속성:Evidence overview
관련 자료를 짧게 정리합니다. 자세한 인용은 자료 항목에 따로 적습니다.
o
Orca: A Distributed Serving System for Transformer-Based Generative Models. OSDI 2022. +
Overcoming the Memory Wall with CXL-Enabled SSDs. USENIX ATC 2023. +
ozz identifying kernel out of order concurrency bugs with in vivo memory access reordering 0b85f639 +
OZZ: Identifying Kernel Out-of-Order Concurrency Bugs with In-Vivo Memory Access Reordering. SOSP 2024. +
p
PaCaR: Improved Buffered I/O Locality on NUMA Systems with Page Cache Replication. EuroSys 2026. +
PACT: A Criticality-First Design for Tiered Memory. ASPLOS 2026. +
Paella: Low-latency Model Serving with Software-defined GPU Scheduling. SOSP 2023. +
papi exploiting dynamic parallelism in large language model decoding with a processing in memory 5f9f53cc +
PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System. ASPLOS 2025. +
partial failure resilient memory management system for cxl based distributed shared memory 48948c1d +
Partial Failure Resilient Memory Management System for (CXL-based) Distributed Shared Memory. SOSP 2023. +
pegasus tolerating skewed workloads in distributed storage with in network coherence directories a4e8c8ec +
Pegasus: Tolerating Skewed Workloads in Distributed Storage with In-Network Coherence Directories. OSDI 2020. +
Publication record 1: Jaehyun Song, Hwanjin Jeong, Jinkyu Jeong, "Performance Optimization of Object Tracking Algorithms in OpenCV on GPUs," Applied Sciences, Vol. 12, Issue 15, pp. 7801, 2022, doi.org/10.3390/app12157801 +
Ruiming Lu et al., "Perseus: A Fail-Slow Detection Framework for Cloud Storage Systemss", FAST 2023.
Source: https://www.usenix.org/conference/fast23/presentation/lu
Verification basis: official_abstract.
Canonical evidence ID: canonical-paper-v2-4e24f100 +
PET: Proactive Demotion for Efficient Tiered Memory Management. EuroSys 2025. +
PhasedRR: Read Reclaim Scheduling without Page-level Access Counting. MSST 2024. +
pit optimization of dynamic sparse deep learning models via permutation invariant transformation 48509ad0 +
PIT: Optimization of Dynamic Sparse Deep Learning Models via Permutation Invariant Transformation. SOSP 2023. +
Source commit 038c9cd00c25fc83678d4d698f8780bfc5d96369; package SHA-256 1ec47d04bc7a0c8ba60f0c3ee615ce0bc9d3026dcbd491c8587a7b5cd65bf781; native SHA-256 0e9b15201e3a6b57a759d138d45098d556b1298ede260dc2388e63e43f83b250; 282 offline pivot tests, 75 scheduler tests, 55 focused tests, and pre-commit passed. +
failed pre-GPU tmux attempt at source commit 01031e6e484bbd98e00bdc3320f77c45d292f6e1; fixed by commit 8ca2dbb68 adding exact .gitignore entries; no artifact or performance data produced +
Source commit 8ca2dbb68d202a8ba8b4ae226b64d77ec3e604ca; failure before bundle creation and GPU compute; logical modules and external target byte hashes independently inspected. +
research/EXPERIMENT_PROTOCOL_V1.md; research/CALIBRATION_PIPELINE_V1.md; scripts/pivot_calibration/generation.py; scripts/pivot_experiment/run_plan.py; scripts/pivot_experiment/cell_worker.py; B200-2 read-only preflight on 2026-07-17 +
Source commit 038c9cd00c25fc83678d4d698f8780bfc5d96369; final calibration pipeline SHA-256 e53f9fca2af42180a8b2b834987788f19e70951e6f2e9d5854e4b81abc13d82e; focused portability tests and full offline suite passed. +
Pane command-not-found at 2026-07-17; no global lock owner, no run directory, and zero B200 compute processes. +