Pengyuan Yu

Learn More
In current Field-Programmable-Logic Architecture (FPGA) design flows, it is very hard to control the routing of submodules. It is thus very hard to make an identical copy of an existing circuit within the same FPGA fabric. We have solved this problem in a way that still enables us to modify the logic function of the copied sub-module. Our technique has(More)
This design presents a system optimized for complex matrix multiplications on the XUP Virtex-II board. Utilizing the GEZEL HW/SW co-simulation environment, the resulting system achieves˜25x speedup over a standard software only implementation. Further system level optimization (with DMA) results in the same coprocessor being speedup by at least another(More)
Multi-processor architectures have gained interest recently because of their ability to exploit programmable silicon par-allelism at acceptable power-efficiency figures. Despite the potential benefit they offer over single-processor architec-tures, it is unresolved how one can write compact and efficient programs for multiple parallel cores. In this paper,(More)
  • 1