Sangwon Lee

Orcid: 0000-0001-6960-5487

Affiliations:
  • KAIST, Daejeon, South Korea
  • Panmnesia, Inc., South Korea


According to our database1, Sangwon Lee authored at least 9 papers between 2020 and 2023.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2023
Failure Tolerant Training With Persistent Memory Disaggregation Over CXL.
IEEE Micro, 2023

Memory Pooling With CXL.
IEEE Micro, 2023

Cache in Hand: Expander-Driven CXL Prefetcher for Next Generation CXL-SSD.
Proceedings of the 15th ACM/USENIX Workshop on Hot Topics in Storage and File Systems, 2023

2022
PreGNN: Hardware Acceleration to Take Preprocessing Off the Critical Path in Graph Neural Networks.
IEEE Comput. Archit. Lett., 2022

Direct Access, High-Performance Memory Disaggregation with DirectCXL.
Proceedings of the 2022 USENIX Annual Technical Conference, 2022

LightPC: hardware and software co-design for energy-efficient full system persistence.
Proceedings of the ISCA '22: The 49th Annual International Symposium on Computer Architecture, New York, New York, USA, June 18, 2022

Large-scale Graph Neural Network Services through Computational SSD and In-Storage Processing Architectures.
Proceedings of the 2022 IEEE Hot Chips 34 Symposium, 2022

Hardware/Software Co-Programmable Framework for Computational SSDs to Accelerate Deep Learning Service on Large-Scale Graphs.
Proceedings of the 20th USENIX Conference on File and Storage Technologies, 2022

2020
TensorPRAM: Designing a Scalable Heterogeneous Deep Learning Accelerator with Byte-addressable PRAMs.
Proceedings of the 12th USENIX Workshop on Hot Topics in Storage and File Systems, 2020


  Loading...