SlideShare a Scribd company logo
1 of 12
Download to read offline
© 2021 Lattice Semiconductor
Sreepada V Hegade
Sr. Manager – ML Software and Solutions
Flexible ML Solution with
Lattice FPGA
© 2021 Lattice Semiconductor
• Review Need for Flexibility in ML
• Flexible Hardware and Engines
• Flexibility with Cost
• Discussion on Trade-Off
• Framework to Enable Flexibility
• Conclusion
2
Agenda
© 2021 Lattice Semiconductor
Flexibility At Every Step
• Interface Flexibility
• Different Type of Sensors interface with required IPs to process sensor data
• Implementation Flexibility
• Proven library of networks, easy to use workflow
• Flexibility with Cost, Performance and Power
• Scalable solution
3
Sensor
Data
Aggregation
and
Augmentation
To
Inference
Post
Processing
Inference with Optimal Network
and Engine Configuration
1
2
3
© 2021 Lattice Semiconductor 4
HARDWARE PLATFORMS
IP CORES
SOFTWARE TOOLS
REFERENCE DESIGNS / DEMOS
CNN Compact
Accelerator
CNN
Accelerator
UPduino Himax Shield
– iCE40 UltraPlus FPGA
ECP5 EVDK
– ECP5 FPGA
CUSTOM DESIGN SERVICES
Smart Car
Smart
Home
Smart City Smart Factory
Neural Network
Compiler
Neural Network
Accelerators
Face
Detection
Speed Sign
Detection
Key Phrase
Detection
Face
Tracking
Object
Counting
Human
Presence
Detection
Hand
Gesture
Detection
1 mW, 5.5 mm2
1 W, 100 mm2
CNN Plus Accelerator
CrossLink-NX EVDK
– CrossLink-NX
50-200 mW 16 mm2
Our Solution
© 2021 Lattice Semiconductor 5
5mm2 16mm2
Flexible Interface
© 2021 Lattice Semiconductor 6
• High Performance at low power
• Configurable Engine (on-chip memory, number of
cores)
• Can support up to 60 fps QVGA and 30fps VGA
resolution image
• Supports TensorFlow on bare metal RISC-V +
coprocessor
• Good for background inference jobs like predictive
maintenance
• Shares computation resources
AHBL Interconnect
RISC-V
CPU
I$ D$
Data
Ram
UART
AHBL2APB
Bridge
PDM
Accelerator
FIFO
DMA
EtherControl
(Main)
QSPI
Memory
Control
+ prefetch
buffer
M S0
M
M S S
S
FIFO
Ethernet
IRQ0
IRQ2
S
M
IRQ1
APB Interconnect
S
GPIO
ISR
Ram
S S1
Configurable ML Engines
© 2021 Lattice Semiconductor 7
38FPS
320x240
48FPS
224x224
64FPS
160x160
48FPS
320x240
60FPS
224x224
72FPS
160x160
0
10
20
30
40
50
60
70
80
0 50 100 150 200 250 300
Frames
Per
Sec
On-Chip Memory (128KB -> 256KB)
32FPS
224x224 (VGG)
60FPS
224x224 (Mobile
Net)
48FPS
224x224 (VGG)
0
10
20
30
40
50
60
70
0 20 40 60 80 100
Frames
Per
Sec
DSP Blocks (48 -> 84 MUL9 Units)
Solution Cost Flexibility
© 2021 Lattice Semiconductor 8
38FPS
320x240 (QVGA)
48 FP
320x240 (QVGA)
0
10
20
30
40
50
60
0 50 100 150 200 250 300 350
Frames
Per
Sec
Runtime Size with Parameters (KB)
~20% performance
with 2% Accuracy loss
Trade-Off With Optimization
© 2021 Lattice Semiconductor 9
Model Zoo
Data
Capture
/ Label
Model
Selection
Transfer
Learning
Compile
Runtime
(inference)
Model
Visualize
(Dashboard)
Optimize
Train
Confi
gure
Evaluate
Framework to Enable Flexibility
© 2021 Lattice Semiconductor 10
Framework Demo
© 2021 Lattice Semiconductor 11
• Flexibility is NOT just about operations supported by engine
▪ It is required at every step
• Finding right trade-off is key to success
• Performance and Power optimized engine with trade-off options
• Lattice solution provides flexibility and framework to achieve right trade-off
• Many possibilities, One framework
Conclusion
Resources
http://www.latticesemi.com
E-mail
Sreepada.hegade@latticesemi.com

