Time Optimization of HEVC Encoder over X86 Processors using SIMD Kushal Shah 1000857252 Advisor: Dr. K. R. Rao Spring 2013 Multimedia.

Slides:



Advertisements
Similar presentations
Towards Efficient Wavefront Parallel Encoding of HEVC: Parallelism Analysis and Improvement Keji Chen, Yizhou Duan, Jun Sun, Zongming Guo 2014 IEEE 16th.
Advertisements

Time Optimization of HEVC Encoder over X86 Processors using SIMD
MULTIMEDIA PROCESSING STUDY AND IMPLEMENTATION OF POPULAR PARALLELING TECHNIQUES APPLIED TO HEVC Under the guidance of Dr. K. R. Rao By: Karthik Suresh.
-1/20- MPEG 4, H.264 Compression Standards Presented by Dukhyun Chang
MULTIMEDIA PROCESSING
Efficient Bit Allocation and CTU level Rate Control for HEVC Picture Coding Symposium, 2013, IEEE Junjun Si, Siwei Ma, Wen Gao Insitute of Digital Media,
1 Adaptive slice-level parallelism for H.264/AVC encoding using pre macroblock mode selection Bongsoo Jung, Byeungwoo Jeon Journal of Visual Communication.
CABAC Based Bit Estimation for Fast H.264 RD Optimization Decision
Shaobo Zhang, Xiaoyun Zhang, Zhiyong Gao
Overview of the H.264/AVC Video Coding Standard
1 An Efficient Mode Decision Algorithm for H.264/AVC Encoding Optimization IEEE TRANSACTION ON MULTIMEDIA Hanli Wang, Student Member, IEEE, Sam Kwong,
Block Partitioning Structure in the HEVC Standard
BY AMRUTA KULKARNI STUDENT ID : UNDER SUPERVISION OF DR. K.R. RAO Complexity Reduction Algorithm for Intra Mode Selection in H.264/AVC Video.
Topics in Signal Processing Project Proposal
Optimizing Baseline Profile in H
HARDEEPSINH JADEJA UTA ID: What is Transcoding The operation of converting video in one format to another format. It is the ability to take.
Shiba Kuanar Analysis of Motion Estimation Algorithm (HEVC), using Multi-core processing Shiba Kuanar
3D EXTENSION of HEVC: Multi-View plus Depth Parashar Nayana Karunakar Student Id: Department of Electrical Engineering.
3D EXTENSION of HEVC: Multi-View plus Depth Parashar Nayana Karunakar Student Id: Department of Electrical Engineering.
PROJECT PROPOSAL HEVC DEBLOCKING FILTER AND ITS IMPLIMENTATION RAKESH SAI SRIRAMBHATLA UTA ID: EE 5359 Under the guidance of DR. K. R. RAO.
By Sudeep Gangavati ID EE5359 Spring 2012, UT Arlington
Multimedia Processing
PROJECT INTERIM REPORT HEVC DEBLOCKING FILTER AND ITS IMPLEMENTATION RAKESH SAI SRIRAMBHATLA UTA ID:
PERFORMANCE COMPARISON OF HEVC AND H
Reducing/Eliminating visual artifacts in HEVC by Deblocking filter By: Harshal Shah Under the guidance of: Dr. K. R. Rao.
By Abhishek Hassan Thungaraj Supervisor- Dr. K. R. Rao.
Multimedia Processing Analysis of Information Hiding Techniques in HEVC. Multimedia Processing EE 5359 Spring 2015 Advisor: Dr. K. R. Rao Department of.
EE 5359 PROJECT PROPOSAL FAST INTER AND INTRA MODE DECISION ALGORITHM BASED ON THREAD-LEVEL PARALLELISM IN H.264 VIDEO CODING Project Guide – Dr. K. R.
Analysis of Motion Estimation Algorithm (HEVC), using Multi-core processing Shiba Kuanar
PERFORMANCE COMPARISON OF HEVC AND H.264 DECODER FINAL PRESENTATION SPRING 2014 ADVISOR: Dr. K.R.Rao VASAVEE VIJAYARAGHAVAN
- By Naveen Siddaraju - Under the guidance of Dr K R Rao Study and comparison of H.264/MPEG4.
Video Compression Standards for High Definition Video : A Comparative Study Of H.264, Dirac pro And AVS P2 By Sudeep Gangavati EE5359 Spring 2012, UT Arlington.
EE 5359 TOPICS IN SIGNAL PROCESSING PROJECT ANALYSIS OF AVS-M FOR LOW PICTURE RESOLUTION MOBILE APPLICATIONS Under Guidance of: Dr. K. R. Rao Dept. of.
Low-Power H.264 Video Compression Architecture for Mobile Communication Student: Tai-Jung Huang Advisor: Jar-Ferr Yang Teacher: Jenn-Jier Lien.
PERFORMANCE COMPARISON OF HEVC AND H.264 DECODER INTERIM PRESENTATION SPRING 2014 ADVISOR: Dr. K.R.Rao VASAVEE VIJAYARAGHAVAN
