Scalable Computing Support Center
Scientific and High-Performance Computing News
For the next fiscal year, we are planning on a small increase in the fee structure for the Condo Service only. The new fees will be:
Condo Service — the “traditional” DSCR service model
$100 per machine for machines still under warranty
NOTE: these machines are currently grandfathered ($0 each), but will now incur a charge
$200 per machine for machines that are out of warranty
These machines were previously $100 each
NOTE: many of the initial blade purchases (made in June 2008) are now falling off warranty
There is no per-hour cost for any usage if you participate in the Condo Service
Cloud Service — pay-per-hour high-priority service
$0.04 per CPU-core-hour (same as the current price)
Fog Service — pay-per-hour low-priority service
$0.005 per CPU-core-hour (same as the current price)
For more information, see https://wiki.duke.edu/display/SCSC/Estimating+Usage
We haven’t done a purchasing round in a while, partially because we were waiting to hear about the availability of the newest Intel CPUs. The latest word is that the new CPUs are still “coming soon” — rather than wait any longer, we’d like to offer the following set of options for new DSCR purchases:
- “Small” — Dell M610 blade, 2x6core, X5650, 48GB
- “Medium” — Dell M610 blade , 2x6core, X5650, 96GB
- “Large” — Dell M710HD blade, 2x6core, X5650, 144GB
- “X-Large” — Dell M710HD blade, 2x6core, X5650, 192GB
- GPU-enabled — Dell M610x blade, 2x6core, X5650, 48GB, NVIDIA M-2050/Tesla GPU
- Please contact scsc at duke edu for pricing information
These prices all represent a significant decrease from the last purchasing round; the larger memory sizes seem to be exceptionally good deals and we know that many of you are starting to run into memory-size issues with your applications. These prices do NOT include the Condo Service fee.
Please let us know if you are interested in making a purchase. We’d like to have fund-codes ready on Friday, December 16th to let our finance team get them into the system before the holidays.
We’ve posted another web-based video on the wiki/Training page:
“Intro to OpenMP” covers the basic use of OpenMP — a programming environment for parallel application development. OpenMP is a set of compiler “directives” for C/C++ and Fortran, so rather than having to learn a whole new programming language, you can continue to code in a familiar language and just add directives (instructions/hints to the compiler) on where you think parallelism could be extracted. A simple example:
#pragma omp parallel do
for(i=0;i<N;i++) {
y[i] = alpha * x[i] + y[i];
}
The addition of that one “pragma” statement converts this single-CPU loop into a multi-CPU/parallel loop. Take a look at the video and see how to add multi-CPU/multi-core parallelism to your existing applications.