Ray-tracing hardware

File:Quake_Wars_Ray_Traced.ogv PCI 3.0 board.]]

Ray-tracing hardware is special-purpose computer hardware designed for accelerating ray tracing calculations.

Introduction: Ray tracing and rasterization

The problem of rendering 3D graphics can be conceptually presented as finding all intersections between a set of "primitives" (typically triangles or polygons) and a set of "rays" (typically one or more per pixel).[https://graphics.cg.uni-saarland.de/fileadmin/cguds/courses/old_courses/OpenRT/Siggraph0f5/Slusallek_Intro.ppt Introduction to real time raytracing]{{dead link|date=April 2018 |bot=InternetArchiveBot |fix-attempted=yes }} Course notes, Course 41, Philipp Slusallek, Peter Shirley, Bill Mark, Gordon Stoll, Ingo Wald, SIGGRAPH 2005, (powerpoint presentation), Slide 26 :Comparison Rasterization vs. Ray Tracing (Definitions) graphics.cg.uni-saarland.de

Up to 2010, all typical graphic acceleration boards, called graphics processing units (GPUs), used rasterization algorithms. The ray tracing algorithm solves the rendering problem in a different way. In each step, it finds all intersections of a ray with a set of relevant primitives of the scene.

Both approaches have their own benefits and drawbacks. Rasterization can be performed using devices based on a stream computing model, one triangle at the time, and access to the complete scene is needed only once.{{Efn|For additional visualisations such as shadows, or reflections such as produced by a large flat body of water, an addition pass of the scene graph is required for each effect.}} The drawback of rasterization is that non-local effects, required for an accurate simulation of a scene, such as reflections and shadows are difficult; and refractions[http://www.cs.uiowa.edu/~cwyman/publications/projects/refractions.html Chris Wyman's Research: Interactive Refractions] {{webarchive|url=https://web.archive.org/web/20100702165822/http://www.cs.uiowa.edu/~cwyman/publications/projects/refractions.html |date=2010-07-02 }} Department of Computer Science at The University of Iowa, www.cs.uiowa.edu nearly impossible to compute.

The ray tracing algorithm is inherently suitable for scaling by parallelization of individual ray renders.SaarCOR —A Hardware Architecture for Ray Tracing, Jörg Schmittler, Ingo Wald, Philipp Slusallek, Section 2, "Previous work" However, anything other than ray casting requires recursion of the ray tracing algorithm (and random access to the scene graph) to complete their analysis,SaarCOR —A Hardware Architecture for Ray Tracing, Jörg Schmittler, Ingo Wald, Philipp Slusallek, Section 3, "The Ray Tracing Algorithm" since reflected, refracted, and scattered rays require that various parts of the scene be re-accessed in a way not easily predicted. But it can easily compute various kinds of physically correct effects, providing much more realistic impression than rasterization.{{Efn|Rasterisation methods are capable of generating realistic shadows (including shadows produced by partially transparent objects), and plane reflections easily (as of 2010), but do not easily implement reflections from non planar surfaces (excluding approximations using normal maps) or refractions.}}

The complexity of a well implemented ray tracing algorithm scales logarithmically;{{Efn|That is if X is the number of triangles, then the number of computations to complete the scene is proportional to log(X).}} this is due to objects (triangles and collections of triangles) being placed into BSP trees or similar structures, and only being analyzed if a ray intersects with the bounding volume of the binary space partition.[http://www.pcper.com/article.php?aid=506&type=expert&pid=3 Ray Tracing and Gaming - One Year Later] Daniel Pohl, 17/1/2008, via "PCperspective", www.pcper.com{{Efn|The same methods can be used in rasterization; in a simplistic implementation, culling is limited to those BSP partitions that lie within the much larger viewing frustum (more advanced implementations including those that implement occlusion culling or predicated rendering scale better than linearly for complex (especially high occluded) scenes (note in common APIs: DirectX 10 D3D10_QUERY_OCCLUSION_PREDICATE [http://msdn.microsoft.com/en-us/library/ee415853(VS.85).aspx], in OpenGL 3.0 HP_occlusion_query ). With ray tracing the viewing frustum is replaced by the volume enclosed by a single ray (or ray bundle).}}

Implementations

Various implementations of ray tracing hardware have been created, both experimental and commercial:

