The Evolution of Modern Parallel Computing
Transcript of The Evolution of Modern Parallel Computing
![Page 1: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/1.jpg)
Taipei | May 19 , 2011
Sanford H. RussellDirector of CUDA Marketing, NVIDIA Corporation
The Evolution of
Modern Parallel Computing
![Page 2: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/2.jpg)
2
GPU Computing
Is not vs.
It is +
CPU
CPU
GPU
GPU
![Page 3: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/3.jpg)
3
GPU Computing
Application Code
+
GPU CPUParallelize using CUDA Programming Model
Only Critical FunctionsRest of Sequential
CPU Code
![Page 4: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/4.jpg)
4
GPU Computing Milestones
2002
GPGPU
Programming on
top of OGL
2007
G80 NVIDIA First Parallel
Computing Architecture (Single Precision)
2007
C Compiler
C SDK for GPU
![Page 5: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/5.jpg)
5
2009
1st True HPC Class GPU
Fermi Architecture
DP, ECC and C++ support
2010
Industry Standard IDE
Parallel Nsight for
Microsoft Visual Studio
GPU Computing Milestones
![Page 6: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/6.jpg)
6
#1 : Tianhe-1A7168 Tesla GPU’s 2.5 PFLOPS
#3 : Nebulae4650 Tesla GPU’s 1.2 PFLOPS
#4 : Tsubame 2.04224 Tesla GPU’s 1.194 PFLOPS
Tesla GPUs Power 3 of Top 5 Supercomputers
![Page 7: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/7.jpg)
7
Tesla in 3 of Top 5 Supercomputers
0
500
1000
1500
2000
2500
Tianhe-1A Jaguar Nebulae Tsubame Hopper II
Gig
afl
ops
Performance
![Page 8: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/8.jpg)
8
0
1
2
3
4
5
6
7
8
0
500
1000
1500
2000
2500
Tianhe-1A Jaguar Nebulae Tsubame Hopper II
Megaw
att
s
Gig
afl
ops
Tesla Best Performance/Watt
Power
![Page 9: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/9.jpg)
9
World’s Fastest HPC ProcessorTesla M2090: The 512 Core Fermi
512 CUDA Cores
665 GFlops
178 GB/s memory B/W
![Page 10: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/10.jpg)
10
Industry and Research Partners
FinanceGovernmentEdu/ResearchOil and gas Life Sciences Manufacturing
Reverse Time Migration
Kirchoff Time Migration
Reservoir Sim
AstrophysicsMolecular Dynamics
Weather / Climate Modeling
Signal ProcessingSatellite ImagingVideo Analytics
Synthetic Aperture Radar
Bio-chemistryBio-informatics
Material ScienceSequence Analysis
Genomics
Risk AnalyticsMonte Carlo
Options PricingInsurance modeling
Structural Mechanics
Computational Fluid DynamicsMachine Vision
Electromagnetics
![Page 11: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/11.jpg)
11
Lattice QCD
Simulating Quarks - Lattice QCD Simulation
“Performance of Blue Gene/L at 1% the Cost”
Professor Ting-Wei Chiu Department of Physics
National Taiwan University
15 Tflops for $200,000
![Page 12: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/12.jpg)
12
Abaqus: Accelerated by CUDA
2x Faster
Faster Better Quality=
Engine Block s4b5 Million Degrees of Freedom
Simulate More ScenariosMore Fuel Efficient Engine
Lower CO2 Emissions
![Page 13: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/13.jpg)
The Future
![Page 14: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/14.jpg)
14
0
1
2
3
4
5
6
7
8
9
2005 2006 2007 2008 2009 2010e 2011e 2012e 2013e 2014e
ARM is Pervasive and Open
… and supported by Microsoft
Unit
s in
Billions
Source: ARM, Mercury Research, NVIDIA
ARM
x86
Annual Shipments
![Page 15: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/15.jpg)
15
Project DenverNVIDIA-Designed
High Performance ARM Core
![Page 16: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/16.jpg)
16
CUDA GPU Roadmap
16
2
4
6
8
10
12
14
DP G
FLO
PS p
er
Watt
2007 2009 2011 2013
TeslaFermi
Kepler
Maxwell
![Page 17: The Evolution of Modern Parallel Computing](https://reader031.fdocuments.net/reader031/viewer/2022012300/61e167f47b9971671d0e7ea7/html5/thumbnails/17.jpg)
17
Summary and Call to Action
Heterogeneous Computing has achieved commercial volume
CPU + GPU
Developers:
Developing on NVIDIA based systems allows you to scale your work onto
Heterogeneous Clusters and Supercomputers
Scientist:
Publish your work, share with your peers
Industry:
Buy systems that are heterogeneous capable