Bodon Jeong

dblp:207/3533 · DBLP profile ↗
← Back
3ranked-venue papers
2as first author
3since 2021 · last 2026
0009-0006-2460-2374ORCID · corroborated

Domains — the database's venue-derived domains; a paper can count in several

Systems, architecture and hardware · 3 · 2 first-author · 3 since 2021
YearPublicationVenuePosition
2026 Quicktopia: Iteration-Level GPU Frequency Control for Energy-Latency Co-Optimization in LLM Inference
Soyang Baek, Bodon Jeong, Hongsu Byun, Sungyong Park
CCGrid2
2026 Dual-Blade: Dual-Path NVMe-Direct KV-Cache Offloading for Edge LLM Inference
Bodon Jeong, Hongsu Byun, Youngjae Kim 0001, Weikuan Yu, Kyungkeun Lee, Jihoon Yang, Sungyong Park
ICDCS1
2025 PACMAN: Power Usage-Aware Capping and Management for All-Flash Storage Servers
abstract
Recently, power management has become increasingly important in storage-centric infrastructures, where SSD arrays are emerging as major power consumers. In such environments, static storage power capping (SSPC) has been used to reduce the peak power consumption of SSD arrays by fixing the power states of individual devices, aiming to stay within constrained power budgets. However, SSPC does not account for workload I/O characteristics or internal SSD behaviors such as garbage collection. This often leads to over-capping, which degrades performance, or underutilization of available power. To address these limitations, we propose PACMAN, a power usageaware capping and management framework designed for the storage layer in all-flash storage servers. PACMAN dynamically reallocates SSD power caps in real time through predictive adjustments based on recent per-device power usage. Without relying on performance counters, PACMAN efficiently adapts to workload variability and optimizes performance and energy efficiency within a given power budget. PACMAN has been extensively evaluated using both the FIO benchmark and a realworld application, RocksDB. Compared with SSPC, PACMAN improved throughput by up to 41% and energy efficiency by up to 24%.
Bodon Jeong, Hongsu Byun, Kyungkeun Lee, Bumjun Kim, Jeong-Uk Kang, Sungyong Park
MASCOTS1