Webinar Ver2
description
Transcript of Webinar Ver2
Creating breakthrough value in the era of Multi-core Processors
Rajagopal AInnovation ArchitectIntel
100.0% credits to Muruga
Objective of this session
Will help you develop & architect new breakthrough ideas
There is a transition in the hardware industry
Look this is an opportunity for you This session will help you discover & seize those opportunities
what
•Opportunities for breakthrough product ideas
how
•New way of writing code .
The age of Multicore, what does it mean for you?
If you are a
ISV Product
Architect or
CTO
If you are
a
Developer/
Architect
or QA
Inevitable future
1965 Data (Moore)
1960 1965 1970 1975 1980 1985 1990 1995 2000 2005 2010
TransistorsPer Die
105
1010
Microprocessor
1.72 Billion Transistorson a chip
Today
1.72 Billion Transistorson a chip
Today
Pentium® III Processor
Itanium™ Processor
Itanium™ 2 Processor
Itanium™ 2
Processor Family
Pentium® 4 Processor
4004
8080
8086
80286
386™ Processor
486™ ProcessorPentium® Processor
Pentium® II Processor
8008
Ever g
rowing
FLOPS/$
More transistor budget, transistors per $ (Moore's law)
“Reduced cost is one of the big attractions of integrated electronics, and the cost advantage continues to increase as the technology evolves toward the production of larger and larger circuit functions on a single semiconductor substrate.”
Gordon Moore, 1965
Directions: PCs have changed
Your Opportunity to use this change
0
50
100
150
200
250
300
350
400
450
2007 2008 2009 2010 2011 2012
Single Core Dual Core Triple Core Quad Core
Hex Core Octal Core 12 Core 16 Core
By 2010, all PCs shipping will be multi-core
By 2010, all PCs shipping will be multi-core
Dual-Core
Quad-Core
20062006/07
Directions: Shift to multi-core & many-core
Single-Core
Previous
Multi core; Many core
Today, Your Home PC can run 16 threads, all simultaneously !!!
Multi & Many, Heterogeneous
12 Cores 24 Cores 144 Cores
C1 C2
C3 C4
Cache Large Core
Cache
SmallCore
SmallCore
what
•Opportunities for breakthrough product ideas
how
•New way of writing code .
The age of Multicore, what does it mean for you?
If you are a
ISV Product
Architect or
CTO
If you are
a
Developer/
Architect
or QA
Looking for the opportunity to ‘wow’ your users?
+-
Perf
orm
ance
2006
“Concurrency is the next major revolution in how
we write software”
-Dr Dobb’s Journal, Herb SutterMarch 2005
Performance ThroughMulti-Core
Performance Throughfrequency
Your opportunity to add surprising capabilities in your apps
Your apps can do
things that wasn’t
possible before!
15
successfulproducts
BUSINESS TECHNOLOGY
USAGE
market-driveninnovation
technologyacceleration
user-centered innovation
16
happiness, togetherness, spirituality, …
ingredients
systems
subsystems
solutions
tasks
human values
human needs& motivations
user experiences
end-user value
platforms
17
?
happiness, togetherness, spirituality, …
what we make possible
what Intel makes
what we collectively make (ecosystem)
end-user value
ingredients
systems
subsystems
solutions
tasks
human values
human needs& motivations
user experiences
platforms
What will be characteristics of a future multicore app?
Terabytes
TIPS
Gigabytes
MIPS
Megabytes
GIPS
Perf
orm
an
ce
Dataset SizeKilobytes
KIPS
Mult-Media
3D &Video
Text
RMS Personal Media Creation and Management
Entertainment
Learning & Travel
HealthSingle CoreSingle Core
Multi-coreMulti-core
Tera-scaleTera-scale
IPS
= I
nstr
ucti
on
per
secon
d
“RMS” ApplicationsRecognition
MiningSynthesis
Opportunities for the Future
Improved Productivity
Immersive Experience
Breakthrough Innovation
Embr
ace
Para
llelis
m
and
Creat
e New
Expe
rien
ces
What is a tumor? Is there a tumor here? What if the tumor progresses?