Sub pixel motion estimation for Wyner-Ziv side information generation Subrahmanya M V (Under the guidance of Dr. Rao and Dr.Jin-soo Kim)
Implementation and comparison study of H.264 and AVS China EE 5359 Multimedia Processing Spring 2012 Guidance : Prof K R Rao Pavan Kumar Reddy Gajjala.
- By Naveen Siddaraju - Under the guidance of Dr K R Rao Study and comparison between H.264.
EE5359 Multimedia Processing Interim Presentation SPRING 2015 ADVISOR: Dr. K.R.Rao EE5359 Multimedia Processing1 BY: BHARGAV VELLALAM SRIKANTESWAR
Figure 1.a AVS China encoder [3] Video Bit stream.
INTERIM Presentation on Topic: Advanced Video Coding (Comparison of HEVC with H.264 and H.264 with MPEG-2) A PROJECT UNDER THE GUIDANCE OF DR. K. R. RAO.
IMPLEMENTATION OF H.264/AVC, AVS China Part 7 and Dirac VIDEO CODING STANDARDS Under the guidance of Dr. K R. Rao Electrical Engineering Department The.
-BY KUSHAL KUNIGAL UNDER GUIDANCE OF DR. K.R.RAO. SPRING 2011, ELECTRICAL ENGINEERING DEPARTMENT, UNIVERSITY OF TEXAS AT ARLINGTON FPGA Implementation.
Study and Optimization of the Deblocking Filter in H.265 and its Advantages over H.264 By: Valay Shah Under the guidance of: Dr. K. R. Rao.
High-efficiency video coding: tools and complexity Oct
ADAPTIVE INTERPOLATION FILTER FOR H.264/AVC Bhavana Prabhakar Student Id: Department of Electrical Engineering.
UNDER THE GUIDANCE DR. K. R. RAO SUBMITTED BY SHAHEER AHMED ID : Encoding H.264 by Thread Level Parallelism.
A HIGH PERFORMANCE DEBLOCKING FILTER IMPLEMENTAION FOR HEVC
-BY KUSHAL KUNIGAL UNDER GUIDANCE OF DR. K.R.RAO. SPRING 2011, ELECTRICAL ENGINEERING DEPARTMENT, UNIVERSITY OF TEXAS AT ARLINGTON FPGA Implementation.
Reducing/Eliminating visual artifacts in HEVC by Deblocking filter Submitted By: Harshal Shah Under the guidance of Dr. K. R. Rao.
Porting of Fast Intra Prediction in HM7.0 to HM9.2
Transcoding from H.264/AVC to HEVC
COMPARATIVE STUDY OF HEVC and H.264 INTRA FRAME CODING AND JPEG2000 BY Under the Guidance of Harshdeep Brahmasury Jain Dr. K. R. RAO ID MS Electrical.
Time Optimization of HEVC Encoder over X86 Processors using SIMD
EE5359 Multimedia Processing Final Presentation SPRING 2015 ADVISOR: Dr. K.R.Rao EE5359 Multimedia Processing1 BY: BHARGAV VELLALAM SRIKANTESWAR
FAST MODE DECISION ALGORITHM FOR INTRA PREDICTION IN HEVC Lanka Naga Venkata Sai Surya Teja Student ID Mail ID
By: Santosh Kumar Muniyappa ( ) Guided by: Dr. K. R. Rao Final Report Multimedia Processing (EE 5359)
A Frame-Level Rate Control Scheme Based on Texture and Nontexture Rate Models for HEVC IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,
Interim Report – Spring 2014 Course: EE5359 – Multimedia Processing Performance Comparison of HEVC & H.264 using various test sequences Under the guidance.
Implementation and comparison study of H.264 and AVS china EE 5359 Multimedia Processing Spring 2012 Guidance : Prof K R Rao Pavan Kumar Reddy Gajjala.
EE 5359 MULTIMEDIA PROCESSING PROJECT PROPOSAL SPRING 2016 STUDY AND PERFORMANCE ANALYSIS OF HEVC, H.264/AVC AND DIRAC By ASHRITA MANDALAPU
E ARLY TERMINATION FOR TZ SEARCH IN HEVC MOTION ESTIMATION PRESENTED BY: Rajath Shivananda ( ) 1 EE 5359 Multimedia Processing Individual Project.
EE 5359 MULTIMEDIA PROCESSING INTERIM PRESENTATION SPRING 2016 STUDY AND PERFORMANCE ANALYSIS OF HEVC, H.264/AVC AND DIRAC By ASHRITA MANDALAPU
Early termination for tz search in hevc motion estimation
Porting of Fast Intra Prediction in HM7.0 to HM9.2
MMX Multi Media eXtensions
Submitted By: Harshal Shah Under the guidance of Dr. K. R. Rao
Study and Optimization of the Deblocking Filter in H
PROJECT PROPOSAL HEVC DEBLOCKING FILTER AND ITS IMPLIMENTATION RAKESH SAI SRIRAMBHATLA UTA ID: EE 5359 Under the guidance of DR. K. R. RAO.
Fast Decision of Block size, Prediction Mode and Intra Block for H
Presentation transcript:

