Message boards : Number crunching : Source code? porting, run as annonnymous?
Message board moderation

To post messages, you must log in.

AuthorMessage
Profile trigggl
Avatar

Send message
Joined: 17 Feb 09
Posts: 22
Credit: 311,184
RAC: 0
Message 21185 - Posted: 17 Feb 2009, 18:55:52 UTC

Is it feasible to get the source code to compile on an alternative platform? I\'ve done this on 2 other projects. I haven\'t yet found source that I couldn\'t get working.
ID: 21185 · Report as offensive     Reply Quote
Profile The Gas Giant

Send message
Joined: 2 Sep 04
Posts: 309
Credit: 715,258
RAC: 0
Message 21186 - Posted: 17 Feb 2009, 19:48:56 UTC - in response to Message 21185.  

Is it feasible to get the source code to compile on an alternative platform? I\\\'ve done this on 2 other projects. I haven\\\'t yet found source that I couldn\\\'t get working.

Due to how sensitive the results are to very minor calculation differences / errors, LHC@home do not release their code for 3rd party compiling.
ID: 21186 · Report as offensive     Reply Quote
Profile trigggl
Avatar

Send message
Joined: 17 Feb 09
Posts: 22
Credit: 311,184
RAC: 0
Message 21187 - Posted: 17 Feb 2009, 20:02:24 UTC - in response to Message 21186.  

Due to how sensitive the results are to very minor calculation differences / errors, LHC@home do not release their code for 3rd party compiling.

And yet, they rely on computers that are most likely overclocked and running Windows. I\'d trust PPC over i686 any day. Oh well. I didn\'t really expect it to be available anyways. My RS6000 will just have to stick with SETI@HOME.
ID: 21187 · Report as offensive     Reply Quote
Brian Silvers

Send message
Joined: 3 Jan 07
Posts: 124
Credit: 7,065
RAC: 0
Message 21188 - Posted: 17 Feb 2009, 23:06:08 UTC - in response to Message 21187.  

Due to how sensitive the results are to very minor calculation differences / errors, LHC@home do not release their code for 3rd party compiling.

And yet, they rely on computers that are most likely overclocked and running Windows. I\\\'d trust PPC over i686 any day. Oh well. I didn\\\'t really expect it to be available anyways. My RS6000 will just have to stick with SETI@HOME.


Gotta love stereotyping....

-Brian...who has had a Windows XP (32-bit) system running overclocked from 2200MHz to 2750MHz and rock solid for, oh, about 3 years now...and from 2000MHz to 2500MHz before that... (AMD 3700+ now, 3200+ then)
ID: 21188 · Report as offensive     Reply Quote
Profile trigggl
Avatar

Send message
Joined: 17 Feb 09
Posts: 22
Credit: 311,184
RAC: 0
Message 21192 - Posted: 18 Feb 2009, 4:46:24 UTC - in response to Message 21188.  

-Brian...who has had a Windows XP (32-bit) system running overclocked from 2200MHz to 2750MHz and rock solid for, oh, about 3 years now...and from 2000MHz to 2500MHz before that... (AMD 3700+ now, 3200+ then)

So you agree that there are a lot of people overclocking Windows PC\'s. There are pro\'s at this (you apparently) and amateurs (me). I\'m thinking there\'s a little of both. Maybe more pro\'s than amateurs, but how many amateurs does it take to mess up a project? Don\'t mind me, I just hate Windows. I hated it before I knew anything about Linux. Of course that was before XP. XP is alright. It works well enough for me at work (with Hummingbird as an X-server to connect to our AIX network and to connect to our oracle based engineering program). I just find Linux (*nix in general) much simpler to administrate. How\'s that for irony?

Anyways, yes I did stereotype. Considering your setup, I don\'t think you need to be insecure about it. I wish I could afford that hardware, but if I could you could bet I\'d be running Linux on it.

On a side not, I\'m giving my old (extremely old) P3 to my daughter and she wanted Windows on it. I have a dual boot of Ubuntu and Windows XP on it. Judging by the benchmarks, Windows has a better floating point speed, Linux has a better integer speed. I have an adapter on it to run a 1.0G processor I just overclocked to 1.1G. I tried for 1.2G, but SETI caused it to be unstable and it crashed. I am the king of unique ancient hardware. I have an RS6000 made in 1999 and a maxed out 1GHz P3 with Rambus, also made in 1999. I wish somebody would have told me what Rambus was before I bought the motherboard on ebay.

