La microarchitecture est morte. Longue vie à la microarchitecture! Burton Smith Microsoft.

Slides:



Advertisements
Similar presentations
InterCell foundations with ParXXL Render Large Scale Computations Interactive Jens Gustedt INRIA Nancy – Grand Est AlGorille Stéphane Vialle Supélec Metz.
Advertisements

Multiprocessors— Large vs. Small Scale Multiprocessors— Large vs. Small Scale.
WHAT IS AN OPERATING SYSTEM? An interface between users and hardware - an environment "architecture ” Allows convenient usage; hides the tedious stuff.
Distributed System Structures Network Operating Systems –provide an environment where users can access remote resources through remote login or file transfer.
CSC Multiprocessor Programming, Spring, 2011 Outline for Chapter 6 – Task Execution Dr. Dale E. Parson, week 7.
Microprocessor Performance, Phase II Yale Patt The University of Texas at Austin STAMATIS Symposium TU-Delft September 28, 2007.
La microarchitecture est morte. Longue vie à la microarchitecture! ISCA 2010 Panel, St. Malo, France (Microarchitecture is dead. Long live microarchitecture!)
MonetDB: A column-oriented DBMS Ryan Johnson CSC2531.
Latency considerations of depth-first GPU ray tracing
© 2003 IBM Corporation IBM Systems and Technology Group Operating System Attributes for High Performance Computing Ken Rozendal Distinguished Engineer.
CSC457 Seminar YongKang Zhu December 6 th, 2001 About Network Processor.
Cache Coherent Distributed Shared Memory. Motivations Small processor count –SMP machines –Single shared memory with multiple processors interconnected.
1: Operating Systems Overview
Parallel and distributed databases R & G Chapter 22.
DB system design for new hardware and sciences Anastasia Ailamaki École Polytechnique Fédérale de Lausanne and Carnegie Mellon University.
University of Michigan Electrical Engineering and Computer Science Amir Hormati, Mehrzad Samadi, Mark Woh, Trevor Mudge, and Scott Mahlke Sponge: Portable.
Virtual Network Servers. What is a Server? 1. A software application that provides a specific one or more services to other computers  Example: Apache.
Computer System Architectures Computer System Software
LOGO OPERATING SYSTEM Dalia AL-Dabbagh
Operating System Review September 10, 2012Introduction to Computer Security ©2004 Matt Bishop Slide #1-1.
Parallel Programming Models Jihad El-Sana These slides are based on the book: Introduction to Parallel Computing, Blaise Barney, Lawrence Livermore National.
Computer Architecture and System Research For Future Computing Jaehyuk Huh.
Parallel and Distributed Systems Instructor: Xin Yuan Department of Computer Science Florida State University.
 Communication Tasks  Protocols  Protocol Architecture  Characteristics of a Protocol.
Virtualization: Not Just For Servers Hollis Blanchard PowerPC kernel hacker.
computer
CSIE30300 Computer Architecture Unit 15: Multiprocessors Hsin-Chou Chi [Adapted from material by and
Web Search Using Mobile Cores Presented by: Luwa Matthews 0.
IM&T Vacation Program Benjamin Meyer Virtualisation and Hyper-Threading in Scientific Computing.
SCHOOL OF ELECTRICAL AND COMPUTER ENGINEERING | SCHOOL OF COMPUTER SCIENCE | GEORGIA INSTITUTE OF TECHNOLOGY Ocelot and the SST-MacSim Simulator Genie.
Lecture 7: Design of Parallel Programs Part II Lecturer: Simon Winberg.
Multi-Core Development Kyle Anderson. Overview History Pollack’s Law Moore’s Law CPU GPU OpenCL CUDA Parallelism.
Jie Chen. 30 Multi-Processors each contains 8 cores at 1.4 GHz 4GB GDDR3 memory offers ~100GB/s memory bandwidth.
Embedded System Lab. 정범종 A_DRM: Architecture-aware Distributed Resource Management of Virtualized Clusters H. Wang et al. VEE, 2015.
Virtual Infrastructure By: Andy Chau Farzana Mohsini Anya Mojiri Virginia Nguyen Bobby Phimmasane.
