SlideShare uma empresa Scribd logo
1 de 30
Baixar para ler offline
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Bringing Intelligent Motion Using
Reinforcement Learning On Intel Client
Manuj Sabharwal, Yaz Khabiri
Agenda
3
Ø Overview of Reinforcement Learning (RL)
Ø Reinforcement Learning in Gaming
Ø Training RL Algorithms
Ø Intelligent Motion Use case
Ø Performance Optimization on Intel® CPU
Ø Inference RL Algorithms
Ø Understanding Motion models
Ø Using DirectML* to leverage Intel GPUs
Ø Summary
Overview of Machine Learning
4
4
m
Machine Learning
Supervised Unsupervised Reinforcement
Data; labels à Class
Task driven
Data à Cluster State à Action
Learn from mistake
Successes Of
Reinforcement
Learning
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
High-Level Reinforcement Learning Overview
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Agent gets state (s) from environment
Agent takes action (a) using policy (π)
Agent receives reward (r)
Goal: Maximize large future reward return (R)
https://unity3d.com/machine-learning
Examples Of RL Algorithms
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
• Actor-Critic algorithms (model based learning)*
• Reduce variance of policy gradient using the actor
(the policy) and critic (value function)
• Value Based
• Q-Learning
• Find best action under current state
• Policy based
• Trust Region Policy Optimization
• Generalized Advantage estimation
http://rail.eecs.berkeley.edu/deeprlcourse-fa17/f17docs/lecture_3_rl_intro.pdf
Brain behind Algorithms
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
• Value Functions
• How much reward a state or an action by prediction of total future
reward (return)
• Policy Methods
• Find the best action directly
• Optimize policy (behavior) directly
• Vanilla Policy Gradients
• For every episode with positive reward use gradient to increase
probability of future actions
• Improved Policy Gradients
• Multiple gradient steps per episode
Popular Path
To Bring
Machine
Learning In
Games
• Microsoft*
• DirectML (DML) framework
• Ubisoft* – LaForge
• Bringing research into industry
• Access to game engines and data
• Unity*
• First party support via ML-Agents
• Interface between research and gaming
• DML backend coming soon
Motion With Reinforcement Learning
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
• Understanding path or motion planning problem is crucial in
unstructured environment
• Data driven input in combination of physics based animation character to create
smooth and robust animation
• RL offers a convenient framework for learning different strategies without
mountain of data
• Solves generalization problems by path or motion planning
Deep Q-Networks : Volodymyr Mnih, Deep RL Bootcamp, Berkeley, DeepMind*
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
• Q-learning (Q) : State × Action → Result, if we were to take an action in a given
state, then we could easily construct a policy that maximizes our rewards:
• A = argmax Q (s,a)
• Neural network helps to resemble Q as it can calculate universal function approximators
• Q(s,a)=r+γQa’(sʹ,aʹ))
Equations to framework
(e.g. Q-Learning à DQN Learning)
Layer-1 Layer-3Layer-2state Q(s,n)
conv conv conv FC FC
Q Values
Straight
Left
Right
Activation
function
Activation
function
Activation
function
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Evaluating Motion Algorithms On Intel® Core Processors
https://github.com/xbpeng/DeepMimic
0 500 1000 1500 2000 2500 3000 3500
5
10
15
20
25
30
35
40
45
50
55
60
Minutes
MillionIterations
TensorFlow Baseline
~52hours of training on
8Core platform
~52hours to train on CPU à Can we do better?
Testing by Intel as of June 28th , 2019 Intel® i9-9900k, 95W TDP, 8C16T; Frequency : 4.3Ghz, Turbo Enabled Graphics: NVIDIA* GTX 2080, Memory: 4x8GB@2133Mhz, Storage: Intel SSD 545 Series 240GB, OS: Windows* 10 RS5
BIOS build: CFLSFX1.R00.X151B01. All data is collected with Tensorflow* 1.12 and DeepMimic branch dates June 28th 2019
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Analyzing Software Stack
~20% of actual time is spend in compute and rest are overhead
Intel® VTune™ Amplifier XE
Actual compute
Inefficiency due to spins
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Optimizing the Software Stack - 1
ØRe-evaluating libraries included in software stack for DeepMimic
• Recompiling Tensorflow* with Intel® MKLDNN
bazel --output_base=output_dir build --config=mkl --config=opt
//tensorflow/tools/pip_package:build_pip_package
python -c "import tensorflow; print(tensorflow.pywrap_tensorflow.IsMklEnabled())“ à Result : True
• Evaluate different threading parameters to reduce spin time
import tensorflow # this sets KMP_BLOCKTIME and OMP_PROC_BIND
import os # delete the existing values
del os.environ['OMP_PROC_BIND’]
del os.environ['KMP_BLOCKTIME’]
ØMoving Python installation à Optimize Intel Python libraries
• Simple optimizations by moving numpy libraries to more efficient Intel
Numpy libraries
Optimizing the Software Stack - 2
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
ØOptimizing math libraries to use FP32 datatype and parallelism instead of
double precision and scalar code
• Mapping libraries from Eigen scaler to Eigen with MKL
Compiling EIGEN with MKL and Bullet3 (Physics SDK : real-time collision library) to use
AVX2 code path
Optimization Results
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Baseline After Optimizations
Putting CPUs to Work
• Application is able to train with acceptable compute instead of spinning
• Most of spinning from OpenMP and threading is removed due to Tensorflow with MKLDNN
• Eigen MKL library in DeepMimic Core is able to take advantage of intrinsic code
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
• Optimizing training is first step for deployment
• Correct libraries and datatype is important for deep learning training
performance
Training Result with Optimized Stack
Reducing training time by 2.6x by enabling multithreading and using MKLDNN instead of Eigen à 50hours to 19hours
0
1000
2000
3000
4000
5 10 15 20 25 30 35 40 45 50 55 60
MINUTES
ITERATIONS (MILLIONS)
Timing After Optimizations
TensorFlow - Baseline TensorFlow- MKLDNN Tensorflow+MKLDNN+EIGEN Libs
2.6x better training performance
Take-away
Use of optimization libraries to train machine
learning algorithms help to boost
performance and reduce training time
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Bringing Motion to Production
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Understanding inference model
Training checkpoint
Inference Model
How can developer read?
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Unity® ML Agents
Bridging Gap between Research and Game integration
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Overview : Unity ML-Agents
Unity
Environment
Agent
Collect
Observations
Agent Action
Vector Action
Brain
Academy
Unity Inference Engine
DirectML CS CPU
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
• Goal: Puppy runs for bone
• Agent: Corgi
• About 50 float32 inputs
• Three hidden layers of 512 nodes
• About 20 float output
Puppo Motion Using Unity ML Agent
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Analyzing inference performance à 1 Agent
No Meta command : 1.8 seconds/inference
Meta command : 0.8 seconds/inference
https://devblogs.microsoft.com/pix/download/
Execution time reduced by 2x with meta commands on kernel level
Microsoft® PIX Tool – Benefits of using Meta Commands
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
3.064msec
1.364msec
More the Agents à Better performance with Metacommands
Results
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
0.00
0.50
1.00
1.50
2.00
2.50
0
0.5
1
1.5
2
2.5
3
3.5
4
4.5
1 Agent 10 Agent 50 Agent
GAIN(%)
MSEC
SCALING WITH Multiple AGENTS
Computer Shader Metacommands Gain
Lower is better
Metacommands gives significant boost in performance by leveraging Intel® Graphics
driver optimizations
Intel® Graphics Performance Analyzer (GPA) DX12 Profiling
Preview
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
DX12 DirectML profiling in Intel® GPA
Summary
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
• Tensorflow with Intel® MKLDNN build is now available on Windows
• Leveraging new instruction set on Intel® Xeon™ and Core™ Processors
• Performance boost on training as Reinforcement learning use cases are
CPU favorable
• Using optimized pre-post libraries gives E2E performance boost
• DirectML from Microsoft leverages metacommands which gives good boost
in performance for game + deep learning infused workloads
References
SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
Tensorflow https://www.tensorflow.org/
Tensorflow Optimization guide https://software.intel.com/en-us/articles/intel-
optimization-for-tensorflow-installation-guide
DeepMimic https://github.com/xbpeng/DeepMimic/tree/master/learning
AI4Animation https://github.com/xbpeng/DeepMimic/tree/master/learning
Unity-ML Agents https://github.com/Unity-Technologies/ml-agents
RL beginner guide https://skymind.ai/wiki/deep-reinforcement-learning
Gym https://gym.openai.com/
Ubisoft https://montreal.ubisoft.com/en/our-engagements/research-and-
development/
Intel® GPA - https://software.intel.com/en-us/gpa
• Subtitle Copy Goes Here

