[9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Josh Marshall]

[-- Attachment #1: Type: text/plain, Size: 657 bytes --]

I'm chugging through the resources, reading, and documentation.  This system
acts differently from anything I've previously used, so I'm at a loss
at...everything.  I visited the IRC channel and am working through the .pdf
and the main site.  Is there anything else I should be looking into?  Also,
the .pdf said that I should have a working plan9 install available to
practice, so I tried using vmplayer but the kernel panics.  I'm learning,
but not well acquainted with kernel programming, debugging, or anything
else.  Also, if this all seems kind of incoherent, I'm sorry, its past 2am
and I've been working on absorbing info for over 4 hours.

[-- Attachment #2: Type: text/html, Size: 677 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Jason Dreisbach]

[-- Attachment #1: Type: text/plain, Size: 83 bytes --]

Try using 9vx to get used to the environment.

http://swtch.com/9vx/

- Jason

[-- Attachment #2: Type: text/html, Size: 205 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Andreas Wagner]

[-- Attachment #1: Type: text/plain, Size: 912 bytes --]

I couldn't get plan9 to run in my qemu vm but 9front (plan9 fork) works
flawlessly.

http://code.google.com/p/plan9front/

- Andreas

On Sun, Jun 5, 2011 at 2:18 AM, Josh Marshall <
joshua.r.marshall.1991@gmail.com> wrote:

> I'm chugging through the resources, reading, and documentation.  This
> system acts differently from anything I've previously used, so I'm at a loss
> at...everything.  I visited the IRC channel and am working through the .pdf
> and the main site.  Is there anything else I should be looking into?  Also,
> the .pdf said that I should have a working plan9 install available to
> practice, so I tried using vmplayer but the kernel panics.  I'm learning,
> but not well acquainted with kernel programming, debugging, or anything
> else.  Also, if this all seems kind of incoherent, I'm sorry, its past 2am
> and I've been working on absorbing info for over 4 hours.
>

[-- Attachment #2: Type: text/html, Size: 1217 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Rudolf Sykora]

> http://code.google.com/p/plan9front/
>
> - Andreas

Why this? What's wrong with plan9? I haven't found a word about the
reasons on the cited pages.

I see there is a problem almost in every piece of plan9 code. I would
like to see people trying to fix it, and only fork, if there is a
reason...
Ruda

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Ethan Grammatikidis]

On Sun, 5 Jun 2011 16:10:12 +0200
Rudolf Sykora <rudolf.sykora@gmail.com> wrote:

> > http://code.google.com/p/plan9front/
> >
> > - Andreas
>
> Why this? What's wrong with plan9? I haven't found a word about the
> reasons on the cited pages.
>
> I see there is a problem almost in every piece of plan9 code. I would
> like to see people trying to fix it, and only fork, if there is a
> reason...
> Ruda
>

There is a reason. Two, in fact: The 9fronters are finding it a great learning experience and they're having a lot of fun.

IMO this "reason" rubbish is why we haven't had systems research in far too long. As Elucid said when a student asked what was the reason for all this learning, "Give him 2 small coins so he may profit from what he has learned." So the student was given the coins and then expelled.

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Francisco J Ballesteros]

On Sun, Jun 5, 2011 at 5:41 PM, Ethan Grammatikidis <eekee57@fastmail.fm> wrote:
> we haven't had systems research in far too long

Ah, yes, that's why I've been working all this time on carefully
studying the licenses of all the
software involved. I didn't notice.

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Iruatã Souza]

On Sun, Jun 5, 2011 at 11:10 AM, Rudolf Sykora <rudolf.sykora@gmail.com> wrote:
>> http://code.google.com/p/plan9front/
>>
>> - Andreas
>
> Why this? What's wrong with plan9? I haven't found a word about the
> reasons on the cited pages.
>
> I see there is a problem almost in every piece of plan9 code. I would
> like to see people trying to fix it, and only fork, if there is a
> reason...
> Ruda
>
>

http://code.google.com/p/plan9front/source/detail?r=bb876e773014caf09c18f4fea6be5100bddbeb2b

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Skip Tavakkolian]

it's a shame that none of this is hosted on Plan 9 systems (including cat-v).