It is all about dealing efficiently with complex multimodal datasetsIt is all about dealing efficiently with complex multimodal datasets
Recognition Mining Synthesis
“What is it?”Modeling and identifying using multi-modal data
Emerging “Killer Apps” (R)
Speech recognition combining speech analysis and lip reading
Recognition
Nefian, et. al, “Dynamic Bayesian networks for audio-visual speech recognition,” Journal of Applied Signal Processing, 2002
Source: Intel
Emerging “Killer Apps” (M)
“Where is it?”Search for a similar instance
Mining
Source: Intel
Emerging “Killer Apps” (S)
“What if?”Creating new model instances
Synthesis
Source: Intel Source: InTrace Source: Stanford
iRMS Loop Illustration
Facial Muscle Activations:Compact motion representation,well suited for modeling and synthesis
Video Input Feature TrackingAnalytically Correct, Muscle-
Activated Human Head ModelPhysics-Based Deformable Tissue
(Finite Element Method)
User Interaction:Modified Muscle Activations
Video Output
User Interaction:Modified Physical Model
Source: E. Sifakis, I. Neverov and R. Fedkiw, “Automatic Determination of Facial Muscle Activations from Sparse Motion Capture Marker Data”, ACM SIGGRAPH, 2005 (to appear)
Educational Simulation…Synthesis“Literacy in the computer age means being able to make dynamic models of the ideas that you're thinking about and trying to explain to others and arguing about. In other words, simulations. In the future, children will grow up learning how to make ideas that actually function on computers and use them as part of their discourse and thinking processes.” – Alan Kay of Viewpoints Research Institute
Visualize and simulate complex natural, physical systems
- NASA Goddard Scientific Visualization Studio
Playing and learning
- LEGO Mindstorms / LEGO Digital Designer
Key Technologies• Advanced Real-Time Graphics• Computer Vision• Machine Learning• Physics• RMS, RTA
Usage Trends
• Graphical “literacy” is part of curriculum
• Visual simulations with “what if” analyses for finances, home renovations, storms
Changing Peoples’ Lives
Multi core in healthcare
Necessity for Terascale performing apps
Source: Intel Digital Health Group
2004 2012
1 TFlops
800 GFlops
600 GFlops
400 GFlops
200 GFlops
100 GFlops
10 GFlops
1 GFlops
2006 2008 2010
Image Reconstruction
Medical Imaging: Needs 1TFlops by 2010
Driving Factors:• Doubling number of slices
(128, 256, 512, 1024, 2048 over an approximate 10 year period )
• Rotational speed
(25% reduction in time per image)
• Number of detector channels
• Number of views per “rotation”
how
•New way of writing code .
The age of Multicore, what does it mean for you?
If you are a
ISV Product
Architect or
CTO
If you are
a
Developer/
Architect
or QA
Parallelism Parallelism
The secretto leverage opportunities
Parallelism
Highway animation
Code Optimize ValidateDesign
Actionable performance
guidance
Across multiple programming models with
data and task parallelism
Applications for Parallelism
Correctness
Simplifying Parallelism
Parallel Developer ToolsDefining the developer experience for constructing parallel
applications
•Design and modeling tools to enable developers to start with zero parallelism debt
Design
•Debug across multiple programming models, with data and task-focused visualizations
Debug
•Actionable performance guidance for understanding and optimizing parallel applications
Optimize
•Tools for developers and testers to validate correctness and cope with inherent non-deterministic execution
Validate
Integrate/Tool/Encapsulate/Raise
Parallelism vs. Concurrent
Concurrent processing: independent requests
(most server applications)
Parallel processing: decompose one task to
enable concurrent execution
“Start concurrent searches …”
“Arbitrate “ownership” of the nodes”
Scheduling tasksSimulating isolation of threads
Multi-threading, Asynchronous, …
What:
How:
Example:
Implement:
Parallel approaches
Designing parallel software
43
Solution with Parallel Extensions
void MultiplyMatrices(int size, double[,] m1, double[,] m2, double[,] result){ Parallel.For (0, size, i => { for (int j = 0; j < size; j++) { result[i, j] = 0; for (int k = 0; k < size; k++) { result[i, j] += m1[i, k] * m2[k, j]; } } });}
Structured parallelism
Copyright © 2006, Intel Corporation. All rights reserved.
Intel and the Intel logo are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States or other countries. *Other brands and names are the property of their respective owners.
Copyright © 2006, Intel Corporation. All rights reserved.
Intel and the Intel logo are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States or other countries. *Other brands and names are the property of their respective owners.
Granularity
Coarse grain
Fine grainParallelizable portionSerial
Parallelizable portion
Serial
Scaling: ~3X
Scaling: ~1.10X
Scaling: ~2.5X
Scaling: ~1.05X
Copyright © 2006, Intel Corporation. All rights reserved.
Intel and the Intel logo are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States or other countries. *Other brands and names are the property of their respective owners.
Concluding Question Can you ignore parallelism?
Parallel computing is ubiquitous
Over the next few years, all computers will be parallel computers.
What about software?
- The free lunch is over: Fundamental Turn towards Concurrency in software
– Software will no longer increase from one generation to the next as hardware improves … unless it is parallel software -Herb Sutter of Microsoft said in Dr. Dobbs’ Journal
Summary
Discover possibilities with multi core –Innovate software capabilities by leveraging multi core compute power– (Examples: Google Desktop search, .NET WPF)
“Parallel thinking” software –Now is the time to start your transition to parallel computing.
–If you aren’t parallel, you can’t fully utilize multi-core processors.
Conclusions
Create opportunities with the multicore era:–create new trends & experiences
– E.g. Research s/w for Visual/3D web
Teach multi-core:–develop your intuitions for parallelism
www.intel.com/software