In this paper, we show a novel approach to accelerate loops by tightly coupling a coprocessor to an ASIP. Latency hiding is used to exploit the parallelism available in this archi...
The current trend is for processors to deliver dramatic improvements in parallel performance while only modestly improving serial performance. Parallel performance is harvested th...
Sanjeev Kumar, Daehyun Kim, Mikhail Smelyanskiy, Y...
A series of recent algorithmic advances has delivered highly effective methods for pairing evaluation and parameter generation. However, the resulting multitude of options means m...
As the number of cores per die increases, be they processors, memory blocks, or custom accelerators, the on-chip interconnect the cores use to communicate gains importance. We beg...
Martha Mercaldi Kim, John D. Davis, Mark Oskin, To...
The design of application (-domain) specific instructionset processors (ASIPs), optimized for code size, has traditionally been accompanied by the necessity to program assembly, ...