(1995) Advanced Rendering Technology (ART) founded[https://highperformancegraphics.org/wp-content/uploads/2018/Hot3D/HPG2018_RenderDrive.pdf Cold Chips: ART's RenderDrive] in Cambridge, UK, based on a 1994 PhD thesis, to produce dedicated ray tracing silicon (initially the "AR250" chip, which accelerated ray-triangle intersection, bounding box traversal and shading), using a "RenderDrive" networked accelerator for off-line rendering.[http://www.art.co.uk ART company website] {{webarchive|url=https://web.archive.org/web/19961227053055/http://www.art.co.uk/ |date=1996-12-27 }} www.art.co.uk Products were first shipped to customers in 1998.[http://www.art.co.uk/press/releases/980121_ar250.html ART press release] {{webarchive|url=https://web.archive.org/web/19980513074300/http://www.art.co.uk/press/releases/980121_ar250.html|date=1998-05-13}} ART Chips In To Accelerate Ray Traced Rendering Software provided integration with Autodesk Maya and Max data formats, and utilized the Renderman scene description language for sending data to the processors (the .RIB or Renderman Interface Bytestream file format).[http://www.protograph.co.uk/artvps.html ALL ABOUT ARTVPS, PURE CARDS, RENDERDRIVES and RAYBOX] {{webarchive|url=https://web.archive.org/web/20090414075505/http://www.protograph.co.uk/artvps.html |date=2009-04-14 }} Mark Segasby (Protograph Ltd), www.protograph.co.uk ART was re-founded as ART-VPS in 2002. As of 2010, ART-VPS no longer produces ray tracing hardware but continues to produce rendering software.[https://web.archive.org/web/20090607034740/http://www.artvps.com/content/artvps About ArtVPS] www.artvps
(1996) Researchers at Princeton university proposed using DSPs to build a hardware unit for ray tracing acceleration, named "TigerSHARK".[http://cscott.net/Publications/tigershark-thesis.pdf A Hardware Accelerated Ray-tracing Engine] Greg Humphreys, C. Scott Ananian (Independent Work), Department of Computer Science, Princeton University, 14/5/1996, cscott.net.
Implementations of volume rendering using ray tracing algorithms on custom hardware were carried out in 1999 by Hanspeter Pfister[http://www.hotchips.org/archives/hc11/3_Tue/hc99.s5.4.Pfister.pdf The vg500 Real-Time Ray-Casting ASIC].{{webarchive|url=https://web.archive.org/web/20081120045616/http://www.hotchips.org/archives/hc11/3_Tue/hc99.s5.4.Pfister.pdf |date=2008-11-20 }} Hanspeter Pfister, MERL - A Mitsubishi Electric Research Laboratory, Cambridge MA (USA) www.hotchips.org and researchers at Mitsubishi Electric Research Laboratories.{{cite journal | url = http://people.csail.mit.edu/fredo/Book/Stuff/volumePro.pdf | title = The VolumePro Real-Time Ray-Casting System |author=Hanspeter Pfister |author2=Jan Hardenbergh |author3=Jim Knittely |author4=Hugh Lauery |author5=Larry Seiler | publisher = Mitsubishi Electric | date = April 1999 | citeseerx = 10.1.1.69.4091 | access-date = 2010-02-27 | archive-url = https://web.archive.org/web/20110616202224/http://people.csail.mit.edu/fredo/Book/Stuff/volumePro.pdf | archive-date = 2011-06-16 }} with the vg500 / VolumePro ASIC based system and in 2002 with FPGAs by researchers at the University of Tübingen with VIZARD II[http://www.doggetts.org/michael/Meissner-2002-VIZARDII.pdf VIZARD II: An FPGA-based Interactive Volume Rendering System] {{webarchive|url=https://web.archive.org/web/20081121145838/http://www.doggetts.org/michael/Meissner-2002-VIZARDII.pdf |date=2008-11-21 }} Urs Kanus, Gregor Wetekam, Johannes Hirche, Michael Meißner, University of Tübingen / Philips Research Hamburg, Graphics Hardware (2002), pp. 1–11, via www.doggetts.org
