10%
29.06.2012
standard “MPI is still great” disclaimer. Higher level languages often try to hide the details of low-level parallel communication. With this “feature” comes some loss of efficiency, similar to writing
9%
20.06.2012
boot times.
Adding users to the compute nodes.
Adding a parallel shell tool, pdsh, to the master node.
Installing and configuring ntp
(a key component for running MPI jobs).
These added
10%
31.05.2012
.
Applying these lessons to HPC, you might ask, “how do I tinker with HPC?” The answer is far from simple. In terms of hardware, a few PCs, an Ethernet switch, and MPI get you a small cluster; or, a video card
9%
22.05.2012
that combines the stateless OS along with important NFS-mounted file systems. In the third article, I will build out the development and run-time environments for MPI applications, and in the fourth article, I
9%
08.05.2012
of the difficulties in producing content is the dynamic nature of the methods and practices of HPC. Some fundamental aspects are well documented – MPI, for instance – and others, such as GPU computing, are currently
9%
10.04.2012
laptop, and open it up again later check on things. When the run is done, PBS Desktop will automatically copy all the files back for you.
AM: What would you tell people if they are thinking about getting
9%
09.04.2012
facing cluster administrators is upgrading software. Commonly, cluster users simply load a standard Linux release on each node and add some message-passing middleware (i.e., MPI) and a batch scheduler
9%
28.03.2012
/O. But measuring CPU and memory usage are very important, maybe even at the detailed level. If the cluster is running MPI codes, then perhaps measuring the interconnect (x
for brief mode and X
for detailed mode
34%
23.02.2012
Sooner or later every cluster develops a plethora of tools and libraries for applications or for building applications. Often the applications or tools need different compilers or different MPI ...
When people first start using clusters, they tend to stick with whatever compiler and MPI library came with the cluster when it was installed. As they become more comfortable with the cluster, using ... MPI, environment modules, compiler, resource manager ...
Sooner or later, every cluster develops a plethora of tools and libraries for applications or for building applications. Often the applications or tools need different compilers or different MPI
13%
15.02.2012
paths might be worth exploring. In particular, the software issue is troubling. Most traditional HPC code uses MPI (Message Passing Interface) to communicate between cores. Although MPI will work