SlideShare a Scribd company logo
1 of 25
Synthesis of Platform Architectures
from OpenCL Programs
Muhsen
Owaida
Konstantis
Daloukas
Nikolaos
Bellas
Christos D.
Antonopoulos
Department of Computer and Communication Engineering
University of Thessaly
Volos, Greece
01/03/16 FCCM 2011 2
Introduction
• High Level Synthesis (HLS) has been at the
research forefront in the last few years.
• Variety of Programming Models have been
introduced: C/C++, C-like Languages,
MATLAB, CUDA.
• Obstacles:
– Parallelism Expression.
– Extensive Compiler Transformations &
Optimizations.
01/03/16 FCCM 2011 3
Motivation
• Lack of parallel programming language for
reconfigurable platforms.
• A major shift of Computing industry toward
many-core computing systems.
• Reconfigurable fabrics bear a strong resemblance
to many core systems.
01/03/16 FCCM 2011 4
Contribution
• Silicon-OpenCL “SOpenCL”.
• A tool flow to convert an
unmodified OpenCL
application into a SoC design
with HW/SW components.
• A template-based hardware
accelerator generation.
• Decouple data movement and
computations.
Streaming
Unit
Datapath
Input
data
Output
data
Architectural Template
01/03/16 FCCM 2011 5
Outline
• High-Level Synthesis
• OpenCL Programming Model
• SOpenCL
– Front-End
– Back-End
– Run-Time
• Experimental Evaluation
• Conclusion
01/03/16 6
OpenCL Programming Language
• Open Computing Language
• OpenCL expresses parallelism at its finest granularity.
• Computation-grid partitioned in a 3-dimensional space of
work groups.
01/03/16 FCCM 2011 7
Data Movement
• Explicit Data Movement: Local Buffers and
Global Buffers.
01/03/16 FCCM 2011 8
Outline
• High-Level Synthesis
• OpenCL Programming Model
• SOpenCL
– Front-End
– Back-End
– Run-Time
• Experimental Evaluation
• Conclusion
01/03/16 FCCM 2011 9
SOpenCL Front-End (I)
Granularity Coarsening
• Work Item represents a light computational load.
• Coarsen the granularity due to limited resources and memory
bandwidth.
SOpenCL Front-End (II)
Barrier Elimination
01/03/16 FCCM 2011 10
triple_nested_loop
{
Statements_block1
}
//barrier();
triple_nested_loop
{
Statements_block2
}
Statements_block1
barrier();
Statements_block2
OpenCL code
C code
01/03/16 FCCM 2011 11
Outline
• High-Level Synthesis
• OpenCL Programming Model
• SOpenCL
– Front-End
– Back-End
– Run-Time
• Experimental Evaluation
• Conclusion
01/03/16 FCCM 2011 12
Hardware Generation
• Perform a series of optimizations and
Transformations.
– Uses LLVM Compiler Infrastructure.
• Generate synthesizable Verilog.
• Generate Test bench and simulation files.
C code
(Nested loop)
LLVM
Compiler
Optimize
LLVM-IR
Predication
Code
slicing
SMS mod
scheduling
Verilog
generation
Simulation
Synthesis
Final
bitstream
Accelerator
Template
User
Performance
Requirements
Synthesizable
Verilog
Test bench
01/03/16 FCCM 2011 13
IF Conversion
• Predication: If-conversion necessary for the
application of Modulo-Scheduler.
Predication
Code
slicing
SMS mod
scheduling
Verilog
generation
bb0:
r0 = cmp eq t, 0
br r0, bb1, bb2
bb1:
r1 = load A
br bb3
bb2:
r2 = add a, 1
br bb3
bb3:
r4 = phi r1, bb1, r2, bb2
br bb4
bb0:
r0 = cmp eq t, 0
p0 = xor r0, true
(r0) r1 = load A
(p0) r2 = add a, 1
r4 = select r0, r1, r2
br bb4
Most-inner loop body
(LLVM assembly)
Predicates
01/03/16
FCCM 2011
Code Slicing
• Decouple Data
movement and
computations.
• Input Streaming
Kernel
• Output Streaming
Kernel
• Computational
Kernel
Predicated
LLVM Loop
Predication
Code
slicing
SMS mod
scheduling
Verilog
generation
Part of Chroma
Interpolation LLVM
Termination
Computation
01/03/16 FCCM 2011 15
Modulo Scheduling
• Software Pipelining:
– II: Initiation Interval.
• Swing Modulo Scheduling (SMS).
• Valid Bits used to implement Prologue and Epilogue.
Predication
Code
slicing
SMS mod
scheduling
Verilog
generation
01/03/16 FCCM 2011 16
Verilog Generation
Feed Data
in Order
Predication
Code
slicing
SMS mod
scheduling
Verilog
generation
Write Data
in Order
FU types,
Bitwidths,
I/O Bandwidth
Requests/Data
FIFO Size
01/03/16 FCCM 2011 17
Outline
• High-Level Synthesis
• OpenCL Programming Model
• SOpenCL
– Front-End
– Back-End
– Run-Time
• Experimental Evaluation
• Conclusion
01/03/16 FCCM 2011 18
Run-Time
• The OpenCL main
program is executed as a
main thread in the host
processor of the platform
(e.g. PowerPC).
• Work-tasks are created
by the helper thread.
Host
Main
thread
Host
helper
thread
Command
Queue
Enqueue
OpenCL
command
1
Accelerator
Work queue
Initialize
Accelerator
Finish signal
Enqueue new
Work tasks
2
3
4
5
Work thread
(PowerPC)
01/03/16 FCCM 2011 19
Outline
• High-Level Synthesis
• OpenCL Programming Model
• SOpenCL Front-End
• SOpenCL Back-End
• Run-Time
• Experimental Evaluation
• Conclusion
01/03/16 FCCM 2011 20
Experimental Evaluation
• We tested the SOpenCL methodology on six OpenCL and
C applications.
• we evaluated our designs on a Xilinx Virtex-5 FX70
FPGA.
• We used Xilinx ISE 11.4 toolset for synthesis, placement
and routing.
• Evaluation Methodology:
– Three levels of resources availability {Ca, Cb, Cc}.
– Three Requests/Data FIFO Sizes.
– Cache Usage.
01/03/16 FCCM 2011 21
Results
01/03/16 FCCM 2011 22
Results
• The Cache is useful for
applications with
temporal locality.
01/03/16 FCCM 2011 23
Outline
• High-Level Synthesis
• OpenCL Programming Model
• SOpenCL
– Front-End
– Back-End
– Run-Time
• Experimental Evaluation
• Conclusion
01/03/16 FCCM 2011 24
Conclusion
• SOpenCL, a tool flow to produce the hardware and
software architecture of accelerator-based SoCs.
• OpenCL serves as a unified programming model
for:
– Heterogeneous many-core platforms.
– Reconfigurable platforms (like FPGA).
• Future Work:
– Multiple accelerators support.
– Automatic hardware configurations selection.
01/03/16 FCCM 2011 25
Questions
Thank you for your attention

