88 citations · 139 across the 5 of their papers we have counts for
5 papers
P4Testgen: An Extensible Test Oracle For P4
Fabian Ruffy, Jed Liu, Prathima Kotikalapudi +7
We present P4Testgen, a test oracle for the P4 language. P4Testgen supports automatic test generation for any P4 target and is designed to be extensible to many P4 targets.…
NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers
Jiawei Liu, Jinkun Lin, Fabian Ruffy +4
Deep-learning (DL) compilers such as TVM and TensorRT are increasingly being used to optimize deep neural network (DNN) models to meet performance, resource utilization and other r…
Gauntlet: Finding Bugs in Compilers for Programmable Packet Processing
Fabian Ruffy, Tao Wang, Anirudh Sivaraman
Programmable packet-processing devices such as programmable switches and network interface cards are becoming mainstream. These devices are configured in a domain-specific language…
The State of Knowledge Distillation for Classification
Fabian Ruffy, Karanbir Chahal
We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments usi…
Iroko: A Framework to Prototype Reinforcement Learning for Data Center Traffic Control
Fabian Ruffy, Michael Przystupa, Ivan Beschastnikh
Recent networking research has identified that data-driven congestion control (CC) can be more efficient than traditional CC in TCP. Deep reinforcement learning (RL), in particular…