This document discusses Intel's compiler optimizations that are specifically designed for Intel microprocessors and warns that optimizations may not be available for non-Intel processors. It outlines the importance of system configuration for the performance of Intel technologies and includes a caution regarding potential risks involved with future predictions and product specifications. Furthermore, it emphasizes the growing significance of IoT and AI technologies, highlighting their expected impact on productivity and economic growth.

1. Jomar Silva
Technical Evangelist

2. Intel’s compilers may or may not optimize to the same degree for non-Intel
microprocessors for optimizations that are not unique to Intel microprocessors.
These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other
optimizations. Intel does not guarantee the availability, functionality, or
effectiveness or any optimization on microprocessors not manufactured by
Intel. Microprocessor-dependent optimizations in this product are intended for
use with Intel microprocessors. Certain optimizations not specific to Intel
microarchitecture are reserved for Intel microprocessors. Please refer to the
applicable product User and Reference Guides for more information regarding
the specific instruction sets covered by this notice. Notice Revision #20110804
2

3. Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on
system configuration. No computer system can be absolutely secure. Check with your system manufacturer or retailer or learn more at www.intel.com.
Performance estimates were obtained prior to implementation of recent software patches and firmware updates intended to address exploits referred to as "Spectre" and
"Meltdown." Implementation of these updates may make these results inapplicable to your device or system.
Cost reduction scenarios described are intended as examples of how a given Intel-based product, in the specified circumstances and configurations, may affect future costs and
provide cost savings. Circumstances will vary. Intel does not guarantee any costs or cost reduction.
This document contains information on products, services and/or processes in development. All information provided here is subject to change without notice. Contact your Intel
representative to obtain the latest forecast, schedule, specifications and roadmaps.
Any forecasts of goods and services needed for Intel’s operations are provided for discussion purposes only. Intel will have no liability to make any purchase in connection with
forecasts published in this document.
ARDUINO 101 and the ARDUINO infinity logo are trademarks or registered trademarks of Arduino, LLC.
Altera, Arria, the Arria logo, Intel, the Intel logo, Intel Atom, Intel Core, Intel Nervana, Intel Xeon Phi, Movidius, Saffron and Xeon are trademarks of Intel Corporation or its
subsidiaries in the U.S. and/or other countries.
*Other names and brands may be claimed as the property of others.
Copyright 2018 Intel Corporation.
3

4. This document contains information on products, services and/or processes in development. All information provided here is subject to change without notice. Contact your Intel
representative to obtain the latest forecast, schedule, specifications and roadmaps.
Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Learn more at intel.com, or from the
OEM or retailer. No computer system can be absolutely secure.
Tests document performance of components on a particular test, in specific systems. Differences in hardware, software, or configuration will affect actual performance. Consult
other sources of information to evaluate performance as you consider your purchase. For more complete information about performance and benchmark results, visit
http://www.intel.com/performance.
Cost reduction scenarios described are intended as examples of how a given Intel-based product, in the specified circumstances and configurations, may affect future costs and
provide cost savings. Circumstances will vary. Intel does not guarantee any costs or cost reduction.
Statements in this document that refer to Intel’s plans and expectations for the quarter, the year, and the future, are forward-looking statements that involve a number of risks and
uncertainties. A detailed discussion of the factors that could affect Intel’s results and plans is included in Intel’s SEC filings, including the annual report on Form 10-K.
The products described may contain design defects or errors known as errata which may cause the product to deviate from published specifications. Current characterized errata
are available on request.
Performance estimates were obtained prior to implementation of recent software patches and firmware updates intended to address exploits referred to as "Spectre" and
"Meltdown." Implementation of these updates may make these results inapplicable to your device or system.
No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document.
Intel does not control or audit third-party benchmark data or the web sites referenced in this document. You should visit the referenced web site and confirm whether referenced
data are accurate.
Intel, the Intel logo, Pentium, Celeron, Atom, Core, Xeon, Movidius, Saffron and others are trademarks of Intel Corporation in the U.S. and/or other countries.
*Other names and brands may be claimed as the property of others.
© 2018 Intel Corporation.
4

