Results 1 
7 of
7
Larrabee: a manycore x86 architecture for visual computing
 In SIGGRAPH ’08: ACM SIGGRAPH 2008 papers
, 2008
"... Abstract 123 This paper presents a manycore visual computing architecture code named Larrabee, a new software rendering pipeline, a manycore programming model, and performance analysis for several applications. Larrabee uses multiple inorder x86 CPU cores that are augmented by a wide vector proces ..."
Abstract

Cited by 181 (9 self)
 Add to MetaCart
Abstract 123 This paper presents a manycore visual computing architecture code named Larrabee, a new software rendering pipeline, a manycore programming model, and performance analysis for several applications. Larrabee uses multiple inorder x86 CPU cores that are augmented by a wide vector processor unit, as well as some fixed function logic blocks. This provides dramatically higher performance per watt and per unit of area than outoforder CPUs on highly parallel workloads. It also greatly increases the flexibility and programmability of the architecture as compared to standard GPUs. A coherent ondie 2 nd level cache allows efficient interprocessor communication and highbandwidth local data access by CPU cores. Task scheduling is performed entirely with software in Larrabee, rather than in fixed function logic. The customizable software graphics rendering pipeline for this
A Survey of RealTime Hard Shadow Mapping Methods
 COMPUTER GRAPHICS FORUM
, 2010
"... Due to its versatility, speed and robustness, shadow mapping has always been a popular algorithm for fast hard shadow generation since its introduction in 1978, first for offline film productions and later increasingly so in realtime graphics. So it is not surprising that recent years have seen an ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
Due to its versatility, speed and robustness, shadow mapping has always been a popular algorithm for fast hard shadow generation since its introduction in 1978, first for offline film productions and later increasingly so in realtime graphics. So it is not surprising that recent years have seen an explosion in the number of shadow map related publications. The last survey that encompassed shadow mapping approaches, but was mainly focused on soft shadow generation, dates back to 2003 [HLHS03], while the last survey for general shadow generation dates back to 1990 [WPF90]. No survey that describes all the advances made in hard shadow map generation in recent years exists. On the other hand, shadow mapping is widely used in the game industry, in production, and in many other applications, and it is the basis of many soft shadow algorithms. Due to the abundance of articles on the topic, it has become very hard for practitioners and researchers to select a suitable shadow algorithm, and therefore many applications miss out on the latest highquality shadow generation approaches. The goal of this survey is to rectify this situation by providing a detailed overview of this field. We provide a detailed analysis of shadow mapping errors and derive a comprehensive classification of the existing methods. We discuss the most influential algorithms, consider their benefits and shortcomings and thereby provide the readers with the means to choose the shadow algorithm best suited to their needs.
Applications of Temporal Coherence in RealTime Rendering
, 2010
"... Realtime rendering imposes the challenging task of creating a new rendering of an input scene at least 60 times a second. Although computer graphics hardware has made staggering advances in terms of speed and freedom of programmability, there still exist a number of algorithms that are too expensiv ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Realtime rendering imposes the challenging task of creating a new rendering of an input scene at least 60 times a second. Although computer graphics hardware has made staggering advances in terms of speed and freedom of programmability, there still exist a number of algorithms that are too expensive to be calculated in this time budget, like exact shadows or an exact global illumination solution. One way to circumvent this hard time limit is to capitalize on temporal coherence to formulate algorithms incremental in time. The main thesis of this work is that temporal coherence is a characteristic of realtime graphics that can be used to redesign wellknown rendering methods to become faster, while exhibiting better visual fidelity. To this end we present our adaptations of algorithms from the fields of exact hard shadows, physically correct soft shadows and fast discrete LOD blending, in which we have successfully incorporated temporal coherence. Additionally, we provide a detailed context of previous work not only in the
Logarithmic Perspective Shadow Maps
, 2007
"... PSM cube map LogPSM PSM cube map error LogPSM error Figure 1: Nighttime scene of robots in a hangar with a point light. We compare our algorithm (LogPSM) to Kozlov’s improved perspective shadow map (PSM) algorithm. Both algorithms use a cube map with a total resolution of 1024×1024. The images have ..."
