BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T143138Z
LOCATION:B312-B313A
DTSTART;TZID=America/New_York:20241120T133000
DTEND;TZID=America/New_York:20241120T140000
UID:submissions.supercomputing.org_SC24_sess370_pap726@linklings.com
SUMMARY:AmgT: Algebraic Multigrid Solver on Tensor Cores
DESCRIPTION:Yuechen Lu, Lijie Zeng, Tengcheng Wang, Xu Fu, Wenxuan Li, Hel
 in Cheng, Dechuang Yang, and Zhou Jin (China University of Petroleum, Beij
 ing); Marc Casas (Barcelona Supercomputing Center (BSC)); and Weifeng Liu 
 (China University of Petroleum, Beijing)\n\nAlgebraic multigrid (AMG) meth
 ods are efficient to solve diverse sparse linear systems, due to their fle
 xibility and adaptability. Even though modern parallel devices brought mas
 sive parallelism to AMG, the latest major hardware tensor core and their l
 ow-precision compute power, have not been exploited to accelerate AMG.\nTh
 is paper proposes AmgT, a new AMG solver that utilizes the tensor core and
  mixed-precision ability. Considering that the SpGEMM and SpMV are extensi
 vely used in the setup and solve phases, respectively, we propose a novel 
 method based on a unified storage format that leverages tensor cores and t
 heir variable precision. To utilize algorithm components in existing libra
 ries, the data format and compute kernels of the AmgT solver are incorpora
 ted into the Hypre. The experimental results on NVIDIA A100 and H100 GPUs 
 show that our AmgT outperforms the GPU version of Hypre by a factor of on 
 average 1.46× and 1.32×, respectively.\n\nTag: Accelerators, Algorithms, D
 ata Compression, Linear Algebra, Tensors\n\nRegistration Category: Tech Pr
 ogram Reg Pass\n\nAward Finalist: Best Paper Finalist\n\nSession Chair: Ri
 o Yokota (Institute of Science Tokyo, RIKEN)\n\n
END:VEVENT
END:VCALENDAR