성균관대학교 소프트웨어학과 | 교수소개

딥러닝 컴파일러 
빅데이터 분석 시스템 
비휘발성 메모리를 위한 시스템SW

(2024) GPU thread throttling for page-level thrashing reduction via static analysis. JOURNAL OF SUPERCOMPUTING. 80, 7
(2021) Idempotence-Based Preemptive GPU Kernel Scheduling for Embedded Systems. IEEE TRANSACTIONS ON COMPUTERS. 70, 3
(2019) Static code transformations for thread-dense memory accesses in GPU computing. CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE. 32, 5
(2018) Thread Scheduling for GPU-Based OPC Simulation on Multi-thread. Proceedings SPIE 10587, Optical Microlithography XXXI. 10587, 1
(2017) Efficient Memory Mapped File I/O for In-Memory File Systems. USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage'17). 1, 1
(2012) Efficient SIMD Code Generation for Irregular Kernels. ACM SIGPLAN NOTICES. 47, 8

서비스형 함수 환경에서의 함수 실행 방법. 10-2022-0160782. 20250430. 대한민국
이종 컴퓨팅 클라우드의 컴퓨팅 유닛 동적 재조립 방법 및 장치. 10-2021-0192932. 20240528. 대한민국
Method of handling page fault in nonvolatile main memory system. US 15/264,628. 20200721. 미국
Memory mapping management method for nonvolatile main memory system. US 15/365,991. 20190122. 미국

(2023) Performance Analysis of ZNS-aware Filesystems on Distributed Applications. IEEE International Conference on Distributed Computing Systems. 홍콩
(2023) Accelerating Deep Neural Networks on Mobile Multicore NPUs. International Symposium on Code Generation and Optimization. 캐나다
(2021) Libpubl: exploiting persistent user buffers as logs for write atomicity. ACM Workshop on Hot Topics in Storage and File Systems (HotStorage). 미국
(2020) SimFL: FPGA 호스트 최적화 프로그래밍 인터페이스. 한국소프트웨어종합학술대회 (KSC). 대한민국
(2020) Libnvmmio: Reconstructing Software IO Path with Failure-Atomic Memory-Mapped Interface. USENIX Annual Technical Conference. 미국
(2017) Compiler-Assisted Preloading in the Shared Memory for Thread-Dense Memory Requests. Workshop on Extreme-Scale Programming Tools (ESPT'17). 미국

교수소개