More Related Content

What's hot

Multi phase mixture media
Multi phase mixture mediaMulti phase mixture media
Multi phase mixture mediaModelon
 
Update on Trinity System Procurement and Plans
Update on Trinity System Procurement and PlansUpdate on Trinity System Procurement and Plans
Update on Trinity System Procurement and Plansinside-BigData.com
 
Concept Drift: Monitoring Model Quality In Streaming ML Applications
Concept Drift: Monitoring Model Quality In Streaming ML ApplicationsConcept Drift: Monitoring Model Quality In Streaming ML Applications
Concept Drift: Monitoring Model Quality In Streaming ML ApplicationsLightbend
 
System Programing Unit 1
System Programing Unit 1System Programing Unit 1
System Programing Unit 1Manoj Patil
 
Zhimeng_luo_resume
Zhimeng_luo_resumeZhimeng_luo_resume
Zhimeng_luo_resumezhimeng luo
 
Loaders ( system programming )
Loaders ( system programming ) Loaders ( system programming )
Loaders ( system programming ) Adarsh Patel
 
Hadoop Summit SJ 2016: Next Gen Big Data Analytics with Apache Apex
Hadoop Summit SJ 2016: Next Gen Big Data Analytics with Apache ApexHadoop Summit SJ 2016: Next Gen Big Data Analytics with Apache Apex
Hadoop Summit SJ 2016: Next Gen Big Data Analytics with Apache ApexApache Apex
 
Automated Deployment of Modelica Models in Excel via Functional Mockup Interf...
Automated Deployment of Modelica Models in Excel via Functional Mockup Interf...Automated Deployment of Modelica Models in Excel via Functional Mockup Interf...
Automated Deployment of Modelica Models in Excel via Functional Mockup Interf...Modelon
 
DataTorrent Presentation @ Big Data Application Meetup
DataTorrent Presentation @ Big Data Application MeetupDataTorrent Presentation @ Big Data Application Meetup
DataTorrent Presentation @ Big Data Application MeetupThomas Weise
 
INTI 13 - Innovations de la version 2 de epragma et perspectives de la troisi...
INTI 13 - Innovations de la version 2 de epragma et perspectives de la troisi...INTI 13 - Innovations de la version 2 de epragma et perspectives de la troisi...
INTI 13 - Innovations de la version 2 de epragma et perspectives de la troisi...Territorial Intelligence
 
Csc8710 001 winter2014-mohammed_shahnawazali-ff2687_presentation_2
Csc8710 001 winter2014-mohammed_shahnawazali-ff2687_presentation_2Csc8710 001 winter2014-mohammed_shahnawazali-ff2687_presentation_2
Csc8710 001 winter2014-mohammed_shahnawazali-ff2687_presentation_2ff2687
 

What's hot (20)

Multi phase mixture media
Multi phase mixture mediaMulti phase mixture media
Multi phase mixture media
 
Update on Trinity System Procurement and Plans
Update on Trinity System Procurement and PlansUpdate on Trinity System Procurement and Plans
Update on Trinity System Procurement and Plans
 
Concept Drift: Monitoring Model Quality In Streaming ML Applications
Concept Drift: Monitoring Model Quality In Streaming ML ApplicationsConcept Drift: Monitoring Model Quality In Streaming ML Applications
Concept Drift: Monitoring Model Quality In Streaming ML Applications
 
Callgraph analysis
Callgraph analysisCallgraph analysis
Callgraph analysis
 
System Programing Unit 1
System Programing Unit 1System Programing Unit 1
System Programing Unit 1
 
Lect01 flow
Lect01 flowLect01 flow
Lect01 flow
 
Zhimeng_luo_resume
Zhimeng_luo_resumeZhimeng_luo_resume
Zhimeng_luo_resume
 
Loaders ( system programming )
Loaders ( system programming ) Loaders ( system programming )
Loaders ( system programming )
 
Loaders
LoadersLoaders
Loaders
 
Ch 4 linker loader
Ch 4 linker loaderCh 4 linker loader
Ch 4 linker loader
 
loaders and linkers
 loaders and linkers loaders and linkers
loaders and linkers
 
Hadoop Summit SJ 2016: Next Gen Big Data Analytics with Apache Apex
Hadoop Summit SJ 2016: Next Gen Big Data Analytics with Apache ApexHadoop Summit SJ 2016: Next Gen Big Data Analytics with Apache Apex
Hadoop Summit SJ 2016: Next Gen Big Data Analytics with Apache Apex
 
Vlsi design flow
Vlsi design flowVlsi design flow
Vlsi design flow
 
Assembler
AssemblerAssembler
Assembler
 
Linkers And Loaders
Linkers And LoadersLinkers And Loaders
Linkers And Loaders
 
Automated Deployment of Modelica Models in Excel via Functional Mockup Interf...
Automated Deployment of Modelica Models in Excel via Functional Mockup Interf...Automated Deployment of Modelica Models in Excel via Functional Mockup Interf...
Automated Deployment of Modelica Models in Excel via Functional Mockup Interf...
 