More Related Content

What's hot

Radarbook Brochure_TACTRON
Radarbook Brochure_TACTRONRadarbook Brochure_TACTRON
Radarbook Brochure_TACTRON
Georg Schmidt
 
Ieee 2015 - 2016 Vlsi title
Ieee 2015 - 2016 Vlsi titleIeee 2015 - 2016 Vlsi title
Ieee 2015 - 2016 Vlsi title
pgembeddedsystem
 
智慧城市通用交通資訊端點系統
智慧城市通用交通資訊端點系統智慧城市通用交通資訊端點系統
智慧城市通用交通資訊端點系統
艾鍗科技
 
3rd 3DDRESD: Red Line Overview
3rd 3DDRESD: Red Line Overview3rd 3DDRESD: Red Line Overview
3rd 3DDRESD: Red Line Overview
Marco Santambrogio
 

What's hot (20)

Advanced embedded training details & syllabus - Wiztech
Advanced embedded training details & syllabus - WiztechAdvanced embedded training details & syllabus - Wiztech
Advanced embedded training details & syllabus - Wiztech
 
Radarbook Brochure_TACTRON
Radarbook Brochure_TACTRONRadarbook Brochure_TACTRON
Radarbook Brochure_TACTRON
 
Implementing AI: Hardware Challenges: Ultra-Low Power AI at the Edge with Lat...
Implementing AI: Hardware Challenges: Ultra-Low Power AI at the Edge with Lat...Implementing AI: Hardware Challenges: Ultra-Low Power AI at the Edge with Lat...
Implementing AI: Hardware Challenges: Ultra-Low Power AI at the Edge with Lat...
 
Ieee Vlsi Titles
Ieee Vlsi TitlesIeee Vlsi Titles
Ieee Vlsi Titles
 
OSMC 2019 | On-board Diagnostics Monitoring and Alerting with Zabbix by Dmitr...
OSMC 2019 | On-board Diagnostics Monitoring and Alerting with Zabbix by Dmitr...OSMC 2019 | On-board Diagnostics Monitoring and Alerting with Zabbix by Dmitr...
OSMC 2019 | On-board Diagnostics Monitoring and Alerting with Zabbix by Dmitr...
 
2013 IEEE M.tech vlsi
2013 IEEE M.tech vlsi2013 IEEE M.tech vlsi
2013 IEEE M.tech vlsi
 
Ieee 2015 - 2016 Vlsi title
Ieee 2015 - 2016 Vlsi titleIeee 2015 - 2016 Vlsi title
Ieee 2015 - 2016 Vlsi title
 
IPv6 implementation for end users
IPv6 implementation for end usersIPv6 implementation for end users
IPv6 implementation for end users
 
High Performance DSP with Xilinx All Programmable Devices (Design Conference ...
High Performance DSP with Xilinx All Programmable Devices (Design Conference ...High Performance DSP with Xilinx All Programmable Devices (Design Conference ...
High Performance DSP with Xilinx All Programmable Devices (Design Conference ...
 
