Wide Single Instruction, Multiple Thread (SIMT) architectures often require a static allocation of thread groups that are executed in lockstep throughout the entire application ker...
— Driven by the need for higher bandwidth and complexity reduction, off-chip interconnect has evolved from proprietary busses to networked architectures. A similar evolution is o...
Paul Gratz, Changkyu Kim, Robert G. McDonald, Step...
- Power estimation in combinational modules is addressed from a probabilistic point of view. The zero-delay hypothesis is considered and under highly correlated input streams, the ...
We present detailed analytical models for estimating the energy dissipation in conventional caches as well as low energy cache architectures. The analytical models use the run tim...
Dynamically reconfigurable embedded systems offer potential for higher performance as well as adaptability to changing system requirements at low cost. Such systems employ run-tim...