DataTorrent Presentation @ Big Data Application Meetup
DataTorrent Presentation @ Big Data Application MeetupDataTorrent Presentation @ Big Data Application Meetup
DataTorrent Presentation @ Big Data Application Meetup
 
TCP/IP
TCP/IPTCP/IP
TCP/IP
 
INTI 13 - Innovations de la version 2 de epragma et perspectives de la troisi...
INTI 13 - Innovations de la version 2 de epragma et perspectives de la troisi...INTI 13 - Innovations de la version 2 de epragma et perspectives de la troisi...
INTI 13 - Innovations de la version 2 de epragma et perspectives de la troisi...
 
Csc8710 001 winter2014-mohammed_shahnawazali-ff2687_presentation_2
Csc8710 001 winter2014-mohammed_shahnawazali-ff2687_presentation_2Csc8710 001 winter2014-mohammed_shahnawazali-ff2687_presentation_2
Csc8710 001 winter2014-mohammed_shahnawazali-ff2687_presentation_2
 

Viewers also liked

Amenazas terroristas en el mundo
Amenazas terroristas en el mundoAmenazas terroristas en el mundo
Amenazas terroristas en el mundovicky3101
 
Final presentation
Final presentationFinal presentation
Final presentationengiuliani
 
Herramientas Web 2.0
Herramientas Web 2.0Herramientas Web 2.0
Herramientas Web 2.0nadia otero
 
Opening%20 of%20the%20dunraven%20centre%20in%20roxboro%20by 1
Opening%20 of%20the%20dunraven%20centre%20in%20roxboro%20by 1Opening%20 of%20the%20dunraven%20centre%20in%20roxboro%20by 1
Opening%20 of%20the%20dunraven%20centre%20in%20roxboro%20by 1Monika Gąciarz
 
5 consejos para proteger tu negocio de Hackers
5 consejos para proteger tu negocio de Hackers5 consejos para proteger tu negocio de Hackers
5 consejos para proteger tu negocio de HackersIvan Bedia García
 
Final Research Paper
Final Research PaperFinal Research Paper
Final Research PaperSarah Lux
 
MBA - IT outsourcing trends in danish smbs_final
MBA - IT outsourcing trends in danish smbs_finalMBA - IT outsourcing trends in danish smbs_final
MBA - IT outsourcing trends in danish smbs_finalPeter Kroul
 
Epicondilitis
Epicondilitis Epicondilitis
Epicondilitis JRL11
 
Survey of The Problem of Object Detection In Real Images
Survey of The Problem of Object Detection In Real ImagesSurvey of The Problem of Object Detection In Real Images
Survey of The Problem of Object Detection In Real ImagesCSCJournals
 
Clase 3 factores del tiempo
Clase 3 factores del tiempoClase 3 factores del tiempo
Clase 3 factores del tiempoJacinto Arroyo
 
Sesión 01: Congruencia y Semejanza
Sesión 01: Congruencia y SemejanzaSesión 01: Congruencia y Semejanza
Sesión 01: Congruencia y Semejanzaaldomat07
 
wine menu september 2015
wine menu september 2015wine menu september 2015
wine menu september 2015David Sherlock
 

Viewers also liked (20)

Leyenda del Rey Arturo
Leyenda del Rey ArturoLeyenda del Rey Arturo
Leyenda del Rey Arturo
 
Amenazas terroristas en el mundo
Amenazas terroristas en el mundoAmenazas terroristas en el mundo
Amenazas terroristas en el mundo
 
Final presentation
Final presentationFinal presentation
Final presentation
 
Mohamed_Adel_Mohamed_El_Zohary (2)
Mohamed_Adel_Mohamed_El_Zohary (2)Mohamed_Adel_Mohamed_El_Zohary (2)
Mohamed_Adel_Mohamed_El_Zohary (2)
 
Herramientas Web 2.0
Herramientas Web 2.0Herramientas Web 2.0
Herramientas Web 2.0
 
Opening%20 of%20the%20dunraven%20centre%20in%20roxboro%20by 1
Opening%20 of%20the%20dunraven%20centre%20in%20roxboro%20by 1Opening%20 of%20the%20dunraven%20centre%20in%20roxboro%20by 1
Opening%20 of%20the%20dunraven%20centre%20in%20roxboro%20by 1
 
Das unileben
Das unilebenDas unileben
Das unileben
 
Sc a-g15
Sc a-g15Sc a-g15
Sc a-g15
 
Rondocap 01
Rondocap 01Rondocap 01
Rondocap 01
 
5 consejos para proteger tu negocio de Hackers
5 consejos para proteger tu negocio de Hackers5 consejos para proteger tu negocio de Hackers
5 consejos para proteger tu negocio de Hackers
 
Ann-Catrin Ljusberg slutversion
Ann-Catrin Ljusberg slutversionAnn-Catrin Ljusberg slutversion
Ann-Catrin Ljusberg slutversion
 
Final Research Paper
Final Research PaperFinal Research Paper
Final Research Paper
 
Ilm leadership skills
Ilm leadership skillsIlm leadership skills
Ilm leadership skills
 
MBA - IT outsourcing trends in danish smbs_final
MBA - IT outsourcing trends in danish smbs_finalMBA - IT outsourcing trends in danish smbs_final
MBA - IT outsourcing trends in danish smbs_final
 
Epicondilitis
Epicondilitis Epicondilitis
Epicondilitis
 
Survey of The Problem of Object Detection In Real Images
Survey of The Problem of Object Detection In Real ImagesSurvey of The Problem of Object Detection In Real Images
Survey of The Problem of Object Detection In Real Images
 
Clase 3 factores del tiempo
Clase 3 factores del tiempoClase 3 factores del tiempo
Clase 3 factores del tiempo
 
Sesión 01: Congruencia y Semejanza
Sesión 01: Congruencia y SemejanzaSesión 01: Congruencia y Semejanza
Sesión 01: Congruencia y Semejanza
 
wine menu september 2015
wine menu september 2015wine menu september 2015
wine menu september 2015
 
0928感覺與知覺
0928感覺與知覺0928感覺與知覺
0928感覺與知覺
 

Similar to Synthesis of Platform Architectures from OpenCL Programs

Current & Future Use-Cases of OpenDaylight
Current & Future Use-Cases of OpenDaylightCurrent & Future Use-Cases of OpenDaylight
Current & Future Use-Cases of OpenDaylightabhijit2511
 
