2 Jan 2012 20:12
2 Jan 2012 20:15
Re: clustering using off the shelf systems in a fish tank full of oil.
Prentice Bisbal <prentice <at> ias.edu>
2012-01-02 19:15:16 GMT
2012-01-02 19:15:16 GMT
On 12/29/2011 07:50 PM, Vincent Diepeveen wrote: > it's very useful Mark, as we know now he works for the company and > also for which nation. > > Vincent For someone who's always bashing on US Foreign policy, you sure sound like a Republican or member of the Department of Homeland Security!
11 Jan 2012 10:13
Course: Parallel Programming of High Performance Systems
Eugen Leitl <eugen <at> leitl.org>
2012-01-11 09:13:02 GMT
2012-01-11 09:13:02 GMT
----- Forwarded message from Georg Hager <Georg.Hager <at> rrze.uni-erlangen.de> ----- From: Georg Hager <Georg.Hager <at> rrze.uni-erlangen.de> Date: Wed, 11 Jan 2012 01:40:09 +0100 (CET) To: eugen <at> leitl.org Subject: Course: Parallel Programming of High Performance Systems "Parallel Programming of High Performance Systems" is the yearly course provided by LRZ and RRZE that gives students and scientists a solid introduction to - Processor and HPC system architectures - Code development and basic tools - Scalar optimizations (generic and architecture-specific) - Parallelization basics - Parallel programming with OpenMP and MPI There will also be an additional course with advanced topics, which covers - Parallel performance tools for MPI and OpenMP - Parallel I/O with MPI I/O - I/O tuning and libraries Hands-on sessions will enable participants to apply the concepts right away. Although the federal HPC system at LRZ Munich is treated in some detail, most of the conveyed concepts are of general use. You can find the preliminary course agendas on the web:(Continue reading)
11 Jan 2012 16:36
Re: Course: Parallel Programming of High Performance Systems
Vincent Diepeveen <diep <at> xs4all.nl>
2012-01-11 15:36:48 GMT
2012-01-11 15:36:48 GMT
Yeah, the sheets are there from the 2003 lecture. filename LRZ210703_1.pdf Very helpful if you have grey hair and want to port your years 80 fortran code to todays HPC hardware. Vincent On Jan 11, 2012, at 10:13 AM, Eugen Leitl wrote: > ----- Forwarded message from Georg Hager <Georg.Hager <at> rrze.uni- > erlangen.de> ----- > > From: Georg Hager <Georg.Hager <at> rrze.uni-erlangen.de> > Date: Wed, 11 Jan 2012 01:40:09 +0100 (CET) > To: eugen <at> leitl.org > Subject: Course: Parallel Programming of High Performance Systems > > "Parallel Programming of High Performance Systems" is the > yearly course provided by LRZ and RRZE that gives students > and scientists a solid introduction to > > - Processor and HPC system architectures > - Code development and basic tools > - Scalar optimizations (generic and architecture-specific) > - Parallelization basics > - Parallel programming with OpenMP and MPI > > There will also be an additional course with advanced topics, > which covers(Continue reading)
11 Jan 2012 17:09
Re: Course: Parallel Programming of High Performance Systems
Lux, Jim (337C <james.p.lux <at> jpl.nasa.gov>
2012-01-11 16:09:00 GMT
2012-01-11 16:09:00 GMT
I don't have grey hair (part grey beard, I confess), but I have plenty of 70s era FORTRAN that benefits from parallelization. Numerical Electromagnetics Code V4, specifically. The implementation has been throughly validated and have been used for decades, finding all the little idiosyncracies and dealing with numerical precision issues, etc. There's extensive software around that generates the card image input files it expects and parses the line printer output files (with the 1 in column 1 for a page break). Rewriting it from scratch would not be a very good use of time. You'd have to revisit all the years of validation, make sure there were subtle differences in function, because while there's an official validation suite, it's more to make sure that the compile worked ok and there's not an egregious problem. And who knows what users out there have depended on some idiosyncratic implementation aspects. I suspect the same is true for lots of fluid mechanics and other FEM codes (NASTRAN, for instance). So an incremental approach of parallelizing that old FORTRAN, replacing pieces with "new FORTRAN", for instance, might be useful. (and don't get me started on my experiences with the f2c engine) On 1/11/12 7:36 AM, "Vincent Diepeveen" <diep <at> xs4all.nl> wrote: >Yeah, the sheets are there from the 2003 lecture. >filename LRZ210703_1.pdf >(Continue reading)
11 Jan 2012 17:18
A cluster of Arduinos
Lux, Jim (337C <james.p.lux <at> jpl.nasa.gov>
2012-01-11 16:18:41 GMT
2012-01-11 16:18:41 GMT
For educational purposes..
Has anyone done something where they implement some sort of message passing API on a network of Arduinos. Since they cost only $20 each, and have a fairly facile development environment, it seems you could put together a simple demonstration of parallel processing and various message passing things.
