A user-programmable vertex engine

By Erik Lindholm, Mark J. Kligard, Henry P. Moreton. International Conference on Computer Graphics and Interactive Techniques, 2001

372 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Computer Graphics and Computer-Aided Design, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/5caca5e0ac48cc53dd159c4ed07bf9aafecde375

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Ian Buck
2. Doug L. James
3. P. Hanrahan
4. Dinesh K. Pai
5. Paul G. Kry
6. Peter Schröder
7. Leif Kobbelt
8. M. Houston

In Computer Graphics and Computer-Aided Design

1. Mario Botsch
2. Doug L. James
3. P. Hanrahan
4. Leif Kobbelt
5. Ian Buck
6. Dinesh K. Pai
7. Paul G. Kry
8. Olga Sorkine-Hornung

In Hardware and Architecture

1. Tor M. Aamodt
2. John R. Nickolls
3. Ian Buck
4. Doug L. James
5. Wilson W. L. Fung
6. George L. Yuan
7. P. Hanrahan
8. Dinesh K. Pai

Citations in the corpus

• A survey of point-based techniques in computer graphics (2004, background): “In the last years, the increasing efficiency and programmability of modern graphic cards [51,52] triggered the development of hardware-based splatting methods.”
• Accelerator: using data parallelism to program GPUs for general-purpose uses (2006, background): “Highly programmable graphics processing units (GPUs) became available in 2001 [ 10 ] and have evolved rapidly since then [15].”
• NVIDIA Tesla: A Unified Graphics and Computing Architecture (2008, methodology): “5 In 2001, the GeForce 3 introduced the first programmable vertex processor executing vertex shaders, along with a configurable 32-bit floating-point fragment pipeline, programmed with DX8 5 and OpenGL.”
• Sparse matrix solvers on the GPU: conjugate gradients and multigrid (2003, background): “With the arrival of programmable vertex and fragment units [Lindholm et al. 2001] the available repertoire increased sig-nificantly.”
• EigenSkin: real time large deformation character skinning in hardware (2002, methodology): “2.5 Eigenskin Vertex Programming Modern vertex programming hardware (e.g., [Lindholm et al. 2001]) is ideally suited to performing the per-vertex weighted lin­ear superposition of eigendisplacements (contained in the large brackets of Equation 2) performed prior to the SSD weighted…”
• Dynamic Warp Formation and Scheduling for Efficient GPU Control Flow (2007, methodology): “The modern graphics processing unit (GPU) can be viewed as an example of the latter approach [ 18 , 28, 6]. Earlier generations of GPUs consisted of fi xed function 3D rendering pipelines.”
• Ray tracing on programmable graphics hardware (2002, methodology): “An NVIDIA vertex program consists of up to 128 4-way SIMD floating point instructions [Lindholm et al. 2001].”
• Brook for GPUs: Stream Computing on Graphics Hardware (2004, methodology): “Each processor executes a user-speci(cid:12)ed assembly-level shader program consisting of 4-way SIMD instructions [Lindholm et al. 2001].”