-Skip

On Sun, Jun 5, 2011 at 9:06 AM, Iruatã Souza <iru.muzgo@gmail.com> wrote:
> On Sun, Jun 5, 2011 at 11:10 AM, Rudolf Sykora <rudolf.sykora@gmail.com> wrote:
>>> http://code.google.com/p/plan9front/
>>>
>>> - Andreas
>>
>> Why this? What's wrong with plan9? I haven't found a word about the
>> reasons on the cited pages.
>>
>> I see there is a problem almost in every piece of plan9 code. I would
>> like to see people trying to fix it, and only fork, if there is a
>> reason...
>> Ruda
>>
>>
>
> http://code.google.com/p/plan9front/source/detail?r=bb876e773014caf09c18f4fea6be5100bddbeb2b
>
>

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Josh Marshall]

[-- Attachment #1: Type: text/plain, Size: 772 bytes --]

Ok, I tried running 9vx for my linux install and it dies.  Ubuntu 11.04
fully updated x64_86.  I don't know what else info will help.

On Sun, Jun 5, 2011 at 12:06 PM, Iruatã Souza <iru.muzgo@gmail.com> wrote:

> On Sun, Jun 5, 2011 at 11:10 AM, Rudolf Sykora <rudolf.sykora@gmail.com>
> wrote:
> >> http://code.google.com/p/plan9front/
> >>
> >> - Andreas
> >
> > Why this? What's wrong with plan9? I haven't found a word about the
> > reasons on the cited pages.
> >
> > I see there is a problem almost in every piece of plan9 code. I would
> > like to see people trying to fix it, and only fork, if there is a
> > reason...
> > Ruda
> >
> >
>
>
> http://code.google.com/p/plan9front/source/detail?r=bb876e773014caf09c18f4fea6be5100bddbeb2b
>
>

[-- Attachment #2: Type: text/html, Size: 1376 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[David du Colombier]

> Ok, I tried running 9vx for my linux install and it dies.  Ubuntu
> 11.04 fully updated x64_86.  I don't know what else info will help.

Are you sure you tried one of the current 9vx repository ([1] or [2]),
and not the old repository [3] (2009-12-27) or a very old binary [4]
(2008-07-01)?

[1] https://bitbucket.org/yiyus/vx32
[2] https://bitbucket.org/rminnich/vx32
[3] https://bitbucket.org/rsc/vx32
[4] http://pdos.csail.mit.edu/~rsc/9vx-0.12.tar.bz2

--
David du Colombier

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Josh Marshall]

[-- Attachment #1: Type: text/plain, Size: 1134 bytes --]

I have the most recent version.  Still doesn't work.  Also, last night(2
days?) someone posted a .pdf about *nix, a fork of plan9 which has a unique
feature where cores are dedicated to certain functions like timing, OS, and
user programs.  Any idea where I can find it?  Code, .iso, or anything
really to research and play with.

I'm a college sophomore, so please be patient with me.  Once I have a
grounding, I would hope to start some sort of development and throw out a
few ideas of my own should they turn out.

On Mon, Jun 6, 2011 at 1:04 AM, David du Colombier <0intro@gmail.com> wrote:

> > Ok, I tried running 9vx for my linux install and it dies.  Ubuntu
> > 11.04 fully updated x64_86.  I don't know what else info will help.
>
> Are you sure you tried one of the current 9vx repository ([1] or [2]),
> and not the old repository [3] (2009-12-27) or a very old binary [4]
> (2008-07-01)?
>
> [1] https://bitbucket.org/yiyus/vx32
> [2] https://bitbucket.org/rminnich/vx32
> [3] https://bitbucket.org/rsc/vx32
> [4] http://pdos.csail.mit.edu/~rsc/9vx-0.12.tar.bz2
>
> --
> David du Colombier
>
>

[-- Attachment #2: Type: text/html, Size: 1732 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Anthony Sorace]

Nix (I believe it's just nix) is on bitbucket, npe/nix. I agree it looks interesting, although I've only read the paper and browsed the tree a bit so far.