5. Internet of
Things
Artificial
Intelligence
Connected &
Autonomous
World
5

6. Internet of
Things
Artificial
Intelligence
Connected &
Autonomous
World
6

7. 200% growth of information-based products & services by
2020 compared with traditional product & services¹
62% developers deem IoT ‘very important’
to digital strategies¹
1. IDC – Digital Transformation Predictions (source)
2. NLC – Cities and Innovation Economy: Perceptions of Local Leaders (source)
3. DataAge 2025, (link)
4. Forbes, December 10, 2017 (link)
>55% percentage of all data forecast to be
generated by IoT in 2025.³
>$300B annual B2B IoT revenue, led by industrial sector ⁴
66% of cities have invested in some type of smart
city technology²
7

8. Optimizing
Productivity
Driving
efficiency
Lowering
cost
Saving
Lives
Improving
QualityofLife
Growing
yield
increase
Security
Protectingthe
planet
8

9. CONNECTED SMART AUTONOMOUS
9

10. 1. Amalgamation of analyst data and Intel analysis.
2. IDC FutureScape: Worldwide Internet of Things 2017 Predictions (link)
3. IDC FutureScape: Worldwide Internet of Things 2015 Predictions (link)
50%
45%
of data will be stored,
analyzed, and acted
on at the edge22018
2019
of IoT deployments will be
network constrained3
By2020
Average
internetuser 1.5GB data/day
Smart
hospital 3TB data/day
Autonomous
automobile 4TB data/day
Connected
airplane 40TB data/day
Smart
factory 1PB data/day
10
10

11. Things Network
Infrastructure
Data
Center/CloudEdgeCompute
11

12. SoftwareEnablement
CommonandSeamlessDeveloperExperience
Other names and brands may be claimed as the property of others.
Workload Accelerators Connectivity
12

13. Single
function
Single
function
Digital Display
Digital Display
Plus Camera
Smart Vending
Digital Surveillance
Virtual Banking
WI-FI Hotspots
Digital Signage
Single
function
ATM
Vending
Machine
Digital
Surveillance
13

14. AutonomousVehicles ResponsiveRetail Manufacturing
EmergencyResponse Financialservices MachineVision Cities/transportation
Publicsector
14

15. SmartCameras VideoGateways/NVRs Datacenter/Cloud
FPGAsolutionsfromintel
CV
Intel®MediaSDK, OPENVINOTM
Industry’sBroadestMediaandComputerVisionandDeepLearningPortfolio
15

16. Internet of
Things
Artificial
Intelligence
Connected &
Autonomous
World
16

17. DataAnalyticsneedsai
Descriptive
Analytics
Diagnostic
Analytics
Predictive
Analytics
Prescriptive
Analytics
Cognitive
Analytics
Operational
Analytics
Advanced
Analytics
EmergingToday
Self-Learning and Completely
Automated Enterprise
Simulation-Driven Analysis
and Decision-Making
Foresight
What Will Happen, When, and Why
Insight
What Happened and Why
Hindsight
What Happened
AI
Datadeluge
COMPUTEbreakthrough
Innovationsurge

18. Source: Forrester Research – Artificial Intelligence: Fact, Fiction. How Enterprises Can Crush It; What’s Possible for Enterprises in 2017
Aiadoptionisjustbeginning
58%
of business and technology
professionals said they're
researching AI, but only…
12%said they are currently
using AI systems.
In a recent Forrester Research survey…

19. Machinelearning DeepLearning
Example
Features
 Detect similarities &
anomalies in sea of data
 Large, diverse dataset
 Fully-explainable
 Real-time updates
 Practical to
‘reverse engineer’
 Tabular/limited dataset
 Good enough accuracy
 Fully-explainable
 Difficult problem to
‘reverse engineer’
 Large, uniform dataset
 Highest accuracy
Other
examples
Credit fraud detection
Issue and defect triage
Predictive maintenance
 Regression
 Anomaly detection
 Feature extraction
 Image/speech recognition
 Natural language
processing (NLP)
 Pattern detection
MULTIPLEapproachestoAI
Anti-Money
Laundering
Facial
recognition
Recommendation
engine
Cognitive
Reasoning
ANDMore…