Mais conteúdo relacionado

Mais procurados

AIDC NY: BODO AI Presentation - 09.19.2019
AIDC NY: BODO AI Presentation - 09.19.2019AIDC NY: BODO AI Presentation - 09.19.2019
AIDC NY: BODO AI Presentation - 09.19.2019Intel® Software
 
Ray Tracing with Intel® Embree and Intel® OSPRay: Use Cases and Updates | SIG...
Ray Tracing with Intel® Embree and Intel® OSPRay: Use Cases and Updates | SIG...Ray Tracing with Intel® Embree and Intel® OSPRay: Use Cases and Updates | SIG...
Ray Tracing with Intel® Embree and Intel® OSPRay: Use Cases and Updates | SIG...Intel® Software
 
Simple Single Instruction Multiple Data (SIMD) with the Intel® Implicit SPMD ...
Simple Single Instruction Multiple Data (SIMD) with the Intel® Implicit SPMD ...Simple Single Instruction Multiple Data (SIMD) with the Intel® Implicit SPMD ...
Simple Single Instruction Multiple Data (SIMD) with the Intel® Implicit SPMD ...Intel® Software
 
Reducing Deep Learning Integration Costs and Maximizing Compute Efficiency| S...
Reducing Deep Learning Integration Costs and Maximizing Compute Efficiency| S...Reducing Deep Learning Integration Costs and Maximizing Compute Efficiency| S...
Reducing Deep Learning Integration Costs and Maximizing Compute Efficiency| S...Intel® Software
 
AIDC Summit LA- Hands-on Training
AIDC Summit LA- Hands-on Training AIDC Summit LA- Hands-on Training
AIDC Summit LA- Hands-on Training Intel® Software
 
Streamline End-to-End AI Pipelines with Intel, Databricks, and OmniSci
Streamline End-to-End AI Pipelines with Intel, Databricks, and OmniSciStreamline End-to-End AI Pipelines with Intel, Databricks, and OmniSci
Streamline End-to-End AI Pipelines with Intel, Databricks, and OmniSciIntel® Software
 
oneAPI: Industry Initiative & Intel Product
oneAPI: Industry Initiative & Intel ProductoneAPI: Industry Initiative & Intel Product
oneAPI: Industry Initiative & Intel ProductTyrone Systems
 
Create a Scalable and Destructible World in HITMAN 2*
Create a Scalable and Destructible World in HITMAN 2*Create a Scalable and Destructible World in HITMAN 2*
Create a Scalable and Destructible World in HITMAN 2*Intel® Software
 
AIDC Summit LA: LA Drones Solution Overview
AIDC Summit LA: LA Drones Solution OverviewAIDC Summit LA: LA Drones Solution Overview
AIDC Summit LA: LA Drones Solution OverviewIntel® Software
 
