본문으로 이동

속성:Observation

S3 연구 메모리

Text

직접 확인한 결과를 적습니다. 원인에 대한 해석은 따로 적습니다.

( | ) (20 | 50 | 100 | 250 | 500) 보기
이 속성을 사용하는 문서 20개를 보여줍니다.
a
archer adaptive memory compression with page association rule awareness for high speed response 98bcc760 +
workloads=mobile application launch, photo processing, and frame-rate workloads; baselines=state-of-the-art mobile memory compression; metrics=correlated-page share and application performance; results=about 25% correlated; 1.55x, 1.42x, and 1.31x improvements  +
asap fast mobile application switch via adaptive prepaging 3f9602cd +
8개 앱에서 vanilla Android 10 대비 switch time: Pixel 4 평균 22.2%/최대 33.3%, Pixel 3a 평균 28.3%/최대 35.7% 감소. CPU와 disk bandwidth utilization이 평균 각각 39.8%, 25.2% 증가; 예측 정확도는 file-backed 79.3%, anonymous 68.4%. 메타데이터는 앱당 평균 약 800 KB.  +
asymmetric raid rethinking raid for ssd heterogeneity bfd97257 +
workloads=fio 512 KiB partial-stripe write와 1 MiB full-stripe write microbenchmark; baselines=3 SATA SSD RAID, 1 SATA+2 NVMe mixed RAID, 3 NVMe SSD RAID; metrics=write bandwidth; results=단일 NVMe SSD는 SATA SSD보다 각각 5.31배/5.35배 빠르지만 mixed RAID는 all-NVMe RAID 성능의 16.2%/16.1%에 그쳤다. 논문은 Asym-RAID data organization을 제안하지만 구현된 prototype, end-to-end capacity/performance, rebuild 평가는 제공하지 않는다.  +
asynchronous i o stack a low latency kernel i o stack for ultra low latency ssds 4b00ffc9 +
Optane의 4KB random read를 single-digit microseconds로 낮췄다. FIO 지연은 15-33% 감소했고 random read는 최대 33%, random write는 최대 31% 감소했다. RocksDB IOPS는 11-44%, Filebench와 OLTP 처리량은 15-30% 증가했다.  +
asynchrony and gpus bridging this dichotomy for i o with agio 6fab41bf +
workloads=known-pattern and data-dependent GPU I/O workloads; baselines=synchronous GPU-centric I/O; metrics=performance and compute-engine use; results=up to 65% and 32% improvement; <50% compute engines for equal/better performance  +
automatically reasoning about how systems code uses the cpu cache 11306b93 +
workloads=4 TCP stacks; 7 OpenSSL algorithms; 51 Hyperkernel syscalls; 2 hash tables; baselines=manual cache analysis; metrics=footprint; hits/misses; bug/vulnerability discovery; results=Found performance bugs, vulnerabilities, and third-party cache impacts; no aggregate numeric speedup in abstract.  +
avoiding read stalls on flash storage 34c6809a +
workloads=MySQL/InnoDB; Zero; baselines=RAW read-after-writeback; metrics=transaction throughput; read latency; stall time; results=up to 2.9x transaction throughput  +
aware automate workload autoscaling with reinforcement learning in production cloud systems cb18da5e +
workloads=production cloud serving and training workloads; baselines=transfer learning; metrics=adaptation speed; reward; utilization; SLO violations; results=5.5× faster adaptation; +47.5% CPU/+39.2% memory utilization; 16.9× fewer SLO violations in training.  +
b
beyond static policies dynamic prac for balanced and efficient rowhammer mitigation edd7af08 +
No verified technical results are publicly available as of 2026-07-17.  +
bind only vllm rpc sockets to a short private path 4bf9d75f +
A fresh project-venv child preserved the long private tempfile.gettempdir(), imported vllm.envs with the explicit short VLLM_RPC_BASE_PATH, and successfully bound and closed a real zmq.PAIR IPC socket. A separate regression proved that a surviving child process group is terminated even when its launcher exits first. Focused tests: 34 passed; full scripts suite before the final cleanup-only test: 283 passed; all changed-file pre-commit hooks passed.  +
bperf bcoz on cpu off cpu 3b259a81 +
공개 메타데이터와 목차에는 독립적인 정량 평가 결과가 제시되지 않는다.  +
breakhammer enhancing rowhammer mitigations by carefully throttling suspect threads 19eb947b +
workloads=eight RowHammer mitigation mechanisms; baselines=each mitigation without BreakHammer; metrics=performance; DRAM energy; fairness; area; results=improves all evaluated mitigations; near-zero area overhead  +
bypassd enabling fast userspace access to shared ssds da9e5d79 +
workloads=4 KB I/O microbenchmarks and WiredTiger; baselines=Linux and SPDK; metrics=latency and application performance; results=42% lower 4 KB latency vs Linux; near SPDK; about 20% WiredTiger improvement  +
byteexpress a high performance and traffic efficient inline transfer of small payloads over nvme a7c01a49 +
workloads=sub-page NVMe payload microbenchmarks on Linux/OpenSSD; baselines=PRP and prior small-I/O method; metrics=PCIe traffic and latency; results=up to 98% less traffic; 40% and 39% lower latency  +
c
cache scheme of shared buffer mappings for energy efficiency of mobile devices 4b6db791 +
상용 smartphone system 대비 video playback 중 processor utilization 약 64%, energy consumption 약 17% 감소를 보고한다.  +
cacheblend fast large language model serving for rag with cached knowledge fusion 056a5f5e +
workloads=three open-source LLMs; four QA/RAG/summarization datasets; baselines=full KV recomputation and naive full reuse; metrics=quality, TTFT, throughput, recomputed-token share; results=<15% typical recomputation; 2.2–3.3x TTFT and 2.8–5x throughput improvement  +
calcspar a contract aware lsm store for cloud storage with low latency spikes accc7c9d +
workloads=Amazon EBS; real-world workloads; baselines=state-of-the-art LSM stores; metrics=p99 latency; average latency; read/write performance; results=p99 <550 μs; average latency -66%.  +
can zns ssds be better storage devices for persistent cache 3ff8980a +
workloads=Cachebench; RocksDB with ZNS secondary cache; baselines=compatible regular SSD; F2FS-based cache; three ZNS integration schemes; metrics=throughput; cache hit ratio; write amplification; capacity; results=qualitative tradeoff study; no numeric result in primary abstract  +
catching two rabbits adaptive real time support for embedded linux ee13b80e +
open-source benchmarks에서 기존 접근과 같거나 더 나은 scheduling latency를 유지하면서 throughput을 개선했다. 공식 초록에는 수치가 없다.  +
characterizing mobile soc for accelerating heterogeneous llm inference 6b900bb7 +
workloads=mobile LLM inference on Snapdragon 8 Gen 3; baselines=GPU-only and NPU-only; metrics=inference speed; results=1.34–6.02x speedup  +
원본 주소 "https://s3wiki.yonsei.ac.kr/index.php?title=속성:Observation&oldid=147"