Abstract—The range of operating conditions for a seriesparallelnetworkofvariablelinearresistors, voltagesources, and current sources can be represented as a convex polygon in a T...
The management of the surviving path memory in Viterbi's algorithm is generally performed by Trace-Back or Exchange.Register. A generalized method using precompiled trace-back...
We present in this paper systolic arrays with constant number of input/output (I/O) ports for twodimensional (2-D) FIR and IIR filtering. Our design has an array of L × N proces...
Recent attention to speculative execution as a mechanism for increasing performance of single instruction streams has demanded substantially better branch prediction than what has...
Parity encoded redundant disk arrays provide highly reliable, cost effective secondary storage with high performance for read accesses and large write accesses. Their performance ...
Parallel programs that use critical sections and are executed on a shared-memory multiprocessor with a writeinvalidate protocol result in invalidation actions that could be elimin...
er uses an abstract machine approach to compare the mechanisms of two parallel machines: the J-Machine and the CM-5. High-level parallel programs are translated by a single optimi...
Ellen Spertus, Seth Copen Goldstein, Klaus E. Scha...
The distribution of resources among processors, memory and caches is a crucial question faced by designers of large-scale parallel machines. If a machine is to solve problems with...