Streamed Cloud Gaming Solutions for Android* and PC Games
Streamed Cloud Gaming Solutions for Android* and PC GamesStreamed Cloud Gaming Solutions for Android* and PC Games
Streamed Cloud Gaming Solutions for Android* and PC GamesIntel® Software
 
The Architecture of 11th Generation Intel® Processor Graphics
The Architecture of 11th Generation Intel® Processor GraphicsThe Architecture of 11th Generation Intel® Processor Graphics
The Architecture of 11th Generation Intel® Processor GraphicsIntel® Software
 
Accelerate Large-Scale Inverse Kinematics with the Intel® Distribution of Ope...
Accelerate Large-Scale Inverse Kinematics with the Intel® Distribution of Ope...Accelerate Large-Scale Inverse Kinematics with the Intel® Distribution of Ope...
Accelerate Large-Scale Inverse Kinematics with the Intel® Distribution of Ope...Intel® Software
 
TDC2019 Intel Software Day - Otimizacao grafica com o Intel GPA
TDC2019 Intel Software Day - Otimizacao grafica com o Intel GPATDC2019 Intel Software Day - Otimizacao grafica com o Intel GPA
TDC2019 Intel Software Day - Otimizacao grafica com o Intel GPAtdc-globalcode
 
A Primer on FPGAs - Field Programmable Gate Arrays
A Primer on FPGAs - Field Programmable Gate ArraysA Primer on FPGAs - Field Programmable Gate Arrays
A Primer on FPGAs - Field Programmable Gate ArraysTaylor Riggan
 
Automated ML Workflow for Distributed Big Data Using Analytics Zoo (CVPR2020 ...
Automated ML Workflow for Distributed Big Data Using Analytics Zoo (CVPR2020 ...Automated ML Workflow for Distributed Big Data Using Analytics Zoo (CVPR2020 ...
Automated ML Workflow for Distributed Big Data Using Analytics Zoo (CVPR2020 ...Jason Dai
 
Embree Ray Tracing Kernels | Overview and New Features | SIGGRAPH 2018 Tech S...
Embree Ray Tracing Kernels | Overview and New Features | SIGGRAPH 2018 Tech S...Embree Ray Tracing Kernels | Overview and New Features | SIGGRAPH 2018 Tech S...
Embree Ray Tracing Kernels | Overview and New Features | SIGGRAPH 2018 Tech S...Intel® Software
 
It Doesn't Have to Be Hard: How to Fix Your Performance Woes
It Doesn't Have to Be Hard: How to Fix Your Performance WoesIt Doesn't Have to Be Hard: How to Fix Your Performance Woes
It Doesn't Have to Be Hard: How to Fix Your Performance WoesIntel® Software
 
Scalability for All: Unreal Engine* 4 with Intel
Scalability for All: Unreal Engine* 4 with Intel Scalability for All: Unreal Engine* 4 with Intel
Scalability for All: Unreal Engine* 4 with Intel Intel® Software
 

Mais procurados (20)

Intel Developer Program
Intel Developer ProgramIntel Developer Program
Intel Developer Program
 
AIDC NY: BODO AI Presentation - 09.19.2019
AIDC NY: BODO AI Presentation - 09.19.2019AIDC NY: BODO AI Presentation - 09.19.2019
AIDC NY: BODO AI Presentation - 09.19.2019
 
Ray Tracing with Intel® Embree and Intel® OSPRay: Use Cases and Updates | SIG...
Ray Tracing with Intel® Embree and Intel® OSPRay: Use Cases and Updates | SIG...Ray Tracing with Intel® Embree and Intel® OSPRay: Use Cases and Updates | SIG...
Ray Tracing with Intel® Embree and Intel® OSPRay: Use Cases and Updates | SIG...
 
Simple Single Instruction Multiple Data (SIMD) with the Intel® Implicit SPMD ...
Simple Single Instruction Multiple Data (SIMD) with the Intel® Implicit SPMD ...Simple Single Instruction Multiple Data (SIMD) with the Intel® Implicit SPMD ...
Simple Single Instruction Multiple Data (SIMD) with the Intel® Implicit SPMD ...
 
Reducing Deep Learning Integration Costs and Maximizing Compute Efficiency| S...
Reducing Deep Learning Integration Costs and Maximizing Compute Efficiency| S...Reducing Deep Learning Integration Costs and Maximizing Compute Efficiency| S...
Reducing Deep Learning Integration Costs and Maximizing Compute Efficiency| S...
 
AIDC Summit LA- Hands-on Training
AIDC Summit LA- Hands-on Training AIDC Summit LA- Hands-on Training
AIDC Summit LA- Hands-on Training
 
Streamline End-to-End AI Pipelines with Intel, Databricks, and OmniSci
Streamline End-to-End AI Pipelines with Intel, Databricks, and OmniSciStreamline End-to-End AI Pipelines with Intel, Databricks, and OmniSci
Streamline End-to-End AI Pipelines with Intel, Databricks, and OmniSci
 
oneAPI: Industry Initiative & Intel Product
oneAPI: Industry Initiative & Intel ProductoneAPI: Industry Initiative & Intel Product
oneAPI: Industry Initiative & Intel Product
 
Create a Scalable and Destructible World in HITMAN 2*
Create a Scalable and Destructible World in HITMAN 2*Create a Scalable and Destructible World in HITMAN 2*
Create a Scalable and Destructible World in HITMAN 2*
 
AIDC Summit LA: LA Drones Solution Overview
AIDC Summit LA: LA Drones Solution OverviewAIDC Summit LA: LA Drones Solution Overview
AIDC Summit LA: LA Drones Solution Overview
 
Streamed Cloud Gaming Solutions for Android* and PC Games
Streamed Cloud Gaming Solutions for Android* and PC GamesStreamed Cloud Gaming Solutions for Android* and PC Games
Streamed Cloud Gaming Solutions for Android* and PC Games
 
AIDC India - AI on IA
AIDC India  - AI on IAAIDC India  - AI on IA
AIDC India - AI on IA
 
The Architecture of 11th Generation Intel® Processor Graphics
The Architecture of 11th Generation Intel® Processor GraphicsThe Architecture of 11th Generation Intel® Processor Graphics
The Architecture of 11th Generation Intel® Processor Graphics
 
Accelerate Large-Scale Inverse Kinematics with the Intel® Distribution of Ope...
Accelerate Large-Scale Inverse Kinematics with the Intel® Distribution of Ope...Accelerate Large-Scale Inverse Kinematics with the Intel® Distribution of Ope...
Accelerate Large-Scale Inverse Kinematics with the Intel® Distribution of Ope...
 