Ardu sat (Arduino based satellite)
Ardu sat (Arduino based satellite)Ardu sat (Arduino based satellite)
Ardu sat (Arduino based satellite)
 
RISC processors: MIPS, ARM and SPARC
RISC processors: MIPS, ARM and SPARCRISC processors: MIPS, ARM and SPARC
RISC processors: MIPS, ARM and SPARC
 
NS-HPDCA
NS-HPDCANS-HPDCA
NS-HPDCA
 
Kubernetes Native Infrastructure and CoreOS Operator Framework for 5G Edge Cl...
Kubernetes Native Infrastructure and CoreOS Operator Framework for 5G Edge Cl...Kubernetes Native Infrastructure and CoreOS Operator Framework for 5G Edge Cl...
Kubernetes Native Infrastructure and CoreOS Operator Framework for 5G Edge Cl...
 
Drive down latency and costs in the access network with the MicroMux™ Edge BiDi
Drive down latency and costs in the access network with the MicroMux™ Edge BiDiDrive down latency and costs in the access network with the MicroMux™ Edge BiDi
Drive down latency and costs in the access network with the MicroMux™ Edge BiDi
 
Alarm system presentation
Alarm system presentationAlarm system presentation
Alarm system presentation
 
智慧城市通用交通資訊端點系統
智慧城市通用交通資訊端點系統智慧城市通用交通資訊端點系統
智慧城市通用交通資訊端點系統
 
Stratix FPGA Overview
Stratix FPGA OverviewStratix FPGA Overview
Stratix FPGA Overview
 
UTM Appliance Fact Sheet
UTM Appliance Fact SheetUTM Appliance Fact Sheet
UTM Appliance Fact Sheet
 
How to Manage Your Time Series Data Pipeline at the Edge with InfluxDB
How to Manage Your Time Series Data Pipeline at the Edge with InfluxDBHow to Manage Your Time Series Data Pipeline at the Edge with InfluxDB
How to Manage Your Time Series Data Pipeline at the Edge with InfluxDB
 
3rd 3DDRESD: Red Line Overview
3rd 3DDRESD: Red Line Overview3rd 3DDRESD: Red Line Overview
3rd 3DDRESD: Red Line Overview
 

Similar to “Flexible Machine Learning Solutions with Lattice FPGAs,” a Presentation from Lattice Semiconductor

“Fast-track Design Cycles Using Lattice’s FPGAs,” a Presentation from Lattice...
“Fast-track Design Cycles Using Lattice’s FPGAs,” a Presentation from Lattice...“Fast-track Design Cycles Using Lattice’s FPGAs,” a Presentation from Lattice...
“Fast-track Design Cycles Using Lattice’s FPGAs,” a Presentation from Lattice...
Edge AI and Vision Alliance
 
“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...
“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...
“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...
Edge AI and Vision Alliance
 
intel Sync. & Edge Solution udpate xEng-v1.0.pptx
intel Sync. & Edge Solution udpate xEng-v1.0.pptxintel Sync. & Edge Solution udpate xEng-v1.0.pptx
intel Sync. & Edge Solution udpate xEng-v1.0.pptx
Alex Wooram Kim
 
Hari Krishna Vetsa Resume
Hari Krishna Vetsa ResumeHari Krishna Vetsa Resume
Hari Krishna Vetsa Resume
Hari Krishna
 

Similar to “Flexible Machine Learning Solutions with Lattice FPGAs,” a Presentation from Lattice Semiconductor (20)

“Fast-track Design Cycles Using Lattice’s FPGAs,” a Presentation from Lattice...
“Fast-track Design Cycles Using Lattice’s FPGAs,” a Presentation from Lattice...“Fast-track Design Cycles Using Lattice’s FPGAs,” a Presentation from Lattice...
“Fast-track Design Cycles Using Lattice’s FPGAs,” a Presentation from Lattice...
 
“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...
“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...
“Accelerate Tomorrow’s Models with Lattice FPGAs,” a Presentation from Lattic...
 
