속성:Context
하드웨어, 부하, 버전, 규모처럼 결과에 영향을 줄 수 있는 조건을 적습니다.
a
archer adaptive memory compression with page association rule awareness for high speed response 98bcc760 +
Venue: FAST. Year: 2025.
Conventional per-page compression misses repeated/correlated content and forces a fixed granularity.
Verification: official USENIX page and abstract; confidence=high. +
Publication scope: international. Lab publication metadata:
1. Sam Son, Seung Yul Lee, Yunho Jin, Jonghyun Bae, Jinkyu Jeong, Tae Jun Ham, Jae W. Lee, and Hongil Yoon, "ASAP: Fast Mobile Application Switch via Adaptive Prepaging", in Proceedings of The 2021 USENIX Annual Technical Conference (ATC'21), Virtual Event, July 2021
Verification level: full_text. Sources checked:
https://www.usenix.org/conference/atc21/presentation/son
https://www.usenix.org/system/files/atc21-son.pdf +
Venue: HotStorage. Year: 2024.
Conventional RAID assumes similar devices and lets the weakest member constrain capacity or speed.
Verification: official_abstract; confidence=medium. +
Venue: USENIX ATC. Year: 2019.
Verification level: full_text. Sources checked:
https://www.usenix.org/conference/atc19/presentation/lee-gyusun
https://www.usenix.org/system/files/atc19-lee-gyusun.pdf +
Venue: ASPLOS. Year: 2026.
Synchronous GPU-centric I/O stalls warps; CPU-managed asynchrony sacrifices GPU autonomy and adds coordination.
Verification: official DOI/publisher abstract; confidence=high. +
Venue: OSDI. Year: 2024.
캐시 footprint·miss·비밀 의존 접근은 수동 측정으로 입력 전반을 설명하기 어렵다.
Verification: abstract_only; confidence=high. +
Venue: SIGMOD. Year: 2022.
Read-after-writeback (RAW) stalls the foreground read until a dirty victim page is flushed to flash.
Verification: official_abstract; confidence=high. +
aware automate workload autoscaling with reinforcement learning in production cloud systems cb18da5e +
Venue: USENIX ATC. Year: 2023.
RL은 학습 비용·초기 안전성·워크로드 변화 때문에 운영 도입이 어렵다.
Verification: abstract_only; confidence=high. +
b
Authors: Jeonghyun Lee; Minwoo Ahn; Jisung Park; Jinkyu Jeong. Venue: IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED 2026). Year: 2026. Type: international conference paper.
Verification level: metadata_only. Sources checked:
https://www.islped.org/2026/final-program/
https://jisung-park.github.io/publications
https://cslab.yonsei.ac.kr/publications +
B200-2 target-generation migration runner, one-GPU sequential Qwen then Mistral collection, immutable effective vLLM snapshot. +
Publication scope: domestic. Lab publication metadata:
1. 안민우, 정진규. "bperf, BCOZ를 활용한 응용의 On-CPU, Off-CPU 동시 성능 프로파일링." 정보과학회지, vol. 43, no. 3, 2025, 42-49.
Verification level: partial_source. Source detail: metadata_and_toc. Sources checked:
https://www.dbpia.co.kr/journal/articleDetail?nodeId=NODE12102543
https://cslab.yonsei.ac.kr/publications +
Venue: MICRO. Year: 2024.
Existing mitigations protect rows globally, so one aggressive or malicious thread can impose refresh/repair overhead on all workloads.
Verification: full_text; confidence=high. +
Venue: ASPLOS. Year: 2024.
Kernel I/O is safe/shareable but slow; kernel-bypass frameworks require exclusive devices or application rewrites.
Verification: official DOI/ASPLOS abstract and arXiv paper; confidence=high. +
byteexpress a high performance and traffic efficient inline transfer of small payloads over nvme a7c01a49 +
Venue: HotStorage. Year: 2025.
For very small payloads, PRP setup and PCIe data movement dominate useful transfer work.
Verification: official DOI metadata and author publication page/abstract; confidence=high. +
c
Publication scope: international. Lab publication metadata:
1. Jinkyu Jeong, Joonwon Lee, and Euiseong Seo, "Cache Scheme of Shared-Buffer Mappings for Energy-Efficiency of Mobile Devices," Electronics Letters, vol. 51, no. 11, pp. 830-832, May 2015.
Verification level: official_abstract. Sources checked:
https://doi.org/10.1049/el.2015.0244
https://yonsei.elsevierpure.com/en/publications/cache-scheme-of-shared-buffer-mappings-for-energy-efficiency-of-m/ +
Venue: EuroSys. Year: 2025.
Full recomputation is slow, while naive KV reuse omits interactions created when chunks are concatenated.
Verification: arXiv abstract/full-text excerpts and DOI metadata; confidence=high. +
Venue: USENIX ATC. Year: 2023.
I/O 압력과 LSM 내부 작업이 클라우드 블록 저장소의 지연 스파이크를 증폭한다.
Verification: abstract_only; confidence=high. +
Venue: HotStorage. Year: 2024.
Block SSD cache updates trigger internal garbage collection and write amplification; ZNS exposes sequential zones but requires host management.
Verification: official_abstract; confidence=high. +
Publication scope: international. Lab publication metadata:
1. Euiseong Seo, Jinkyu Jeong, Seonyeong Park, Jinsoo Kim, and Joonwon Lee, "Catching Two Rabbits: Adaptive Real-Time Support for Embedded Linux," Software: Practice and Experience, Vol. 39, No. 5, pp. 531-550, April 2009
Verification level: official_abstract. Sources checked:
https://doi.org/10.1002/spe.911
https://yonsei.elsevierpure.com/en/publications/catching-two-rabbits-adaptive-real-time-support-for-embedded-linu/
https://koasas.kaist.ac.kr/handle/10203/93501 +
Venue: SOSP. Year: 2025.
Peak accelerator specifications obscure synchronization, operator support, and unified-bandwidth contention in real SoCs.
Verification: DOI metadata and the official SOSP listing are recorded in the preserved review ledger; claim-bearing O/I/R source coverage remains pending; confidence=low. +