(2002) The computer graphics laboratory at Saarland University headed by Dr.-Ing. Philipp Slusallek has produced prototype ray tracing hardware including the FPGA based fixed function data driven SaarCOR (Saarbrücken's Coherence Optimized Ray Tracer) chip{{cite journal | url = http://graphics.cg.uni-saarland.de/index.php?id=343 | title = SaarCOR - A Hardware Architekture for Ray Tracing }}{{cite journal | url=http://graphics.cg.uni-saarland.de/fileadmin/cguds/papers/2002/gh02/Schmittler-AHardwareArchitectureForRayTracing.pdf | title=SaarCOR —A Hardware Architecture for Ray Tracing | journal=Graphics Hardware | year=2002 | pages=1–11 | first1=Jörg | last1=Schmittler | first2=Ingo | last2=Wald | first3=Philipp | last3=Slusallek | publisher=Computer Graphics Group, Saarland University | location=Germany | access-date=2011-11-22 | archive-url=https://web.archive.org/web/20110814155510/http://graphics.cg.uni-saarland.de/fileadmin/cguds/papers/2002/gh02/Schmittler-AHardwareArchitectureForRayTracing.pdf | archive-date=2011-08-14 }}{{cite journal | title = Realtime Ray Tracing of Dynamic Scenes on an FPGA Chip | citeseerx=10.1.1.72.2947 | journal = Graphics Hardware | year = 2004 |author1=Jörg Schmittler |author2=Sven Woop |author3=Daniel Wagner |author4=Wolfgang J. Paul |author5=Philipp Slusallek | publisher = Computer Science, Saarland University, Germany }} and a more advanced programmable (2005) processor, the Ray Processing Unit (RPU){{cite journal | url = http://graphics.cg.uni-saarland.de/fileadmin/cguds/papers/2005/rpu_siggraph/RPU_SIGGRAPH05.pdf | title = RPU: A Programmable Ray Processing Unit for Realtime Ray Tracing |author=Sven Woop |author2=Jorg Schmittler |author3=Philipp Slusallek | publisher = Saarland University | access-date = 2011-11-22 | archive-url = https://web.archive.org/web/20120415113958/http://graphics.cg.uni-saarland.de/fileadmin/cguds/papers/2005/rpu_siggraph/RPU_SIGGRAPH05.pdf | archive-date = 2012-04-15 }}
(2009–2010) Intel{{Cite web|title=Sean Maloney's IDF 2009 Larrabee graphics demo - YouTube|url=https://www.youtube.com/watch?v=G-FKBMct21g |archive-url=https://ghostarchive.org/varchive/youtube/20211221/G-FKBMct21g |archive-date=2021-12-21 |url-status=live|access-date=2021-01-06|website=www.youtube.com| date=22 September 2009 }}{{cbignore}} showcased their prototype "Larrabee" GPU and Knights Ferry MIC at the Intel Developer Forum in 2009 with a demonstration of real-time ray-tracing.
Caustic Graphics[http://www.caustic.com/ Caustic Graphics company website] www.caustic.com produced a plug in card, the "CausticOne" (2009),{{Cite web |date=2009-04-20 |title=Caustic Graphics Ray Tracing Acceleration Technology Review - PC Perspective |url=https://pcper.com/2009/04/caustic-graphics-ray-tracing-acceleration-technology-review/3/ |access-date=2022-08-05 |website=pcper.com |language=en-US}} that accelerated global illumination and other ray based rendering processes when coupled to a PC CPU and GPU. The hardware is designed to organize scattered rays (typically produced by global illumination problems) into more coherent sets (lower spatial or angular spread) for further processing by an external processor.[http://www.drdobbs.com/hpc-high-performance-computing/218500694 Reinventing Ray Tracing] 15/7/2009, Jonathan Erickson interview with James McCombe of Caustic Graphics, www.drdobbs.com
Siliconarts[http://www.siliconarts.com Siliconarts company website] www.siliconarts.com developed a dedicated real-time ray tracing hardware (2010). RayCore (2011), which is the world's first real-time ray tracing semiconductor IP, was announced.
In August 2013 Imagination Technologies, after acquiring Caustic Graphics, produced the Caustic Professional's R2500 and R2100 plug in cards containing RT2 ray trace units (RTUs). Each RTU was capable of calculating up to 50 million incoherent rays per second.{{Cite web|title = The future of ray tracing, reviewed: Caustic's R2500 accelerator finally moves us towards real-time ray tracing {{!}} ExtremeTech|url = http://www.extremetech.com/extreme/161074-the-future-of-ray-tracing-reviewed-caustics-r2500-accelerator-finally-moves-us-towards-real-time-ray-tracing|date = 2013-08-01|website = ExtremeTech|access-date = 2015-10-05}}
