Presentation is loading. Please wait.

Presentation is loading. Please wait.

2012-10-26 FSOSS Dr. Chris Szalwinski Professor School of Information and Communication Technology Seneca College, Toronto, Canada GPU Research Capabilities.

Similar presentations


Presentation on theme: "2012-10-26 FSOSS Dr. Chris Szalwinski Professor School of Information and Communication Technology Seneca College, Toronto, Canada GPU Research Capabilities."— Presentation transcript:

1 2012-10-26 FSOSS Dr. Chris Szalwinski Professor School of Information and Communication Technology Seneca College, Toronto, Canada GPU Research Capabilities at Seneca

2 2 A Fresh Initiative From Some Personal History To Heterogeneous Computing

3 3 A Fresh Initiative The 80287

4 4 A Fresh Initiative Floating-Point Co-Processor (1985)

5 5 A Fresh Initiative ATI 3D Rage II Co-Processor (1996)

6 6 A Fresh Initiative A Paradigm Shift In Programming

7 7 Paradigm Shift The Turn Towards Concurrency

8 8 Paradigm Shift

9 9 Can still increase  transistor density – but it's getting more expensive

10 10 Paradigm Shift Can still increase  transistor density – but it's getting more expensive Can't increase  processor frequencies < 10 GHz chips

11 11 Paradigm Shift Can still increase  transistor density – but it's getting more expensive Can't increase  processor frequencies < 10 GHz chips  power consumption – can't melt chips

12 12 Paradigm Shift Can still increase  transistor density – but it's getting more expensive Can't increase  processor frequencies < 10 GHz chips  power consumption – can't melt chips The Free Lunch is Over  we can't just wait for improvement like we did before  we need new routes to improvement

13 13 Paradigm Shift Use Different Computational Units For Distinctly Different Tasks

14 14 Heterogeneous Computing Intel Core i7 (2008), NVIDIA GeForce GTX580 (2010)

15 15 Heterogeneous Computing

16 16 Heterogeneous Computing

17 17 Heterogeneous Computing Serial processing Parallel processing +

18 18 Heterogeneous Computing NVIDIA many-core GPUs vs Intel multi-core CPUs  Floating point operations per sec (GFLOP/s)  Memory bandwidth (GB/s)

19 19 Industry Momentum STI (Sony + Toshiba + IBM)  Broadband Cell Processor – CPU + GPU on one chip

20 20 Industry Momentum STI (Sony + Toshiba + IBM)  Broadband Cell Processor – CPU + GPU on one chip Intel  Xeon Phi – MIC (Many Integrated Core)

21 21 Industry Momentum STI (Sony + Toshiba + IBM)  Broadband Cell Processor – CPU + GPU on one chip Intel  Xeon Phi – MIC (Many Integrated Core) AMD  APUs (Fusion) – CPU + GPU on a single chip

22 22 Industry Momentum STI (Sony + Toshiba + IBM)  Broadband Cell Processor – CPU + GPU on one chip Intel  Xeon Phi – MIC (Many Integrated Core) AMD  APUs (Fusion) – CPU + GPU on a single chip  HSA Foundation (2012) – AMD + ARM + TI + Imagination + MediaTek + Samsung + Ateris + Multicore Ware + Apical + Sonics + Symbio + Vivante

23 23 Industry Momentum STI (Sony + Toshiba + IBM)  Broadband Cell Processor – CPU + GPU on one chip Intel  Xeon Phi – MIC (Many Integrated Core) AMD  APUs (Fusion) – CPU + GPU on a single chip  HSA Foundation (2012) – AMD + ARM + TI + Imagination + MediaTek + Samsung + Ateris + Multicore Ware + Apical + Sonics + Symbio + Vivante  Radeon – Discrete GPUs

24 24 Industry Momentum STI (Sony + Toshiba + IBM)  Cell Processor – CPU + GPU on one chip Intel  Xeon Phi – MIC (Many Integrated Core) AMD  APUs (Fusion) – CPU + GPU on a single chip  HSA Foundation (2012) – AMD + ARM + TI + Imagination + MediaTek + Samsung + Ateris + Multicore Ware + Apical + Sonics + Symbio + Vivante  Radeon – Discrete GPUs NVIDIA – Discrete GPUs  GeForce (digital gaming)  Quadro (engineering workstations - graphics)  Tesla (scientific computations – double precision)

25 25 Industry Momentum Discrete GPUs - Add-in board shipments

26 26 Industry Momentum Predictions

27 27 Industry Predictions Computer Graphics Market 1974-2015

28 28 Industry Predictions Computer Graphics Market 1974-2015  Traditional processors + low-cost graphics processors enable combinations of science and entertainment

29 29 Industry Predictions Embedded Graphics Processors (EGPs) are killing off Integrated Graphics Processors (IGPs)

30 30 Industry Predictions Embedded Graphics Processors (EGPs) are no threat to Discrete Graphics

31 31 Programming Heterogeneous Computers Concurrency-Oriented Programming  Core Languages Fortran C C++

32 32 Programming Heterogeneous Computers Concurrency-Oriented Programming (COP)  Core Languages Fortran C C++  Extensions for COP Cilk Plus (Intel) OpenCL (Khronos Group – AMD and HSA) CUDA  C/C++ (NVIDIA)  Fortran 2008, C-x86 (PGI) DirectCompute (Microsoft)

33 33 Programming Heterogeneous Computers CUDA Teaching Centers in Ontario  McMaster University (2010) High Performance Parallel Computing on Graphical Processing Units – ECE709 – part of Master's Degree  University of Toronto (2011) Special Topics in Software Engineering: Programming Massively Parallel Graphics Processors – ECE1724H – part of Master's Degree  Seneca College (2012) Introduction to Parallel Programming – Professional Option – GPU610/DPS915 – CPA Diploma and BSD Degree

34 34 Programming Heterogeneous Computers School of Information and Communications Technology (ICT) Our Capabilities and Plans

35 35 ICT Facilities Fully Equipped Teaching Classroom and Lab  40 seats  38 CUDA enabled desktops with GTX480s (480 cores) Maximus Workstation  Quadro 600 for visualization  Tesla C2075 for computation SCI-Net Research  Accelerator Research Cluster – research testbed  8 x [2 Intel Xeon X5550 + 2 NVIDIA Tesla M2070]

36 36 ICT Facilities The 80287

37 37 ICT Courses Introductory Course – Student Skill Set  Solid tested background in both C and C++  Profile for computationally intensive code  Move critical code to the GPU using CUDA  Optimize to hide memory latency with computations Programmer Training Workshops – on demand Advanced Course – (in the planning stage)  Interactive Real-Time Computations + Visualization  Parallelizing Fortran Applications  OpenGL, DirectX Graphics Interoperability

38 38 ICT Faculty Areas of Interest or Domain Expertise  Big Data – Geocomputation  Cognition – Cognitive Tutors  Intrusion Detection – Information Security  Finite Element Analysis – Soft Matter

39 39 ICT Scope Areas of Application (source: NVIDIA)  Image Processing  Big Data Mining  Gaming  Advertising  Genetics  Quantum Chemistry  Mathematics  Product Design  Scientific Computing  Computational Finance

40 2012-10-26 FSOSS Dr. Chris Szalwinski Professor School of Information and Communication Technology Seneca College, Toronto, Canada GPU Research Capabilities at Seneca

41 41 Science and Entertainment Science Art ComputationVisualization


Download ppt "2012-10-26 FSOSS Dr. Chris Szalwinski Professor School of Information and Communication Technology Seneca College, Toronto, Canada GPU Research Capabilities."

Similar presentations


Ads by Google