一种针对H.264的高性能反变换结构

A High Performance Inverse Integer Transform Architecture for H.264

H.264的整数变换存在8×8和4×4两种尺寸大小,这增加了硬件设计的复杂性。同时,高清视频应用要求解码器具有更强的处理能力。针对这两个问题,文章提出了一种高性能的反变换硬件实现结构。对于4×4整数反变换,重构一个8×8亚宏块的4个4×4块,从而使两种尺寸大小的整数反变换具有相同的结构。采用优化的数据存储和流水设计,行列反变换能够同时执行,处理一个8×8亚宏块平均只需要32个时钟周期。转置存储器采用一个32×32b its的双口SRAM和8组寄存器组实现,和以前的设计相比,可以节省53.7%的存储器面积。在108 MHz工作频率下,本文提出的硬件结构能够有效执行H.264高清实时解码的反变换运算。

There are two kinds of integer transform in H. 264,8 × 8 integer transform and 4 × 4 integer transform. This makes hardware design more complex. At the same time, more powerful decoder is required for high definition video application. High performance hardware architecture is proposed for 2D inverse integer transform in H. 264. For 4 × 4 inverse integer transform, four 4 × 4 blocks in an 8 × 8 sub-macroblock was reconstructed, Therefore, the 8 × 8 2D inverse integer transform and 4 × 4 2D inverse integer transform could have the same architecture. With a new strategy of data storage and pipeline, inverse transform for column data and inverse transform for row data could perform at the same time. On average, 32 clocks were needed for processing an 8 × 8 sub-macroblock. The transpose memory was composed of a two-port 32 × 32bits SRAM and 8 groups of registers. Compared with former design, the new architecture could reduce 53.7% area of transpose memory. When clocked at 108 MHz, the proposed design can perform real-time inverse transform for high definition video decoder of H. 264.