For instance, you could introduce errors in the message links and do experiments with Byzantine General type algorithms, or with multiple parallel routes, etc.
I've not actually tried hooking up multiple arduinos through a USB hub to one PC, but if that works, it gives you a nice "head node, debug console" sort of interface.
Smaller, lighter, cheaper than lashing together MiniITX mobos or building a Wal-Mart Cluster.
<div> <div><br></div> <div>For educational purposes..</div> <div><br></div> <div>Has anyone done something where they implement some sort of message passing API on a network of Arduinos. Since they cost only $20 each, and have a fairly facile development environment, it seems you could put together a simple demonstration of parallel processing and various message passing things.</div> <div><br></div> <div>For instance, you could introduce errors in the message links and do experiments with Byzantine General type algorithms, or with multiple parallel routes, etc.</div> <div><br></div> <div>I've not actually tried hooking up multiple arduinos through a USB hub to one PC, but if that works, it gives you a nice "head node, debug console" sort of interface.</div> <div><br></div> <div>Smaller, lighter, cheaper than lashing together MiniITX mobos or building a Wal-Mart Cluster.</div> <div><br></div> <div><br></div> </div>
11 Jan 2012 18:00
Re: Course: Parallel Programming of High Performance Systems
Vincent Diepeveen <diep <at> xs4all.nl>
2012-01-11 17:00:43 GMT
2012-01-11 17:00:43 GMT
On Jan 11, 2012, at 5:09 PM, Lux, Jim (337C) wrote: > I don't have grey hair (part grey beard, I confess), but I have > plenty of > 70s era FORTRAN that benefits from parallelization. > Numerical Electromagnetics Code V4, specifically. > > The implementation has been throughly validated and have been used for > decades, finding all the little idiosyncracies and dealing with > numerical > precision issues, etc. There's extensive software around that > generates > the card image input files it expects and parses the line printer > output > files (with the 1 in column 1 for a page break). > > Rewriting it from scratch would not be a very good use of time. > You'd have > to revisit all the years of validation, make sure there were subtle > differences in function, because while there's an official validation > suite, it's more to make sure that the compile worked ok and > there's not > an egregious problem. And who knows what users out there have > depended on > some idiosyncratic implementation aspects. > > I suspect the same is true for lots of fluid mechanics and other > FEM codes > (NASTRAN, for instance). > > So an incremental approach of parallelizing that old FORTRAN, > replacing > pieces with "new FORTRAN", for instance, might be useful. > > (and don't get me started on my experiences with the f2c engine) > No need to get started Jim, NASA can ask that the Russians as well. > > > On 1/11/12 7:36 AM, "Vincent Diepeveen" <diep <at> xs4all.nl> wrote: > >> Yeah, the sheets are there from the 2003 lecture. >> filename LRZ210703_1.pdf >> >> Very helpful if you have grey hair and want to port your years 80 >> fortran code to todays HPC hardware. >> >> Vincent >> >> On Jan 11, 2012, at 10:13 AM, Eugen Leitl wrote: >> >>> ----- Forwarded message from Georg Hager <Georg.Hager <at> rrze.uni- >>> erlangen.de> ----- > >
11 Jan 2012 17:58
Re: A cluster of Arduinos
Prentice Bisbal <prentice <at> ias.edu>
2012-01-11 16:58:59 GMT
2012-01-11 16:58:59 GMT
On 01/11/2012 11:18 AM, Lux, Jim (337C) wrote: > > For educational purposes.. > > Has anyone done something where they implement some sort of message > passing API on a network of Arduinos. Since they cost only $20 each, > and have a fairly facile development environment, it seems you could > put together a simple demonstration of parallel processing and various > message passing things. > > For instance, you could introduce errors in the message links and do > experiments with Byzantine General type algorithms, or with multiple > parallel routes, etc. > > I've not actually tried hooking up multiple arduinos through a USB hub > to one PC, but if that works, it gives you a nice "head node, debug > console" sort of interface. > > Smaller, lighter, cheaper than lashing together MiniITX mobos or > building a Wal-Mart Cluster. > I started tinkering with Arduinos a couple of months ago. Got lots of related goodies for Christmas, so I've been looking like a mad scientist building arduino things lately. I'm still a beginner arduino hacker, but I'd be game for giving this a try, if anyone else wants to give this a go. The Arduino Due, which is overdue in the marketplace, will have a Cortex-M3 ARM processor. -- Prentice
11 Jan 2012 18:43
Re: A cluster of Arduinos
Vincent Diepeveen <diep <at> xs4all.nl>
2012-01-11 17:43:17 GMT
2012-01-11 17:43:17 GMT
