iap09 cuda@mit 6.963 - lecture 01: logistics (nicolas pinto, mit)

38
IAP09 CUDA@MIT / 6.963 Supercomputing on your desktop: Programming the next generation of cheap and massively parallel hardware using CUDA Lecture 01 Kick Off session - Nicolas Pinto (MIT)

Upload: npinto

Post on 29-Nov-2014

5.363 views

Category:

Education


2 download

DESCRIPTION

See http://sites.google.com/site/cudaiap2009 and http://pinto.scripts.mit.edu/Classes/CUDAIAP2009

TRANSCRIPT

Page 1: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

IAP09 CUDA@MIT / 6.963

Supercomputing on your desktop:Programming the next generation of cheap

and massively parallel hardware using CUDA

Lecture 01

Kick Off session-

Nicolas Pinto (MIT)

Page 2: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Solve Tomorrow’s

Problems,

Today!

Page 3: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Need More Throughput?

Page 4: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Still doing your computations the old way?

Page 5: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Tired Of Waiting For Your Computations?

Page 6: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

HPC has changed.

Did You?

Page 7: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

6.963 (IAP09)

Fresh New Technology Available NOW!

Page 8: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)
Page 9: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Guaranteed

Page 10: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)
Page 11: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)
Page 12: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

© David Kirk/NVIDIA and Wen-mei W. Hwu, 2007ECE 498AL1, University of Illinois, Urbana-Champaign

Course Goals

• Learn how to program massively parallel processors and achieve–high performance–functionality and maintainability–scalability across future generations

• Acquire technical knowledge required to achieve the above goals–principles and patterns of parallel programming–processor architecture features and constraints–programming API, tools and techniques

adapted for 6.963

Page 13: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Todayyey!!

Page 14: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)
Page 15: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Class logisticsTeaching Staff (MIT)

Page 16: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Class logisticsTeaching Staff (MIT)

GPU Computing with CUDA David Luebke (NVIDIA)

CUDA DemosMarc Adams (NVIDIA)

Page 17: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

High-Throughput Scientific ComputingHanspeter Pfister (Harvard)

Class logisticsTeaching Staff (MIT)

GPU Computing with CUDA David Luebke (NVIDIA)

CUDA DemosMarc Adams (NVIDIA)

Page 18: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Some Logistics...

Page 19: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Faculty: Prof. Steven G. Johnson

Teaching Staff

Page 20: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

TAs: Justin Riley and Nicolas Poilvert

Teaching Staff

Page 21: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Instructor: Nicolas PintoContact: [email protected]

Teaching Staff

Page 22: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Lectures: M/W/F 10-12 (#32-155)HandsOn: M/W/F 2-5 (#32-141)

Project Hours: T/R 2-5 (#3-370)

Schedule

Page 23: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

// CUDA Basics// CUDA Advanced// Theory// Case Studies// Projects

Schedule

Page 24: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Resources

Page 25: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Resources

Page 26: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Hardware

30+ GPUs

Page 27: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Hardware

19 MacBook Pro

Page 28: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Hardware

$70,000+from NVIDIA, Rowland/Harvard and MIT (OEIT, DiCarlo Lab, Graphics CSAIL, EECS)

Page 29: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

The “Project”

Page 30: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)
Page 31: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

The Project(s)

Page 32: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

The Project

Page 33: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Project Presentations@the_end_of_the_course

6.963MIT

The Project

Page 34: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Competition

Page 35: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

Personal

Supercomputer Gifts

Page 36: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

1) Discussion Group 2) Team Project3) Assignments4) Enjoy!

TODO

Contact: [email protected]

Page 37: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)
Page 38: IAP09 CUDA@MIT 6.963 - Lecture 01: Logistics (Nicolas Pinto, MIT)

COME