top of page

A Scalable GPU Architecture based on Dynamically Reconfigurable Embedded Processor

 

Won-Jong Lee, Sang-Oak Woo, Kwon-Teak Kwon, Sung-Jin Son, Kyung-June Min, Choong-Hoon Lee,

Kyung-Ja Jang, Jeong-Soo Park, Jeongae Park, Chan-Min Park, Seok-Yoon Jung, and Shi-Hwa Lee

Samsung Advanced Institute of Technology

srpgpu.png

Abstract

The increasing cost of ASIC has been driving designers to choose more flexible solutions, as new chip architectures should be able to deliver high performance while maintaining low power consumption, area, and costs in shorter time-to-market environments. As a result, reconfigurable processors (RPs) have become increasingly important in recent years. In this work, we present a new approach that utilizes an RP to design a tile-based GPU, a core component of today’s mobile application processors. Experimental results show that the use of RP based GPUs can be a versatile graphics solution, as they support scalable, flexible architecture models.

Relative talk & posters

  • W-J. Lee "A Scalable and Flexible GPU Architecture for OpenGL|ES 2.0," SIGGRAPH 2011, OpenGL|ES BOF Meeting, Khronos Group  (Talk)

  • W-J. Lee, S-O. Woo, K-T. Kwon, S-J. Son, K-J. Min, C-H. Lee, K-J. Jang, C-M. Park, S-Y. Jung, and S-H. Lee, "A Scalable GPU Architecture Based on Dynamically Embedded Reconfigurable Processor," ACM Conference on High-Performance Graphics, Aug. 2011. (Abstract, Poster)

  • S-O. Woo, J-S Park, K-T. Kwon, S-J. Son, J-A. Park, S-Y. Jung, S-H. Lee, "Fast Tile-Binning Algorithm in Tile-Based Rendering," ACM Conference on High-Performance Graphics, June. 2012. (Poster)

  • K-T. Kwon, K-J. Min, S-O. Woo, S-Y. Jung, S-H. Lee, D. Lentz, "Software Pipelining Shader Core with Streaming Interface, " ACM Conference on High-Performance Graphics, June. 2012. (Poster)

  • S-Y. Jung, K-T. Kwon, S-O. Woo, and S-J. Son, "A Novel Texture Cache Architecture for Fully Pipeline Graphics Engine," ACM Conference on High-Performance Graphics, June. 2012. (Poster)

  • W-J. Lee, S-Y. Jung, and S-H. Lee, "An Effective Task Scheduling Scheme for Multicore Tile-based Rendering GPU," ACM Conference on High-Performance Graphics, June. 2012. (AbstractPoster)

  • J-A. Park, W-J. Lee, S-O. Woo, S-Y. Jung, and S-H. Lee, "Compact Alpha-Texture Compression Unit for Mobile GPU," ACM Conference on High-Performance Graphics, June. 2012. (Poster)

bottom of page