SF-TAP: Scalable and Flexible Traffic Analysis Platform (USENIX LISA 2015)
SF-TAP: Scalable and Flexible Traffic Analysis Platform (USENIX LISA 2015)SF-TAP: Scalable and Flexible Traffic Analysis Platform (USENIX LISA 2015)
SF-TAP: Scalable and Flexible Traffic Analysis Platform (USENIX LISA 2015)Yuuki Takano
 
Boosting your HTML Apps – Overview of OpenCL and Hello World of WebCL
Boosting your HTML Apps – Overview of OpenCL and Hello World of WebCLBoosting your HTML Apps – Overview of OpenCL and Hello World of WebCL
Boosting your HTML Apps – Overview of OpenCL and Hello World of WebCLJanakiRam Raghumandala
 
CloudLightning and the OPM-based Use Case
CloudLightning and the OPM-based Use CaseCloudLightning and the OPM-based Use Case
CloudLightning and the OPM-based Use CaseCloudLightning
 
Operationalizing Machine Learning: Serving ML Models
Operationalizing Machine Learning: Serving ML ModelsOperationalizing Machine Learning: Serving ML Models
Operationalizing Machine Learning: Serving ML ModelsLightbend
 
Runos OpenFlow Controller (eng)
Runos OpenFlow Controller (eng)Runos OpenFlow Controller (eng)
Runos OpenFlow Controller (eng)Alexander Shalimov
 
OpenPOWER Acceleration of HPCC Systems
OpenPOWER Acceleration of HPCC SystemsOpenPOWER Acceleration of HPCC Systems
OpenPOWER Acceleration of HPCC SystemsHPCC Systems
 
PyMADlib - A Python wrapper for MADlib : in-database, parallel, machine learn...
PyMADlib - A Python wrapper for MADlib : in-database, parallel, machine learn...PyMADlib - A Python wrapper for MADlib : in-database, parallel, machine learn...
PyMADlib - A Python wrapper for MADlib : in-database, parallel, machine learn...Srivatsan Ramanujam
 
System on Chip Design and Modelling Dr. David J Greaves
System on Chip Design and Modelling   Dr. David J GreavesSystem on Chip Design and Modelling   Dr. David J Greaves
System on Chip Design and Modelling Dr. David J GreavesSatya Harish
 
btNOG 5: Network Automation
btNOG 5: Network AutomationbtNOG 5: Network Automation
btNOG 5: Network AutomationAPNIC
 
Machine Learning At Speed: Operationalizing ML For Real-Time Data Streams
Machine Learning At Speed: Operationalizing ML For Real-Time Data StreamsMachine Learning At Speed: Operationalizing ML For Real-Time Data Streams
Machine Learning At Speed: Operationalizing ML For Real-Time Data StreamsLightbend
 
Parallelization of Coupled Cluster Code with OpenMP
Parallelization of Coupled Cluster Code with OpenMPParallelization of Coupled Cluster Code with OpenMP
Parallelization of Coupled Cluster Code with OpenMPAnil Bohare
 
SDN: Situação do mercado e próximos movimentos
SDN: Situação do mercado e próximos movimentosSDN: Situação do mercado e próximos movimentos
SDN: Situação do mercado e próximos movimentosChristian Esteve Rothenberg
 
Legion - AI Runtime Platform
Legion -  AI Runtime PlatformLegion -  AI Runtime Platform
Legion - AI Runtime PlatformAlexey Kharlamov
 
OpenDaylight Openflow & OVSDB use cases ODL summit 2016
OpenDaylight Openflow & OVSDB use cases ODL summit 2016OpenDaylight Openflow & OVSDB use cases ODL summit 2016
OpenDaylight Openflow & OVSDB use cases ODL summit 2016abhijit2511
 
OpenCL - The Open Standard for Heterogeneous Parallel Programming
OpenCL - The Open Standard for Heterogeneous Parallel ProgrammingOpenCL - The Open Standard for Heterogeneous Parallel Programming
OpenCL - The Open Standard for Heterogeneous Parallel ProgrammingAndreas Schreiber
 
Using Spark Mllib Models in a Production Training and Serving Platform: Exper...
Using Spark Mllib Models in a Production Training and Serving Platform: Exper...Using Spark Mllib Models in a Production Training and Serving Platform: Exper...
Using Spark Mllib Models in a Production Training and Serving Platform: Exper...Databricks
 
OS for AI: Elastic Microservices & the Next Gen of ML
OS for AI: Elastic Microservices & the Next Gen of MLOS for AI: Elastic Microservices & the Next Gen of ML
OS for AI: Elastic Microservices & the Next Gen of MLNordic APIs
 
Harnessing OpenCL in Modern Coprocessors
Harnessing OpenCL in Modern CoprocessorsHarnessing OpenCL in Modern Coprocessors
Harnessing OpenCL in Modern CoprocessorsUnai Lopez-Novoa
 

Similar to Synthesis of Platform Architectures from OpenCL Programs (20)

Current & Future Use-Cases of OpenDaylight
Current & Future Use-Cases of OpenDaylightCurrent & Future Use-Cases of OpenDaylight
Current & Future Use-Cases of OpenDaylight
 
SF-TAP: Scalable and Flexible Traffic Analysis Platform (USENIX LISA 2015)
SF-TAP: Scalable and Flexible Traffic Analysis Platform (USENIX LISA 2015)SF-TAP: Scalable and Flexible Traffic Analysis Platform (USENIX LISA 2015)
SF-TAP: Scalable and Flexible Traffic Analysis Platform (USENIX LISA 2015)
 
Boosting your HTML Apps – Overview of OpenCL and Hello World of WebCL
Boosting your HTML Apps – Overview of OpenCL and Hello World of WebCLBoosting your HTML Apps – Overview of OpenCL and Hello World of WebCL
Boosting your HTML Apps – Overview of OpenCL and Hello World of WebCL
 
CloudLightning and the OPM-based Use Case
CloudLightning and the OPM-based Use CaseCloudLightning and the OPM-based Use Case
CloudLightning and the OPM-based Use Case
 
Operationalizing Machine Learning: Serving ML Models
Operationalizing Machine Learning: Serving ML ModelsOperationalizing Machine Learning: Serving ML Models
Operationalizing Machine Learning: Serving ML Models
 
Runos OpenFlow Controller (eng)
Runos OpenFlow Controller (eng)Runos OpenFlow Controller (eng)
Runos OpenFlow Controller (eng)
 
OpenPOWER Acceleration of HPCC Systems
OpenPOWER Acceleration of HPCC SystemsOpenPOWER Acceleration of HPCC Systems
OpenPOWER Acceleration of HPCC Systems
 
PyMADlib - A Python wrapper for MADlib : in-database, parallel, machine learn...
PyMADlib - A Python wrapper for MADlib : in-database, parallel, machine learn...PyMADlib - A Python wrapper for MADlib : in-database, parallel, machine learn...
PyMADlib - A Python wrapper for MADlib : in-database, parallel, machine learn...
 
