The search functionality is under construction.

Author Search Result

[Author] Jae W. LEE(4hit)

1-4hit
  • Right-Angle H-Plane Waveguide Double Bend

    Jae W. LEE  Hyo J. EOM  Kazunori UCHIDA  

     
    LETTER-Antennas and Propagation

      Vol:
    E77-B No:12
      Page(s):
    1647-1649

    A simple solution for the right-angle H-plane waveguide double bend is obtained in analytic series form. The simultaneous equations are solved to obtain the transmission and reflection coefficients in fast convergent series forms. The numerical computations are performed to show the behaviors of the transmission coefficient versus frequency.

  • Eager Memory Management for In-Memory Data Analytics

    Hakbeom JANG  Jonghyun BAE  Tae Jun HAM  Jae W. LEE  

     
    LETTER-Computer System

      Pubricized:
    2018/12/11
      Vol:
    E102-D No:3
      Page(s):
    632-636

    This paper introduces e-spill, an eager spill mechanism, which dynamically finds the optimal spill-threshold by monitoring the GC time at runtime and thereby prevent expensive GC overhead. Our e-spill adopts a slow-start model to gradually increase the spill-threshold until it reaches the optimal point without substantial GCs. We prototype e-spill as an extension to Spark and evaluate it using six workloads on three different parallel platforms. Our evaluations show that e-spill improves performance by up to 3.80× and saves the cost of cluster operation on Amazon EC2 cloud by up to 51% over the baseline system following Spark Tuning Guidelines.

  • Layerweaver+: A QoS-Aware Layer-Wise DNN Scheduler for Multi-Tenant Neural Processing Units

    Young H. OH  Yunho JIN  Tae Jun HAM  Jae W. LEE  

     
    LETTER-Fundamentals of Information Systems

      Pubricized:
    2021/11/11
      Vol:
    E105-D No:2
      Page(s):
    427-431

    Many cloud service providers employ specialized hardware accelerators, called neural processing units (NPUs), to accelerate deep neural networks (DNNs). An NPU scheduler is responsible for scheduling incoming user requests and required to satisfy the two, often conflicting, optimization goals: maximizing system throughput and satisfying quality-of-service (QoS) constraints (e.g., deadlines) of individual requests. We propose Layerweaver+, a low-cost layer-wise DNN scheduler for NPUs, which provides both high system throughput and minimal QoS violations. For a serving scenario based on the industry-standard MLPerf inference benchmark, Layerweaver+ significantly improves the system throughput by up to 266.7% over the baseline scheduler serving one DNN at a time.

  • Scattering from a Folded Short in Parallel-Plate Waveguide

    Jae W. LEE  Hyo J. EOM  

     
    LETTER->Communication Cable and Wave Guide

      Vol:
    E78-B No:10
      Page(s):
    1424-1426

    A folded short in parallel-plate waveguide is investigated using the Fourier transform and the mode-matching. A fast-converging series solution for scattering from the folded short is obtained and its characteristics are presented. Our solution for the E-plane short agrees well with measurements and is numerically more efficient than the existing moment-method solution. The presented scattering characteristics are useful for the design of the E- and H -plane shorts in rectangular waveguide.