For 9vx, you're going to need to provide some more details about the failure mode. What exactly do you do to try and get it running, what exactly does it say as a result?

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Jason Dreisbach]

[-- Attachment #1: Type: text/plain, Size: 240 bytes --]

My roommate had quite an experience trying to get 9vx to work on the new
ubuntus. The big problem is the 64 bit. Have you tried running it on a 32
bit linux? I think what worked well for him was a ubuntu 9.04 32 bit
install.

- Jason

[-- Attachment #2: Type: text/html, Size: 261 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Balwinder S Dheeman]

On 06/05/2011 11:51 AM, Josh Marshall wrote:
> I'm chugging through the resources, reading, and documentation.  This
> system acts differently from anything I've previously used, so I'm at a
> loss at...everything.  I visited the IRC channel and am working through
> the .pdf and the main site.  Is there anything else I should be looking
> into?  Also, the .pdf said that I should have a working plan9 install
> available to practice, so I tried using vmplayer but the kernel panics.
> I'm learning, but not well acquainted with kernel programming,
> debugging, or anything else.  Also, if this all seems kind of
> incoherent, I'm sorry, its past 2am and I've been working on absorbing
> info for over 4 hours.

Try http://werc.homelinux.net/hacks/nano9/

Hope that helps :)
--
Balwinder S "bdheeman" Dheeman
(http://werc.homelinux.net/contact/)

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Comeau At9Fans]

[-- Attachment #1: Type: text/plain, Size: 897 bytes --]

On Mon, Jun 6, 2011 at 1:04 AM, David du Colombier <0intro@gmail.com> wrote:

> > Ok, I tried running 9vx for my linux install and it dies.  Ubuntu
> > 11.04 fully updated x64_86.  I don't know what else info will help.
>
> Are you sure you tried one of the current 9vx repository ([1] or [2]),
> and not the old repository [3] (2009-12-27) or a very old binary [4]
> (2008-07-01)?
>
> [1] https://bitbucket.org/yiyus/vx32
> [2] https://bitbucket.org/rminnich/vx32
> [3] https://bitbucket.org/rsc/vx32
> [4] http://pdos.csail.mit.edu/~rsc/9vx-0.12.tar.bz2



Where does http://swtch.com/9vx fit into things these days?

--
Greg Comeau / 4.3.10.1 with C++0xisms now in beta!
Comeau C/C++ ONLINE ==>     http://www.comeaucomputing.com/tryitout
World Class Compilers:  Breathtaking C++, Amazing C99, Fabulous C90.
Comeau C/C++ with Dinkumware's Libraries... Have you tried it?

[-- Attachment #2: Type: text/html, Size: 1629 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Peter A. Cejchan]

[-- Attachment #1: Type: text/plain, Size: 486 bytes --]

Hi, friend,
sry 4 a bit offending response:
IMHO, maybe, you should get a 0.5 GB partition & try to run p9 natively,
believe me, or not, it is worth to. Or, get a $20 i386
 box and install p9 on it. And yes, I am not a techie, I am a paleobiologist
w/some basic skills on C programming. Yes, the learning curve was a bit
steep (BTW: when  time vs. skills is plotted, the curve is flat, not
steep).., please, don't give up and ask me if I can be of any help,
sincerely,
Peter.

[-- Attachment #2: Type: text/html, Size: 506 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Nicolas BERCHER]

On 05/06/2011 08:18, Josh Marshall wrote:
> I'm chugging through the resources, reading, and documentation.  This
> system acts differently from anything I've previously used, so I'm at a
> loss at...everything.  I visited the IRC channel and am working through
> the .pdf and the main site.  Is there anything else I should be looking
> into?  Also, the .pdf said that I should have a working plan9 install
> available to practice, so I tried using vmplayer but the kernel panics.
> I'm learning, but not well acquainted with kernel programming,
> debugging, or anything else.  Also, if this all seems kind of
> incoherent, I'm sorry, its past 2am and I've been working on absorbing
> info for over 4 hours.

