No Access

AN EFFICIENT MEMORY ADDRESS CONVERTER FOR SoC-BASED 3D GRAPHICS SYSTEM

JOUNG-YOUN KIM

Department of EECS, Korea Advanced Institute of Science and Technology, 373-1 Kusong-dong, Yusong-ku, Taejon, Korea

MagnaChip Semiconductor, Inc., Daechi Tower, Kangnamg-ku, Daechi-dong, Seoul, Korea.

Search for more papers by this author

and

LEE-SUP KIM

Department of EECS, Korea Advanced Institute of Science and Technology, 373-1 Kusong-dong, Yusong-ku, Taejon, Korea

Search for more papers by this author

https://doi.org/10.1142/S0218126605002647Cited by:1 (Source: Crossref)

Abstract

In this paper, we propose an architecture level analysis of the frame buffer access pattern of the recent 3D graphics accelerators that utilize multiple pipelined rendering engines. Based on this analysis, we propose an energy efficient memory address converter for an SoC-based 3D graphics system with an SDRAM frame buffer. About 30% of energy reduction and 20% of runtime reduction is obtained with the address converter. With dynamic power management feature of SDRAM, the energy gains increase to about 50%. The energy and runtime gains are generated by an access pattern analysis based division and assignment of frame buffer onto multiple memory modules. With this proposed access pattern analysis, a frame buffer system optimization of an IP-based 3D graphics accelerator can be performed at early architecture design level.

Keywords:

References

R. Woo et al., A 210mW graphics LSI implementing full 3D pipeline with 264Mtexels/s texturing for mobile multimedia applications, Proc. ISSCC 2003, San Francisco, USA (2003), pp. 44–45 . Google Scholar
NVIDIA Corporation, NVIDIA lightspeed memory architecture, http://developer. nvidia.com/object/IO_20010601_6418. html . Google Scholar
J. McCormack et al., Neon- a single-chip 3D workstation graphics accelerator, Proc. 1998 ACM Workshop on Graphics Hardware 98, Lisbon, Portugal (1998), pp. 123–132 . Google Scholar
F. Catthoor et al. , Custom Memory Management Methodology ( Kluwer Academic Publishers , 1998 ) . Crossref, Google Scholar
H. Kim and I.-C. Park, IEEE Trans. CSVT 11, 1160 (2001). Google Scholar
ATI Technologies Inc., Charisma engine and pixel tapestry architecture, http://mirror.ati.com/companyinfo/glossary/includes/list.html#ce . Google Scholar
C.-H. Yu and L.-S. Kim, A hierarchical depth buffer for minimizing memory bandwidth in 3D rendering engine: Depth Filter, Proc. ISCAS '03, Bangkok, Thailand (2003), pp. II-512–515 . Google Scholar
Imagination Technology Ltd., PowerVR MBX, http://www.powervr.com/Products/Graphics/MBX/index.asp . Google Scholar
OpenGL organization, The OpenGL graphics system: A specification (Version 2.0), http://www.opengl.org/documentation/specs/version2.0/glspec20.pdf . Google Scholar
Microsoft Inc., DirectX, http://www.microsoft.com/windows/directx/default.aspx . Google Scholar
NVIDIA Corporation, Advanced Pixel Shaders Details, http://developer.nvidia.com/object/advanced_dx8_pixel_shaders.html . Google Scholar
J. D. Foley et al. , Computer Graphics: Principles and Practice ( Addison-Wesley , USA , 1996 ) . Google Scholar
H. Igehy, M. Eldridge and K. Proudfoot, Prefetching in a texture cache architecture, Proc. ACM SIGGRAPH/EUROGRAPHICS workshop on Graphics Hardware . Google Scholar
Elpida Memory Inc., How to use SDRAM, http://www.elpida.com/pdfs/E0123N50.pdf . Google Scholar
I. Lee et al., A hardware-like high-level language based environment for 3D graphics architecture exploration, Proc. ISCAS '03, Bangkok, Thailand (2003), pp. II-512–515 . Google Scholar
Samsung Electronics, 1M x 16 SDRAM, http://www.samsung.com/Products/Semi-conductor/DRAM/SDRAM/DRAMcomponent/16Mbit/K4S161622D.htm . Google Scholar