Recently I learned that Unix time passed 1234567890 on Feb. Friday the 13th US Central timezone. That\'s seconds elapsed since Jan. 1 1970. I also discovered that 32-bit kernels have a y2038 bug. I tested this out on my pc and my 64-bit ppc. The pc stopped at 2038, the ppc64 naturally counted millions of years past that. So, I\'m just thinking there are some calculations that a 64-bit machine can do that maybe a 32-bit machine couldn\'t. I\'ll probably not find that in a boinc project though and I really shouldn\'t by whining about it.

I don\'t know how much longer this RS6000 will last, but I suspect it could run as a diskless machine for a very long time. The hard drive will probably be the first thing to go. It will probably last until 2038. I\'ll probably still be determined to find a use for it.

Thanks for visiting my porting thread. I\'ll go hide under a rock now.
ID: 21192 · Report as offensive     Reply Quote
Profile The Gas Giant

Send message
Joined: 2 Sep 04
Posts: 309
Credit: 715,258
RAC: 0
Message 21202 - Posted: 19 Feb 2009, 19:24:05 UTC - in response to Message 21187.  

Due to how sensitive the results are to very minor calculation differences / errors, LHC@home do not release their code for 3rd party compiling.

And yet, they rely on computers that are most likely overclocked and running Windows. I\\\'d trust PPC over i686 any day. Oh well. I didn\\\'t really expect it to be available anyways. My RS6000 will just have to stick with SETI@HOME.

The project does have issues with OC\'d machines that return invalid results. My OC\'d 3.0GHz P4 doesn\'t do this project for that reason, but it does happily do other projects with no problems.
ID: 21202 · Report as offensive     Reply Quote
noderaser
Avatar

Send message
Joined: 4 Oct 05
Posts: 32
Credit: 344,444
RAC: 0
Message 21208 - Posted: 20 Feb 2009, 3:36:10 UTC

Overclocked and malfunctioning processors are why the quorum and validation are in place on BOINC projects. IIRC, there is also a policy that limits the amount of work that goes to hosts that frequently return errored WUs, although settings like that may vary from project to project.

There hasn\'t been work from here in a while anyway, so perhaps your porting efforts would be better vested in another project? You should also take a look around, as there are some who specialize in BOINC porting, so you aren\'t wasting your effort--assuming you\'re planning on sharing your ported software.
Click here to see My Detailed BOINC Stats
ID: 21208 · Report as offensive     Reply Quote
Dotsch
Avatar

Send message
Joined: 7 Aug 05
Posts: 60
Credit: 73,746
RAC: 0
Message 21213 - Posted: 21 Feb 2009, 14:40:44 UTC - in response to Message 21187.  

My RS6000 will just have to stick with SETI@HOME.

SIMAP and Superlink@technion has also Applications for Linux on the Power/PowerPC architecture. AIX will be supported by SIMAP and SETI@home.
ID: 21213 · Report as offensive     Reply Quote
Profile Paul D. Buck

Send message
Joined: 2 Sep 04
Posts: 545
Credit: 148,912
RAC: 0
Message 21214 - Posted: 21 Feb 2009, 17:23:31 UTC

If you are into it ... you could also look at Milky Way in that the source code is available. Though I have to wonder how many hosts are going to be added if you make the effort ...
ID: 21214 · Report as offensive     Reply Quote
Profile trigggl
Avatar

Send message
Joined: 17 Feb 09
Posts: 22
Credit: 311,184
RAC: 0
Message 21710 - Posted: 3 Dec 2009, 18:15:37 UTC - in response to Message 21214.  

If you are into it ... you could also look at Milky Way in that the source code is available. Though I have to wonder how many hosts are going to be added if you make the effort ...

So far, I\'m able to crunch SETI, Milkyway, Einstein, Pirates, Enigma, Genlife and Primegrid. Those projects that \"support\" linux ppc only support powerpc-unknown-linux-gnu and not powerpc64-unknown-linux-gnu. I have a 64-bit kernel with a 64-bit userspace.
ID: 21710 · Report as offensive     Reply Quote

Message boards : Number crunching : Source code? porting, run as annonnymous?


©2024 CERN