Time Optimization of HEVC Encoder over X86 Processors using SIMD Kushal Shah Advisor: Dr. K. R. Rao Spring 2013 Multimedia Processing EE5359

Objective With a lot of enhanced coding tools introduced, HEVC is expected to achieve 50% bit rate reductions at similar mean opinion score (MOS) compared with the previous standard H.264/AVC. However, the computational complexity of HEVC has greatly increased, making encoding speed a serious problem in the implementation of HEVC.[2]

Overview of HEVC[1] High Efficiency Video Coding (HEVC) is the newest video coding standard of the ITU-T Video Coding Experts Group and the ISO/IEC Moving Picture Experts Group. The main goal of the HEVC standardization effort is to enable significantly improved compression performance relative to existing standards—in the range of 50% bit-rate reduction for equal perceptual video quality.

Encoder Block Diagram[1] Fig.1: Encoder Block Diagram[1]

Macroblocks in HEVC[5] Fig. 2 Macroblocks in HEVC[5]

Time Analysis of HEVC Encoder[2][3] Fig. 3: Time Analysis of HEVC Encoder[2][3]

Time Analysis of HEVC Encoder[2][3] HEVC utilizes a quadtree structure [4] to support large and flexible block sizes. The size of a coding unit (CU) can be 64x64, 32x32, 16x16 and 8x8. Each CU is split into one or more prediction units (PU) and transform units (TU). For PU, the width and height of a PU varies from 4 to 64, indicating that the blocks to be processed in motion compensation (MC) can be as large as 64x64.