In January 2018, Nvidia, partnering with Microsoft DirectX, announced the Nvidia RTX developer library,{{Cite news|url=https://developer.nvidia.com/rtx|title=NVIDIA RTX™ Technology|date=2018-03-06|work=NVIDIA Developer|access-date=2018-04-20|language=en}} which promised fast GPU software ray tracing solutions in the Volta-generation GPUs.{{Cite news|url=https://www.anandtech.com/show/12546/nvidia-unveils-rtx-technology-real-time-ray-tracing-acceleration-for-volta-gpus-and-later|title=NVIDIA Announces RTX Technology: Real Time Ray Tracing Acceleration for Volta GPUs and Later|last=Oh|first=Nate|access-date=2018-04-20}}
In September 2018, Nvidia introduced their GeForce RTX and Quadro RTX GPUs, based on the Turing architecture, with hardware-accelerated ray tracing using a separate functional block, publicly called an "RT core". This unit is somewhat comparable to a texture unit in size, latency, and interface to the processor core. The unit features BVH traversal, compressed BVH node decompression, ray-AABB intersection testing, and ray-triangle intersection testing.{{cite web|url=https://developer.nvidia.com/blog/nvidia-turing-architecture-in-depth|title=NVIDIA Turing Architecture In-Depth|last1=Kilgariff|first1=Emmett|last2=Moreton|first2=Henry|last3=Stam|first3=Nick|last4=Bell|first4=Brandon|website=Nvidia Developer|date=2018-09-14|access-date=2022-11-13|archive-url=https://web.archive.org/web/20221113010753/https://developer.nvidia.com/blog/nvidia-turing-architecture-in-depth/|archive-date=2022-11-13|url-status=live}} The GeForce RTX 2080 and 2080 Ti became the first consumer-oriented brand of graphics card that can perform ray tracing in real time,.{{cite web|url=https://venturebeat.com/games/nvidia-unveils-geforce-rtx-graphics-chips-for-real-time-ray-tracing-games|title=Nvidia unveils GeForce RTX graphics chips for real-time ray tracing games|last=Takahashi|first=Dean|work=VentureBeat|date=2018-08-20|access-date=2022-11-13|archive-url=https://web.archive.org/web/20221113013850/https://venturebeat.com/games/nvidia-unveils-geforce-rtx-graphics-chips-for-real-time-ray-tracing-games|archive-date=2022-11-13|url-status=live}}
In October 2020, AMD announced further information regarding the "refresh" of the RDNA micro-architecture. According to the company, the RDNA 2 micro-architecture supports real-time hardware accelerated ray tracing, consisting of BVH node decoding, ray-AABB intersection testing, and ray-triangle intersection testing.{{cite web|url=https://www.eurogamer.net/articles/digitalfoundry-2020-10-28-amd-unveils-three-radeon-6000-graphics-cards-with-ray-tracing-and-impressive-performance|title=AMD unveils three Radeon 6000 graphics cards with ray tracing and RTX-beating performance|last=Judd|first=Will|work=Eurogamer|date=October 28, 2020|access-date=October 28, 2020}}{{cite web|url=https://www.anandtech.com/show/16077/amd-announces-ryzen-zen-3-and-radeon-rdna2-presentations-for-october-a-new-journey-begins|title=AMD Announces Ryzen "Zen 3" and Radeon "RDNA2" Presentations for October: A New Journey Begins|website=anandtech.com|publisher=AnandTech|date=2020-09-09|access-date=2020-10-25}}
