAIL PROTECTED]>
Sent: Monday, July 28, 2003 3:52 PM
Subject: Re: Intel Hyper Threading on Linux..
> On Mon, 2003-07-28 at 02:00, Louie Miranda wrote:
> > > But yes Linux in general does support it. If your specific kernel does
> > > not take a look at the previous mes
On Mon, 2003-07-28 at 00:44, Bob Proulx wrote:
> Louie Miranda wrote:
> > Does Debian/Kernel? Support HT?
>
> Works fine for me. One of the systems here is a dual processor with
> hyperthreading enabled. It was an accident that HT was enabled but we
> decided to leave it that way and run some be
On Mon, 2003-07-28 at 02:00, Louie Miranda wrote:
> > But yes Linux in general does support it. If your specific kernel does
> > not take a look at the previous message I wrote about how to compile and
> > install your own Debian Kernel... Makes it a snap.
>
> Hi, where does your howto located? Ca
thanks a lot, i'll post more if i get any troubles with HT. If ever..
--
Thank you,
Louie Miranda ([EMAIL PROTECTED])
- Original Message -
From: "Bob Proulx" <[EMAIL PROTECTED]>
To: "Debian-User" <[EMAIL PROTECTED]>
Sent: Monday, July 28,
Louie Miranda wrote:
> Does Debian/Kernel? Support HT?
Works fine for me. One of the systems here is a dual processor with
hyperthreading enabled. It was an accident that HT was enabled but we
decided to leave it that way and run some benchmarks on it. It is a
dual cpu and so it shows up as fou
y the Intel® Pentium® 4
> Processor with HT Technology logo:
> a.. Red Hat Linux* 9 (Professional and Personal versions)
> b.. SuSE Linux* 8.2 (Professional and Personal versions)
> c.. Red Flag Linux* Desktop 4.0
One other thing, in Windoze this is a Black Herring - Enabled Hyper
T
Does Debian/Kernel? Support HT? Found this article on intel's website. and i
just bought a new D865Perl Board. Just curious.. And how come redhat and
suse are always on ads, well commercialzed linux.
--- -
Linux* Operating System Desktop Based PCs
The following Linux operating
73 matches
Mail list logo