TDC2019 Intel Software Day - Otimizacao grafica com o Intel GPA
TDC2019 Intel Software Day - Otimizacao grafica com o Intel GPATDC2019 Intel Software Day - Otimizacao grafica com o Intel GPA
TDC2019 Intel Software Day - Otimizacao grafica com o Intel GPA
 
A Primer on FPGAs - Field Programmable Gate Arrays
A Primer on FPGAs - Field Programmable Gate ArraysA Primer on FPGAs - Field Programmable Gate Arrays
A Primer on FPGAs - Field Programmable Gate Arrays
 
Automated ML Workflow for Distributed Big Data Using Analytics Zoo (CVPR2020 ...
Automated ML Workflow for Distributed Big Data Using Analytics Zoo (CVPR2020 ...Automated ML Workflow for Distributed Big Data Using Analytics Zoo (CVPR2020 ...
Automated ML Workflow for Distributed Big Data Using Analytics Zoo (CVPR2020 ...
 
Embree Ray Tracing Kernels | Overview and New Features | SIGGRAPH 2018 Tech S...
Embree Ray Tracing Kernels | Overview and New Features | SIGGRAPH 2018 Tech S...Embree Ray Tracing Kernels | Overview and New Features | SIGGRAPH 2018 Tech S...
Embree Ray Tracing Kernels | Overview and New Features | SIGGRAPH 2018 Tech S...
 
It Doesn't Have to Be Hard: How to Fix Your Performance Woes
It Doesn't Have to Be Hard: How to Fix Your Performance WoesIt Doesn't Have to Be Hard: How to Fix Your Performance Woes
It Doesn't Have to Be Hard: How to Fix Your Performance Woes
 
Scalability for All: Unreal Engine* 4 with Intel
Scalability for All: Unreal Engine* 4 with Intel Scalability for All: Unreal Engine* 4 with Intel
Scalability for All: Unreal Engine* 4 with Intel
 

Semelhante a SIGGRAPH 2019 Conference in Los Angeles, 28 July - 1 August

Python* Scalability in Production Environments
Python* Scalability in Production EnvironmentsPython* Scalability in Production Environments
Python* Scalability in Production EnvironmentsIntel® Software
 
Large Model support and Distribute deep learning
Large Model support and Distribute deep learningLarge Model support and Distribute deep learning
Large Model support and Distribute deep learningGanesan Narayanasamy
 
(Im2col)accelerating deep neural networks on low power heterogeneous architec...
(Im2col)accelerating deep neural networks on low power heterogeneous architec...(Im2col)accelerating deep neural networks on low power heterogeneous architec...
(Im2col)accelerating deep neural networks on low power heterogeneous architec...Bomm Kim
 
Continuous Machine and Deep Learning with Apache Ignite
Continuous Machine and Deep Learning with Apache IgniteContinuous Machine and Deep Learning with Apache Ignite
Continuous Machine and Deep Learning with Apache IgniteDenis Magda
 
AI Bridging Cloud Infrastructure (ABCI) and its communication performance
AI Bridging Cloud Infrastructure (ABCI) and its communication performanceAI Bridging Cloud Infrastructure (ABCI) and its communication performance
AI Bridging Cloud Infrastructure (ABCI) and its communication performanceinside-BigData.com
 
Accelerating Data Science With GPUs
Accelerating Data Science With GPUsAccelerating Data Science With GPUs
Accelerating Data Science With GPUsiguazio
 
DATE 2020: Design, Automation and Test in Europe Conference
DATE 2020: Design, Automation and Test in Europe ConferenceDATE 2020: Design, Automation and Test in Europe Conference
DATE 2020: Design, Automation and Test in Europe ConferenceLEGATO project
 
Enabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. LowndesEnabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. LowndesWithTheBest
 
"How to Get the Best Deep Learning Performance with the OpenVINO Toolkit," a ...
"How to Get the Best Deep Learning Performance with the OpenVINO Toolkit," a ..."How to Get the Best Deep Learning Performance with the OpenVINO Toolkit," a ...
"How to Get the Best Deep Learning Performance with the OpenVINO Toolkit," a ...Edge AI and Vision Alliance
 
Nexxworks bootcamp ML6 (27/09/2017)
Nexxworks bootcamp ML6 (27/09/2017)Nexxworks bootcamp ML6 (27/09/2017)
Nexxworks bootcamp ML6 (27/09/2017)Karel Dumon
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)ijceronline
 
Zipline—Airbnb’s Declarative Feature Engineering Framework
Zipline—Airbnb’s Declarative Feature Engineering FrameworkZipline—Airbnb’s Declarative Feature Engineering Framework
Zipline—Airbnb’s Declarative Feature Engineering FrameworkDatabricks
 
How to Get the Best Deep Learning performance with OpenVINO Toolkit
How to Get the Best Deep Learning performance with OpenVINO ToolkitHow to Get the Best Deep Learning performance with OpenVINO Toolkit
How to Get the Best Deep Learning performance with OpenVINO ToolkitYury Gorbachev
 
Onyx relap5 Presentation from SCS 2019
Onyx relap5 Presentation from SCS 2019Onyx relap5 Presentation from SCS 2019
Onyx relap5 Presentation from SCS 2019GSE Systems, Inc.
 
