In this paper, a highly parallel deblocking filter architecture for H.264/AVC is proposed to process one macroblock in 48 clock cycles and give real-time support to QFHD@60 fps sequences at less than 100 MHz. 4 edge filters organized in 2 groups for simultaneously processing vertical and horizontal edges are applied in this architecture to enhance its throughput. While parallelism increases, pipeline hazards arise owing to the latency of edge filters and data dependency of deblocking algorithm. To solve this problem, a zig-zag processing schedule is proposed to eliminate the pipeline bubbles. Data path of the architecture is then derived according to the processing schedule and optimized through data flow merging, so as to minimize the cost of logic and internal buffer. Meanwhile, the architecture's data input rate is designed to be identical to its throughput, while the transmission order of input data can also match the zig-zag processing schedule. Therefore no intercommunication buffer is required between the deblocking filter and its previous component for speed matching or data reordering. As a result, only one 24
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Dajiang ZHOU, Jinjia ZHOU, Jiayi ZHU, Satoshi GOTO, "A 48 Cycles/MB H.264/AVC Deblocking Filter Architecture for Ultra High Definition Applications" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 12, pp. 3203-3210, December 2009, doi: 10.1587/transfun.E92.A.3203.
Abstract: In this paper, a highly parallel deblocking filter architecture for H.264/AVC is proposed to process one macroblock in 48 clock cycles and give real-time support to QFHD@60 fps sequences at less than 100 MHz. 4 edge filters organized in 2 groups for simultaneously processing vertical and horizontal edges are applied in this architecture to enhance its throughput. While parallelism increases, pipeline hazards arise owing to the latency of edge filters and data dependency of deblocking algorithm. To solve this problem, a zig-zag processing schedule is proposed to eliminate the pipeline bubbles. Data path of the architecture is then derived according to the processing schedule and optimized through data flow merging, so as to minimize the cost of logic and internal buffer. Meanwhile, the architecture's data input rate is designed to be identical to its throughput, while the transmission order of input data can also match the zig-zag processing schedule. Therefore no intercommunication buffer is required between the deblocking filter and its previous component for speed matching or data reordering. As a result, only one 24
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.3203/_p
Copy
@ARTICLE{e92-a_12_3203,
author={Dajiang ZHOU, Jinjia ZHOU, Jiayi ZHU, Satoshi GOTO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A 48 Cycles/MB H.264/AVC Deblocking Filter Architecture for Ultra High Definition Applications},
year={2009},
volume={E92-A},
number={12},
pages={3203-3210},
abstract={In this paper, a highly parallel deblocking filter architecture for H.264/AVC is proposed to process one macroblock in 48 clock cycles and give real-time support to QFHD@60 fps sequences at less than 100 MHz. 4 edge filters organized in 2 groups for simultaneously processing vertical and horizontal edges are applied in this architecture to enhance its throughput. While parallelism increases, pipeline hazards arise owing to the latency of edge filters and data dependency of deblocking algorithm. To solve this problem, a zig-zag processing schedule is proposed to eliminate the pipeline bubbles. Data path of the architecture is then derived according to the processing schedule and optimized through data flow merging, so as to minimize the cost of logic and internal buffer. Meanwhile, the architecture's data input rate is designed to be identical to its throughput, while the transmission order of input data can also match the zig-zag processing schedule. Therefore no intercommunication buffer is required between the deblocking filter and its previous component for speed matching or data reordering. As a result, only one 24
keywords={},
doi={10.1587/transfun.E92.A.3203},
ISSN={1745-1337},
month={December},}
Copy
TY - JOUR
TI - A 48 Cycles/MB H.264/AVC Deblocking Filter Architecture for Ultra High Definition Applications
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 3203
EP - 3210
AU - Dajiang ZHOU
AU - Jinjia ZHOU
AU - Jiayi ZHU
AU - Satoshi GOTO
PY - 2009
DO - 10.1587/transfun.E92.A.3203
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2009
AB - In this paper, a highly parallel deblocking filter architecture for H.264/AVC is proposed to process one macroblock in 48 clock cycles and give real-time support to QFHD@60 fps sequences at less than 100 MHz. 4 edge filters organized in 2 groups for simultaneously processing vertical and horizontal edges are applied in this architecture to enhance its throughput. While parallelism increases, pipeline hazards arise owing to the latency of edge filters and data dependency of deblocking algorithm. To solve this problem, a zig-zag processing schedule is proposed to eliminate the pipeline bubbles. Data path of the architecture is then derived according to the processing schedule and optimized through data flow merging, so as to minimize the cost of logic and internal buffer. Meanwhile, the architecture's data input rate is designed to be identical to its throughput, while the transmission order of input data can also match the zig-zag processing schedule. Therefore no intercommunication buffer is required between the deblocking filter and its previous component for speed matching or data reordering. As a result, only one 24
ER -