System on Chip Design and Modelling Dr. David J Greaves
System on Chip Design and Modelling   Dr. David J GreavesSystem on Chip Design and Modelling   Dr. David J Greaves
System on Chip Design and Modelling Dr. David J Greaves
 
btNOG 5: Network Automation
btNOG 5: Network AutomationbtNOG 5: Network Automation
btNOG 5: Network Automation
 
Machine Learning At Speed: Operationalizing ML For Real-Time Data Streams
Machine Learning At Speed: Operationalizing ML For Real-Time Data StreamsMachine Learning At Speed: Operationalizing ML For Real-Time Data Streams
Machine Learning At Speed: Operationalizing ML For Real-Time Data Streams
 
Parallelization of Coupled Cluster Code with OpenMP
Parallelization of Coupled Cluster Code with OpenMPParallelization of Coupled Cluster Code with OpenMP
Parallelization of Coupled Cluster Code with OpenMP
 
SDN: Situação do mercado e próximos movimentos
SDN: Situação do mercado e próximos movimentosSDN: Situação do mercado e próximos movimentos
SDN: Situação do mercado e próximos movimentos
 
Legion - AI Runtime Platform
Legion -  AI Runtime PlatformLegion -  AI Runtime Platform
Legion - AI Runtime Platform
 
OpenDaylight Openflow & OVSDB use cases ODL summit 2016
OpenDaylight Openflow & OVSDB use cases ODL summit 2016OpenDaylight Openflow & OVSDB use cases ODL summit 2016
OpenDaylight Openflow & OVSDB use cases ODL summit 2016
 
Japan's post K Computer
Japan's post K ComputerJapan's post K Computer
Japan's post K Computer
 
OpenCL - The Open Standard for Heterogeneous Parallel Programming
OpenCL - The Open Standard for Heterogeneous Parallel ProgrammingOpenCL - The Open Standard for Heterogeneous Parallel Programming
OpenCL - The Open Standard for Heterogeneous Parallel Programming
 
Using Spark Mllib Models in a Production Training and Serving Platform: Exper...
Using Spark Mllib Models in a Production Training and Serving Platform: Exper...Using Spark Mllib Models in a Production Training and Serving Platform: Exper...
Using Spark Mllib Models in a Production Training and Serving Platform: Exper...
 
OS for AI: Elastic Microservices & the Next Gen of ML
OS for AI: Elastic Microservices & the Next Gen of MLOS for AI: Elastic Microservices & the Next Gen of ML
OS for AI: Elastic Microservices & the Next Gen of ML
 
Harnessing OpenCL in Modern Coprocessors
Harnessing OpenCL in Modern CoprocessorsHarnessing OpenCL in Modern Coprocessors
Harnessing OpenCL in Modern Coprocessors
 

Recently uploaded

Makarba ( Call Girls ) Ahmedabad ✔ 6297143586 ✔ Hot Model With Sexy Bhabi Rea...
Makarba ( Call Girls ) Ahmedabad ✔ 6297143586 ✔ Hot Model With Sexy Bhabi Rea...Makarba ( Call Girls ) Ahmedabad ✔ 6297143586 ✔ Hot Model With Sexy Bhabi Rea...
Makarba ( Call Girls ) Ahmedabad ✔ 6297143586 ✔ Hot Model With Sexy Bhabi Rea...Naicy mandal
 
presentation about microsoft power point
presentation about microsoft power pointpresentation about microsoft power point
presentation about microsoft power pointchhavia330
 
Call Girls in Vashi Escorts Services - 7738631006
Call Girls in Vashi Escorts Services - 7738631006Call Girls in Vashi Escorts Services - 7738631006
Call Girls in Vashi Escorts Services - 7738631006Pooja Nehwal
 
Low Rate Call Girls Nashik Vedika 7001305949 Independent Escort Service Nashik
Low Rate Call Girls Nashik Vedika 7001305949 Independent Escort Service NashikLow Rate Call Girls Nashik Vedika 7001305949 Independent Escort Service Nashik
Low Rate Call Girls Nashik Vedika 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
Call Girls Service Kolkata Aishwarya 🤌 8250192130 🚀 Vip Call Girls Kolkata
Call Girls Service Kolkata Aishwarya 🤌  8250192130 🚀 Vip Call Girls KolkataCall Girls Service Kolkata Aishwarya 🤌  8250192130 🚀 Vip Call Girls Kolkata
Call Girls Service Kolkata Aishwarya 🤌 8250192130 🚀 Vip Call Girls Kolkataanamikaraghav4
 
Lucknow 💋 Call Girls Adil Nagar | ₹,9500 Pay Cash 8923113531 Free Home Delive...
Lucknow 💋 Call Girls Adil Nagar | ₹,9500 Pay Cash 8923113531 Free Home Delive...Lucknow 💋 Call Girls Adil Nagar | ₹,9500 Pay Cash 8923113531 Free Home Delive...
Lucknow 💋 Call Girls Adil Nagar | ₹,9500 Pay Cash 8923113531 Free Home Delive...anilsa9823
 
Russian Call Girls Kolkata Chhaya 🤌 8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls Kolkata Chhaya 🤌  8250192130 🚀 Vip Call Girls KolkataRussian Call Girls Kolkata Chhaya 🤌  8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls Kolkata Chhaya 🤌 8250192130 🚀 Vip Call Girls Kolkataanamikaraghav4
 
