속성:Context
하드웨어, 부하, 버전, 규모처럼 결과에 영향을 줄 수 있는 조건을 적습니다.
k
Venue: ASPLOS. Year: 2025.
Adding batches lengthens compute but activates more experts, which can increase I/O and create new pipeline bubbles.
Verification: author_preprint_full_text; confidence=medium. +
Venue: FAST. Year: 2024.
여러 캐시 크기를 따로 시뮬레이션하면 메모리·연산 비용이 크다.
Verification: abstract_only; confidence=high. +
kvaccel a novel write accelerator for lsm tree based kv stores with host ssd collaboration 968f5966 +
Venue: IPDPS. Year: 2025.
Host-managed LSM stores suffer write stalls and overhead, while KV SSDs alone do not preserve the conventional block interface.
Verification: conference paper PDF, DOI metadata, and arXiv preprint; confidence=high. +
kvcache cache in the wild characterizing and optimizing kvcache cache at a large cloud provider 0b39b53c +
Venue: USENIX ATC. Year: 2025.
KV-cache policies are often designed from synthetic multi-turn assumptions rather than cloud traces.
Verification: official USENIX paper PDF and arXiv abstract; confidence=high. +
l
Venue: OSDI. Year: 2018.
Monolithic kernels assume resources share one server and do not naturally support independent scaling or failure domains.
Verification: official USENIX page and abstract; confidence=high. +
Publication scope: domestic. Lab publication metadata:
1. 정진규, 서의성, "전력 상한 제한을 강제하는 수단으로써 동적 이전의 실효성 분석," 정보과학회논문지 시스템 및 이론, 제 39권, 제 4호, 2012년 8월
Verification level: official_abstract. Sources checked:
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART001685500
https://cslab.yonsei.ac.kr/publications +
Publication scope: domestic. Lab publication metadata:
1. 정환진, 강태호, 김규석, 신영호, 정진규, "대용량 분산처리 플랫폼 공유 모델 연구," 정보과학회 컴퓨팅의 실제 논문지, 제 22권 제 11호, pp. 601-613, 2016년 11월
Verification level: official_abstract. Sources checked:
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002164736
https://cslab.yonsei.ac.kr/publications +
Publication scope: domestic. Lab publication metadata:
1. 김준, 이준원, 정진규, "서브시스템의 빠른 구동을 위한 스냅샷 구동 기법 설계 및 구현," 정보처리학회 컴퓨터 통신 및 시스템, 제 3권, 제 7호, pp. 209-218, 2014년 7월
Verification level: official_abstract. Sources checked:
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART001899004
https://doi.org/10.3745/KTCCS.2014.3.7.209 +
Publication scope: domestic. Lab publication metadata:
1. 신석하, 이규선, 정진규, "고성능 저장장치 환경에서의 비동기적 미리 읽기의 인터럽트 대리 처리 효용성 연구", 2017 한국소프트웨어종합학술대회 (KSC 2017), Dec. 20~22, 2017
Verification level: metadata_only. Sources checked:
https://cslab.yonsei.ac.kr/publications +
Publication scope: domestic. Lab publication metadata:
1. 성민철, 권세준, 정진규, "메모리 부족상황에서 앱 실행시간에 관한 연구", 한국정보과학회 동계학술발표회 논문집, 2015 (최우수상, 학부생부문)
Verification level: metadata_only. Sources checked:
https://cslab.yonsei.ac.kr/publications +
Publication scope: domestic. Lab publication metadata:
1. 김성윤, 하성준, 안민우, 정진규, "하이퍼스레딩 환경에서의 저장장치 입출력 폴링 태스크 배치 기법," 2019 한국컴퓨터종합학술대회 (KCC 2019), 한국정보과학회 학술 발표논문집 pp. 2070-2072, 2019 (우수상, 학부생부문)
Verification level: partial_source. Source detail: official_abstract_partial. Sources checked:
https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE08763759
https://cslab.yonsei.ac.kr/publications +
light dedup a light weight inline deduplication framework for non volatile memory file systems 000ae22e +
Venue: USENIX ATC. Year: 2023.
전역 fingerprint index는 NVM 접근과 metadata amplification이 크다.
Verification: abstract_only; confidence=high. +
Venue: SOSP. Year: 2025.
MPS and existing schedulers have coarse control over thread-block execution, interference, and energy/capacity tradeoffs.
Verification: DOI metadata and the official SOSP program are recorded in the preserved review ledger; claim-bearing O/I/R source coverage remains pending; confidence=low. +
Venue: SOSP. Year: 2025.
High-frequency telemetry can produce millions of records per second; sampling or read-optimized indexing can drop rare events or add probe effect.
Verification: full_text; confidence=high. +
Publication scope: domestic. Lab publication metadata:
1. 한정민, 안민우, 정진규. "LSM-Tree의 읽기 성능 개선을 위한 병렬적 필터/인덱스 접근 기법," 정보과학회 컴퓨팅의 실제 논문지, 제 29권, 제 9호, pp. 444-449, 2023년 9월
Verification level: official_abstract. Sources checked:
https://www.kci.go.kr/kciportal/ci/sereArticleSearch/ciSereArtiView.kci?sereArticleSearchBean.artiId=ART002996539
https://doi.org/10.5626/KTCP.2023.29.9.444 +
Publication scope: domestic. Lab publication metadata:
1. 김가을, 안민우, 고동현, 정진규, "LSM-Tree 기반 키-값 저장소에서 대용량 데이터 로딩 기법 성능 분석", 2025 한국컴퓨터종합학술대회 (KCC 2025), 2025
Verification level: official_abstract. Sources checked:
https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE12318613
https://cslab.yonsei.ac.kr/publications +
m
Venue: ASPLOS. Year: 2025.
CPU schemes can confuse warm with hot pages and waste DRAM on pages containing only a few hot cache lines.
Verification: official DOI metadata and author project/publication page; confidence=high. +
Current Inventory V2 directly revalidates the immutable machine receipt and its artifact, file, semantic, and source-commit bindings. Repository/PR review records human accountability; final-run authorization remains a separate short-lived gate. +
Publication scope: international. Lab publication metadata:
1. Sejun Kwon, Sang-Hoon Kim, Jin-Soo Kim, and Jinkyu Jeong, "Managing GPU Buffers for Caching More Apps in Mobile Systems," in Proceedings of The ACM International Conference on Embedded Software (EMSOFT 2015), Amsterdam, The Netherlands, October 2015.
Verification level: official_abstract. Sources checked:
https://doi.org/10.1109/EMSOFT.2015.7318276
https://www.sigbed.org/emsoft-info/participants/Jeong%2C%20Jinkyu.html
https://yonsei.elsevierpure.com/en/publications/managing-gpu-buffers-for-caching-more-apps-in-mobile-systems/ +
Venue: OSDI. Year: 2024.
Intel Flat Memory Mode (FMM) is the first hardware-managed CXL tiering mechanism, but workload sensitivity creates large outliers.
Verification: full_text; confidence=high. +