Webinar: NVIDIA JETSON – A Inteligência Artificial na palma de sua mão
Webinar: NVIDIA JETSON – A Inteligência Artificial na palma de sua mãoWebinar: NVIDIA JETSON – A Inteligência Artificial na palma de sua mão
Webinar: NVIDIA JETSON – A Inteligência Artificial na palma de sua mão
 
Building the SD-Branch using uCPE
Building the SD-Branch using uCPEBuilding the SD-Branch using uCPE
Building the SD-Branch using uCPE
 
Summit 16: Deploying Virtualized Mobile Infrastructures on Openstack
Summit 16: Deploying Virtualized Mobile Infrastructures on OpenstackSummit 16: Deploying Virtualized Mobile Infrastructures on Openstack
Summit 16: Deploying Virtualized Mobile Infrastructures on Openstack
 
ODSA Proof of Concept SmartNIC Speeds & Feeds
ODSA Proof of Concept SmartNIC Speeds & FeedsODSA Proof of Concept SmartNIC Speeds & Feeds
ODSA Proof of Concept SmartNIC Speeds & Feeds
 
DPDK summit 2015: It's kind of fun to do the impossible with DPDK
DPDK summit 2015: It's kind of fun  to do the impossible with DPDKDPDK summit 2015: It's kind of fun  to do the impossible with DPDK
DPDK summit 2015: It's kind of fun to do the impossible with DPDK
 
DPDK Summit 2015 - NTT - Yoshihiro Nakajima
DPDK Summit 2015 - NTT - Yoshihiro NakajimaDPDK Summit 2015 - NTT - Yoshihiro Nakajima
DPDK Summit 2015 - NTT - Yoshihiro Nakajima
 
Huawei Innovative ICT Solutions, CeBIT
Huawei Innovative ICT Solutions, CeBITHuawei Innovative ICT Solutions, CeBIT
Huawei Innovative ICT Solutions, CeBIT
 
intel Sync. & Edge Solution udpate xEng-v1.0.pptx
intel Sync. & Edge Solution udpate xEng-v1.0.pptxintel Sync. & Edge Solution udpate xEng-v1.0.pptx
intel Sync. & Edge Solution udpate xEng-v1.0.pptx
 
Webinar Renesas - IoT é Segura? Com Renesas Synergy sim! E o SSP 1.5 tornou a...
Webinar Renesas - IoT é Segura? Com Renesas Synergy sim! E o SSP 1.5 tornou a...Webinar Renesas - IoT é Segura? Com Renesas Synergy sim! E o SSP 1.5 tornou a...
Webinar Renesas - IoT é Segura? Com Renesas Synergy sim! E o SSP 1.5 tornou a...
 
Esperanto accelerates machine learning with 1000+ low power RISC-V cores on a...
Esperanto accelerates machine learning with 1000+ low power RISC-V cores on a...Esperanto accelerates machine learning with 1000+ low power RISC-V cores on a...
Esperanto accelerates machine learning with 1000+ low power RISC-V cores on a...
 
GTC 2022 Keynote
GTC 2022 KeynoteGTC 2022 Keynote
GTC 2022 Keynote
 
Dataplane networking acceleration with OpenDataplane / Максим Уваров (Linaro)
Dataplane networking acceleration with OpenDataplane / Максим Уваров (Linaro)Dataplane networking acceleration with OpenDataplane / Максим Уваров (Linaro)
Dataplane networking acceleration with OpenDataplane / Максим Уваров (Linaro)
 
Resume_Bhasker
Resume_BhaskerResume_Bhasker
Resume_Bhasker
 
VEDLIoT at FPL'23_Accelerators for Heterogenous Computing in AIoT
VEDLIoT at FPL'23_Accelerators for Heterogenous Computing in AIoTVEDLIoT at FPL'23_Accelerators for Heterogenous Computing in AIoT
VEDLIoT at FPL'23_Accelerators for Heterogenous Computing in AIoT
 
Intel xeon e5v3 y sdi
Intel xeon e5v3 y sdiIntel xeon e5v3 y sdi
Intel xeon e5v3 y sdi
 
Hari Krishna Vetsa Resume
Hari Krishna Vetsa ResumeHari Krishna Vetsa Resume
Hari Krishna Vetsa Resume
 
