RT Engine: An Efficient Hardware Architecture for Ray Tracing
The reality of the ray tracing technology that leads to its rendering effect is becoming increasingly apparent in computer vision and industrial applications. However, designing efficient ray tracing hardware is challenging due to memory access issues, divergent branches, and daunting computation in...
| Asıl Yazarlar: | , , , , , , , , |
|---|---|
| Materyal Türü: | Makale |
| Dil: | English |
| Baskı/Yayın Bilgisi: |
MDPI AG
2022-09-01
|
| Seri Bilgileri: | Applied Sciences |
| Konular: | |
| Online Erişim: | https://www.mdpi.com/2076-3417/12/19/9599 |
| _version_ | 1827655331727015936 |
|---|---|
| author | Run Yan Libo Huang Hui Guo Yashuai Lü Ling Yang Nong Xiao Yongwen Wang Li Shen Mengqiao Lan |
| author_facet | Run Yan Libo Huang Hui Guo Yashuai Lü Ling Yang Nong Xiao Yongwen Wang Li Shen Mengqiao Lan |
| author_sort | Run Yan |
| collection | DOAJ |
| description | The reality of the ray tracing technology that leads to its rendering effect is becoming increasingly apparent in computer vision and industrial applications. However, designing efficient ray tracing hardware is challenging due to memory access issues, divergent branches, and daunting computation intensity. This article presents a novel architecture, a RT engine (Ray Tracing engine), that accelerates ray tracing. First, we set up multiple stacks to store information for each ray so that the RT engine can process many rays parallel in the system. The information in these stacks can effectively improve the performance of the system. Second, we choose the three-phase break method during the triangle intersection test, which can make the loop break earlier. Third, the reciprocal unit adopts the approximation method, which combines Parabolic Synthesis and Second-Degree interpolation. Combined with these strategies, we implement our system at RTL level with agile chip development. Simulation and experimental results show that our architecture achieves a performance per area which is 2.4 × greater than the best reported results for ray tracing on dedicated hardware. |
| first_indexed | 2024-03-09T22:05:16Z |
| format | Article |
| id | doaj.art-2147bc9de37b4f60aa8d2d0be7997e80 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:05:16Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-2147bc9de37b4f60aa8d2d0be7997e802023-11-23T19:42:21ZengMDPI AGApplied Sciences2076-34172022-09-011219959910.3390/app12199599RT Engine: An Efficient Hardware Architecture for Ray TracingRun Yan0Libo Huang1Hui Guo2Yashuai Lü3Ling Yang4Nong Xiao5Yongwen Wang6Li Shen7Mengqiao Lan8School of Computer, National University of Defense Technology, Changsha 410005, ChinaSchool of Computer, National University of Defense Technology, Changsha 410005, ChinaSchool of Computer, National University of Defense Technology, Changsha 410005, ChinaHuawei 2012 Labs, Beijing 100089, ChinaSchool of Computer, National University of Defense Technology, Changsha 410005, ChinaSchool of Computer, National University of Defense Technology, Changsha 410005, ChinaSchool of Computer, National University of Defense Technology, Changsha 410005, ChinaSchool of Computer, National University of Defense Technology, Changsha 410005, ChinaSchool of Computer, National University of Defense Technology, Changsha 410005, ChinaThe reality of the ray tracing technology that leads to its rendering effect is becoming increasingly apparent in computer vision and industrial applications. However, designing efficient ray tracing hardware is challenging due to memory access issues, divergent branches, and daunting computation intensity. This article presents a novel architecture, a RT engine (Ray Tracing engine), that accelerates ray tracing. First, we set up multiple stacks to store information for each ray so that the RT engine can process many rays parallel in the system. The information in these stacks can effectively improve the performance of the system. Second, we choose the three-phase break method during the triangle intersection test, which can make the loop break earlier. Third, the reciprocal unit adopts the approximation method, which combines Parabolic Synthesis and Second-Degree interpolation. Combined with these strategies, we implement our system at RTL level with agile chip development. Simulation and experimental results show that our architecture achieves a performance per area which is 2.4 × greater than the best reported results for ray tracing on dedicated hardware.https://www.mdpi.com/2076-3417/12/19/9599machine visioncomputer graphicshardware architecturerenderingray tracinggraphics accelerators |
| spellingShingle | Run Yan Libo Huang Hui Guo Yashuai Lü Ling Yang Nong Xiao Yongwen Wang Li Shen Mengqiao Lan RT Engine: An Efficient Hardware Architecture for Ray Tracing Applied Sciences machine vision computer graphics hardware architecture rendering ray tracing graphics accelerators |
| title | RT Engine: An Efficient Hardware Architecture for Ray Tracing |
| title_full | RT Engine: An Efficient Hardware Architecture for Ray Tracing |
| title_fullStr | RT Engine: An Efficient Hardware Architecture for Ray Tracing |
| title_full_unstemmed | RT Engine: An Efficient Hardware Architecture for Ray Tracing |
| title_short | RT Engine: An Efficient Hardware Architecture for Ray Tracing |
| title_sort | rt engine an efficient hardware architecture for ray tracing |
| topic | machine vision computer graphics hardware architecture rendering ray tracing graphics accelerators |
| url | https://www.mdpi.com/2076-3417/12/19/9599 |
| work_keys_str_mv | AT runyan rtengineanefficienthardwarearchitectureforraytracing AT libohuang rtengineanefficienthardwarearchitectureforraytracing AT huiguo rtengineanefficienthardwarearchitectureforraytracing AT yashuailu rtengineanefficienthardwarearchitectureforraytracing AT lingyang rtengineanefficienthardwarearchitectureforraytracing AT nongxiao rtengineanefficienthardwarearchitectureforraytracing AT yongwenwang rtengineanefficienthardwarearchitectureforraytracing AT lishen rtengineanefficienthardwarearchitectureforraytracing AT mengqiaolan rtengineanefficienthardwarearchitectureforraytracing |