Hi,

I recently installed Plan 9 (the real one from the Bell Labs) on qemu (hosted by a 32bits
Debian).   Since kvm and qemu share the same user interface (yes I'm talking about command
line), I use kvm to get the benefice of my intel cpu that is "vmx-aware" (aka VT-x).


If you are already familiar with partitioning disks, it should be relatively easy for you
to install Plan 9.  It is quite simple, even with "fossil+venti" option.  The installer
will propose you a partition map that you can accept at first.

Nicolas

Ps: in my installation, I wanted to use two qemu hard drive images: one for Plan 9/fossil
and another one for venti (the later contains a first partition for the arenas, it uses
95% of the disk, and the second partition uses 5% of the disk and is used for the venti
index).

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Jack Norton]

Balwinder S Dheeman wrote:
> On 06/05/2011 11:51 AM, Josh Marshall wrote:
>> I'm chugging through the resources, reading, and documentation.  This
>> system acts differently from anything I've previously used, so I'm at a
>> loss at...everything.  I visited the IRC channel and am working through
>> the .pdf and the main site.  Is there anything else I should be looking
>> into?  Also, the .pdf said that I should have a working plan9 install
>> available to practice, so I tried using vmplayer but the kernel panics.
>> I'm learning, but not well acquainted with kernel programming,
>> debugging, or anything else.  Also, if this all seems kind of
>> incoherent, I'm sorry, its past 2am and I've been working on absorbing
>> info for over 4 hours.
>
> Try http://werc.homelinux.net/hacks/nano9/
>
> Hope that helps :)


Good lord.  Between these things and '9front' I am missing much.  I need
to get back on IRC.
Either that or you guys could consolidate all your personal 'werc' sites
into one Plan 9 'experimental stuff' wiki.  It seems a bit ridiculous
that werc offers multi-user editing and comments, yet everyone and their
mom has their own werc site with a Plan 9 sub-page.  Or better yet,
resurrect the 'ole webring concept with those silly links to traverse it
:).  Personally I'd like to see work put into the Plan 9 wiki backend.
I'd rather use it than werc (which I do -- but I've only got a little
placeholder page that says "coming soon" -- and has for 6 months...).
As for 9front, it looks like fun.  I say that even though the word
'fork' scares me.
Unfortunately IRC requires free time behind the computer -- which I
never have.  Boo hoo, I know...
Well that's my useless post for the day.

As for the OP, I'm with Peter C.  Install it native and forget all of
this other nonsense for now.  You could probably find a good candidate
PC in a dumpster somewhere.  Or a $70 atom board with a bit of memory
could do you just fine (the plain intel ones -- not those omg-ION
graphics ones).  I know the NMO510 guy works with only one core (but it
works).

Cheers,
Jack

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[David du Colombier]

> > [1] https://bitbucket.org/yiyus/vx32
> > [2] https://bitbucket.org/rminnich/vx32
> > [3] https://bitbucket.org/rsc/vx32
> > [4] http://pdos.csail.mit.edu/~rsc/9vx-0.12.tar.bz2
>
> Where does http://swtch.com/9vx fit into things these days?

The mercurial repository referenced on this page doesn't exist
anymore, it was moved to [3] in june 2008, and the binary
distribution is [4].

--
David du Colombier

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Rudolf Sykora]

> Either that or you guys could consolidate all your personal 'werc' sites
> into one Plan 9 'experimental stuff' wiki.  It seems a bit ridiculous that
> werc offers multi-user editing and comments, yet everyone and their mom has
> their own werc site with a Plan 9 sub-page.

I would put my signature below this.
R

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Gabriel Díaz López de la llave]

[-- Attachment #1: Type: text/plain, Size: 2838 bytes --]

Hello

I'm glad plan9 works fine in a lot of virtual machines (thanks for it). And
you can run plan9 on recent machines too, plan9 and 9atom have worked for me
quite well with my Intel Core i7-920 computer.

