If you're using AT&T's email-to-SMS gateway, use number@mobile.mycingular.com rather than number@txt.att.net. The mycingular.com address always uses the same sending number, so it appears as a single conversation that can be deleted with one swipe, rather than one per message.
Not sure if other providers have a similar setup, but this one saved me from ditching the iPhone entirely. Now if only I could use my own custom SMS ringtones....
I've got to agree... I've been experimenting with the trial version, and am quite impressed. I'm finding more and more uses for it the more I've played with it. I'm about ready to purchase a copy, even though it only runs on Windows. Anyone else request a native Linux version from MindJet?
As far as I knew, the local cable loop is 27 mb, but the ethernet connection from the cable modem is 10 mb. In the nine months I had RoadRunner, I never saw anything close to 10 mb, and dumped it last week in favor of ADSL because of the horrible (often 1500 ms+) latencies I was seeing on the cable modem.
As the member of the UT research group that actually assembled the cluster and ran the tests, they were comparable in terms of execution time and speedup. Our cluster of 300 MHz PIIs with 440LX motherboards, the cluster was about 1.8 times slower than the MHPCC SP, which uses 160 MHz P2SC thin nodes. Using 400 MHz PIIs with 440BX motherboards (and also 400 MHz Xeons), the cluster is as fast as the MHPCC SP.
As for case color, the SP definately outperforms the cluster. Rows of beige cases on metal shelves hardly compare to black refridgerator-sized boxes with more blinking lights. Maybe if we build a cluster of the new SGI boxes...
I would have liked to see more details of our work in the article, but the reporter just wanted to verify that the Hess results weren't out of line. You can find more details of our results at http://topeka.cpge.utexas.edu. Feel free to email me if you'd like specific details that aren't on the webpage.
You don't need the rpms from beowulf.org unless you want to use extensions to the standard kernel such as channel bonding or distributed pids. Otherwise, just install your favorite distribution on several machines, grab MPICH or PVM, and start experimenting.
Re:or, CIOs Discover Linux Saves Shrinking Budgets
on
Practical Beowulf
·
· Score: 2
I think this is definately going to happen. I taked with the reporter who wrote this Computerworld article (I'm part of the group at the University of Texas that is mentioned at the end of the article). He said that Computerworld is mainly read by business-types who want to use technology to cut costs. I think Linux just starting to be accepted in this community, and will soon take off there like it has in other areas.
Microsoft being less than honest with a customer doesn't surprise me. What I found particularly interesting was the quote by the Y2K product manager:
"I don't want people taking action based on Microsoft thinking about doing something," said Don Jones, year 2000 product manager at Microsoft. "Until I'm 100% sure that we're going to provide an update or fix, I don't want to tell anybody," Jones added. "People will spend millions of dollars, [implementing strategies based on such information], and the last thing I want to do is spread fear, uncertainty and doubt in their minds."
Not only does a Microsoft employee acknowledge the existance of FUD, he makes it sound like they are actively opposed to it!
Actually there are a number of F90 compilers under Linux. We've been using the Portland Group compiler for more than a year. There are several others. See the Linux Fortran Information Page for all the details.
In vectorcomputing, each node computes a very small part of the big picture, making communication time a very big (or small in this case) bottleneck. Thus these computers need super fast, specialized networking connections.
Umm, I think you're confused. Vector computers, such as the older Cray machines, use special vector processors that can operate very efficiently on long vectors of data, applying the same operations (hence the name). Things get a little more confusing with later machines which are actually parallel-vector computers (i.e. they had multiple vector processors that worked in parallel).
It is generally accepted that parallel computers, whether they are "big iron" type machines, such as the T3E, Origin 2000 or SP2, or clusters of workstations and PCs, are the way to go for high-performance computing. Of course, some people would point to the latest vector machines from Japan to contradict this...
You are right that the true measure of performance is based on applications, and there are applications suited to each of these architectures. We have found that for our problems (large-scale reservoir modelling) clusters of commodity PCs perform quite well in comparision to an SP or T3E, even with 100 Mbps networking, but there certainly are other applications with more fine-grained communication requirements for which even a T3E or O2k is barely sufficient.
Overall it depends on the application. GCC is not that bad on Alpha integer. The performance loss is mostly in floating point and math libraries.
This shouldn't be true for much longer. Compaq released their math library for the Alpha last week (see here for details), and, acording to posts to comp.lang.fortan they will be releasing their Fortran compiler as well (as a commercial product, not for free). This should make Alphas much more appealing for cluster use.