Abstract
 Add to MetaCart
PSM cube map LogPSM PSM cube map error LogPSM error Figure 1: Nighttime scene of robots in a hangar with a point light. We compare our algorithm (LogPSM) to Kozlov’s improved perspective shadow map (PSM) algorithm. Both algorithms use a cube map with a total resolution of 1024×1024. The images have a resolution of 512×512. (Left) Compared to a standard cube map, the PSM cube map greatly reduces aliasing artifacts near the viewer, but some aliasing is still visible. The shadows are severely stretched on the back wall. LogPSMs provide higher quality both near the viewer and in the distance. The shadow map grid has been superimposed to aid visualization (grid lines every 20 texels). (Right) An error visualization for both algorithms. We use an error metric m that is essentially the maximum extent of a shadow map texel projected into the image. Green represents no aliasing (m = 1) and dark red (m> 10) represents high aliasing. LogPSMs provide significantly lower maximum error and the error is more evenly distributed. We present a novel shadow map parameterization to reduce perspective aliasing artifacts for both point and directional light sources. We derive the aliasing error equations for both types of light sources in general position. Using these equations we compute tight bounds on the aliasing error. From these bounds we derive our shadow map parameterization, which is a simple combination of a perspective projection with a logarithmic transformation. We then extend existing algorithms to formulate three types of logarithmic perspective shadow maps (LogPSMs) and analyze the error for each type. Compared with competing algorithms, LogPSMs can produce significantly less aliasing error. Equivalently, for the same error as competing algorithms, LogPSMs can produce significant savings in storage and bandwidth. We demonstrate the benefit of LogPSMs for several models of varying complexity. 1
Rays With a Common Origin and Arbitrary Directions
"... Learn everything you can, anytime you can, from anyone you can there will always come a time when you will be grateful you did. – Sarah Caldwell I have had the good fortune to know and to learn from several individuals who wittingly or otherwise contributed to this work. Foremost among these, my ad ..."
Abstract
 Add to MetaCart
(Show Context)
Learn everything you can, anytime you can, from anyone you can there will always come a time when you will be grateful you did. – Sarah Caldwell I have had the good fortune to know and to learn from several individuals who wittingly or otherwise contributed to this work. Foremost among these, my advisor Bill Mark. For persistently insisting on a high standard of research, writing, and clarity of thought, I am grateful. I am likewise grateful for five years of advice and encouragement. To the other members of my graduate committee, particularly Don Fussell, I am grateful for the wisdom and for making the proposal and defense among the most positive experiences of my student career. Beyond my committee, I am indebted to Jay Boisseau. He is the Ranger to my ring bearer. To Jay and to Kelly Gaither I am grateful for seven years of guidance and unfailing support. Several others have directly participated in this research, none more so than Chris Burns. Chris will (rightly) attest that one of Dante’s nine circles of Hell is reserved for systems researchers who dare to write a hardware simulator. Though
CNRS
"... Figure 1: Examples of nonlinear projections: a paraboloid projection shadow map (left), a cosinesphere projection (center), and a photographic fisheye lens used for direct rendering of the scene (right). Linear perspective projections are used extensively in graphics. They provide a nondistorted ..."
Abstract
 Add to MetaCart
Figure 1: Examples of nonlinear projections: a paraboloid projection shadow map (left), a cosinesphere projection (center), and a photographic fisheye lens used for direct rendering of the scene (right). Linear perspective projections are used extensively in graphics. They provide a nondistorted view, with simple computations that map easily to hardware. Nonlinear projections, such as the view given by a fisheye lens are also used, either for artistic reasons or in order to provide a larger field of view, e.g. to approximate environment reflections or omnidirectional shadow maps. As the computations related to nonlinear projections are more involved, they are harder to implement, especially in hardware, and have found little use so far in practical applications. In this paper, we apply existing methods for nonlinear projections [Lloyd et al. 2006; Hou et al. 2006; Fournier 2005] to a specific class: nonlinear projections with a single center of projection, radial symmetry and convexity. This class includes, but is not limited to, paraboloid projections, hemispherical projections and fisheye lenses. We show that, for this class, the projection of a 3D triangle is a single curved triangle, and we give a mathematical analysis of the curved edges of the triangle; this analysis allows us to reduce the computations involved, and to provide a faster implementation. The overhead for nonlinearity is bearable and can be balanced with the fact that a single nonlinear projection can replaces as many as five linear projections (in a hemicube), with less discontinuities and a smaller memory cost, thus making nonlinear projections a practical alternative.
1Nonlinear Beam Tracing on a GPU
"... Abstract—Beam tracing [8] combines the flexibility of ray tracing and the speed of polygon rasterization. However, beam tracing so far only handles linear transformations; thus, it is only applicable to linear effects such as planar mirror reflections but not to nonlinear effects such as curved mirr ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract—Beam tracing [8] combines the flexibility of ray tracing and the speed of polygon rasterization. However, beam tracing so far only handles linear transformations; thus, it is only applicable to linear effects such as planar mirror reflections but not to nonlinear effects such as curved mirror reflection, refraction, caustics, and shadows. In this paper, we introduce nonlinear beam tracing to render these nonlinear effects. Nonlinear beam tracing is highly challenging because commodity graphics hardware supports only linear vertex transformation and triangle rasterization. We overcome this difficulty by designing a nonlinear graphics pipeline and implementing it on top of a commodity GPU. This allows beams to be nonlinear where rays within the same beam do not have to be parallel or intersect at a single point. Using these nonlinear beams, realtime GPU applications can render secondary rays via polygon streaming similar to how they render primary rays. A major strength of this methodology is that it naturally supports fully dynamic scenes without the need to prestore a scene database. Utilizing our approach, nonlinear ray tracing effects can be rendered in realtime on a commodity GPU under a unified framework.