Time Analysis of HEVC Encoder[2][3] In motion estimation (ME), sum of absolute differences (SAD) and sum of absolute transformed differences (SATD) of different block sizes are calculated. Due to the flexible block structure, each 4x4 block will be calculated several times from 4x4 to 64x64 ME, which can be quite time- consuming.

Motion Compensation[7] 8-Tap Interpolation Filter: Fig. 4: Equation for Motion Compensation[7]

Intel SSE Instruction[6] Streaming SIMD Extensions (SSE) is the SIMD instruction set extension over the x86 architecture. It is further enhanced to SSE2, SSE3, SSSE3 and SSE4 subsequently. SSE contains eight 128-bit registers originally, known as XMM0 through XMM7. And the number of register is extended to sixteen in AMD64. Each 128-bit register can be divided into two 64-bit integers, four 32-bit integers, eight 16-bit short integers or sixteen 8-bit bytes. With SSE series instructions, several XMM registers can be operated at the same time, indicating considerable data- level parallelism.

Intel SSE Instruction[6] The PMADDUBSW instruction takes two 128-bit SSE registers as operands, with the first one containing sixteen unsigned 8- bit integers, and the second one containing sixteen signed 8- bit integers. With this instruction, we only need to sum the values in the result register to get the final results. Fig 5: Instruction structure [6]

Intel SSE Instruction[6] The PMADDW instruction takes two 64-bit SSE registers as operands, with the first one containing eight unsigned 8-bit integers, and the second one containing eight signed 8-bit integers. This instruction adds and concatenates values of this two operands. Fig 6: Instruction structure [6]

Calculating MC Vectors[7] Fig. 7 : Luminance Row Interpolation [7]

Experiment Configuration IntraPeriod: 32# Period of I-Frame GOPSize: 8 # GOP Size QP: 32# Quantization Parameter FramesToBeEncoded : 100# Number of frames to be coded FrameRate : 60# Frame Rate per second Intel COREi5, Windows 8 and 8GB RAM

Test Sequence[8] BQSquare_416x240_60.yuv BQMall_832x480_60.yuv BQTerrace_1920x1080_60.yuv Fig 8: Test Sequence

Results PSNR Fig 9: PSNR Comparison

Result Bit Rate Fig 10: Bitrate Comparison

Result Time Fig 11: TimeComparison

Abbreviation SIMD : Single Instruction Multiple Data ME: Motion Estimation SAD: Sum of Absolute Differences SATD: Sum of Absolute Transformed Differences (SATD) CTU: Coding Tree Unit CB: Coding Block PB: Prediction Unit TB: Transform Unit

References [1] G. J. Sullivan, J.-R. Ohm, W.-J. Han, and T. Wiegand, “Overview of the High Efficiency Video Coding (HEVC) standard,” IEEE Trans. Circuits Syst. Video Technol., vol. 22, no. 12, pp. 1648–1667, Dec [2] Keji Chen, Yizhou Duan, Leju Yan, Jun Sun and Zongming Guo, “Efficient SIMD Optimization of HEVC Encoder over X86 Processors,” Institute of Computer Science and Technology, Peking University, Beijing , China. [3] JCT-VC, “HM6: High Efficiency Video Coding (HEVC) Test Model 6 Encoder Description,”JCTVC- H1002, Feb [4] D. Marpe et al., “Video compression using nested quadtree structures, leaf merging, and improved techniques for motion representation and entropy coding,” IEEE Trans. Circuits Syst. Video Technol., vol. 20, no. 12, pp –1687, Dec [5] [6] Intel Corp., Intel® 64 and IA-32 Architectures Software Developers Manual [7] Leju Yan; Yizhou Duan; Jun Sun; Zongming Guo, “Implementation of HEVC decoder on x86 processors with SIMD optimization,” VCIP, pp. 1-6, Nov [8] Test Sequence : ftp://ftp.tnt.uni-hannover.de/testsequencesftp://ftp.tnt.uni-hannover.de/testsequences

THANK YOU