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:20230712T175215Z
LOCATION:3006\, 3rd Floor
DTSTART;TZID=America/Los_Angeles:20230713T154000
DTEND;TZID=America/Los_Angeles:20230713T155500
UID:dac_DAC 2023_sess144_RESEARCH1050@linklings.com
SUMMARY:Automatic End-to-End Joint Optimization for Kernel Compilation on 
 DSPs
DESCRIPTION:Research Manuscript\n\nXiaolei Zhao, Zhaoyun Chen, Yang Shi, M
 ei Wen, and Chunyuan Zhang (National University of Defense Technology)\n\n
 Digital signal processors (DSPs)  are extensively applied in more compute-
 heavy embedded sensing applications.\nThe compilation for DSP kernels is a
  static process, relied heavily on vendor-made compiler and optimization b
 y experts.\nHand-crafted methods suffer from heavy burden on programmers, 
 while state-of-the-art automatic compilation methods focus more on a certa
 in aspect，requiring empirical adjustments by programmers in the actual sce
 nario.\n\nWe propose JOKer, an automatic end-to-end multi-level joint opti
 mizer for kernel compilation on DSPs.\nJOKer integrates means of optimizat
 ion at core steps in compiling process and automatically tunes compilation
  configurations for hiding the details of optimization workload and provid
 es an end-to-end workflow.\n\nTopic: Embedded Systems, RISC-V\n\nKeyword: 
 Embedded Software\n\nSession Chair: Chen Pan (Texas A&M University, Corpus
  Christi)
END:VEVENT
END:VCALENDAR