| 1. |
- Akenine-Möller, Tomas, et al.
(författare)
-
Performance per What?
- 2012
-
Ingår i: Journal of Computer Graphics Techniques. - 2331-7418. ; 1:1, s. 37-41
-
Tidskriftsartikel (refereegranskat)abstract
- In this short note, we argue that performance per watt, which is often cited in the graphics hardware industry, is not a particularly useful unit for power efficiency in scientific and engineering discussions. We argue that joules per task and watts are more reasonable units. We show a concrete example where nanojoules per pixel is much more intuitive, easier to compute aggregate statistics from, and easier to reason about.
|
|
| 2. |
- Barringer, Rasmus, et al.
(författare)
-
Dynamic Stackless Binary Tree Traversal
- 2013
-
Ingår i: Journal of Computer Graphics Techniques. - 2331-7418. ; 2:1, s. 38-49
-
Tidskriftsartikel (refereegranskat)abstract
- A fundamental part of many computer algorithms involves traversing a binary tree. One notable example is traversing a space-partitioning acceleration structure when computing ray-traced images. Traditionally, the traversal requires a stack to be temporarily stored for each ray, which results in both additional storage and memory-bandwidth usage. We present a novel algorithm for traversing a binary tree that does not require a stack and, unlike previous approaches, works with dynamic descent direction without restarting. Our algorithm will visit exactly the same sequence of nodes as a stack-based counterpart with extremely low computational overhead. No additional memory accesses are made for implicit binary trees. For sparse trees, parent links are used to backtrack the shortest path. We evaluate our algorithm using a ray tracer with a bounding volume hierarchy for which source code is supplied.
|
|
| 3. |
- Ganestam, Per, et al.
(författare)
-
Bonsai: Rapid Bounding Volume Hierarchy Generation using Mini Trees
- 2015
-
Ingår i: Journal of Computer Graphics Techniques. - 2331-7418. ; 4:3, s. 23-42
-
Tidskriftsartikel (refereegranskat)abstract
- We present an algorithm, called Bonsai, for rapidly building bounding volume hierarchies for ray tracing. Our method starts by computing midpoints of the triangle bounding boxes and then performs a rough hierarchical top-down split using the midpoints, creating triangle groups with tight bounding boxes. For each triangle group, a mini tree is built using an improved sweep SAH method. Once all mini trees have been built, we use them as leaves when building the top tree of the bounding volume hierarchy. We also introduce a novel and inexpensive optimization technique, called mini-tree pruning, that can be used to detect and improve poorly built parts of the tree. We achieve a little better than 100% in ray-tracing performance compared to a "ground truth" greedy top-down sweep SAH method, and our build times are the lowest we have seen with comparable tree quality.
|
|
| 4. |
- Hasselgren, Jon, et al.
(författare)
-
A Compressed Depth Cache
- 2012
-
Ingår i: Journal of Computer Graphics Techniques. - 2331-7418. ; 1:1, s. 101-118
-
Tidskriftsartikel (refereegranskat)abstract
- We propose a depth cache that keeps the depth data in compressed format, when possible. Compared to previous work, this requires a more flexible cache implementation, where a tile may occupy a variable number of cache lines depending on whether it can be compressed or not. The advantage of this is that the effective cache size increases proportionally to the compression ratio. We show that the depth-buffer bandwidth can be reduced, on average, by 17%, compared to a system compressing the data after the cache. Alternatively, and perhaps more interestingly, we show that pre-cache compression in all cases increases the effective cache size by a factor of two or more, compared to a post-cache compressor, at equal or higher performance.
|
|
| 5. |
- Johansson, Mikael, 1975
(författare)
-
Efficient Stereoscopic Rendering of Building Information Models (BIM)
- 2016
-
Ingår i: Journal of Computer Graphics Techniques (JCGT). - 2331-7418. ; 5:3, s. 1-17
-
Tidskriftsartikel (refereegranskat)abstract
- This paper describes and investigates stereo instancing — a single-pass stereo rendering technique based on hardware-accelerated geometry instancing — for the purpose of rendering building information models (BIM) on modern head-mounted displays (HMD), such as the Oculus Rift. It is shown that the stereo instancing technique is very well suited for integration with query-based occlusion culling as well as conventional geometry instancing, and it outperforms the traditional two-pass stereo rendering approach, geometry shader-based stereo duplication, as well as brute-force stereo rendering of typical BIMs on recent graphics hardware.
|
|
| 6. |
- Johnsson, Björn M, et al.
(författare)
-
Measuring Per-Frame Energy Consumption of Real-Time Graphics Applications
- 2014
-
Ingår i: Journal of Computer Graphics Techniques. - 2331-7418. ; 3:1, s. 60-73
-
Tidskriftsartikel (refereegranskat)abstract
- Energy and power efficiency are becoming important topics within the graphics community. In this paper, we present a simple, straightforward method for measuring per-frame energy consumption of real-time graphics workloads. The method is non-invasive, meaning that source code is not needed, which makes it possible to measure on a much wider range of applications. We also discuss certain behaviors of the measured platforms that can affect energy measurements, e.g., what happens when calling glFinish(), which ensures that all issued graphics commands are finished executing. Measurements are done both on a smartphone and on CPUs with integrated graphics processors.
|
|
| 7. |
- Rönnow, Mads, 1988, et al.
(författare)
-
Improved Accuracy for Prism-Based Motion Blur
- 2022
-
Ingår i: The Journal of Computer Graphics Techniques. - 2331-7418. ; 11:1, s. 82-95
-
Tidskriftsartikel (refereegranskat)abstract
- For motion blur of dynamic triangulated objects, it is common to construct a prism-like shape for each triangle, from the linear trajectories of its three edges and the triangle’s start and end position during the delta time step. Such a prism can be intersected with a primary ray to find the time points where the triangle starts and stops covering the pixel center. These intersections are paired into time intervals for the triangle and pixel. Then, all time intervals, potentially from many prisms, are used to aggregate a motion-blurred color contribution to the pixel. For real-time rendering purposes, it is common to linearly interpolate the ray-triangle intersection and uv coordinates over the time interval. This approximation often works well, but the true path in 3D and uv space for the ray-triangle intersection, as a function of time, is in general nonlinear. In this article, we start by noting that the path of the intersection point can even partially reside outside of the prism volume itself: i.e., the prism volume is not always identical to the volume swept by the triangle. Hence, we must first show that the prisms still work as bounding volumes when finding the time intervals with primary rays, as that may be less obvious when the volumes differ. Second, we show a simple and potentially common class of cases where this happens, such as when a triangle undergoes a wobbling- or swinging-like motion during a time step. Third, when the volumes differ, linear interpolation between two points on the prism surfaces for triangle properties works particularly poorly, which leads to visual artifacts. Therefore, we finally modify a prism-based real-time motion-blur algorithm to use adaptive sampling along the correct paths regarding the triangle location and uv coordinates over which we want to compute a filtered color. Due to being adaptive, the algorithm has a negligible performance penalty on pixels where linear interpolation is sufficient, while being able to significantly improve the visual quality where needed, for a very small additional cost.
|
|
