NOTE: A few of these links may be for just "distributed" computing which is not
necessarily high-performance in the usual sense; just high-usefulness computing.
Definitions for use on this page:
-
These are very fuzzy and often misused, so you might consider them synonymous for practical purposes.
-
Multi-processing: Multiple CPUs on a common motherboard or backplane (a non-wire hardware bus).
-
Clustered processing: Multiple coordinated computers on a fast locale area network.
-
Distributed processing: Multiple coordinated computers on a wide area network.
Conferences:
-
SC Conference Series  "The International Conference of High Performing Computing and Communications"
-
SIGARCH (ACM's SC Supercomputing Conference)
Misc:
-
Book: High Performance Computing (at O'Reilly)
-
Beowolf:
-
CCF - Collaborative Computing Frameworks (from Emory U.; for X).
-
Cilk (C-addon specializing in fine-grain multi-threading for multiprocessors)
-
Clusters:
-
Extreme Linux Systems (at linas.org; large/fast actual systems)
-
extremelinux.org
-
Linux in High-Performance Computing
-
Distributed processing, load balancing, job scheduling, etc.:
-
Note: This classification probably covers many entries found elsewhere on this page.
-
Amoeba Distributed OS (OS is distributed across multiple computers; free)
-
Avatar Job Scheduling Suite  $ and free-for-some. Super-cron? Multi-computer capable.
-
CommProc - Communications Processor  "a set of APIs and pre-constructed frameworks which build the
components (clients and resources) of a message-based distributed-computing system."
-
Condor (SW runs on a cluster looking for idle computers and dispatching batch jobs to them;
with good intro docs)
"The goal of the Condor project is to develop, implement, deploy, and evaluate mechanisms and
policies that support High Throughput Computing (HTC) on large collections of distributively owned
computing resources."
-
distributed.net - node 0 (network of distributed computers; mostly code cracking)
-
dsh (a tool to distribute tasks to computers in a cluster)
-
Generic NQS Web Site "one of the world's leading freely-available batch processing systems"
-
Queue "load-balancing/distributed batch processing and local rsh replacement system"
-
Linux Network Address Translation (at linas.org; also covers load balancing, more)
-
MP - MultiProcessing:
-
MOSIX (Adaptive resource managment SW for clusters; Linux port started Summer'98)
-
Parallel Processing/Computing:
-
SMP:
-
Systems, preconfigured for sale:
-
TOP500 (A list of "Global Top 500" supercomputers.)
Last Modified 17-Mar-1999
End of page.