Clusters of workstations have become a cost-effective means of performing scientific computations. However, large network latencies, resource sharing, and heterogeneity found in ...
For multi-gigahertz designs in nanometer technologies, data transfers on global interconnects take multiple clock cycles. In this paper, we propose a regular distributed register ...
Image processing applications tend to access their data non-sequentially and reuse that data infrequently. As a result, they tend to perform poorly on conventional memory systems ...
Lixin Zhang, John B. Carter, Wilson C. Hsieh, Sall...
We describe an efficient technique for out-of-core management and interactive rendering of planet sized textured terrain surfaces. The technique, called P-Batched Dynamic Adaptiv...
Paolo Cignoni, Fabio Ganovelli, Enrico Gobbetti, F...
— We discuss a distributed imaging architecture with active illumination for sensor network applications. An event-based CMOS imager is employed at the sensor level, to convert l...
Eugenio Culurciello, Thiago Teixeira, Andreas G. A...