Publications

2024 

• Low-overhead General-purpose Near-Data Processing in CXL Memory Expanders (Accepted)
  Hyungkyu Ham*, Jeongmin Hong*, Geonwoo Park, Yunseon Shin, Okkyun Woo, Wonhyuk Yang, Jinhoon Bae, Eunhyeok Park, Hyojin Sung, Euicheol Lim, Gwangsun Kim (*: co-first authors)
  The 57th IEEE/ACM International Symposium on Microarchitecture (MICRO) (Acceptance rate: 22.7%)

• NavCim: Comprehensive Design Space Exploration for Analog Computing-in-Memory Architectures (Accepted)
  Juseong Park*, Boseok Kim*, Hyojin Sung  (*: co-first authors)
  International Conference on Parallel Architectures and Compilation Techniques (PACT)

2023 

• Multi-Objective Architecture Search and Optimization for Heterogeneous Neuromorphic Architecture
  Juseong Park, Yongwon Shin, Hyojin Sung
  IEEE/ACM  International Conference on Computer-Aided Design (ICCAD)
  
  

• PRIMO: A Full-Stack Processing-in-DRAM Emulation Framework for Machine Learning Workloads
  Jaehoon Heo, Yongwon Shin, Sangjin Choi, Sungwoong Yune, Junghoon Kim, Hyojin Sung, Youngjin Kwon, Joo-Young Kim
  IEEE/ACM  International Conference on Computer-Aided Design (ICCAD)
  
  

• XLA-NDP: Efficient Scheduling and Code Generation for DL Model Training on Near-Data Processing Memory
  Jueon Park, Hyojin Sung
  IEEE Computer Architecture Letters (CAL)
  
  

• PIMFlow: Compiler and Runtime Support for CNN Models on Processing-in-Memory DRAM with Mixed-Parallel Execution Model  [Link]
  Yongwon Shin*, Juseong Park*, Sungjun Cho, Hyojin Sung (*: co-first authors)
  IEEE/ACM International Symposium on Code Generation and Optimization (CGO)

2022

• Runtime Support for Accelerating CNN Models on Digital DRAM Processing-in-Memory Hardware  [Link]
  Yongwon Shin, Juseong Park, Jeongmin Hong, Hyojin Sung
  IEEE Computer Architecture Letters (CAL)
  
  

• One-Shot Tuner for Deep Learning Compilers  [Link]
  Jaehun Ryu, Eunhyeok Park, Hyojin Sung
  International Conference on Compiler Construction (CC)

2021

• MetaTune: Meta-Learning Based Cost Model for Fast and Efficient Auto-tuning Frameworks  [Link]
  Jaehun Ryu, Hyojin Sung
  Arxiv

• Near-Data Processing in Memory Expander for DNN Acceleration on GPUs  [Link]
  Hyungkyu Ham*, Hyunuk Cho*, Minjae Kim, Jueon Park, Jeongmin Hong, Hyojin Sung, Eunhyeok Park, Euicheol Lim, Gwangsun Kim (*: co-first authors)
  IEEE Computer Architecture Letters (CAL)
  
  

• Hybrid Register Allocation with Spill Cost and Pattern Guided Optimization  [Link]
  Yongwon Shin, Hyojin Sung
  International Workshop on Languages and Compilers for Parallel Computing (LCPC)

2017

• Efficient Fork-Join on GPUs Through Warp Specialization  [Link]
  A. C.Jacob, A. E. Eichenberger, H. Sung, S. F. Antao, G. Bercea, C. Bertolli, A. Bataev, T. Jin, T. Chen, Z. Sura, G. Rokos, K. O'Brien
  IEEE 24th International Conference on High Perforamcne Computing (HiPC)
  
  

• Leveraging OpenMP 4.5 Support in CLANG for Fortran  [Link]
  Hyojin Sung, Tong Chen, Zehra Sura, Tarique Islam
  The 13th international workshop on OpenMP (IWOMP)
  
  

• Implementing implicit OpenMP data sharing on GPUs  [Link]
  Gheorghe-Teodor Bercea, Carlo Bertolli, Arpith C. Jacob, Alexandre E. Eichenberger, Alexey Bataev, Georgios Rokos, Hyojin Sung, Tong Chen, Kevin O’Brien
  The Fourth Workshop on the LLVM Compiler Infrastructure in HPC at SC'17

2016

• Offloading Support for OpenMP in Clang and LLVM  [Link]
  Samuel F. Ant˜ao, Alexey Bataev, Arpith C. Jacob, Gheorghe-Teodor Bercea, Alexandre E. Eichenberger, Georgios Rokos, Matt Martineau, Tian Jin, Guray Ozen, Zehra Sura, Tong Chen, Hyojin Sung, Carlo Bertolli, Kevin O’Brien
  The Fourth Workshop on the LLVM Compiler Infrastructure in HPC at SC'16
  
