Daniel Mendoza

EE PhD Student at Stanford
Systems for ML for Systems

About Me

I'm a third year EE PhD student at Stanford, advised by Professor Caroline Trippel. My recent interests include systems for ML and ML for systems.

Research

Interference-Aware Inference Serving
The profiliferation of machine learning inference to many domains has highlighted the importance of developing inference serving systems which meet applications' service level objectives. To improve resource utilization, inference serving systems often co-locate multiple models on the same backend machine. However, co-location can cause latency degradation due to interference and can subsequently violate latency requirements. In collaboration with Professor Christos Kozyrakis lab, we characterized the challenges of interference-aware scheduling in inference serving systems and demonstrated its potential benefits.

Out-of-order Parallel SystemC Simulation
SystemC is a generic discrete event simulation framework often used for embedded system models with hardware and software components. Although SystemC enables model developers to simulate concurrent processes, implementations of SystemC simulators execute all processes sequentially and thus do not exploit the inherent parallelism of the model to speedup simulation. Thus the Recoding Infrastructure for SystemC (RISC) project was introduced to enable advanced analysis and aggressive parallel simulation of SystemC models. Under mentorship of Professor Rainer Doemer, we developed efficient scheduling algorithms for parallel simulation, integrated parallel SystemC into virtual platform simulation, and developed tools for visualizing SystemC models.

Publications

Model Selection for Latency-Critical Inference Serving
Daniel Mendoza, Francisco Romero, Caroline Trippel
Eurosys 2024: 19th European Conference on Computer Systems (to appear)

nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Models
Matthias Cosler, Christopher Hahn, Daniel Mendoza, Frederik Schmitt, Caroline Trippel
CAV 2023: 35th International Conference on Computer Aided Verification

Interference-Aware Scheduling for Inference Serving
Daniel Mendoza, Francisco Romero, Qian Li, Neeraja J. Yadwadkar, Christos Kozyrakis
EuroMLSys 2021: Proceedings of the 1st Workshop on Machine Learning and Systems

Pushing the Limits of Parallel Discrete Event Simulation for SystemC
Rainer Doemer, Zhongqi Cheng, Daniel Mendoza, Emad Arasteh
A Journey of Embedded and Cyber-Physical Systems 2021

Lazy Event Prediction using defining trees and schedule bypass for out-of-order PDES
Daniel Mendoza, Zhongqi Cheng, Emad Arasteh, Rainer Doemer
DATE 2020: Proceedings of the Design, Automation and Test in Europe Conference

Integrating Parallel SystemC Simulation into Simics Virtual Platform
Daniel Mendoza, Ajit Dingankar, Zhongqi Cheng, Rainer Doemer
DVCon Europe 2019: Proceedings of the Design and Verification Conference in Europe

RISC Compiler and Simulator, Release V0.6.0: Out-of-Order Parallel Simulatable SystemC Subset
Guantao Liu, Tim Schmidt, Zhongqi Cheng, Daniel Mendoza, Rainer Doemer
Center for Embedded and Cyber-Physical Systems, Technical Report 2019

RISC: Recoding Infrastructure for SystemC, Open Source Framework for Parallel Simulation
Rainer Doemer, Zhongqi Cheng, Daniel Mendoza, Ajit Dingankar
Workshop on Open Source EDA Technology at ICCAD 2018

A Tool for Visualization of SystemC Models
Daniel Mendoza, Rainer Doemer
Center for Embedded and Cyber-Physical Systems, Technical Report 2017