BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260114T163643Z
LOCATION:Meeting Room C4.11\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231215T111500
DTEND;TZID=Australia/Melbourne:20231215T113000
UID:siggraphasia_SIGGRAPH Asia 2023_sess136_papers_405@linklings.com
SUMMARY:SLANG.D: Fast, Modular and Differentiable Shader Programming
DESCRIPTION:Sai Praveen Bangaru (MIT CSAIL), Lifan Wu (NVIDIA), Tzu-Mao Li
  (University of California San Diego), Jacob Munkberg (NVIDIA), Gilbert Be
 rnstein (University of Washington), Jonathan Ragan-Kelley (MIT CSAIL), Aar
 on Lefohn (NVIDIA), Fredo Durand (MIT CSAIL), and Yong He (NVIDIA)\n\nWe i
 ntroduce SLANG.D, a shading language that incorporates first-class automat
 ic differentiation support derived from the Slang language. The new shadin
 g language allows us to transform a Direct3D-based path tracer to be fully
  differentiable with minor modifications to existing code. SLANG.D enables
  a shared ecosystem between machine learning frameworks and pre-existing g
 raphics hardware API-based rendering systems, promoting the interchange of
  components and ideas across these two domains.\n\nOur contributions inclu
 de a differentiable type system designed to ensure type safety and semanti
 c clarity in codebases that blend differentiable and non-differentiable co
 de, language primitives that automatically generate both forward and rever
 se gradient propagation methods, and a compiler architecture that generate
 s efficient derivative propagation shader code for graphics pipelines. Our
  compiler supports differentiating code that involves arbitrary control-fl
 ow, dynamic dispatch, generics and higher-order differentiation, while pro
 viding developers flexible control of checkpointing and gradient aggregati
 on strategies for best performance. Our system allows us to differentiate 
 an existing real-time path tracer, Falcor, with minimal change to its shad
 er code.\nWe show that the compiler-generated derivative kernels perform a
 s efficiently as handwritten ones. In several benchmarks, the SLANG.D code
  achieves significant speedup when compared to prior automatic differentia
 tion systems.\n\nRegistration Category: Full Access\n\nSession Chair: Bo R
 en (TMCC, College of Computer Science, Nankai University)\n\n
URL:https://asia.siggraph.org/2023/full-program?id=papers_405&sess=sess136
END:VEVENT
END:VCALENDAR