본문으로 이동

속성:Applicability

S3 연구 메모리

Text

이 메모가 맞는 조건과 예외를 적습니다.

( | ) (20 | 50 | 100 | 250 | 500) 보기
이 속성을 사용하는 문서 20개를 보여줍니다.
e
Checkpoint, journaling, compaction이 foreground request와 경합하는 database 및 key-value store에 높다.  +
공간·분석 데이터 ingest KV. Limits: 효과가 spatial locality에 의존하고 일반 YCSB에서는 우위가 작다.  +
ETL, ML 파이프라인, stateful serverless DAG. Limits: annotation 정확성과 외부 부작용의 멱등성·커밋 가정에 의존한다.  +
느린 dedicated subsystem core와 빠른 application CPU가 공존하는 mobile SoC boot 또는 startup 경로에 해당한다.  +
장시간 GPU batch/HPC job을 호스팅하는 VM 환경에 해당하며, fine-grained multi-tenant inference에는 그대로 일반화할 수 없다.  +
Persistent-memory, CXL-memory, and other high-latency memory filesystems with controllable on-chip DMA. Limits: Only an official institutional summary is preserved, so exact workloads, baselines, and all quantitative breakdowns remain unverified.  +
Applications that need in-process programmable extensions at low latency. Limits: Constrained by eBPF/verifier expressiveness and MPK availability; exact overhead was not extracted.  +
Data-intensive Linux applications needing custom allocation, migration, or reclamation. Limits: Applications must supply useful policy semantics; correctness and benefit remain policy- and backend-dependent.  +
f
Serverless/FaaS clusters with a remote memory pool. Limits: Relies on function lifetime/access regularity, remote-memory bandwidth, and evaluated serverless workloads.  +
Low-latency core scheduling and colocated services on UINTR/MPK-capable CPUs. Limits: Requires userspace interrupts, MPK, shared-process abstractions, and constrained syscall behavior; numeric evaluation not verified.  +
Linux networking, observability, and in-kernel extension frameworks. Limits: Runtime checks, cancellation, and verifier assumptions remain in the TCB; full upstream integration is incomplete.  +
On-device LLM inference on SoCs with CPU, GPU, and NPU. Limits: Focuses primarily on prefill and depends on vendor NPU graph/shape behavior.  +
Linux tracing, observability, and security instrumentation. Limits: Needs toolchain/kernel-layout changes; some code and architectures remain unsupported.  +
Linux VM prefetch experimentation and workload-specific deployment. Limits: The demonstrated domain is prefetching; eBPF verifier and helper interfaces bound policy expressiveness.  +
웹·블록·객체 캐시. Limits: 결과는 트레이스와 캐시 크기에 의존하고 모든 워크로드에서 우세하지는 않다.  +
다단계 LSM-tree의 filter-block cache miss 경로.  +
Multi-tenant cloud SSD virtualization and programmable storage. Limits: RL behavior depends on training coverage, reward tuning, trace stationarity, programmable-device features, and SLO definitions.  +
Linux heterogeneous/tiered-memory systems. Limits: Tuning and gains depend on hardware counters, memory topology, migration costs, and workload phase length.  +
데이터 집약 serverless workflow. Limits: 새 bucket/trigger 프로그래밍 모델 도입이 필요하고 정확한 수치는 초록에 없다.  +
DRAM-less UFS/eMMC 설계와 host-managed flash metadata 가속에 높음; 상용 적용에는 firmware 변경 필요.  +