2 papers
cs.AR2024
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
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…