SoC~FPGA~ASIC~Embedded
SoC~FPGA~ASIC~EmbeddedSoC~FPGA~ASIC~Embedded
SoC~FPGA~ASIC~Embedded
 
Новые коммутаторы QFX10000. Технология JunOS Fusion
Новые коммутаторы QFX10000. Технология JunOS FusionНовые коммутаторы QFX10000. Технология JunOS Fusion
Новые коммутаторы QFX10000. Технология JunOS Fusion
 

More from Edge AI and Vision Alliance

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
Edge AI and Vision Alliance
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
Edge AI and Vision Alliance
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
Edge AI and Vision Alliance
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
Edge AI and Vision Alliance
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
Edge AI and Vision Alliance
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
Edge AI and Vision Alliance
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
Edge AI and Vision Alliance
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
Edge AI and Vision Alliance
 

More from Edge AI and Vision Alliance (20)

“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
“Learning Compact DNN Models for Embedded Vision,” a Presentation from the Un...
 
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
“Introduction to Computer Vision with CNNs,” a Presentation from Mohammad Hag...
 
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
“Selecting Tools for Developing, Monitoring and Maintaining ML Models,” a Pre...
 
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
“Building Accelerated GStreamer Applications for Video and Audio AI,” a Prese...
 
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
“Understanding, Selecting and Optimizing Object Detectors for Edge Applicatio...
 
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
“Introduction to Modern LiDAR for Machine Perception,” a Presentation from th...
 
“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...“Vision-language Representations for Robotics,” a Presentation from the Unive...
“Vision-language Representations for Robotics,” a Presentation from the Unive...
 
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
“ADAS and AV Sensors: What’s Winning and Why?,” a Presentation from TechInsights
 
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
“Computer Vision in Sports: Scalable Solutions for Downmarkets,” a Presentati...
 
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
“Detecting Data Drift in Image Classification Neural Networks,” a Presentatio...
 
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
“Deep Neural Network Training: Diagnosing Problems and Implementing Solutions...
 
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
“AI Start-ups: The Perils of Fishing for Whales (War Stories from the Entrepr...
 
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
“A Computer Vision System for Autonomous Satellite Maneuvering,” a Presentati...
 
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
“Bias in Computer Vision—It’s Bigger Than Facial Recognition!,” a Presentatio...
 
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
“Sensor Fusion Techniques for Accurate Perception of Objects in the Environme...
 
“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara“Updating the Edge ML Development Process,” a Presentation from Samsara
“Updating the Edge ML Development Process,” a Presentation from Samsara
 
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
“Combating Bias in Production Computer Vision Systems,” a Presentation from R...
 
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
“Developing an Embedded Vision AI-powered Fitness System,” a Presentation fro...
 
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
“Navigating the Evolving Venture Capital Landscape for Edge AI Start-ups,” a ...
 
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
“Advanced Presence Sensing: What It Means for the Smart Home,” a Presentation...
 

Recently uploaded

+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
?#DUbAI#??##{{(☎️+971_581248768%)**%*]'#abortion pills for sale in dubai@
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
panagenda
 

Recently uploaded (20)

Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024Top 10 Most Downloaded Games on Play Store in 2024
Top 10 Most Downloaded Games on Play Store in 2024
 
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live StreamsTop 5 Benefits OF Using Muvi Live Paywall For Live Streams
Top 5 Benefits OF Using Muvi Live Paywall For Live Streams
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
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
 
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
+971581248768>> SAFE AND ORIGINAL ABORTION PILLS FOR SALE IN DUBAI AND ABUDHA...
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
 
Artificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : UncertaintyArtificial Intelligence Chap.5 : Uncertainty
Artificial Intelligence Chap.5 : Uncertainty
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 

“Flexible Machine Learning Solutions with Lattice FPGAs,” a Presentation from Lattice Semiconductor