Alluxio Webinar - Maximize GPU Utilization for Model Training
Alluxio Webinar - Maximize GPU Utilization for Model TrainingAlluxio Webinar - Maximize GPU Utilization for Model Training
Alluxio Webinar - Maximize GPU Utilization for Model TrainingAlluxio, Inc.
 
GPGPU Accelerates PostgreSQL (English)
GPGPU Accelerates PostgreSQL (English)GPGPU Accelerates PostgreSQL (English)
GPGPU Accelerates PostgreSQL (English)Kohei KaiGai
 
Debug, Analyze and Optimize Games with Intel Tools
Debug, Analyze and Optimize Games with Intel Tools Debug, Analyze and Optimize Games with Intel Tools
Debug, Analyze and Optimize Games with Intel Tools Matteo Valoriani
 

Semelhante a SIGGRAPH 2019 Conference in Los Angeles, 28 July - 1 August (20)

Python* Scalability in Production Environments
Python* Scalability in Production EnvironmentsPython* Scalability in Production Environments
Python* Scalability in Production Environments
 
Intel python 2017
Intel python 2017Intel python 2017
Intel python 2017
 
Large Model support and Distribute deep learning
Large Model support and Distribute deep learningLarge Model support and Distribute deep learning
Large Model support and Distribute deep learning
 
OpenPOWER Boot camp in Zurich
OpenPOWER Boot camp in ZurichOpenPOWER Boot camp in Zurich
OpenPOWER Boot camp in Zurich
 
(Im2col)accelerating deep neural networks on low power heterogeneous architec...
(Im2col)accelerating deep neural networks on low power heterogeneous architec...(Im2col)accelerating deep neural networks on low power heterogeneous architec...
(Im2col)accelerating deep neural networks on low power heterogeneous architec...
 
Continuous Machine and Deep Learning with Apache Ignite
Continuous Machine and Deep Learning with Apache IgniteContinuous Machine and Deep Learning with Apache Ignite
Continuous Machine and Deep Learning with Apache Ignite
 
AI Bridging Cloud Infrastructure (ABCI) and its communication performance
AI Bridging Cloud Infrastructure (ABCI) and its communication performanceAI Bridging Cloud Infrastructure (ABCI) and its communication performance
AI Bridging Cloud Infrastructure (ABCI) and its communication performance
 
Accelerating Data Science With GPUs
Accelerating Data Science With GPUsAccelerating Data Science With GPUs
Accelerating Data Science With GPUs
 
DATE 2020: Design, Automation and Test in Europe Conference
DATE 2020: Design, Automation and Test in Europe ConferenceDATE 2020: Design, Automation and Test in Europe Conference
DATE 2020: Design, Automation and Test in Europe Conference
 
Enabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. LowndesEnabling Artificial Intelligence - Alison B. Lowndes
Enabling Artificial Intelligence - Alison B. Lowndes
 
"How to Get the Best Deep Learning Performance with the OpenVINO Toolkit," a ...
"How to Get the Best Deep Learning Performance with the OpenVINO Toolkit," a ..."How to Get the Best Deep Learning Performance with the OpenVINO Toolkit," a ...
"How to Get the Best Deep Learning Performance with the OpenVINO Toolkit," a ...
 
LEGaTO: Use cases
LEGaTO: Use casesLEGaTO: Use cases
LEGaTO: Use cases
 
Nexxworks bootcamp ML6 (27/09/2017)
Nexxworks bootcamp ML6 (27/09/2017)Nexxworks bootcamp ML6 (27/09/2017)
Nexxworks bootcamp ML6 (27/09/2017)
 
International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)International Journal of Computational Engineering Research(IJCER)
International Journal of Computational Engineering Research(IJCER)
 
Zipline—Airbnb’s Declarative Feature Engineering Framework
Zipline—Airbnb’s Declarative Feature Engineering FrameworkZipline—Airbnb’s Declarative Feature Engineering Framework
Zipline—Airbnb’s Declarative Feature Engineering Framework
 
How to Get the Best Deep Learning performance with OpenVINO Toolkit
How to Get the Best Deep Learning performance with OpenVINO ToolkitHow to Get the Best Deep Learning performance with OpenVINO Toolkit
How to Get the Best Deep Learning performance with OpenVINO Toolkit
 
Onyx relap5 Presentation from SCS 2019
Onyx relap5 Presentation from SCS 2019Onyx relap5 Presentation from SCS 2019
Onyx relap5 Presentation from SCS 2019
 
Alluxio Webinar - Maximize GPU Utilization for Model Training
Alluxio Webinar - Maximize GPU Utilization for Model TrainingAlluxio Webinar - Maximize GPU Utilization for Model Training
Alluxio Webinar - Maximize GPU Utilization for Model Training
 
GPGPU Accelerates PostgreSQL (English)
GPGPU Accelerates PostgreSQL (English)GPGPU Accelerates PostgreSQL (English)
GPGPU Accelerates PostgreSQL (English)
 
Debug, Analyze and Optimize Games with Intel Tools
Debug, Analyze and Optimize Games with Intel Tools Debug, Analyze and Optimize Games with Intel Tools
Debug, Analyze and Optimize Games with Intel Tools
 

Mais de Intel® Software

AI for All: Biology is eating the world & AI is eating Biology
AI for All: Biology is eating the world & AI is eating Biology AI for All: Biology is eating the world & AI is eating Biology
AI for All: Biology is eating the world & AI is eating Biology Intel® Software
 
Python Data Science and Machine Learning at Scale with Intel and Anaconda
Python Data Science and Machine Learning at Scale with Intel and AnacondaPython Data Science and Machine Learning at Scale with Intel and Anaconda
Python Data Science and Machine Learning at Scale with Intel and AnacondaIntel® Software
 