VIP Call Girls Hitech City ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With R...
VIP Call Girls Hitech City ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With R...VIP Call Girls Hitech City ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With R...
VIP Call Girls Hitech City ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With R...Suhani Kapoor
 
Call Girls Delhi {Rs-10000 Laxmi Nagar] 9711199012 Whats Up Number
Call Girls Delhi {Rs-10000 Laxmi Nagar] 9711199012 Whats Up NumberCall Girls Delhi {Rs-10000 Laxmi Nagar] 9711199012 Whats Up Number
Call Girls Delhi {Rs-10000 Laxmi Nagar] 9711199012 Whats Up NumberMs Riya
 
《伯明翰城市大学毕业证成绩单购买》学历证书学位证书区别《复刻原版1:1伯明翰城市大学毕业证书|修改BCU成绩单PDF版》Q微信741003700《BCU学...
《伯明翰城市大学毕业证成绩单购买》学历证书学位证书区别《复刻原版1:1伯明翰城市大学毕业证书|修改BCU成绩单PDF版》Q微信741003700《BCU学...《伯明翰城市大学毕业证成绩单购买》学历证书学位证书区别《复刻原版1:1伯明翰城市大学毕业证书|修改BCU成绩单PDF版》Q微信741003700《BCU学...
《伯明翰城市大学毕业证成绩单购买》学历证书学位证书区别《复刻原版1:1伯明翰城市大学毕业证书|修改BCU成绩单PDF版》Q微信741003700《BCU学...ur8mqw8e
 
High Profile Call Girls In Andheri 7738631006 Call girls in mumbai Mumbai ...
High Profile Call Girls In Andheri 7738631006 Call girls in mumbai  Mumbai ...High Profile Call Girls In Andheri 7738631006 Call girls in mumbai  Mumbai ...
High Profile Call Girls In Andheri 7738631006 Call girls in mumbai Mumbai ...Pooja Nehwal
 
WhatsApp 9892124323 ✓Call Girls In Khar ( Mumbai ) secure service - Bandra F...
WhatsApp 9892124323 ✓Call Girls In Khar ( Mumbai ) secure service -  Bandra F...WhatsApp 9892124323 ✓Call Girls In Khar ( Mumbai ) secure service -  Bandra F...
WhatsApp 9892124323 ✓Call Girls In Khar ( Mumbai ) secure service - Bandra F...Pooja Nehwal
 
(ANIKA) Wanwadi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(ANIKA) Wanwadi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...(ANIKA) Wanwadi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(ANIKA) Wanwadi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...ranjana rawat
 
(=Towel) Dubai Call Girls O525547819 Call Girls In Dubai (Fav0r)
(=Towel) Dubai Call Girls O525547819 Call Girls In Dubai (Fav0r)(=Towel) Dubai Call Girls O525547819 Call Girls In Dubai (Fav0r)
(=Towel) Dubai Call Girls O525547819 Call Girls In Dubai (Fav0r)kojalkojal131
 
如何办理(Adelaide毕业证)阿德莱德大学毕业证成绩单Adelaide学历认证真实可查
如何办理(Adelaide毕业证)阿德莱德大学毕业证成绩单Adelaide学历认证真实可查如何办理(Adelaide毕业证)阿德莱德大学毕业证成绩单Adelaide学历认证真实可查
如何办理(Adelaide毕业证)阿德莱德大学毕业证成绩单Adelaide学历认证真实可查awo24iot
 
Dubai Call Girls O528786472 Call Girls In Dubai Wisteria
Dubai Call Girls O528786472 Call Girls In Dubai WisteriaDubai Call Girls O528786472 Call Girls In Dubai Wisteria
Dubai Call Girls O528786472 Call Girls In Dubai WisteriaUnited Arab Emirates
 
VIP Call Girls Kavuri Hills ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With ...
VIP Call Girls Kavuri Hills ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With ...VIP Call Girls Kavuri Hills ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With ...
VIP Call Girls Kavuri Hills ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With ...Suhani Kapoor
 
(PARI) Alandi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(PARI) Alandi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(PARI) Alandi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(PARI) Alandi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escortsranjana rawat
 
定制加拿大滑铁卢大学毕业证(Waterloo毕业证书)成绩单(文凭)原版一比一
定制加拿大滑铁卢大学毕业证(Waterloo毕业证书)成绩单(文凭)原版一比一定制加拿大滑铁卢大学毕业证(Waterloo毕业证书)成绩单(文凭)原版一比一
定制加拿大滑铁卢大学毕业证(Waterloo毕业证书)成绩单(文凭)原版一比一zul5vf0pq
 

Recently uploaded (20)

Makarba ( Call Girls ) Ahmedabad ✔ 6297143586 ✔ Hot Model With Sexy Bhabi Rea...
Makarba ( Call Girls ) Ahmedabad ✔ 6297143586 ✔ Hot Model With Sexy Bhabi Rea...Makarba ( Call Girls ) Ahmedabad ✔ 6297143586 ✔ Hot Model With Sexy Bhabi Rea...
Makarba ( Call Girls ) Ahmedabad ✔ 6297143586 ✔ Hot Model With Sexy Bhabi Rea...
 
presentation about microsoft power point
presentation about microsoft power pointpresentation about microsoft power point
presentation about microsoft power point
 
Call Girls in Vashi Escorts Services - 7738631006
Call Girls in Vashi Escorts Services - 7738631006Call Girls in Vashi Escorts Services - 7738631006
Call Girls in Vashi Escorts Services - 7738631006
 
Low Rate Call Girls Nashik Vedika 7001305949 Independent Escort Service Nashik
Low Rate Call Girls Nashik Vedika 7001305949 Independent Escort Service NashikLow Rate Call Girls Nashik Vedika 7001305949 Independent Escort Service Nashik
Low Rate Call Girls Nashik Vedika 7001305949 Independent Escort Service Nashik
 
🔝 9953056974🔝 Delhi Call Girls in Ajmeri Gate
🔝 9953056974🔝 Delhi Call Girls in Ajmeri Gate🔝 9953056974🔝 Delhi Call Girls in Ajmeri Gate
🔝 9953056974🔝 Delhi Call Girls in Ajmeri Gate
 
Call Girls Service Kolkata Aishwarya 🤌 8250192130 🚀 Vip Call Girls Kolkata
Call Girls Service Kolkata Aishwarya 🤌  8250192130 🚀 Vip Call Girls KolkataCall Girls Service Kolkata Aishwarya 🤌  8250192130 🚀 Vip Call Girls Kolkata
Call Girls Service Kolkata Aishwarya 🤌 8250192130 🚀 Vip Call Girls Kolkata
 
Lucknow 💋 Call Girls Adil Nagar | ₹,9500 Pay Cash 8923113531 Free Home Delive...
Lucknow 💋 Call Girls Adil Nagar | ₹,9500 Pay Cash 8923113531 Free Home Delive...Lucknow 💋 Call Girls Adil Nagar | ₹,9500 Pay Cash 8923113531 Free Home Delive...
Lucknow 💋 Call Girls Adil Nagar | ₹,9500 Pay Cash 8923113531 Free Home Delive...
 
