BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260522T150115Z
LOCATION:D170
DTSTART;TZID=America/Chicago:20181111T121400
DTEND;TZID=America/Chicago:20181111T123000
UID:submissions.supercomputing.org_SC18_sess149_ws_mchpc108@linklings.com
SUMMARY:Data Placement Optimization in GPU Memory Hierarchy Using Predicti
 ve Modeling
DESCRIPTION:Larisa Stoltzfus (University of Edinburgh) and Murali Emani, P
 ei-Hung Lin, and Chunhua Liao (Lawrence Livermore National Laboratory)\n\n
 Modern supercomputers often use Graphic Processing Units (or GPUs) to meet
  the ever-growing demands for high performance computing. GPUs typically h
 ave a complex memory architecture with various types of memories and cache
 s, such as global memory, shared memory, constant memory, and texture memo
 ry.The placement of data on these memories has a tremendous impact on the 
 performance of the HPC applications and identifying the optimal placement 
 location is non-trivial. \n \nIn this paper, we propose a machine learning
 -based approach to determine the best class of GPU memory that will minimi
 ze GPU kernel execution time. The machine learning process utilizes a set 
 of performance counters obtained from profiling runs and combines with rel
 evant hardware features to generate trained models. We evaluate our approa
 ch on several generations of NVIDIA GPUs, including Kepler, Maxwell, Pasca
 l, and Volta on a set of benchmarks. The results show that the trained mod
 els achieve prediction accuracies over 90%.\n\nTag: Memory, NVRAM, Paralle
 l Programming Languages, Libraries, and Models\n\nRegistration Category: W
 orkshop Reg Pass\n\nSession Chairs: Ron Brightwell (Sandia National Labora
 tories); Maya Gokhale (Lawrence Livermore National Laboratory (LLNL)); Xia
 n-He Sun (Illinois Institute of Technology); and Yonghong Yan (University 
 of North Carolina, Charlotte)\n\n
END:VEVENT
END:VCALENDAR