The CODE (Computing Optimization and Data-driven Exploration) Lab is a research lab led by Professor Hyojin Sung in the graduate school of data science of Seoul National University (SNU).
We are committed to designing new compilers and innovating the modern compilers to improve performance and energy-efficiency of various modern applications and hardware systems. In particular, We aim at making the compiler better support the ML/DL applications, emerging hardware systems such as PIM/NDP, and Next-generation supercomputers.
We are actively looking for outstanding graduate and undergraduate students and postdoctoral researchers. If you have any questions, please do not hesitate to contact Prof. Hyojin Sung for further information.
News
[Jun. 27, 2024] Our paper titled "NavCim: Comprehensive Design Space Exploration for Analog Computing-in-Memory Architectures (Accepted)" has been accepted at International Conference on Parallel Architectures and Compilation Techniques (PACT)!
[Jul. 21, 2023] Our paper titled "Multi-Objective Architecture Search and Optimization for Heterogeneous Neuromorphic Architecture" has been accepted at International Conference on Computer-Aided Design (ICCAD)!
[Jul. 21, 2023] Our paper titled "PRIMO: A Full-Stack Processing-in-DRAM Emulation Framework for Machine Learning Workloads" has been accepted at International Conference on Computer-Aided Design (ICCAD)!
[Feb. 20, 2023] Yoon-ho Choi (PhD student), Jieun Lee (Integrated MS/PhD student), Boseok Kim (MS student), and Jung-ho Lee (MS student) have joined our lab.
[Feb. 10, 2023] Our paper titled "XLA-NDP: Efficient Scheduling and Code Generation for DL Model Training on Near-Data Processing Memory" has been published in IEEE Computer Architecture Letters (CAL)!
[Nov. 07, 2022] Our paper titled "PIMFlow: Compiler and Runtime Support for CNN Models on Processing-in-Memory DRAM with Mixed-Parallel Execution Model" is accepted for publication in IEEE/ACM International Symposium on Code Generation and Optimization (CGO)!