On Jan 11, 2012, at 5:58 PM, Prentice Bisbal wrote: > On 01/11/2012 11:18 AM, Lux, Jim (337C) wrote: >> >> For educational purposes.. >> >> Has anyone done something where they implement some sort of message >> passing API on a network of Arduinos. Since they cost only $20 each, >> and have a fairly facile development environment, it seems you could >> put together a simple demonstration of parallel processing and >> various >> message passing things. >> >> For instance, you could introduce errors in the message links and do >> experiments with Byzantine General type algorithms, or with multiple >> parallel routes, etc. >> >> I've not actually tried hooking up multiple arduinos through a USB >> hub >> to one PC, but if that works, it gives you a nice "head node, debug >> console" sort of interface. >> >> Smaller, lighter, cheaper than lashing together MiniITX mobos or >> building a Wal-Mart Cluster. >> > > I started tinkering with Arduinos a couple of months ago. Got lots of > related goodies for Christmas, so I've been looking like a mad > scientist > building arduino things lately. I'm still a beginner arduino > hacker, but > I'd be game for giving this a try, if anyone else wants to give > this a go. > > The Arduino Due, which is overdue in the marketplace, will have a > Cortex-M3 ARM processor. Completely superior chip that Cortex-M3. Though i couldn't program much for it so far - difficult to get contract jobs for. Can do fast multiplication 32 x 32 bits. You can even implement RSA very fast on that chip. Runs at 70Mhz or so? Usually writing assembler for such CPU's is more efficient by the way than using a compiler. Compilers are not so efficient, to say polite, for embedded cpu's. Writing assembler for such cpu's is pretty straightforward, whereas in HPC things are far more complicated because of vectorization. AVX is the latest there. Speaking of AVX, is there already lots of HPC support for AVX? I see that after years of wrestling the George Woltman released some prime number code (GWNUM), of course as always: in beta for the remainder of this century, which uses AVX. Claims are that it's a tad faster than the existing SIMD codes. I saw claims of even above 20% faster, which is really a lot at that level of engineering; usually you work 6 months for 0.5% speedup. If you improve algorithm, you still lose it from this code, as your C/ C++ code will be default a factor 10 slower if not more. I remember how i found a clever caching trick in 2006 for a Numeric Theoretic Transform (that's a FFT but then in integers, so without the rounding errors that the floating point FFT's give), yet after some hard work there my C code still was factor 8 slower than Woltman's SIMD assembler. > > -- > Prentice > > > _______________________________________________ > Beowulf mailing list, Beowulf <at> beowulf.org sponsored by Penguin > Computing > To change your subscription (digest mode or unsubscribe) visit > http://www.beowulf.org/mailman/listinfo/beowulf
11 Jan 2012 18:44
Re: A cluster of Arduinos
Vincent Diepeveen <diep <at> xs4all.nl>
2012-01-11 17:44:43 GMT
2012-01-11 17:44:43 GMT
That's all very expensive considering the cpu's are under $1 i'd guess. I actually might need some of this stuff some months from now to build some robots. On Jan 11, 2012, at 6:31 PM, Nathan Moore wrote: > I think something like the Raspberry Pi might be easier for this sort > of task. They'll also be about $25, but they'll run something like > ARM/linux. Not out yet thought. > > http://www.raspberrypi.org/ > > On Wed, Jan 11, 2012 at 10:58 AM, Prentice Bisbal > <prentice <at> ias.edu> wrote: >> On 01/11/2012 11:18 AM, Lux, Jim (337C) wrote: >>> >>> For educational purposes.. >>> >>> Has anyone done something where they implement some sort of message >>> passing API on a network of Arduinos. Since they cost only $20 >>> each, >>> and have a fairly facile development environment, it seems you could >>> put together a simple demonstration of parallel processing and >>> various >>> message passing things. >>> >>> For instance, you could introduce errors in the message links and do >>> experiments with Byzantine General type algorithms, or with multiple >>> parallel routes, etc. >>> >>> I've not actually tried hooking up multiple arduinos through a >>> USB hub >>> to one PC, but if that works, it gives you a nice "head node, debug >>> console" sort of interface. >>> >>> Smaller, lighter, cheaper than lashing together MiniITX mobos or >>> building a Wal-Mart Cluster. >>> >> >> I started tinkering with Arduinos a couple of months ago. Got lots of >> related goodies for Christmas, so I've been looking like a mad >> scientist >> building arduino things lately. I'm still a beginner arduino >> hacker, but >> I'd be game for giving this a try, if anyone else wants to give >> this a go. >> >> The Arduino Due, which is overdue in the marketplace, will have a >> Cortex-M3 ARM processor. >> >> -- >> Prentice >> >> >> _______________________________________________ >> Beowulf mailing list, Beowulf <at> beowulf.org sponsored by Penguin >> Computing >> To change your subscription (digest mode or unsubscribe) visit >> http://www.beowulf.org/mailman/listinfo/beowulf > > > > -- > - - - - - - - - - - - - - - - - - - - - - > Nathan Moore > Associate Professor, Physics > Winona State University > - - - - - - - - - - - - - - - - - - - - - > _______________________________________________ > Beowulf mailing list, Beowulf <at> beowulf.org sponsored by Penguin > Computing > To change your subscription (digest mode or unsubscribe) visit > http://www.beowulf.org/mailman/listinfo/beowulf >
RSS Feed