  

• Performance Analysis and Optimization of Clang’s OpenMP 4.5 GPU Support  [Link]
  Matt Martineau, Simon McIntosh-Smith, Carlo Bertolli, Arpith C. Jacob, Samuel F. Ant˜ao, Alexandre E. Eichenberger, Gheorghe-Teodor Bercea, Tong Chen, Tian Jin, Kevin O’Brien, Georgios Rokos, Hyojin Sung, Zehra Sura
  The 7th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS16) at SC'16
  
  

• Automatic Copying of Pointer-based Data Structures  [Link]
  Tong Chen, Zehra Sura, Hyojin Sung
  The 29th International Workshop on Languages and Compilers for Parallel Computing (LCPC)

2015

• Integrating GPU Support for OpenMP Offloading Directives into Clang  [Link]
  Carlo Bertolli, Samuel Antao, Gheorghe-Theodor Bercea, Arpith Jacob, Alexandre Eichenberger, Tong Chen, Zehra Sura, Hyojin Sung, Georgious Rokos, David Appelhans, Kevin O’Brien
  The Second Workshop on the LLVM Compiler Infrastructure in HPC at SC'15
  
  

• Performance Analysis of OpenMP on a GPU Using a CORAL Proxy Application  [Link]
  Gheorghe-Teodor Bercea, Carlo Bertolli, Samuel F. Antao, Arpith C. Jacob, Alexandre E. Eichenberger, Tong Chen, Zehra Sura, Hyojin Sung, Georgios Rokos, David Appelhans, Kevin O’Brien
  The 6th International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS15) at SC'15
  
  

• Towards Performance Portable GPU Programming with RAJA  [Link]
  Arpith C. Jacob, Samuel F. Antao, Hyojin Sung, Alexandre Eichenberger, Carlo Bertolli, Gheorghe-Teodor Bercea, Tong Chen, Zehra Sura, Georgios Rokos, Kevin O’Brien
  The Workshop on Portability Among HPC Architectures for Scientific Applications at SC'15
  
  

• Eliminating On-Chip TrafficWaste: Are We There Yet?  [Link]
  Robert Smolinski, Rakesh Komuravelli, Hyojin Sung, Sarita V. Adve
  2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) (poster presentation)
  
  

• DeNovoSync: Efficient Support for Arbitrary Synchronization without Writer-Initiated Invalidations  [Link]
  Hyojin Sung, Sarita V. Adve
  20th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)

2014

• DeNovoND: Efficient Hardware Support for Disciplined Non-Determinism  [Link]
  Hyojin Sung, Rakesh Komuravelli, Sarita V. Adve
  IEEE Micro Top Picks from the Computer Architecture Conferences

2013

• DeNovoND: Efficient Hardware Support for Disciplined Non-Determinism  [Link]
  Hyojin Sung, Rakesh Komuravelli, Sarita V. Adve
  18th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)

2011

• DeNovo: Rethinking the Memory Hierarchy for Disciplined Parallelism  [Link]
  Byn Choi, Rakesh Komuravelli, Hyojin Sung, Robert Smolinski, Nima Honarmand, Sarita V. Adve, Vikram S. Adve, Nicholas P. Carter, Ching-Tsun Chou
  20th International Conference on Parallel Architectures and Compilation Techniques (PACT) (citation count: 118)
  Best Paper Award

2010

• Parallel SAH k-D Tree Construction  [Link]
  Byn Choi, Rakesh Komuravelli, Victor Lu, Hyojin Sung, Robert L. Bocchino, Sarita V. Adve, John C. Hart
  High Performance Graphics (HPG) (citation count: 102)
  
  

• DeNovo: Rethinking Hardware for Disciplined Parallelism  [Link]
  Byn Choi, Rakesh Komuravelli, Hyojin Sung, Robert Bocchino, Sarita V. Adve, Vikram V. Adve
  Second USENIX Workshop on Hot Topics in Parallelism (HotPar)
  
  

• A Language for Deterministic-by-Default Parallel Programming  [Link]
  Robert Bocchino, Vikram Adve, Danny Dig, Sarita Adve, Stephen Heumann, Rakesh Komuravelli, Jeffrey Overbey, Patric Simmons, Hyojin Sung, Mohsen Vakillian
  15th Workshop on Compilers and Parallel Computing (CPC)

2009

• A Type and Effect System for Deterministic Parallel Java  [Link]
  Robert Bocchino, Vikram Adve, Danny Dig, Sarita Adve, Stephen Heumann, Rakesh Komuravelli, Jeffrey Overbey, Patric Simmons, Hyojin Sung, Mohsen Vakillian
  The International Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA)
  
  

• A Portable MATLAB Front-End for Tiled Microprocessors  [Link]
  Hyojin Sung
  Master Thesis, http://roger.ucsd.edu/record=b6636516˜S7