Also, we all like to rule the world with a couple of emails. I could email
Mr. Carmack to port Doom IV to plan9, but that will not
work, unfortunately XD. If you want a fix for the wiki, you know where's the
source. That's the plan9 way afaict. If you want your change into the
distribution...that's another story :)

slds.

gabi


On Mon, Jun 6, 2011 at 3:36 PM, Jack Norton <jack@0x6a.com> wrote:

> Balwinder S Dheeman wrote:
>
>> On 06/05/2011 11:51 AM, Josh Marshall wrote:
>>
>>> I'm chugging through the resources, reading, and documentation.  This
>>> system acts differently from anything I've previously used, so I'm at a
>>> loss at...everything.  I visited the IRC channel and am working through
>>> the .pdf and the main site.  Is there anything else I should be looking
>>> into?  Also, the .pdf said that I should have a working plan9 install
>>> available to practice, so I tried using vmplayer but the kernel panics.
>>> I'm learning, but not well acquainted with kernel programming,
>>> debugging, or anything else.  Also, if this all seems kind of
>>> incoherent, I'm sorry, its past 2am and I've been working on absorbing
>>> info for over 4 hours.
>>>
>>
>> Try http://werc.homelinux.net/hacks/nano9/
>>
>> Hope that helps :)
>>
>
>
> Good lord.  Between these things and '9front' I am missing much.  I need to
> get back on IRC.
> Either that or you guys could consolidate all your personal 'werc' sites
> into one Plan 9 'experimental stuff' wiki.  It seems a bit ridiculous that
> werc offers multi-user editing and comments, yet everyone and their mom has
> their own werc site with a Plan 9 sub-page.  Or better yet, resurrect the
> 'ole webring concept with those silly links to traverse it :).  Personally
> I'd like to see work put into the Plan 9 wiki backend. I'd rather use it
> than werc (which I do -- but I've only got a little placeholder page that
> says "coming soon" -- and has for 6 months...).
> As for 9front, it looks like fun.  I say that even though the word 'fork'
> scares me.
> Unfortunately IRC requires free time behind the computer -- which I never
> have.  Boo hoo, I know...
> Well that's my useless post for the day.
>
> As for the OP, I'm with Peter C.  Install it native and forget all of this
> other nonsense for now.  You could probably find a good candidate PC in a
> dumpster somewhere.  Or a $70 atom board with a bit of memory could do you
> just fine (the plain intel ones -- not those omg-ION graphics ones).  I know
> the NMO510 guy works with only one core (but it works).
>
> Cheers,
> Jack
>
>

[-- Attachment #2: Type: text/html, Size: 3647 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[erik quanstrom]

> I'm glad plan9 works fine in a lot of virtual machines (thanks for it). And
> you can run plan9 on recent machines too, plan9 and 9atom have worked for me
> quite well with my Intel Core i7-920 computer.

works fine for me on the second-generation core stuff, too such
as the e3-1220.

- erik

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Anthony Sorace]

[-- Attachment #1: Type: text/plain, Size: 514 bytes --]

Jack Norton said:

> Personally I'd like to see work put into the Plan 9 wiki backend.

Good thing there's a Summer of Code project for that! The student is
looking to upgrade the format of stored documents and the html
generation from it. Should make it much more useful.

Greg Comeau asked:

> Where does http://swtch.com/9vx fit into things these days?

That has not kept up with later developments. Use it's good for the
text, but users should absolutely be using ron's (or yiyus's) repo.

a


[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 210 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[cinap_lenrek]

DooM is functional on plan9front, including sound and
keyboard input.

The main thanks go to this guy who did the initial port:

http://jtomaschke.blogspot.com/

--
cinap

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Josh Marshall]

[-- Attachment #1: Type: text/plain, Size: 1487 bytes --]

Right now, wading through this email list, also put my signature behind
consolidating these resources.  While I don't know much about the forks and
the culture behind this OS, Having a central info-hub with heavier file
hosting supported by sorceforge or something would be nice.  I'm actually
working in a web-dev class right now, and the prof. isn't giving me any new
information on anything.  Who's up for figuring out what could/should be
done with the site?  Also, a super god Dr. Who master reference to plan9,
and other OS's derived from it or involved the the whole next generation of
computing would be nice and save me a few google searches, but I have no
idea where to start on that one.

