63 citations · 105 across the 9 of their papers we have counts for
10 papers
Supercharging Packet-level Network Simulation of Large Model Training via Memoization and Fast-Forwarding
Fei Long, Kaihui Gao, Li Chen +6
Packet-level discrete-event simulation (PLDES) is a prevalent tool for evaluating detailed performance of large model training. Although PLDES offers high fidelity and generality,…
BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing
Tianfeng Liu, Yangrui Chen, Dan Li +7
Graph neural networks (GNNs) have extended the success of deep neural networks (DNNs) to non-Euclidean graph data, achieving ground-breaking performance on various tasks such as no…
Analyzing Open-Source Serverless Platforms: Characteristics and Performance
Junfeng Li, Sameer G. Kulkarni, K. K. Ramakrishnan +1
Serverless computing is increasingly popular because of its lower cost and easier deployment. Several cloud service providers (CSPs) offer serverless computing on their public clou…
High Performance and Scalable NAT System on Commodity Platforms
Junfeng Li, Dan Li, Yukai Huang +2
Quick network address translation (NAT) is proposed to improve the network performance of the NAT system on the commodity server by three ways. First, the quick NAT search algorith…
Quick NAT: High performance NAT system on commodity platforms
Junfeng Li, Dan Li, Yukai Huang +2
NAT gateway is an important network system in today's IPv4 network when translating a private IPv4 address to a public address. However, traditional NAT system based on Linux Netfi…
An Upbound of Hausdorff's Dimension of the Divergence Set of the fractional Schrödinger Operator on $H^s(\mathbb R^n)
Dan Li, Junfeng Li, Jie Xiao
This paper shows $$ \sup_{f\in H^s(\mathbb{R}^n)}\dim _H\left\{x\in\mathbb{R}^n:\ \lim_{t\rightarrow0}e^{it(-Δ)^α}f(x)\neq f(x)\right\}\leq n+1-\frac{2(n+1)s}{n}\ \ \text{under}\ \…