The Direct3D 10 system

By D. Blythe. ACM Transactions on Graphics, 2006

338 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/d3de83b4fc0e9b410e8cae9d5873832cd9082a3d

How researchers see this paper

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

In Computer Networks and Communications

1. John R. Nickolls
2. Bingsheng He
3. Qiong Luo
4. Mark J. Harris
5. Tuyong Wang
6. Daniel Reiter Horn
7. Christopher E. Peters
8. P. Hanrahan

In Hardware and Architecture

1. Mark J. Harris
2. John R. Nickolls
3. P. Hanrahan
4. David P. Luebke
5. M. Houston
6. John Douglas Owens
7. Naga K. Govindaraju
8. Tuyong Wang

Citations in the corpus

• GPU Computing (2008, background): “0 on both vertex and fragment shaders [2]:”
• Accelerator: using data parallelism to program GPUs for general-purpose uses (2006, background): “…(b) Run the vertex shader given the vertex buffer as input; (c) Run the rasterizer on the output of the vertex shader; (d) Run the pixel shader on the output of the rasterizer and any specified input textures; (e) Pass the output value to display memory or texture memory, as specified by the user.”
• A Survey of General‐Purpose Computation on Graphics Hardware (2007, background): “Blythe’s recent Siggraph paper [Bly06] summarizes the major hardware and software changes that will characterize these upcoming GPUs.”
• Interactive k-d tree GPU raytracing (2007, methodology): “Direct3D 10 capable GPUs will deliver one straightforward improvement: integer types and instructions [Blythe 2006].”
• Relational joins on graphics processors (2008, methodology): “We have implemented all of our GPU-based primitives and join algorithms using CUDA [27], NVIDIA’s GPGPU language, and DirectX 10 [6], a graphics API for programmable GPUs.”
• A survey of medical image registration on graphics hardware (2011, methodology): “The OpenGL shading language (GLSL) [13] is the high level shading language for OpenGL [14], HLSL is the equivalent for DirectX [15], whereas the output of a Cg [16] compiler can work with either OpenGL or DirectX.”
• NVIDIA Tesla: A Unified Graphics and Computing Architecture (2008, methodology): “It contained a fixedfunction 32-bit floating-point vertex transform and lighting processor and a fixedfunction integer pixel-fragment pipeline, which were programmed with OpenGL and the Microsoft DX7 API.”
• rCUDA: Reducing the number of GPU-based accelerators in high performance clusters (2010, background): “Therefore, as there is no low-level standard interface to drive GPUs, the virtualization boundary has to be placed at the high-level standard APIs, thus leading to different strategies for virtualizing GPUs depending on the target usage.”
• Developing serious games for cultural heritage: a state-of-the-art review (2010, methodology): “Alternatively, six cameras can be used to produce a dynamic environment map (Blythe 2006).”
• Mars: A MapReduce Framework on graphics processors (2008, methodology): “Previously, GPGPU developers used graphics APIs such as OpenGL [25] and DirectX [4] to map applications to the graphics rendering mechanism.”
• Larrabee: a many-core x86 architecture for visual computing (2008, background): “Recent years have seen the evolution of commodity graphics hardware from fixed function units toward an increasingly programmable graphics pipeline, offering greater flexibility and performance to graphics programmers [Blythe 2006].”