Also, for running plan9, I'm not familiar with a standards install because I
haven't gotten to the reading yet.  I'm not even sure if I'm qualified to
know the advanced topics in the reading I've gotten into because they are so
different from all models I've even been shown, introduced to, or talked
about.  Is there a book which I could look up to help with this?

Finally for this, what would it take to have the GPU treated as a processor
bank for idling and tasks not requiring a full CPU core?

On Mon, Jun 6, 2011 at 10:21 AM, <cinap_lenrek@gmx.de> wrote:

> DooM is functional on plan9front, including sound and
> keyboard input.
>
> The main thanks go to this guy who did the initial port:
>
> http://jtomaschke.blogspot.com/
>
> --
> cinap
>
>

[-- Attachment #2: Type: text/html, Size: 1871 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[erik quanstrom]

> Finally for this, what would it take to have the GPU treated as a processor
> bank for idling and tasks not requiring a full CPU core?

leaving trifling software problems tiny running general-purpose
code on a special-purpose bit of haradware and running multiple
cpu arches in the same machine aside, why wouldn't you prefer
to idle the gpu, since it usually less power-efficient than your cpu?
pci-sig is working on 300+w pcie power for gpus.

- erik

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Carlos Oliveira]

I downloaded this distribution and it runs fine on Mac OS X.
I am trying to compile a C program by following the manual, but
I get to a point where the loader 8l can't find the file /386/lib/libc.a

Can you guys tell how to get this library?

-----------------------------------------------------
Carlos Oliveira
http://coliveira.net





On Sun, Jun 5, 2011 at 2:33 AM, Jason Dreisbach <jtdreisb@gmail.com> wrote:
> Try using 9vx to get used to the environment.
> http://swtch.com/9vx/
> - Jason

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Josh Marshall]

[-- Attachment #1: Type: text/plain, Size: 1709 bytes --]

Well, two reasons come to my mind immediately.  First, I'd be cool.  Second,
the wattage you listed is the max wattage, not the idle or light load
wattage which would likely be used.  Per processing element, GPUs use less
power, and you get more processing power per watt than a CPU under certain
loads.  Further more, this would greatly increase the available processing
power to system, could spur a change in model for GPUs to a processor bank
which does distributed work for the whole system, including graphics and the
real video card could change to something extrmely abstract which only takes
in an image and converts it to a signal for the display(s).

So, in short, more system power, and could have long term benifit to
hardware development, abstraction, and model change.

This concept could be taken as far as to bring all processing off
specialized areas for general purpose use, allowing potentially for an
internally distributed system with high regularity, fault tolerance, etc.
That's on the far end, but not to be totally discounted.

Also, I'd like to do something interesting with my free time.

On Mon, Jun 6, 2011 at 6:36 PM, erik quanstrom <quanstro@quanstro.net>wrote:

> > Finally for this, what would it take to have the GPU treated as a
> processor
> > bank for idling and tasks not requiring a full CPU core?
>
> leaving trifling software problems tiny running general-purpose
> code on a special-purpose bit of haradware and running multiple
> cpu arches in the same machine aside, why wouldn't you prefer
> to idle the gpu, since it usually less power-efficient than your cpu?
> pci-sig is working on 300+w pcie power for gpus.
>
> - erik
>
>

[-- Attachment #2: Type: text/html, Size: 2066 bytes --]

Re: [9fans] Utilizing the GPU (WAS: Hey, new to this. Trying to get plan9 to work in a VM.)

[Ethan Grammatikidis]

On Tue, 7 Jun 2011 02:57:28 +0000
Josh Marshall <joshua.r.marshall.1991@gmail.com> wrote:

> Also, I'd like to do something interesting with my free time.

