Abstract
Coarse-grained overlay architectures have been shown to be effective when paired with general purpose processors, offering software-like programmability, fast compilation, and improved design productivity. These architectures enable general purpose hardware accelerators, allowing hardware design at a higher level of abstraction, but at the cost of area and performance overheads. This paper examines the DySER overlay architecture as a hardware accelerator paired with a general purpose processor in a hybrid FPGA such as the Xilinx Zynq. We evaluate the DySER architecture mapped on the Xilinx Zynq and show that it suffers from a significant area and performance overhead. We then propose an improved functional unit architecture using the flexibility of the DSP48E1 primitive which results in a 2.5 times frequency improvement and 25% area reduction compared to the original functional unit architecture. We demonstrate that this improvement results in the routing architecture becoming the bottleneck in performance.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have