AI for good: Scaling AI in science, healthcare, and more.
AI for good: Scaling AI in science, healthcare, and more.AI for good: Scaling AI in science, healthcare, and more.
AI for good: Scaling AI in science, healthcare, and more.Intel® Software
 
Advanced Techniques to Accelerate Model Tuning | Software for AI Optimization...
Advanced Techniques to Accelerate Model Tuning | Software for AI Optimization...Advanced Techniques to Accelerate Model Tuning | Software for AI Optimization...
Advanced Techniques to Accelerate Model Tuning | Software for AI Optimization...Intel® Software
 
AWS & Intel Webinar Series - Accelerating AI Research
AWS & Intel Webinar Series - Accelerating AI ResearchAWS & Intel Webinar Series - Accelerating AI Research
AWS & Intel Webinar Series - Accelerating AI ResearchIntel® Software
 
Intel AIDC Houston Summit - Overview Slides
Intel AIDC Houston Summit - Overview SlidesIntel AIDC Houston Summit - Overview Slides
Intel AIDC Houston Summit - Overview SlidesIntel® Software
 
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019Intel® Software
 
AIDC India - Intel Movidius / Open Vino Slides
AIDC India - Intel Movidius / Open Vino SlidesAIDC India - Intel Movidius / Open Vino Slides
AIDC India - Intel Movidius / Open Vino SlidesIntel® Software
 
AIDC India - AI Vision Slides
AIDC India - AI Vision SlidesAIDC India - AI Vision Slides
AIDC India - AI Vision SlidesIntel® Software
 
ANYFACE*: Create Film Industry-Quality Facial Rendering & Animation Using Mai...
ANYFACE*: Create Film Industry-Quality Facial Rendering & Animation Using Mai...ANYFACE*: Create Film Industry-Quality Facial Rendering & Animation Using Mai...
ANYFACE*: Create Film Industry-Quality Facial Rendering & Animation Using Mai...Intel® Software
 
Bring the Future of Entertainment to Your Living Room: MPEG-I Immersive Video...
Bring the Future of Entertainment to Your Living Room: MPEG-I Immersive Video...Bring the Future of Entertainment to Your Living Room: MPEG-I Immersive Video...
Bring the Future of Entertainment to Your Living Room: MPEG-I Immersive Video...Intel® Software
 
Intel® AI: Parameter Efficient Training
Intel® AI: Parameter Efficient TrainingIntel® AI: Parameter Efficient Training
Intel® AI: Parameter Efficient TrainingIntel® Software
 
Intel® AI: Non-Parametric Priors for Generative Adversarial Networks
Intel® AI: Non-Parametric Priors for Generative Adversarial Networks Intel® AI: Non-Parametric Priors for Generative Adversarial Networks
Intel® AI: Non-Parametric Priors for Generative Adversarial Networks Intel® Software
 
Persistent Memory Programming with Pmemkv
Persistent Memory Programming with PmemkvPersistent Memory Programming with Pmemkv
Persistent Memory Programming with PmemkvIntel® Software
 
Big Data Uses with Distributed Asynchronous Object Storage
Big Data Uses with Distributed Asynchronous Object StorageBig Data Uses with Distributed Asynchronous Object Storage
Big Data Uses with Distributed Asynchronous Object StorageIntel® Software
 
Debugging Tools & Techniques for Persistent Memory Programming
Debugging Tools & Techniques for Persistent Memory ProgrammingDebugging Tools & Techniques for Persistent Memory Programming
Debugging Tools & Techniques for Persistent Memory ProgrammingIntel® Software
 
Persistent Memory Development Kit (PMDK): State of the Project
Persistent Memory Development Kit (PMDK): State of the ProjectPersistent Memory Development Kit (PMDK): State of the Project
Persistent Memory Development Kit (PMDK): State of the ProjectIntel® Software
 

Mais de Intel® Software (17)

AI for All: Biology is eating the world & AI is eating Biology
AI for All: Biology is eating the world & AI is eating Biology AI for All: Biology is eating the world & AI is eating Biology
AI for All: Biology is eating the world & AI is eating Biology
 
Python Data Science and Machine Learning at Scale with Intel and Anaconda
Python Data Science and Machine Learning at Scale with Intel and AnacondaPython Data Science and Machine Learning at Scale with Intel and Anaconda
Python Data Science and Machine Learning at Scale with Intel and Anaconda
 
AI for good: Scaling AI in science, healthcare, and more.
AI for good: Scaling AI in science, healthcare, and more.AI for good: Scaling AI in science, healthcare, and more.
AI for good: Scaling AI in science, healthcare, and more.
 
Advanced Techniques to Accelerate Model Tuning | Software for AI Optimization...
Advanced Techniques to Accelerate Model Tuning | Software for AI Optimization...Advanced Techniques to Accelerate Model Tuning | Software for AI Optimization...
Advanced Techniques to Accelerate Model Tuning | Software for AI Optimization...
 
AWS & Intel Webinar Series - Accelerating AI Research
AWS & Intel Webinar Series - Accelerating AI ResearchAWS & Intel Webinar Series - Accelerating AI Research
AWS & Intel Webinar Series - Accelerating AI Research
 
Intel AIDC Houston Summit - Overview Slides
Intel AIDC Houston Summit - Overview SlidesIntel AIDC Houston Summit - Overview Slides
Intel AIDC Houston Summit - Overview Slides
 
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
AIDC NY: Applications of Intel AI by QuEST Global - 09.19.2019
 
AIDC India - Intel Movidius / Open Vino Slides
AIDC India - Intel Movidius / Open Vino SlidesAIDC India - Intel Movidius / Open Vino Slides
AIDC India - Intel Movidius / Open Vino Slides
 
AIDC India - AI Vision Slides
AIDC India - AI Vision SlidesAIDC India - AI Vision Slides
AIDC India - AI Vision Slides
 
ANYFACE*: Create Film Industry-Quality Facial Rendering & Animation Using Mai...
ANYFACE*: Create Film Industry-Quality Facial Rendering & Animation Using Mai...ANYFACE*: Create Film Industry-Quality Facial Rendering & Animation Using Mai...
ANYFACE*: Create Film Industry-Quality Facial Rendering & Animation Using Mai...
 