A Multi-platform Co-array Fortran Compiler for High-Performance Computing John Mellor-Crummey, Yuri Dotsenko, Cristian Coarfa {johnmc, dotsenko,
Workshop on Parallelization of Coupled-Cluster Methods Panel 1: Parallel efficiency An incomplete list of thoughts Bert de Jong High Performance Software.
CS/EE 5810 CS/EE 6810 F00: 1 Main Memory. CS/EE 5810 CS/EE 6810 F00: 2 Main Memory Bottom Rung of the Memory Hierarchy 3 important issues –capacity »BellÕs.
CS6068 Week 2 Quiz. What are David Patterson’s Three Wall of Computer Architecture?
1 Many-Core Software Burton Smith Microsoft. 2 Computing is at a Crossroads Continual performance improvement is our field’s lifeblood  It encourages.
Scalable and Coordinated Scheduling for Cloud-Scale computing
Extreme Computing’05 Parallel Graph Algorithms: Architectural Demands of Pathological Applications Bruce Hendrickson Jonathan Berry Keith Underwood Sandia.
Shouqing Hao Institute of Computing Technology, Chinese Academy of Sciences Processes Scheduling on Heterogeneous Multi-core Architecture.
3/12/2013Computer Engg, IIT(BHU)1 PARALLEL COMPUTERS- 2.
University of Michigan Electrical Engineering and Computer Science 1 Embracing Heterogeneity with Dynamic Core Boosting Hyoun Kyu Cho and Scott Mahlke.
BCS361: Computer Architecture I/O Devices. 2 Input/Output CPU Cache Bus MemoryDiskNetworkUSBDVD …
1 Cloud Systems Panel at HPDC Boston June Geoffrey Fox Community Grids Laboratory, School of informatics Indiana University
Computer Organization Yasser F. O. Mohammad 1. 2 Lecture 1: Introduction Today’s topics:  Why computer organization is important  Logistics  Modern.
Exploring Parallelism with Joseph Pantoga Jon Simington.
A 1.2V 26mW Configurable Multiuser Mobile MIMO-OFDM/-OFDMA Baseband Processor Motivations –Most are single user, SISO, downlink OFDM solutions –Training.
The CAE Architecture: Decoupled Program Control for Energy-Efficient Performance Ronny Krashinsky and Michael Sung Change in project direction from original.
Background Computer System Architectures Computer System Software.
Heterogeneous Processing KYLE ADAMSKI. Overview What is heterogeneous processing? Why it is necessary Issues with heterogeneity CPU’s vs. GPU’s Heterogeneous.
CS 352H: Computer Systems Architecture
Lynn Choi School of Electrical Engineering
Chapter 1: Introduction
Web: Parallel Computing Rabie A. Ramadan , PhD Web:
UPC Parallel I/O Library
Chilimbi, et al. (2014) Microsoft Research
BASIC OF THE COMPUTER SYSTEM. INPUT/OUTPUT INPUT DEVICES MOUSE KEYBOARD SCANNER OUTPUT DEVICES PRINTER MONITER.
Things you should not skip about Cloud computing.

Address Translation for Manycore Systems
التأهيل التربوي المملكة العربية السعودية جامعة الملك عبدالعزيز
Intro to Architecture & Organization
مفاهیم بهره وري.
Introduction to Multiprocessors
Performance, Applications, Security
A microprocessor into a memory chip Dave Patterson, Berkeley, 1997
Facts About High-Performance Computing
Presentation transcript:

La microarchitecture est morte. Longue vie à la microarchitecture! Burton Smith Microsoft

Verities Parallelism is now our lifeblood – We must be able to use all varieties of it Locality is still important, especially spatial – Pollack’s Rule (AKA AT 2 complexity) – Maybe we can migrate computations to the data Generality and power efficiency compete – Microarchitecture needs to focus here

Approaches Fine-grain producer/consumer synchronization – For value passing, not just isolated+atomic updates Engineered asymmetry and heterogeneity – Several core types cooperating in one application – I/O “devices” become value-passing services More attention to the memory wall – More latency tolerance and memory bandwidth – Put memory in the package