Newsletter Downloads
A massively parallel and distributed I/O subsystem
This paper presents ParFiSys, a parallel and distributed file system developed at the UPM. It provides several types of distributed file systems, which may be accessed using different mapping functions. Grouped management and parallelization are ...
Distributing and load-balancing for loops in scientific applications
We present experimental results for two engineering applications that have had load balancing and fault tolerance mechanisms added through the use of a standard interface. The abstraction technique employed forms the foundation of a problem solving ...
A discussion on non-blocking/lockup-free caches
Cache memories are commonly used to bridge the gap between processor and memory speed. Caches provide fast access to a subset of memory. When a memory request does not find an address in the cache, a cache miss is incurred. In most commercial processors ...
Internet Nuggets
This column consists of selected traffic from the comp.arch newsgroup, a forum for discussion of computer architecture on Internet---an international computer network.