Bring the Future of Entertainment to Your Living Room: MPEG-I Immersive Video...
Bring the Future of Entertainment to Your Living Room: MPEG-I Immersive Video...Bring the Future of Entertainment to Your Living Room: MPEG-I Immersive Video...
Bring the Future of Entertainment to Your Living Room: MPEG-I Immersive Video...
 
Intel® AI: Parameter Efficient Training
Intel® AI: Parameter Efficient TrainingIntel® AI: Parameter Efficient Training
Intel® AI: Parameter Efficient Training
 
Intel® AI: Non-Parametric Priors for Generative Adversarial Networks
Intel® AI: Non-Parametric Priors for Generative Adversarial Networks Intel® AI: Non-Parametric Priors for Generative Adversarial Networks
Intel® AI: Non-Parametric Priors for Generative Adversarial Networks
 
Persistent Memory Programming with Pmemkv
Persistent Memory Programming with PmemkvPersistent Memory Programming with Pmemkv
Persistent Memory Programming with Pmemkv
 
Big Data Uses with Distributed Asynchronous Object Storage
Big Data Uses with Distributed Asynchronous Object StorageBig Data Uses with Distributed Asynchronous Object Storage
Big Data Uses with Distributed Asynchronous Object Storage
 
Debugging Tools & Techniques for Persistent Memory Programming
Debugging Tools & Techniques for Persistent Memory ProgrammingDebugging Tools & Techniques for Persistent Memory Programming
Debugging Tools & Techniques for Persistent Memory Programming
 
Persistent Memory Development Kit (PMDK): State of the Project
Persistent Memory Development Kit (PMDK): State of the ProjectPersistent Memory Development Kit (PMDK): State of the Project
Persistent Memory Development Kit (PMDK): State of the Project
 

Último

Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphNeo4j
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?XfilesPro
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 

Último (20)

Pigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping ElbowsPigging Solutions Piggable Sweeping Elbows
Pigging Solutions Piggable Sweeping Elbows
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
#StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge GraphSIEMENS: RAPUNZEL – A Tale About Knowledge Graph
SIEMENS: RAPUNZEL – A Tale About Knowledge Graph
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 

