SIMD 프로그래머블 셰이더를 위한 멀티포트 레지스터 파일 설계 및 구현

Multi-Port Register File Design and Implementation for the SIMD Programmable Shader

  • 발행 : 2008.09.25

초록

3D 그래픽 알고리즘은 특성상 방대한 양의 스트림 데이터에 대하여 복잡한 연산을 수행하여야 한다. 이러한 알고리즘을 하드웨어에서 신속하게 수행할 수 있는 버텍스 셰이더와 픽셀 세이더의 도입으로 그래픽 프로세서는 "소프트웨어 셰이더의 하드웨어화"라는 목표를 어느 정도 달성한 것처럼 보이지만, 여전히 Z-버퍼 기반이라는 특정 알고리즘의 틀에서 벗어나지 못하고 있다. 향후 그래픽 프로세서가 궁극적으로 추구하는 모델은 알고리즘에 독립적인 그리고 버텍스 셰이더와 픽셀 셰이더가 통합된 셰이더로 발전할 것이다. 본 논문에서는 프로그래머블 통합 셰이더 프로세서에서 고성능 3차원 컴퓨터 그래픽 영상을 지원하기 위한 멀티포트 레지스터 파일 모델을 설계하고 구현하였다. 설계한 멀티포트 레지스터 파일을 기능적 레벨에서 시뮬레이션을 하여 그 성능을 검증 하였으며, FPGA Virtex-4(xc4vlx200)에 직접 구현하여 하드웨어 리소스 사용율과 속도를 확인 하였다.

Characteristically, 3D graphic algorithms have to perform complex calculations on massive amount of stream data. The vertex and pixel shaders have enabled efficient execution of graphic algorithms by hardware, and these graphic processors may seem to have achieved the aim of "hardwarization of software shaders." However, the hardware shaders have hitherto been evolving within the limits of Z-buffer based algorithms. We predict that the ultimate model for future graphic processors will be an algorithm-independent integrated shader which combines the functions of both vertex and pixel shaders. We design the register file model that supports 3-dimensional computer graphic on the programmable unified shader processor. we have verified the accurate calculated value using FPGA Virtex-4(xcvlx200) made by Xilinx for operating binary files made by the implementation progress based on synthesis results.

키워드

참고문헌

  1. T. Mitra, T. Chiueh, "Dynamic 3D Graphics Workload Characterization and the Architectural Implications", In MICRO International Symposium on Microar-chitecture, 1999
  2. W. K. Jeong, A SIMD-DSP/FPU for High- Performance Embedded Microprocessors, Phd Thesis, Yonsei University, Dec, 2002
  3. Cheol-Ho Jeong, "The Design of Geometry Processor for 3D Graphics," Master Thesis, Yonsei University, Dec, 1998
  4. J. H. Sohn., R. Woo, H. J. Yoo, "A Programmable Vertex Shader with Fixed-point SIMD Data Path for Low Power Wireless" Applications. Graphics Hardware, 2004
  5. D. Kim, K. Chung, C. Yu, C. Kim, I. Lee, J. Bae, Y. Kim, J. Park, N. Seong, "An SoC with 1.3Gtexels/s 3-D Graphics Full Pipeline for Consumer plications," IEEE Journal of Solid State Circuits Vol 40, No.1, Jan. 2006
  6. B. Khailany, "The VLSI Implementation And Evaluation Of AREA-And Energy-efficient Streaming Media Processors", PhD dissertation, Stanford University, Jun. 2003
  7. J. L. Hennessy and D. A. Patterson, Computer Architecture: A Quantitative Approach, Third Edition, Morgan Kaufmann, 2003
  8. Foley, V. D., Feiner, Hughes, Computer Graphics Principle and Practice, Addison & Wesley, 1996
  9. R. Balasubramonian, S. Dwarkadas, and D. H. Albonesi, "Reducing the complexity of the register file in dynamic superscalar processors", Proceedings of 34th annual ACM/IEEE international symposium on Micro architecture, pp. 237-248, 2001
  10. J. L. Cruz, A. Gonzalez and M. Valero and N. P. Topham, "Multiple-banked register file architectures", Proceedings of 27th annual international symposium on computer architecture, pp. 316-325, 2000
  11. S. Wallace and N. Bagherzadeh, "A Scalable Register File Architecture for Dynamically Scheduled Processors", Proceedings of the Conference on Parallel Architectures and Compilation Techniques, 20-23 Oct. pp. 179-184, 1996
  12. B. Khailany, "The VLSI Implementation And Evaluation Of AREA-And Energy-efficient Streaming Media Processors," PhD dissertation, Stanford University, Jun. 2003
  13. U. J. Kapasi, W. J. Dally, S. Rixner, J. D. Owens, and B. Khailany. The Imagine Stream Processor. In Proceedings of the 2002 IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD'02)
  14. T. Imagire, DirectX9 Shader Programming Book, Tuttle-Mori, 2004
  15. Microsoft, MSDN Asm Shader Reference Vertex/Pixel Shader 3.0
  16. M. Johnson, Superscalar Microprocessor Design, Prentice Hall, pp. 9-22, 1991