BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152640Z
LOCATION:Exhibit Hall
DTSTART;TZID=America/Los_Angeles:20260728T175300
DTEND;TZID=America/Los_Angeles:20260728T175300
UID:dac_DAC 2026_sess306_WIP3286@linklings.com
SUMMARY:GZswap: Mitigating GPU I/O Bottlenecks in Heterogeneous Memory Sys
 tems through On-Device Zswap
DESCRIPTION:Boyeol Choi, Sanghyun Park, Sanyhyun Hong, and Jungrae Kim (Su
 ngkyunkwan University)\n\nModern GPUs face a memory capacity wall as large
 -scale workloads outgrow practical device-memory limits. Scale-up designs 
 with heterogeneous memory (HBM plus DDR and CXL) offer larger footprints, 
 but under memory oversubscription current systems rely on Inter-memory rel
 ocation (IMR), which drives high relocation I/O traffic over off-package l
 inks and creates severe I/O bottlenecks. We propose GZswap, a hardware-man
 aged, on-device zswap scheme that reserves a portion of GPU memory as a co
 mpressed swap region (Zpool). Instead of evicting pages to host memory, GZ
 swap compresses and keeps them on-device, then transparently decompresses 
 them upon reuse, converting relocation I/O traffic over off-package interc
 onnects into on-package memory accesses. As a result, GZswap significantly
  reduces inter-memory I/O traffic and improves performance and energy effi
 ciency under oversubscription, without requiring any changes to applicatio
 ns.\n\nTrack: Student\n\n
END:VEVENT
END:VCALENDAR