I guess you'll be writing a compiler and assembler for the GPU and.. not too much else, probably. Using the GPU as a proc gives you a NUMA architecture if I'm not wrong, and the just-released nix[1] system is a development of Plan 9 for NUMA systems, with some interesting additions such as the ability to dedicate a core to an application. Best read the paper[2], I only scanned enough to determine if it was worth remembering. ;)

[1]: https://bitbucket.org/npe/nix
[2]: https://bitbucket.org/npe/nix/src/c1ba3d50a74a/doc/papers/nix/nix.pdf

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[erik quanstrom]

> Well, two reasons come to my mind immediately.  First, I'd be cool.  Second,
> the wattage you listed is the max wattage, not the idle or light load
> wattage which would likely be used.  Per processing element, GPUs use less
> power, and you get more processing power per watt than a CPU under certain
> loads.

i'd sure like a reference to a case where a system with a gpu draws less
power than the same system without.  it's not like you can turn the cpu
off.

> This concept could be taken as far as to bring all processing off
> specialized areas for general purpose use, allowing potentially for an
> internally distributed system with high regularity, fault tolerance, etc.
> That's on the far end, but not to be totally discounted.

please explain.  how is a machine more of any of these things than
a regular multi-core machine?

- erik

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Josh Marshall]

[-- Attachment #1: Type: text/plain, Size: 2657 bytes --]

A system running more hardware will, for all practical purposes, use more
energy.  What this would do is increase the efficiency of that power use.
Say you're using a single threaded indexing program, and its indexing a very
slow medium.  Why use a CPU processor when you can idle them, and idle most
of the other GPU processors and just use the one?  This is mainly for max
hardware utilization though.

In the VERY long run, I'm seeing thing trending towards very distributed
models.  As system resources grow, I believe it will become practical to
"network" within a system.  This can manifest itself in two ways.  First, is
that due to multi-core systems slowly changing to many-core systems, a
networking model is very scalable and with so many things to break, the
fault tolerance will become a must.  This could allow then for computer
systems to continue their march towards a more biological like organization,
like a multi-cellular organism.  This will likely be abstracted to
programmers and users, but on a hardware level, it allows for variable
redundancy, extreme fault tolerance, internal and external networking
models, and any few components which break will have no or minimal impact on
the stability and usability of the system.  This is WAY WAY in the future,
but that's where I imagine it going and this could be a step in that
direction.  Was that as coherent as it should be?  I'm still playing with
this in the back of my head, so its by no means well planned :P  I'd be more
than happy to talk to someone about this, because no one at my university
knows this area--our math and CS/CIS departments are feeble.

On Mon, Jun 6, 2011 at 9:19 PM, erik quanstrom <quanstro@quanstro.net>wrote:

> > Well, two reasons come to my mind immediately.  First, I'd be cool.
>  Second,
> > the wattage you listed is the max wattage, not the idle or light load
> > wattage which would likely be used.  Per processing element, GPUs use
> less
> > power, and you get more processing power per watt than a CPU under
> certain
> > loads.
>
> i'd sure like a reference to a case where a system with a gpu draws less
> power than the same system without.  it's not like you can turn the cpu
> off.
>
> > This concept could be taken as far as to bring all processing off
> > specialized areas for general purpose use, allowing potentially for an
> > internally distributed system with high regularity, fault tolerance, etc.
> > That's on the far end, but not to be totally discounted.
>
> please explain.  how is a machine more of any of these things than
> a regular multi-core machine?
>
> - erik
>
>

[-- Attachment #2: Type: text/html, Size: 3056 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[Gabriel Díaz López de la llave]

[-- Attachment #1: Type: text/plain, Size: 2954 bytes --]

Hello

AMD and IBM/Sony think a bit different with their Fusion and Cell
processors+gpu integrated, no?

slds.