20. Machine
Learning
How do you
engineer the best
features?
Machinelearning
𝑁 × 𝑁
Arjun
NEURAL NETWORK
𝒇 𝟏, 𝒇 𝟐, … , 𝒇 𝑲
Roundness of face
Dist between eyes
Nose width
Eye socket depth
Cheek bone structure
Jaw line length
…etc.
CLASSIFIER
ALGORITHM
SVM
Random Forest
Naïve Bayes
Decision Trees
Logistic Regression
Ensemble methods
𝑁 × 𝑁
Arjun
DeepLearning
How do you guide
the model to find
the best features?

21. Deeplearning:Trainingvs.inference
Lots of
labeled data!
Training
Inference
Forward
Backward
Model weights
Forward
“Bicycle”?
“Strawberry”
“Bicycle”?
Error
Human
Bicycle
Strawberry
??????
Data set size
Accuracy
Didyouknow?
Training requires a very large
data set and deep neural
network (i.e. many layers) to
achieve the highest accuracy
in most cases

22. AIportfolio
†Beta available
‡ Future
*Other names and brands may be claimed as the property of others.
Tools
Platforms
technology
Frameworks
libraries
END-TO-END COMPUTE SYSTEMS & COMPONENTS
Intel® Deep
Learning System
‡
*
Solutions
Data
Scientists
Technical
Services
Reference
Solutions
REASONING
Intel® AI
DevCloud
ON
*‡
Intel® Deep
Learning
Studio‡
Intel® Deep Learning
Deployment Toolkit† OpenVINO™
Intel® Movidius™
Software Development
Kit (SDK)
* * *
*
*‡
*‡
*‡
‡
DIRECT OPTIMIZATION
Intel® MKL/MKL-DNN,
clDNN, DAAL, Intel Python
Distribution, etc.
Intel® nGraph™ Library †
NNP Transformer
‡
CPU Transformer
†
Other

24. Today
DigitalSecurity&Surveillance
2018+
ScalingtoIndustrial&Retail,EnabledbySWTools
OpenVINO™
24

25. “Computer vision is concerned with the automatic
extraction, analysis and understanding of useful
information from a single image or a sequence of
images.”
Source: http://www.bmva.org/visionoverview

26. “OpenCV (Open Source Computer Vision Library) is an open source
computer vision and machine learning software library.”
• BSD License
• More than 2500 optimized algorithms
• User community with more than 47k people
• Estimated 14 million downloads
• C++, Python, Java and MATLAB interfaces
• Supports Linux, Windows, MacOS and Android
• Uses MMX and SSE instructions
• Officially launched in 1999, the OpenCV project was initially an Intel
Research initiative
Sources: https://opencv.org/about.html and https://en.wikipedia.org/wiki/OpenCV

27. • In a nutshell: a color image is a three dimensional array (one element for each
pixel, one layer for each color)
Computational image manipulation is
basically array-based math

28. • Open and loose definition: “an interesting part of an image”
• Some OpenCV algorithms from version 2.x are patented (removed on OpenCV
3.x)

29. The complexity of the problem (data set) dictates the network structure. The
more complex the problem, the more ‘features’ required, the deeper the
network.

30. Traditional
With OpenVINO™ Toolkit
Pre-trained Models
Video/Image
Pre-trained Models
Video/Image
One-Time Process
.xml, .bin
User Application + Inference
Engine
Model
Optimizer
User Application +
Inference

31. • Converts models from various frameworks (Intel® Optimization for Caffe*, Intel®
Optimization for TensorFlow*, Apache* MXNet*)
• Converts to a unified model (IR, later n-graph)
• Optimizes topologies (node merging, batch normalization elimination,
performing horizontal fusion)
• Folds constants paths in graph

