BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171530Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241206T154300
DTEND;TZID=Asia/Tokyo:20241206T155400
UID:siggraphasia_SIGGRAPH Asia 2024_sess149_papers_194@linklings.com
SUMMARY:GPU Coroutines for Flexible Splitting and Scheduling of Rendering 
 Tasks
DESCRIPTION:Shaokun Zheng, Xin Chen, and Zhong Shi (Tsinghua University); 
 Ling-Qi Yan (University of California Santa Barbara); and Kun Xu (Tsinghua
  University)\n\nWe introduce coroutines into GPU kernel programming, provi
 ding an automated solution for flexible splitting and scheduling of render
 ing tasks. This approach addresses a prevalent challenge in harnessing the
  power of modern GPUs for complex, imbalanced graphics workloads like path
  tracing. Usually, to accommodate the SIMT execution model and latency-hid
 ing architecture, developers have to decompose a monolithic mega-kernel in
 to smaller sub-tasks for improved thread coherence and reduced register pr
 essure. However, involving the handling of intricate nested control flows 
 and numerous interdependent program states, this process can be exceedingl
 y tedious and error-prone when performed manually.\n\nCoroutines, a buildi
 ng block for asynchronous programming in many high-level CPU languages, ex
 hibit untapped potential for restructuring GPU kernels due to their versat
 ility in control representation. By extending Luisa [Zheng et al. 2022], w
 e implement an asymmetric, stackless coroutine model with programming lang
 uage support and multiple built-in schedulers for modern GPUs. To showcase
  the effectiveness of our model and implementation, we examine them in dif
 ferent application scenarios, including path tracing, SDF rendering, and i
 ncorporation with custom passes.\n\nRegistration Category: Full Access, Fu
 ll Access Supporter\n\nLanguage Format: English Language\n\nSession Chair:
  Valentin Deschaintre (Adobe Research)\n\n
URL:https://asia.siggraph.org/2024/program/?id=papers_194&sess=sess149
END:VEVENT
END:VCALENDAR