I recently installed Linux (RH5.2) on a Thinkpad 560, and it went quite smoothly. It is a pretty nice machine - P133, 40 MB memory, 1 GB disk, 12" TFT screen. It runs Linux quite well, and is a nice, light machine. I think you can pick one up used for less than $1000.
Slashdot Mirror
If you're using AT&T's email-to-SMS gateway, use number@mobile.mycingular.com rather than number@txt.att.net. The mycingular.com address always uses the same sending number, so it appears as a single conversation that can be deleted with one swipe, rather than one per message.
Not sure if other providers have a similar setup, but this one saved me from ditching the iPhone entirely. Now if only I could use my own custom SMS ringtones....
I've got to agree... I've been experimenting with the trial version, and am quite impressed. I'm finding more and more uses for it the more I've played with it. I'm about ready to purchase a copy, even though it only runs on Windows. Anyone else request a native Linux version from MindJet?
As far as I knew, the local cable loop is 27 mb, but the ethernet connection from the cable modem is 10 mb. In the nine months I had RoadRunner, I never saw anything close to 10 mb, and dumped it last week in favor of ADSL because of the horrible (often 1500 ms+) latencies I was seeing on the cable modem.
-jason
As the member of the UT research group that actually assembled the cluster and ran the tests, they were comparable in terms of execution time and speedup. Our cluster of 300 MHz PIIs with 440LX motherboards, the cluster was about 1.8 times slower than the MHPCC SP, which uses 160 MHz P2SC thin nodes. Using 400 MHz PIIs with 440BX motherboards (and also 400 MHz Xeons), the cluster is as fast as the MHPCC SP.
As for case color, the SP definately outperforms the cluster. Rows of beige cases on metal shelves hardly compare to black refridgerator-sized boxes with more blinking lights. Maybe if we build a cluster of the new SGI boxes...
I would have liked to see more details of our work in the article, but the reporter just wanted to verify that the Hess results weren't out of line. You can find more details of our results at http://topeka.cpge.utexas.edu. Feel free to email me if you'd like specific details that aren't on the webpage.
-jason
You don't need the rpms from beowulf.org unless you want to use extensions to the standard kernel such as channel bonding or distributed pids. Otherwise, just install your favorite distribution on several machines, grab MPICH or PVM, and start experimenting.
Feel free to send questions my way if you need help with this. Or check out any of the documentation at http://www.beowulf-underground.org/.
-jason
I think this is definately going to happen. I taked with the reporter who wrote this Computerworld article (I'm part of the group at the University of Texas that is mentioned at the end of the article). He said that Computerworld is mainly read by business-types who want to use technology to cut costs. I think Linux just starting to be accepted in this community, and will soon take off there like it has in other areas.
-jason
Not only does a Microsoft employee acknowledge the existance of FUD, he makes it sound like they are actively opposed to it!
Actually there are a number of F90 compilers under Linux. We've been using the Portland Group compiler for more than a year. There are several others. See the Linux Fortran Information Page for all the details.
In vectorcomputing, each node computes a very small part of the big picture, making communication time a very big (or small in this
case) bottleneck. Thus these computers need super fast, specialized networking connections.
Umm, I think you're confused. Vector computers, such as the older Cray machines, use special vector processors that can operate very efficiently on long vectors of data, applying the same operations (hence the name). Things get a little more confusing with later machines which are actually parallel-vector computers (i.e. they had multiple vector processors that worked in parallel).
It is generally accepted that parallel computers, whether they are "big iron" type machines, such as the T3E, Origin 2000 or SP2, or clusters of workstations and PCs, are the way to go for high-performance computing. Of course, some people would point to the latest vector machines from Japan to contradict this...
You are right that the true measure of performance is based on applications, and there are applications suited to each of these architectures. We have found that for our problems (large-scale reservoir modelling) clusters of commodity PCs perform quite well in comparision to an SP or T3E, even with 100 Mbps networking, but there certainly are other applications with more fine-grained communication requirements for which even a T3E or O2k is barely sufficient.
Overall it depends on the application. GCC is not that bad on Alpha integer. The performance loss is mostly in floating point and math libraries.
This shouldn't be true for much longer. Compaq released their math library for the Alpha last week (see here for details), and, acording to posts to comp.lang.fortan they will be releasing their Fortran compiler as well (as a commercial product, not for free). This should make Alphas much more appealing for cluster use.
-jason
I recently installed Linux (RH5.2) on a Thinkpad 560, and it went quite smoothly. It is a pretty nice machine - P133, 40 MB memory, 1 GB disk, 12" TFT screen. It runs Linux quite well, and is a nice, light machine. I think you can pick one up used for less than $1000.