SIGGRAPH 2019 Conference in Los Angeles, 28 July - 1 August

  • 1. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
  • 2. Bringing Intelligent Motion Using Reinforcement Learning On Intel Client Manuj Sabharwal, Yaz Khabiri
  • 3. Agenda 3 Ø Overview of Reinforcement Learning (RL) Ø Reinforcement Learning in Gaming Ø Training RL Algorithms Ø Intelligent Motion Use case Ø Performance Optimization on Intel® CPU Ø Inference RL Algorithms Ø Understanding Motion models Ø Using DirectML* to leverage Intel GPUs Ø Summary
  • 4. Overview of Machine Learning 4 4 m Machine Learning Supervised Unsupervised Reinforcement Data; labels à Class Task driven Data à Cluster State à Action Learn from mistake
  • 5. Successes Of Reinforcement Learning SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
  • 6. High-Level Reinforcement Learning Overview SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Agent gets state (s) from environment Agent takes action (a) using policy (π) Agent receives reward (r) Goal: Maximize large future reward return (R) https://unity3d.com/machine-learning
  • 7. Examples Of RL Algorithms SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST • Actor-Critic algorithms (model based learning)* • Reduce variance of policy gradient using the actor (the policy) and critic (value function) • Value Based • Q-Learning • Find best action under current state • Policy based • Trust Region Policy Optimization • Generalized Advantage estimation http://rail.eecs.berkeley.edu/deeprlcourse-fa17/f17docs/lecture_3_rl_intro.pdf
  • 8. Brain behind Algorithms SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST • Value Functions • How much reward a state or an action by prediction of total future reward (return) • Policy Methods • Find the best action directly • Optimize policy (behavior) directly • Vanilla Policy Gradients • For every episode with positive reward use gradient to increase probability of future actions • Improved Policy Gradients • Multiple gradient steps per episode
  • 9. Popular Path To Bring Machine Learning In Games • Microsoft* • DirectML (DML) framework • Ubisoft* – LaForge • Bringing research into industry • Access to game engines and data • Unity* • First party support via ML-Agents • Interface between research and gaming • DML backend coming soon
  • 10. Motion With Reinforcement Learning SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST • Understanding path or motion planning problem is crucial in unstructured environment • Data driven input in combination of physics based animation character to create smooth and robust animation • RL offers a convenient framework for learning different strategies without mountain of data • Solves generalization problems by path or motion planning Deep Q-Networks : Volodymyr Mnih, Deep RL Bootcamp, Berkeley, DeepMind*
  • 11. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST • Q-learning (Q) : State × Action → Result, if we were to take an action in a given state, then we could easily construct a policy that maximizes our rewards: • A = argmax Q (s,a) • Neural network helps to resemble Q as it can calculate universal function approximators • Q(s,a)=r+γQa’(sʹ,aʹ)) Equations to framework (e.g. Q-Learning à DQN Learning) Layer-1 Layer-3Layer-2state Q(s,n) conv conv conv FC FC Q Values Straight Left Right Activation function Activation function Activation function
  • 12. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Evaluating Motion Algorithms On Intel® Core Processors https://github.com/xbpeng/DeepMimic 0 500 1000 1500 2000 2500 3000 3500 5 10 15 20 25 30 35 40 45 50 55 60 Minutes MillionIterations TensorFlow Baseline ~52hours of training on 8Core platform ~52hours to train on CPU à Can we do better? Testing by Intel as of June 28th , 2019 Intel® i9-9900k, 95W TDP, 8C16T; Frequency : 4.3Ghz, Turbo Enabled Graphics: NVIDIA* GTX 2080, Memory: 4x8GB@2133Mhz, Storage: Intel SSD 545 Series 240GB, OS: Windows* 10 RS5 BIOS build: CFLSFX1.R00.X151B01. All data is collected with Tensorflow* 1.12 and DeepMimic branch dates June 28th 2019
  • 13. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Analyzing Software Stack ~20% of actual time is spend in compute and rest are overhead Intel® VTune™ Amplifier XE Actual compute Inefficiency due to spins
  • 14. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Optimizing the Software Stack - 1 ØRe-evaluating libraries included in software stack for DeepMimic • Recompiling Tensorflow* with Intel® MKLDNN bazel --output_base=output_dir build --config=mkl --config=opt //tensorflow/tools/pip_package:build_pip_package python -c "import tensorflow; print(tensorflow.pywrap_tensorflow.IsMklEnabled())“ à Result : True • Evaluate different threading parameters to reduce spin time import tensorflow # this sets KMP_BLOCKTIME and OMP_PROC_BIND import os # delete the existing values del os.environ['OMP_PROC_BIND’] del os.environ['KMP_BLOCKTIME’] ØMoving Python installation à Optimize Intel Python libraries • Simple optimizations by moving numpy libraries to more efficient Intel Numpy libraries
  • 15. Optimizing the Software Stack - 2 SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST ØOptimizing math libraries to use FP32 datatype and parallelism instead of double precision and scalar code • Mapping libraries from Eigen scaler to Eigen with MKL Compiling EIGEN with MKL and Bullet3 (Physics SDK : real-time collision library) to use AVX2 code path
  • 16. Optimization Results SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Baseline After Optimizations Putting CPUs to Work • Application is able to train with acceptable compute instead of spinning • Most of spinning from OpenMP and threading is removed due to Tensorflow with MKLDNN • Eigen MKL library in DeepMimic Core is able to take advantage of intrinsic code
  • 17. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST • Optimizing training is first step for deployment • Correct libraries and datatype is important for deep learning training performance Training Result with Optimized Stack Reducing training time by 2.6x by enabling multithreading and using MKLDNN instead of Eigen à 50hours to 19hours 0 1000 2000 3000 4000 5 10 15 20 25 30 35 40 45 50 55 60 MINUTES ITERATIONS (MILLIONS) Timing After Optimizations TensorFlow - Baseline TensorFlow- MKLDNN Tensorflow+MKLDNN+EIGEN Libs 2.6x better training performance
  • 18. Take-away Use of optimization libraries to train machine learning algorithms help to boost performance and reduce training time SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
  • 19. Bringing Motion to Production SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST
  • 20. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Understanding inference model Training checkpoint Inference Model How can developer read?
  • 21. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Unity® ML Agents Bridging Gap between Research and Game integration
  • 22. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Overview : Unity ML-Agents Unity Environment Agent Collect Observations Agent Action Vector Action Brain Academy Unity Inference Engine DirectML CS CPU
  • 23. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST • Goal: Puppy runs for bone • Agent: Corgi • About 50 float32 inputs • Three hidden layers of 512 nodes • About 20 float output Puppo Motion Using Unity ML Agent
  • 24. SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Analyzing inference performance à 1 Agent No Meta command : 1.8 seconds/inference Meta command : 0.8 seconds/inference https://devblogs.microsoft.com/pix/download/ Execution time reduced by 2x with meta commands on kernel level
  • 25. Microsoft® PIX Tool – Benefits of using Meta Commands SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST 3.064msec 1.364msec More the Agents à Better performance with Metacommands
  • 26. Results SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST 0.00 0.50 1.00 1.50 2.00 2.50 0 0.5 1 1.5 2 2.5 3 3.5 4 4.5 1 Agent 10 Agent 50 Agent GAIN(%) MSEC SCALING WITH Multiple AGENTS Computer Shader Metacommands Gain Lower is better Metacommands gives significant boost in performance by leveraging Intel® Graphics driver optimizations
  • 27. Intel® Graphics Performance Analyzer (GPA) DX12 Profiling Preview SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST DX12 DirectML profiling in Intel® GPA
  • 28. Summary SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST • Tensorflow with Intel® MKLDNN build is now available on Windows • Leveraging new instruction set on Intel® Xeon™ and Core™ Processors • Performance boost on training as Reinforcement learning use cases are CPU favorable • Using optimized pre-post libraries gives E2E performance boost • DirectML from Microsoft leverages metacommands which gives good boost in performance for game + deep learning infused workloads
  • 29. References SIGGRAPH 2019 | LOS ANGLES | 28 JULY - 1 AUGUST Tensorflow https://www.tensorflow.org/ Tensorflow Optimization guide https://software.intel.com/en-us/articles/intel- optimization-for-tensorflow-installation-guide DeepMimic https://github.com/xbpeng/DeepMimic/tree/master/learning AI4Animation https://github.com/xbpeng/DeepMimic/tree/master/learning Unity-ML Agents https://github.com/Unity-Technologies/ml-agents RL beginner guide https://skymind.ai/wiki/deep-reinforcement-learning Gym https://gym.openai.com/ Ubisoft https://montreal.ubisoft.com/en/our-engagements/research-and- development/ Intel® GPA - https://software.intel.com/en-us/gpa
  • 30. • Subtitle Copy Goes Here