基于无裁剪图形流水线的三维图形处理器
A 3D graphics processor with clip-free graphics pipeline
赵皓宇 1王重熙 1宋鹏皓 1章隆兵1
作者信息
- 1. 处理器芯片全国重点实验室(中国科学院计算技术研究所) 北京 100190;中国科学院大学 北京 100049
- 折叠
摘要
传统的三维图形处理器通过裁剪操作获取三角形的可见区域.然而,裁剪操作的延迟长且硬件开销高,大量的裁剪操作会降低图形处理器的性能.本文设计了一款基于OpenGL ES 2.0标准的三维图形处理器芯片,采用了统一渲染架构.该图形处理器采用高效的无裁剪图形流水线结构,消除了裁剪所带来的硬件开销和性能损耗.此外,本文为该图形处理器设计了一个符合IEEE-754标准的三维向量内积(DP3)计算单元,用于固定功能流水线,以提高图形处理器的性能,并消除图形渲染过程中浮点乘加操作的误差,增强了图形处理器的图形渲染鲁棒性.该三维图形处理器每秒能够处理500 M个顶点和8 G个纹素,功耗为1 000 mW,采用了 28 nm工艺,面积为7.92 mm2.实现结果表明,与之前的工作相比,本文设计的图形处理器的性能-功耗比提高了 27.8％.
Abstract
Traditional 3D graphics processors rely on clipping operations to determine the visible area of triangles.How-ever,clipping operations introduce latency,high hardware overhead,and can negatively impact performance when dealing with a large number of clipping operations.This paper presents the design of a 3D graphics processor with a unified rendering architecture based on the OpenGL ES 2.0 specification.This proposed graphics processor incor-porates an efficient clip-free graphics pipeline architecture,effectively eliminating the hardware overhead and per-formance loss associated with clipping.Furthermore,an IEEE-754 compliant 3D vector inner product unit is intro-duced into the fixed function pipeline of the proposed processor,enhancing performance and eliminating errors in floating-point multiplication and addition operations during graphics rendering,improving the robustness of the graphics rendering.The implemented 3D graphics processor achieves a processing capacity of 500 M vertices and 8 G texels per second,consuming 1 000 mW of power.Utilizing a 28 nm process with an area of 7.92 mm2,the proposed implementation demonstrates a 27.8％improvement in the performance-to-power ratio compared with pre-vious work.
关键词
三维图形处理器/图形流水线/裁剪/向量内积Key words
3D graphics processor/graphics pipeline/clipping/vector inner product引用本文复制引用
基金项目
国家重点研发计划(2022YFB3105103)
出版年
2024
国家科技期刊平台
NSTL
万方数据