Russian Call Girls Kolkata Chhaya 🤌 8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls Kolkata Chhaya 🤌  8250192130 🚀 Vip Call Girls KolkataRussian Call Girls Kolkata Chhaya 🤌  8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls Kolkata Chhaya 🤌 8250192130 🚀 Vip Call Girls Kolkata
 
VIP Call Girls Hitech City ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With R...
VIP Call Girls Hitech City ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With R...VIP Call Girls Hitech City ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With R...
VIP Call Girls Hitech City ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With R...
 
Call Girls Delhi {Rs-10000 Laxmi Nagar] 9711199012 Whats Up Number
Call Girls Delhi {Rs-10000 Laxmi Nagar] 9711199012 Whats Up NumberCall Girls Delhi {Rs-10000 Laxmi Nagar] 9711199012 Whats Up Number
Call Girls Delhi {Rs-10000 Laxmi Nagar] 9711199012 Whats Up Number
 
《伯明翰城市大学毕业证成绩单购买》学历证书学位证书区别《复刻原版1:1伯明翰城市大学毕业证书|修改BCU成绩单PDF版》Q微信741003700《BCU学...
《伯明翰城市大学毕业证成绩单购买》学历证书学位证书区别《复刻原版1:1伯明翰城市大学毕业证书|修改BCU成绩单PDF版》Q微信741003700《BCU学...《伯明翰城市大学毕业证成绩单购买》学历证书学位证书区别《复刻原版1:1伯明翰城市大学毕业证书|修改BCU成绩单PDF版》Q微信741003700《BCU学...
《伯明翰城市大学毕业证成绩单购买》学历证书学位证书区别《复刻原版1:1伯明翰城市大学毕业证书|修改BCU成绩单PDF版》Q微信741003700《BCU学...
 
High Profile Call Girls In Andheri 7738631006 Call girls in mumbai Mumbai ...
High Profile Call Girls In Andheri 7738631006 Call girls in mumbai  Mumbai ...High Profile Call Girls In Andheri 7738631006 Call girls in mumbai  Mumbai ...
High Profile Call Girls In Andheri 7738631006 Call girls in mumbai Mumbai ...
 
WhatsApp 9892124323 ✓Call Girls In Khar ( Mumbai ) secure service - Bandra F...
WhatsApp 9892124323 ✓Call Girls In Khar ( Mumbai ) secure service -  Bandra F...WhatsApp 9892124323 ✓Call Girls In Khar ( Mumbai ) secure service -  Bandra F...
WhatsApp 9892124323 ✓Call Girls In Khar ( Mumbai ) secure service - Bandra F...
 
(ANIKA) Wanwadi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(ANIKA) Wanwadi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...(ANIKA) Wanwadi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(ANIKA) Wanwadi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
 
(=Towel) Dubai Call Girls O525547819 Call Girls In Dubai (Fav0r)
(=Towel) Dubai Call Girls O525547819 Call Girls In Dubai (Fav0r)(=Towel) Dubai Call Girls O525547819 Call Girls In Dubai (Fav0r)
(=Towel) Dubai Call Girls O525547819 Call Girls In Dubai (Fav0r)
 
如何办理(Adelaide毕业证)阿德莱德大学毕业证成绩单Adelaide学历认证真实可查
如何办理(Adelaide毕业证)阿德莱德大学毕业证成绩单Adelaide学历认证真实可查如何办理(Adelaide毕业证)阿德莱德大学毕业证成绩单Adelaide学历认证真实可查
如何办理(Adelaide毕业证)阿德莱德大学毕业证成绩单Adelaide学历认证真实可查
 
Dubai Call Girls O528786472 Call Girls In Dubai Wisteria
Dubai Call Girls O528786472 Call Girls In Dubai WisteriaDubai Call Girls O528786472 Call Girls In Dubai Wisteria
Dubai Call Girls O528786472 Call Girls In Dubai Wisteria
 
VIP Call Girls Kavuri Hills ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With ...
VIP Call Girls Kavuri Hills ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With ...VIP Call Girls Kavuri Hills ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With ...
VIP Call Girls Kavuri Hills ( Hyderabad ) Phone 8250192130 | ₹5k To 25k With ...
 
(PARI) Alandi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(PARI) Alandi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts(PARI) Alandi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
(PARI) Alandi Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Escorts
 
定制加拿大滑铁卢大学毕业证(Waterloo毕业证书)成绩单(文凭)原版一比一
定制加拿大滑铁卢大学毕业证(Waterloo毕业证书)成绩单(文凭)原版一比一定制加拿大滑铁卢大学毕业证(Waterloo毕业证书)成绩单(文凭)原版一比一
定制加拿大滑铁卢大学毕业证(Waterloo毕业证书)成绩单(文凭)原版一比一
 

