most citedLUTMUL: Exceed Conventional FPGA Roofline Limit by LUT-based Efficient Multiplication for Neural Network Inference

6 citations · 11 across the 2 of their papers we have counts for

collaborators

2 papers

cs.AR2024★ 6 cited

LUTMUL: Exceed Conventional FPGA Roofline Limit by LUT-based Efficient Multiplication for Neural Network Inference

Yanyue Xie, Zhengang Li, Dana Diaconu +3

For FPGA-based neural network accelerators, digital signal processing (DSP) blocks have traditionally been the cornerstone for handling multiplications. This paper introduces LUTMU…

cs.NI2024★ 5 cited

Extracting TCPIP Headers at High Speed for the Anonymized Network Traffic Graph Challenge

Zhaoyang Han, Andrew Briasco-Stewart, Michael Zink +1

Field Programmable Gate Arrays (FPGAs) play a significant role in computationally intensive network processing due to their flexibility and efficiency. Particularly with the high-l…