Embedded Computing Lab Chia-Lin Yang Department of Computer Science and Information Engineering National Taiwan University Website:

Slides:



Advertisements
Similar presentations
CHEP 2012 Computing in High Energy and Nuclear Physics Forrest Norrod Vice President and General Manager, Servers.
Advertisements

System Simulation Of 1000-cores Heterogeneous SoCs Shivani Raghav Embedded System Laboratory (ESL) Ecole Polytechnique Federale de Lausanne (EPFL)
G-Number 1 Challenges and Opportunities for Technion and the Israeli Chip Industry Avinoam Kolodny EE Department Technion – Israel Institute of Technology.
GPU Virtualization Support in Cloud System Ching-Chi Lin Institute of Information Science, Academia Sinica Department of Computer Science and Information.
Early Linpack Performance Benchmarking on IPE Mole-8.5 Fermi GPU Cluster Xianyi Zhang 1),2) and Yunquan Zhang 1),3) 1) Laboratory of Parallel Software.
Chp 1 – Introduction to Computers
1.  Computer applications today: ◦ Word processing (Word) ◦ Spreadsheets (Excel) ◦ Presentation software (PowerPoint) ◦ Communication ( , Internet)
Why GPU Computing. GPU CPU Add GPUs: Accelerate Science Applications © NVIDIA 2013.
What is next for accelerators? Turf war or collaboration? Stefan Möhl, Co-Founder, Chief Strategy Officer, Mitrionics.
1 ITCS 6/8010 CUDA Programming, UNC-Charlotte, B. Wilkinson, Jan 19, 2011 Emergence of GPU systems and clusters for general purpose High Performance Computing.
6/30/2015HY220: Ιάκωβος Μαυροειδής1 Moore’s Law Gordon Moore (co-founder of Intel) predicted in 1965 that the transistor density of semiconductor chips.
1 AppliedMicro X-Gene ® ARM Processors Optimized Scale-Out Solutions for Supercomputing.
Introduction What is GPU? It is a processor optimized for 2D/3D graphics, video, visual computing, and display. It is highly parallel, highly multithreaded.
11 Establishing the Framework for Datacenter of the Future Richard Curran Director Product Marketing, Intel EMEA.
Real Parallel Computers. Modular data centers Background Information Recent trends in the marketplace of high performance computing Strohmaier, Dongarra,
Four Problem Areas Phil Bernstein Microsoft Research.
F1031 COMPUTER HARDWARE CLASSES OF COMPUTER. Classes of computer Mainframe Minicomputer Microcomputer Portable is a high-performance computer used for.
Week 1 Game Design & Development for Mobile Devices.
Presenter : Ching-Hua Huang 2012/11/3 Implementation and Prototyping of a Complex Multi-Project System-on-a-Chip Chun-Ming Huang, Chien-Ming Wu, Chih-Chyau.
Nvidia Tegra 2 The world's first mobile super chip.
Lecture 2 : Introduction to Multicore Computing Bong-Soo Sohn Associate Professor School of Computer Science and Engineering Chung-Ang University.
A.V. Bogdanov Private cloud vs personal supercomputer.
Introduction to Computers
PPT Slides by Dr. Craig Tyran and Kraig Pencil Information Systems Hardware MIS 320 Kraig K. Pencil Summer 2014.
1 CHAPTER 2 COMPUTER HARDWARE. 2 The Significance of Hardware  Pace of hardware development is extremely fast. Keeping up requires a basic understanding.
UC Berkeley 1 The Datacenter is the Computer David Patterson Director, RAD Lab January, 2007.
Hardware.
Living in a Digital World Discovering Computers Fundamentals, 2010 Edition.
Cloud Computing 1. Outline  Introduction  Evolution  Cloud architecture  Map reduce operation  Platform 2.
Lecture 2 : Introduction to Multicore Computing
1 CS503: Operating Systems Spring 2014 Dongyan Xu Department of Computer Science Purdue University.
Your Interactive Guide to the Digital World Discovering Computers 2012.
By Arun Bhandari Course: HPC Date: 01/28/12. GPU (Graphics Processing Unit) High performance many core processors Only used to accelerate certain parts.