  • 1. © 2021 Lattice Semiconductor Sreepada V Hegade Sr. Manager – ML Software and Solutions Flexible ML Solution with Lattice FPGA
  • 2. © 2021 Lattice Semiconductor • Review Need for Flexibility in ML • Flexible Hardware and Engines • Flexibility with Cost • Discussion on Trade-Off • Framework to Enable Flexibility • Conclusion 2 Agenda
  • 3. © 2021 Lattice Semiconductor Flexibility At Every Step • Interface Flexibility • Different Type of Sensors interface with required IPs to process sensor data • Implementation Flexibility • Proven library of networks, easy to use workflow • Flexibility with Cost, Performance and Power • Scalable solution 3 Sensor Data Aggregation and Augmentation To Inference Post Processing Inference with Optimal Network and Engine Configuration 1 2 3
  • 4. © 2021 Lattice Semiconductor 4 HARDWARE PLATFORMS IP CORES SOFTWARE TOOLS REFERENCE DESIGNS / DEMOS CNN Compact Accelerator CNN Accelerator UPduino Himax Shield – iCE40 UltraPlus FPGA ECP5 EVDK – ECP5 FPGA CUSTOM DESIGN SERVICES Smart Car Smart Home Smart City Smart Factory Neural Network Compiler Neural Network Accelerators Face Detection Speed Sign Detection Key Phrase Detection Face Tracking Object Counting Human Presence Detection Hand Gesture Detection 1 mW, 5.5 mm2 1 W, 100 mm2 CNN Plus Accelerator CrossLink-NX EVDK – CrossLink-NX 50-200 mW 16 mm2 Our Solution
  • 5. © 2021 Lattice Semiconductor 5 5mm2 16mm2 Flexible Interface
  • 6. © 2021 Lattice Semiconductor 6 • High Performance at low power • Configurable Engine (on-chip memory, number of cores) • Can support up to 60 fps QVGA and 30fps VGA resolution image • Supports TensorFlow on bare metal RISC-V + coprocessor • Good for background inference jobs like predictive maintenance • Shares computation resources AHBL Interconnect RISC-V CPU I$ D$ Data Ram UART AHBL2APB Bridge PDM Accelerator FIFO DMA EtherControl (Main) QSPI Memory Control + prefetch buffer M S0 M M S S S FIFO Ethernet IRQ0 IRQ2 S M IRQ1 APB Interconnect S GPIO ISR Ram S S1 Configurable ML Engines
  • 7. © 2021 Lattice Semiconductor 7 38FPS 320x240 48FPS 224x224 64FPS 160x160 48FPS 320x240 60FPS 224x224 72FPS 160x160 0 10 20 30 40 50 60 70 80 0 50 100 150 200 250 300 Frames Per Sec On-Chip Memory (128KB -> 256KB) 32FPS 224x224 (VGG) 60FPS 224x224 (Mobile Net) 48FPS 224x224 (VGG) 0 10 20 30 40 50 60 70 0 20 40 60 80 100 Frames Per Sec DSP Blocks (48 -> 84 MUL9 Units) Solution Cost Flexibility
  • 8. © 2021 Lattice Semiconductor 8 38FPS 320x240 (QVGA) 48 FP 320x240 (QVGA) 0 10 20 30 40 50 60 0 50 100 150 200 250 300 350 Frames Per Sec Runtime Size with Parameters (KB) ~20% performance with 2% Accuracy loss Trade-Off With Optimization
  • 9. © 2021 Lattice Semiconductor 9 Model Zoo Data Capture / Label Model Selection Transfer Learning Compile Runtime (inference) Model Visualize (Dashboard) Optimize Train Confi gure Evaluate Framework to Enable Flexibility
  • 10. © 2021 Lattice Semiconductor 10 Framework Demo
  • 11. © 2021 Lattice Semiconductor 11 • Flexibility is NOT just about operations supported by engine ▪ It is required at every step • Finding right trade-off is key to success • Performance and Power optimized engine with trade-off options • Lattice solution provides flexibility and framework to achieve right trade-off • Many possibilities, One framework Conclusion