On Tue, Jun 7, 2011 at 4:38 PM, Josh Marshall <
joshua.r.marshall.1991@gmail.com> wrote:

> A system running more hardware will, for all practical purposes, use more
> energy.  What this would do is increase the efficiency of that power use.
> Say you're using a single threaded indexing program, and its indexing a very
> slow medium.  Why use a CPU processor when you can idle them, and idle most
> of the other GPU processors and just use the one?  This is mainly for max
> hardware utilization though.
>
> In the VERY long run, I'm seeing thing trending towards very distributed
> models.  As system resources grow, I believe it will become practical to
> "network" within a system.  This can manifest itself in two ways.  First, is
> that due to multi-core systems slowly changing to many-core systems, a
> networking model is very scalable and with so many things to break, the
> fault tolerance will become a must.  This could allow then for computer
> systems to continue their march towards a more biological like organization,
> like a multi-cellular organism.  This will likely be abstracted to
> programmers and users, but on a hardware level, it allows for variable
> redundancy, extreme fault tolerance, internal and external networking
> models, and any few components which break will have no or minimal impact on
> the stability and usability of the system.  This is WAY WAY in the future,
> but that's where I imagine it going and this could be a step in that
> direction.  Was that as coherent as it should be?  I'm still playing with
> this in the back of my head, so its by no means well planned :P  I'd be more
> than happy to talk to someone about this, because no one at my university
> knows this area--our math and CS/CIS departments are feeble.
>
>
> On Mon, Jun 6, 2011 at 9:19 PM, erik quanstrom <quanstro@quanstro.net>wrote:
>
>> > Well, two reasons come to my mind immediately.  First, I'd be cool.
>>  Second,
>> > the wattage you listed is the max wattage, not the idle or light load
>> > wattage which would likely be used.  Per processing element, GPUs use
>> less
>> > power, and you get more processing power per watt than a CPU under
>> certain
>> > loads.
>>
>> i'd sure like a reference to a case where a system with a gpu draws less
>> power than the same system without.  it's not like you can turn the cpu
>> off.
>>
>> > This concept could be taken as far as to bring all processing off
>> > specialized areas for general purpose use, allowing potentially for an
>> > internally distributed system with high regularity, fault tolerance,
>> etc.
>> > That's on the far end, but not to be totally discounted.
>>
>> please explain.  how is a machine more of any of these things than
>> a regular multi-core machine?
>>
>> - erik
>>
>>
>

[-- Attachment #2: Type: text/html, Size: 3594 bytes --]

Re: [9fans] Hey, new to this. Trying to get plan9 to work in a VM.

[erik quanstrom]

> that due to multi-core systems slowly changing to many-core systems, a
> networking model is very scalable and with so many things to break, the
> fault tolerance will become a must.  This could allow then for computer

i'm not sure i follow along.  since i've been paying attention, processors
have ranged from ~6e4 transistors to 2e9 transistors.  over than range,
processors have not gotten 1e5 times less reliable.  as a rough first-order
guess, reliablity has remained steady.

it's also important to remember that unless you have a z/os mainframe,
fault-tolerance within the box is a pipe dream.  i've never seem a white box
pc with redundant motherboards.  and motherboards are up near the top
of component failures.

on the other hand if you want to scale to 1e5 commodity-style systems like
google and others do, you're right, fault tolerance outside the box becomes
interesting.  but that doesn't relate to gpu computing.

- erik

[9fans] NIX

[Lyndon Nerenberg]

> [2]: https://bitbucket.org/npe/nix/src/c1ba3d50a74a/doc/papers/nix/nix.pdf

Is the full BLTJ paper available anyplace?  Failing that, could someone
tell me which issue it was printed in?

Re: [9fans] NIX

[Francisco J Ballesteros]

It's still a draft.
We'll link the papers in the web site (http://lsub.org/ls/nix.html) once they
are ready.


On Mon, Jun 20, 2011 at 2:01 AM, Lyndon Nerenberg <lyndon@orthanc.ca> wrote:
>> [2]: https://bitbucket.org/npe/nix/src/c1ba3d50a74a/doc/papers/nix/nix.pdf
>
> Is the full BLTJ paper available anyplace?  Failing that, could someone tell
> me which issue it was printed in?
>
>