Status of the L1 STS Tracking I. Kisel GSI / KIP CBM Collaboration Meeting GSI, March 12, 2009.
Sogang University Advanced Computing System Chap 1. Computer Architecture Hyuk-Jun Lee, PhD Dept. of Computer Science and Engineering Sogang University.
CS/ECE 3330 Computer Architecture Kim Hazelwood Fall 2009.
1 Recap (from Previous Lecture). 2 Computer Architecture Computer Architecture involves 3 inter- related components – Instruction set architecture (ISA):
Chapter 1 Intro to Computer Department of Computer Engineering Khon Kaen University.
Taking the Complexity out of Cluster Computing Vendor Update HPC User Forum Arend Dittmer Director Product Management HPC April,
Programming Concepts in GPU Computing Dušan Gajić, University of Niš Programming Concepts in GPU Computing Dušan B. Gajić CIITLab, Dept. of Computer Science.
Use of GPUs in ALICE (and elsewhere) Thorsten Kollegger TDOC-PG | CERN |
Porting Irregular Reductions on Heterogeneous CPU-GPU Configurations Xin Huo, Vignesh T. Ravi, Gagan Agrawal Department of Computer Science and Engineering.
TheTeacher Computing Data Storage Computing. TheTeacher Computing Primary Storage One of the fundamental properties of a computer is that it can store.
Emergence of GPU systems and clusters for general purpose high performance computing ITCS 4145/5145 April 3, 2012 © Barry Wilkinson.
Seamless Mobility: Michael Wehrs Director of Technology & Standards Mobile Device Division, Microsoft Corp. Wireless Software Innovations Spurring User.
Chapter 1 — Computer Abstractions and Technology — 1 The Computer Revolution Progress in computer technology – Underpinned by Moore’s Law Makes novel applications.
1 Latest Generations of Multi Core Processors
Linchuan Chen. 图形处理器( Graphics Processing Unit ), 是一种专门用来处理在个人电脑、工作站或游 戏机上图像运算工作的微处理器。 图形处理器使显卡减少了对中央处理器的依赖, 并分担了部分原本是由中央处理器所担当的工 作 Efficient at manipulating.
Next Generation Operating Systems Zeljko Susnjar, Cisco CTG June 2015.
Implications of Emerging Hardware Tom Wenisch (University of Michigan) Nikos Hardavellas (Northwestern University) Sangyeun Cho (University of Pittsburgh)
1 Evolving ATLAS Computing Model and Requirements Michael Ernst, BNL With slides from Borut Kersevan and Karsten Koeneke U.S. ATLAS Distributed Facilities.
Copyright © 2006 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill Technology Education Copyright © 2006 by The McGraw-Hill Companies,
© GCSE Computing Computing Hardware Starter. Creating a spreadsheet to demonstrate the size of memory. 1 byte = 1 character or about 1 pixel of information.
Program Optimizations and Recent Trends in Heterogeneous Parallel Computing Dušan Gajić, University of Niš Program Optimizations and Recent Trends in Heterogeneous.
POWERPOINT PRESENTATION EXAMPLES Design include: background, texts, front pages and mixed layouts Created by Nikki Lin /
GFlow: Towards GPU-based High- Performance Table Matching in OpenFlow Switches Author : Kun Qiu, Zhe Chen, Yang Chen, Jin Zhao, Xin Wang Publisher : Information.
Tackling I/O Issues 1 David Race 16 March 2010.
CSE 102 Introduction to Computer Engineering Central Processing Unit.
Lecture # 10 Processors Microcomputer Processors.
Hardware Architecture
Unit 3—Part B Computer Storage Computer Technology (S1 Obj 2-3 and S3 Obj 1-1) Unit 3—Part B Computer Storage Computer Technology (S1 Obj 2-3 and S3 Obj.
Hardware refers to the tangible parts of computer systems and typically includes support for processing, storage, input, and output. Hardware Processing.
Memory P2 Understand hardware technologies for game platforms
Lynn Choi School of Electrical Engineering
3.2 Virtualisation.
Morgan Kaufmann Publishers
Memory P2 Understand hardware technologies for game platforms
Today’s agenda Hardware architecture and runtime system
Chapter 1 Introduction.
Part C Computer Storage
Presentation transcript:

Embedded Computing Lab Chia-Lin Yang Department of Computer Science and Information Engineering National Taiwan University Website:

Embedded Computing Lab  8 Ph.D students, 9 master students  Research Directions Architecture Design  Low-power architecture  Memory hierarchy design  Multicore/GPU architecture design System-Level Synthesis  ESL for platform-based SOC  Task scheduling/placement for FPGAs  Task scheduling/routing for microfluidic biochips

The Bridge Connecting Hardware and Software

Mission Innovative system architectural design to meet the performance/power demands for future mobile cloud computing

ECO System of Virtualized Mobile Cloud Computing Smart Phone Tablet PC E-book Reader Cloud Server virtualization Computation 5 GPUs Storage Game console

The amount of data being created is growing significantly faster than Moore’s law, e.g., from 5 exabytes (10^18), in 2002 to 280 exabytes in 2009 Partnership with 旺宏, 鈺創 From Micro-processors to Nanostores: rethinking data-centric systems Storage Architecture for Data-Centric Computing Fusion Memory Architecture

Optimizing NAND Flash-Based SSDs via Retention Relaxation First work to trade away the excess retention for optimizing the write speed or ECC cost/performance of SSDs in datacenters (published in USENIX FAST 2012) Result in 2x write speedup or 8x ECC cost reduction NAND standards: 1 to 10 years App. requirements: days or shorter vs. Retention-Aware SSD architecture Press Reports

Storage Industry in Taiwan QNAP ( 威聯通 ) Promising Taiwan-based storage provider Western Digital (WD) World’s leading hard disk drive supplier Set up its first oversea R&D center in Taiwan in 2012 …

GPU Virtualization CPU Server user CPU Server switch user GPU server Virtualization Layer Virtualization Layer GPU is gaining its popularity in clouds 3 of top 10 fastest supercomputers in the world use GPUs GPU virtualization is an open problem Non-preemptive nature of GPU makes it a challenging problem for QoS consideration

Heterogeneous Computing Platform Integrated CPU/GPU architecture is the future trend for many-core architecture E.g. AMD Fusion, Intel Sandybridge, ARM Mali and NVIDIA Tegra We have developed the first cycle-level GPU simulation framework for both graphics and GPGPU applications Memory system optimization is crucial for the integrated architecture Interference between CPU and GPU 3D-stacked memory Usage of Non-Volatile Memory Partnership with Intel and 工研院 Intel Sandy Bridge AMD Fusion Issues for CPU/GPU integration with 3D-stacked memory

Why Join Embedded Computing Lab? What’s missing in Taiwan’s Industry? Application, e.g., smart phone app. ASIC, e.g., mpeg decoder DRAM chips Flash memory chips System-on-Chip China HPC. 天河一號 No #1 Super Computer -> Intel Xeon, Nvidia Tesla -> Next-generation -> GodSon CPUs Platform/System Architecture Design System Software SW/HW Co-Design

Why Join Embedded Computing Lab? Strong industrial alliance

成為一個炙手可熱的人才 ! 最前瞻的研究 ! IEEE Micro’10, first paper from Taiwan in 15 years USENIX Fast’12, first paper from Taiwan ISLPED’09 Best Paper Award ICCAD’09 Best Paper Nomination VLSI-CAD’09 Best Paper Nomination 與世界接軌 ! Internship at International Research Lab E.g., IBM Austin Research Lab, Intel Research Lab Why Join Embedded Computing Lab? System Software

Join Us !!!! Please stop by at my office CSIE 411,