Synthesis of Platform Architectures from OpenCL Programs

  • 1. Synthesis of Platform Architectures from OpenCL Programs Muhsen Owaida Konstantis Daloukas Nikolaos Bellas Christos D. Antonopoulos Department of Computer and Communication Engineering University of Thessaly Volos, Greece
  • 2. 01/03/16 FCCM 2011 2 Introduction • High Level Synthesis (HLS) has been at the research forefront in the last few years. • Variety of Programming Models have been introduced: C/C++, C-like Languages, MATLAB, CUDA. • Obstacles: – Parallelism Expression. – Extensive Compiler Transformations & Optimizations.
  • 3. 01/03/16 FCCM 2011 3 Motivation • Lack of parallel programming language for reconfigurable platforms. • A major shift of Computing industry toward many-core computing systems. • Reconfigurable fabrics bear a strong resemblance to many core systems.
  • 4. 01/03/16 FCCM 2011 4 Contribution • Silicon-OpenCL “SOpenCL”. • A tool flow to convert an unmodified OpenCL application into a SoC design with HW/SW components. • A template-based hardware accelerator generation. • Decouple data movement and computations. Streaming Unit Datapath Input data Output data Architectural Template
  • 5. 01/03/16 FCCM 2011 5 Outline • High-Level Synthesis • OpenCL Programming Model • SOpenCL – Front-End – Back-End – Run-Time • Experimental Evaluation • Conclusion
  • 6. 01/03/16 6 OpenCL Programming Language • Open Computing Language • OpenCL expresses parallelism at its finest granularity. • Computation-grid partitioned in a 3-dimensional space of work groups.
  • 7. 01/03/16 FCCM 2011 7 Data Movement • Explicit Data Movement: Local Buffers and Global Buffers.
  • 8. 01/03/16 FCCM 2011 8 Outline • High-Level Synthesis • OpenCL Programming Model • SOpenCL – Front-End – Back-End – Run-Time • Experimental Evaluation • Conclusion
  • 9. 01/03/16 FCCM 2011 9 SOpenCL Front-End (I) Granularity Coarsening • Work Item represents a light computational load. • Coarsen the granularity due to limited resources and memory bandwidth.
  • 10. SOpenCL Front-End (II) Barrier Elimination 01/03/16 FCCM 2011 10 triple_nested_loop { Statements_block1 } //barrier(); triple_nested_loop { Statements_block2 } Statements_block1 barrier(); Statements_block2 OpenCL code C code
  • 11. 01/03/16 FCCM 2011 11 Outline • High-Level Synthesis • OpenCL Programming Model • SOpenCL – Front-End – Back-End – Run-Time • Experimental Evaluation • Conclusion
  • 12. 01/03/16 FCCM 2011 12 Hardware Generation • Perform a series of optimizations and Transformations. – Uses LLVM Compiler Infrastructure. • Generate synthesizable Verilog. • Generate Test bench and simulation files. C code (Nested loop) LLVM Compiler Optimize LLVM-IR Predication Code slicing SMS mod scheduling Verilog generation Simulation Synthesis Final bitstream Accelerator Template User Performance Requirements Synthesizable Verilog Test bench
  • 13. 01/03/16 FCCM 2011 13 IF Conversion • Predication: If-conversion necessary for the application of Modulo-Scheduler. Predication Code slicing SMS mod scheduling Verilog generation bb0: r0 = cmp eq t, 0 br r0, bb1, bb2 bb1: r1 = load A br bb3 bb2: r2 = add a, 1 br bb3 bb3: r4 = phi r1, bb1, r2, bb2 br bb4 bb0: r0 = cmp eq t, 0 p0 = xor r0, true (r0) r1 = load A (p0) r2 = add a, 1 r4 = select r0, r1, r2 br bb4 Most-inner loop body (LLVM assembly) Predicates
  • 14. 01/03/16 FCCM 2011 Code Slicing • Decouple Data movement and computations. • Input Streaming Kernel • Output Streaming Kernel • Computational Kernel Predicated LLVM Loop Predication Code slicing SMS mod scheduling Verilog generation Part of Chroma Interpolation LLVM Termination Computation
  • 15. 01/03/16 FCCM 2011 15 Modulo Scheduling • Software Pipelining: – II: Initiation Interval. • Swing Modulo Scheduling (SMS). • Valid Bits used to implement Prologue and Epilogue. Predication Code slicing SMS mod scheduling Verilog generation
  • 16. 01/03/16 FCCM 2011 16 Verilog Generation Feed Data in Order Predication Code slicing SMS mod scheduling Verilog generation Write Data in Order FU types, Bitwidths, I/O Bandwidth Requests/Data FIFO Size
  • 17. 01/03/16 FCCM 2011 17 Outline • High-Level Synthesis • OpenCL Programming Model • SOpenCL – Front-End – Back-End – Run-Time • Experimental Evaluation • Conclusion
  • 18. 01/03/16 FCCM 2011 18 Run-Time • The OpenCL main program is executed as a main thread in the host processor of the platform (e.g. PowerPC). • Work-tasks are created by the helper thread. Host Main thread Host helper thread Command Queue Enqueue OpenCL command 1 Accelerator Work queue Initialize Accelerator Finish signal Enqueue new Work tasks 2 3 4 5 Work thread (PowerPC)
  • 19. 01/03/16 FCCM 2011 19 Outline • High-Level Synthesis • OpenCL Programming Model • SOpenCL Front-End • SOpenCL Back-End • Run-Time • Experimental Evaluation • Conclusion
  • 20. 01/03/16 FCCM 2011 20 Experimental Evaluation • We tested the SOpenCL methodology on six OpenCL and C applications. • we evaluated our designs on a Xilinx Virtex-5 FX70 FPGA. • We used Xilinx ISE 11.4 toolset for synthesis, placement and routing. • Evaluation Methodology: – Three levels of resources availability {Ca, Cb, Cc}. – Three Requests/Data FIFO Sizes. – Cache Usage.
  • 21. 01/03/16 FCCM 2011 21 Results
  • 22. 01/03/16 FCCM 2011 22 Results • The Cache is useful for applications with temporal locality.
  • 23. 01/03/16 FCCM 2011 23 Outline • High-Level Synthesis • OpenCL Programming Model • SOpenCL – Front-End – Back-End – Run-Time • Experimental Evaluation • Conclusion
  • 24. 01/03/16 FCCM 2011 24 Conclusion • SOpenCL, a tool flow to produce the hardware and software architecture of accelerator-based SoCs. • OpenCL serves as a unified programming model for: – Heterogeneous many-core platforms. – Reconfigurable platforms (like FPGA). • Future Work: – Multiple accelerators support. – Automatic hardware configurations selection.
  • 25. 01/03/16 FCCM 2011 25 Questions Thank you for your attention