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:20240626T180034Z
LOCATION:3012\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20240625T153000
DTEND;TZID=America/Los_Angeles:20240625T154500
UID:dac_DAC 2024_sess112_RESEARCH1098@linklings.com
SUMMARY:SpaHet: A Software/Hardware Co-design for Accelerating Heterogeneo
 us-Sparsity based Sparse Matrix Multiplication
DESCRIPTION:Research Manuscript\n\nHaoqin Huang, Pengcheng Yao, Zhaozeng A
 n, Yufei Sun, Ao Hu, Peng Xu, Long Zheng, Xiaofei Liao, and Hai Jin (Huazh
 ong University of Science and Technology)\n\nSparse general matrix-matrix 
 multiplication is widely used in data mining applications. Its irregular m
 emory access patterns limit the performance of general-purpose processors,
  thus motivating many FPGA-based hardware innovations. Nevertheless, exist
 ing accelerators fail to efficiently support heterogeneous input matrix sp
 arsity, which is universal in various real-world applications. With in-dep
 th experimental analysis, we observe that their performance is bottlenecke
 d by their fixed tiling mechanisms, which only alleviate the irregularity 
 of one input matrix. Based on the observation, we propose SpaHet, a softwa
 re/hardware co-design to accelerate heterogeneous-sparsity based sparse ma
 trix multiplication. Our experimental results show that SpaHet outperforms
  state-of-the-art FPGA-based solutions by 2.74× in performance.\n\nTopic: 
 Design\n\nKeyword: SoC, Heterogeneous, and Reconfigurable Architectures\n\
 nSession Chairs: Dimitrios Soudris (National Technical University of Athen
 s) and George Tzimpragos (University of Michigan)
END:VEVENT
END:VCALENDAR