Intel released Arc Alchemist GPU in 2022,{{Cite web |title=Intel officially launches Arc A380 desktop graphics card in China, costs 153 USD |url=https://videocardz.com/newz/intel-officially-launches-arc-a380-desktop-graphics-card-in-china-costs-153-usd |access-date=2022-12-13 |website=VideoCardz.com |language=en-US}}{{Cite web |last=updated |first=Mark Tyson last |date=2022-09-28 |title=Intel Arc A310 Graphics Card Quietly Goes Official |url=https://www.tomshardware.com/news/intel-arc-a310-quietly-goes-official |access-date=2022-12-13 |website=Tom's Hardware |language=en}}{{Cite news |date=2022-10-12 |title=Intel Arc A770 and Arc A750 graphics cards now available to buy from $289 |language=en-US |work=XDA Developers |url=https://www.xda-developers.com/intel-arc-a770-and-arc-a750-graphics-cards-now-available-to-buy-from-289/ |access-date=2022-12-13}} in which the GPU featured ray tracing acceleration core that are performing comparatively with RTX 3000 series mid-range GPU.{{Cite web |date=2022-10-08 |title=Does ray tracing work on the Intel Arc GPUs? |url=https://www.digitaltrends.com/computing/does-ray-tracing-work-on-intel-arc-gpus/ |access-date=2022-12-13 |website=Digital Trends |language=en}}
On 4 November 2021, Imagination Technologies announced their IMG CXT GPU with hardware-accelerated ray tracing.{{Cite web |last=93digital |date=2021-11-04 |title=Imagination launches the most advanced ray tracing GPU |url=https://www.imaginationtech.com/news/imagination-launches-the-most-advanced-ray-tracing-gpu/ |access-date=2023-09-17 |website=Imagination |language=en-GB}}{{Cite web |title=Ray Tracing |url=https://www.imaginationtech.com/products/ray-tracing/ |access-date=2023-09-17 |website=Imagination |language=en-GB}}
On January 18, 2022, Samsung announced their Exynos 2200 AP SoC with hardware-accelerated ray tracing based on the AMD RDNA2 GPU architecture.{{Cite web |title=Samsung Introduces Game Changing Exynos 2200 Processor With Xclipse GPU Powered by AMD RDNA 2 Architecture |url=https://news.samsung.com/global/samsung-introduces-game-changing-exynos-2200-processor-with-xclipse-gpu-powered-by-amd-rdna-2-architecture |access-date=2023-09-17 |website=news.samsung.com |language=en}}
On June 28, 2022, Arm announced their Immortalis-G715 with hardware-accelerated ray tracing.{{Cite web |date=2022-06-28 |title=Gaming Performance Unleashed with Arm's new GPUs - Announcements - Arm Community blogs - Arm Community |url=https://community.arm.com/arm-community-blogs/b/announcements/posts/gaming-performance-unleashed |access-date=2023-09-17 |website=community.arm.com |language=en}}
On November 16, 2022, Qualcomm announced their Snapdragon 8 Gen 2 with hardware-accelerated ray tracing.{{Cite web |title=Snapdragon 8 Gen 2 Defines a New Standard for Premium Smartphones |url=https://www.qualcomm.com/news/releases/2022/11/snapdragon-8-gen-2-defines-a-new-standard-for-premium-smartphone |access-date=2023-09-17 |website=www.qualcomm.com |language=en}}{{Cite web |title=New, Snapdragon 8 Gen 2: 8 extraordinary mobile experiences, unveiled |url=https://www.qualcomm.com/news/onq/2022/11/new-snapdragon-8-gen-2-8-extraordinary-mobile-experiences-unveiled |access-date=2023-09-17 |website=www.qualcomm.com |language=en}}
On September 12, 2023, Apple announced their Apple A17 with hardware-accelerated ray tracing.{{Cite web |last=Bonshor |first=Ryan Smith, Gavin |title=The Apple 2023 Fall iPhone Event Live Blog (Starts at 10am PT/17:00 UTC) |url=https://www.anandtech.com/show/20051/the-apple-2023-fall-iphone-event-live-blog |access-date=2023-09-17 |website=www.anandtech.com}} A month later Apple announced the M3 chip family for Mac computers with support for hardware-accelerated ray tracing.{{Cite web |title=Apple unveils M3, M3 Pro, and M3 Max, the most advanced chips for a personal computer |url=https://www.apple.com/newsroom/2023/10/apple-unveils-m3-m3-pro-and-m3-max-the-most-advanced-chips-for-a-personal-computer/ |access-date=2024-10-27 |website=Apple Newsroom |language=en-US}}

Ray-tracing hardware

Introduction: Ray tracing and rasterization

Implementations

Notes

References

Further reading