32. • Simple and unified API for inference
across all Intel® architecture
• Optimized inference on large Intel®
architecture hardware targets
(CPU/GEN/FPGA)
• Heterogeneous support allows
execution of layers across hardware
types
• Asynchronous execution improves
performance
• Futureproof/scale development for
future Intel® architecture processors
Inference Engine Common API
PluginArchitecture
Inference
Engine
Runtime
Intel®
Movidius™ API
Intel® Movidius™
Myriad™ 2
DLA
Intel Integrated
Graphics (GPU)
CPU: Intel® Xeon®/Intel®
Core™/Intel Atom®
clDNN Plugin
Intel® MKL-DNN
Plugin
OpenCL™Intrinsics*
FPGA Plugin
Applications/Service
Intel® Arria®
10 FPGA
Intel® Movidius™
Plugin

33. • Power/Performance Efficiency Varies
– Running the right workload on the right
piece of hardware  higher efficiency
– Hardware acceleration is a must
– Heterogeneous computing?
• Tradeoffs
– Power/performance
– Price
– Software flexibility, portability
PowerEfficiency
Computation Flexibility
Dedicated
Hardware
GPU
CPU
X1
X10
X100 Vision Processing
Efficiency
Vision DSPs
FPGA

34. • Neural network accelerator in USB stick form factor
• Tensorflow* and Caffe* and many popular frames are
supported
• Prototype, tune, validate, and deploy deep neural networks at
the edge
• Features the same Intel® Movidius™ Vision Processing Unit
(VPU) used in drones, surveillance cameras, virtual reality
headsets, and other low-power intelligent and autonomous
products

35. Source: https://software.intel.com/en-us/distribution-for-python
• Support for Python 3.6
• Performance accelerations: Scikit-learn with Intel® Data Analytics Acceleration
Library (Intel® DAAL), fast Fourier transforms in SciPy and Numpy, universal
functions (ufuncs) can use multiple cores and Single Instructions Multiple Data
(SIMD), and neural network enhancements for pyDAAL
• Stand-Alone version: Linux*, Windows* and macOS*
• Conda* Packages
• Docker* Images
• Linux* Package Management Repositories (YUM / APT)
• Support forum

36. Internet of
Things
Artificial
Intelligence
Connected &
Autonomous
World
36

37. 37
Demo available at: https://intel.ly/2IVUMRp
Face Access Control Solution

38. 38
Internet
User
Interface
Gateway
Lock
MQTT
HTTP
Server 1
Application
Server 2
Front End
MQTT
Broker
MQTT

39. *Other names and brands may be claimed as the property of others.
39

40. Inspiringandinvestingindevelopers
1 The total addressable market for IoT was 7.4M developers in Q2 2017, Developer Economics Q3 2017 | www.DeveloperEconomics.com & Slash Data
2 IoT devices 50 billion by 2020 representing $6 trillion invested, Technocracy News & Trends 2016, & PCMag
IoTDevelopersandgrowing1
Multi-$Billionsinmarketopportunities2
7.4Million
40

41. KITS IDEs
Resources
Optimization Notice
Copyright © 2018, Intel Corporation. All rights reserved. *Other names and brands may be claimed as the property of others.
UP Squared* Grove*
IoT Development Kit
For Rapid Prototyping
For Production &
Performance Optimization
Hardware Board
OS
Sensors
Plugs-in easily into Eclipse*, Microsoft Visual Studio*,
or Wind River Workbench*
150+ code samples
Reference implementations
Tools, Libraries, SDKs, APIs
Sensor drivers
SDKs
Accelerate Computer Vision,
Integrate Deep Learning Inference
OpenVINO™
Deliver Fast, High-Density Video
& Image Processing - Intel® Media SDK or
Intel® Media Server Studio
Customize Solutions,
Optimize Compute with Intel® Graphics
Intel® SDK for OpenCL* Applications
FREE Special Function SDKs:
software.intel.com/IoT
How-to articles
Documentation
OS resources
41

42. Learn Develop Share
 Online tutorials
 Webinars
 Student kits
 Support forums
 Intel Optimized
Frameworks
 Exclusive access
to Intel® AI
DevCloud
 Project showcase
opportunities at
 Intel Developer
Mesh
 Industry &
Academic events
 Comprehensive
courseware
 Hands-on labs
 Cloud compute
 Technical Support
Teach
For developers, students, instructors and startups
Intel®AIacademy
software.intel.com/ai