TeMCO: Tensor Memory Compiler Optimization across Tensor Decompositions in Deep Learning Inference [abstract] (ACM, PDF) Seungbin Song, Ju Min Lee, Haeeun Jeong, Hyunho Kwon, Shinnung Jeong, Jaeho Lee, and Hanjun Kim Proceedings of the 53rd International Conference on Parallel Processing (ICPP), August 2024.
Occamy: Memory-efficient GPU Compiler for DNN Inference [abstract] (IEEE Xplore, Github, PDF) Jaeho Lee, Shinnung Jeong, Seungbin Song, Kunwoo Kim, Heelim Choi, Youngsok Kim, and Hanjun Kim Proceedings of the 60th Annual Design Automation Conference 2023 (DAC), July 2023.
Decoupling Schedule, Topology Layout, and Algorithm to Easily Enlarge the Tuning Space of GPU Graph Processing [abstract] (ACM, PDF) Shinnung Jeong, Yongwoo Lee, Jaeho Lee, Heelim Choi, Seungbin Song, Jinho Lee, Youngsok Kim, and Hanjun Kim Proceedings of the 31st International Conference on Parallel Architectures and Compilation Techniques (PACT), October 2022.
Precise Correlation Extraction for IoT Fault Detection with Concurrent Activities [abstract] (ACM DL, PDF) Gyeongmin Lee, Bongjun Kim, Seungbin Song, Changsu Kim, Jong Kim, and Hanjun Kim Proceedings of the International Conference on
Embedded Software (EMSOFT), October 2021.
Accept Rate: NaN% (/).
Fine-Grained Pipeline Parallelization for Network Function Programs [abstract] (IEEE Xplore, PDF) Seungbin Song, Heelim Choi, and Hanjun Kim Proceedings of the 2021 International Symposium on Code Generation
and Optimization (CGO), March 2021.
Sharing-aware Data Acquisition Scheduling for Multiple Rules in the IoT [abstract] (IEEE Xplore, DATASET, PDF) Seonyeong Heo, Seungbin Song, Bongjun Kim, and Hanjun Kim Proceedings of the IEEE Real-Time And Embedded Technology And Applications Symposium (RTAS), April 2020.
Accept Rate: 27% (29/107).
Spinal Code: Automatic Code Extraction for Near-User Computation in Fogs [abstract] (ACM DL, PDF) Bongjun Kim, Seonyeong Heo, Gyeongmin Lee, Seungbin Song, Jong Kim, and Hanjun Kim Proceedings of the 28th International Conference on
Compiler Construction (CC), February 2019.
Accept Rate: 40% (18/45).
RT-IFTTT: Real-Time IoT Framework with Trigger Condition-aware Flexible Polling Intervals
[abstract] (IEEE Xplore, PDF) Seonyeong Heo, Seungbin Song, Jong Kim, and Hanjun Kim 2017 IEEE Real-Time Systems Symposium (RTSS), December 2017.
Accept Rate: 23% (31/131).
Refereed International Journal Publications
ComFlex: Composable and Flexible Resource Management for the IoT [abstract] (IEEE Xplore) Gyeongmin Lee, Bongjun Kim, Seungbin Song, Seonyeong Heo, and Hanjun Kim IEEE Internet of Things Journal, Volume 8, Number 22, November 2021.
IF=9.936, Q1 (JCR 2019)
Refereed Domestic Publications
Data Plane Optimization with Pipeline Parallelism [abstract] Seungbin Song and Hanjun Kim Proceedings of the Korea Software Congress, December 2018.
Patents
Scheduling Apparatus and Method based on Data Sharing between Multiple Rules in IoT Environment [abstract] Hanjun Kim, Seungbin Song, Bongjun Kim, and Seonyeong Heo KR Patent Number 10-2382328-0000, March 2022.
Apparatus and Method for Parallelizing and Compiling Packet Processing Program [abstract] Hanjun Kim and Seungbin Song KR Patent Number 10-2236700-0000, March 2021.
Method for Static Analysis based on Data Dependence on Data Plane Towards Network Switch Parallelization, and Parallelization Apparatus using the same [abstract] Hanjun Kim and Seungbin Song KR Patent Number 10-2207775-0000, January 2021.
Theses
Static Analysis on Programmable Data Plane: Towards Network Switch Parallelization [abstract] Seungbin Song Master's Thesis, Department of Creative IT Engineering,
Pohang University of Science and Technology, June 2018.