SlideShare ist ein Scribd-Unternehmen logo
1 von 25
Downloaden Sie, um offline zu lesen
1 Is it an open door to common parallelization strategy  for topological operators on multi-core multi-thread architecture ? R. MAHMOUDI – A3SI Laboratory– 2009 April
2 Summary General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
3 Summary General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
4 General framework 1. Scientific and technical context (1) Image processingoperators Fourier Transformation Opening Thinning Dynamic  redistribution Linear filters Closing Crest restoring Not-linear  filters  Euclidean  Distance Transformation Thresholding Smoothing Attributed Filter Watershed  Associated class Topological  operators Morphological  operators Local  operators Point-to-Point  operators Global operators R. MAHMOUDI – A3SI Laboratory– 2009 April
5 General framework 1. Scientific and technical context (2) (Associated class) Vs (Parallelizationstrategies) Global operators Topological  operators Morphological  operators Local  operators Point-to-Point  operators Sienstra [1] (2002) Wilkinson [2] (2007) Meijster [3] [1]  F. J. Seinstra, D. Koelma, and J. M. Geusebroek, “A software architecture for user transparent parallel image processing”. [2] M.H.F. Wilkinson, H. Gao, W.H. Hesselink, “Concurrent Computation of Attribute Filters on Shared Memory Parallel Machines”. [3]  A. Meijster, J. B. T. M. Roerdink, and W. H. Hesselink, “A general algorithm for computing distance transforms in linear time” . R. MAHMOUDI – A3SI Laboratory– 2009 April
6 General framework 2. Ph. D. objectives (1) Topological operators Thinning operator [1] common parallelization strategy Crest restoring [1] 2D and 3D smoothing [2] Watershed based on w-thinning [3] Watershed based on graph [4] Homotopic kernel transformation [5] Leveling kernel transformation [5] [1] M. Couprie, F. N. Bezerra, and G. Bertrand, “Topological operators for grayscale image processing”,  [2] M. Couprie, and G. Bertrand, “Topology preserving alternating sequential filter for smoothing 2D and 3D objects”. [3] G. Bertrand, “On Topological Watersheds”.   [4] J. Cousty, M. Couprie, L. Najman and G. Betrand “Weighted fusion graphs: Merging properties and watersheds”. [5] G. Bertrand, J. C. Everat, and M. Couprie, "Image segmentation through operators based on topology“  R. MAHMOUDI – A3SI Laboratory– 2009 April
7 General framework 2. Ph. D. objectives (2) Main Architectural Classes  SISD machines SIMD machines MISD machines MIMD Machine : (Execute several instruction streams in parallel on different data) Shared Memory Machine Distributed  Memory  System CPU1 CPU2 CPU3 CPUn Random Access Memory  R. MAHMOUDI – A3SI Laboratory– 2009 April
8 General framework 2. Ph. D. objectives (3) Needs Common  parallelization strategy of topological operators on multi-core multithread architecture (MIMD Machines – Shared Memory System)? Main Objectives Unifyingparallelizationmethod of topologicaloperators class (Algorithmiclevel) Implementation Methodology and optimization techniques on multi-core multithread        architecture (Architecture level). R. MAHMOUDI – A3SI Laboratory– 2009 April
9 General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
10 Parallel thinning operator 1. Theoretical background Filtered thinning method that allows to selectively simplify the topology, based on a  local  contrast parameter λ. (b) filtered skeleton   with λ = 10. (a) After Deriche  gradient operator R. MAHMOUDI – A3SI Laboratory– 2009 April
11 Parallel thinning operator 1. Parallelization strategy (1) Definesearch area Startparallelcharacterization  Create new shared data structure End parallelcharacterization  Mergemodifiedsearch area Restart process until stability R. MAHMOUDI – A3SI Laboratory– 2009 April
12 Parallel thinning operator 1. Parallelization strategy (2) SDM-Strategy (Divide and conquer principle) Up level DATA PARALLELISM MIXED PARALLELISM Down level THREAD PARALLELISM R. MAHMOUDI – A3SI Laboratory– 2009 April
13 Parallel thinning operator 1. Parallelization strategy (3) R. MAHMOUDI – A3SI Laboratory– 2009 April
14 Parallel thinning operator 2. Coordination of threads (1) Thread 1 Thread 2 First implementation using a lock-based shared FIFO queue. Lock() Unlock() Push() Fail Success Blocked R. MAHMOUDI – A3SI Laboratory– 2009 April
15 Parallel thinning operator 2. Coordination of threads (2) Thread 1 Thread 2 Lock() and access semaphore Unlock() and leave semaphore Semaphore Push() Second implementation using a private-shared concurrent FIFO queue R. MAHMOUDI – A3SI Laboratory– 2009 April
16 Parallel thinning operator 3. Performance testing (1) R. MAHMOUDI – A3SI Laboratory– 2009 April
17 Parallel thinning operator 3. Performance testing (2) First implementation using a lock-based shared FIFO queue. R. MAHMOUDI – A3SI Laboratory– 2009 April
18 Parallel thinning operator 3. Performance testing (3) Second implementation using a private-shared concurrent FIFO queue R. MAHMOUDI – A3SI Laboratory– 2009 April
19 Parallel thinning operator 4. Conclusion Non-specific nature of the proposed  parallelization strategy. Threads coordination and communication  during computing dependently parallel read/write  for managing cache-resident data  1 2 R. MAHMOUDI – A3SI Laboratory– 2009 April
20 General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
21 Future work 1. Extension SDM - Strategy Performance enhancement (speed up) Efficiency (work distribution) Cache miss ParallelThinning Operator IMBRICATE  TWO Operators Crest restoring  R. MAHMOUDI – A3SI Laboratory– 2009 April
22 Future work 2. New parallel topological watershed % Achievement Parallelwatershed Operator SDM - Strategy Performance enhancement (speed up) Efficiency (work distribution) Cache miss 80% R. MAHMOUDI – A3SI Laboratory– 2009 April
23 General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
24 Discussion Introduce future programming model  (make it easy to write programs that execute efficiently on highly parallel C.S) Introduce new “Draft”to design and evaluate parallel programming models  (instead of old benchmark) Maximize programmer productivity, future programming model must be more human-centric (than the conventional focus on hardware or application) R. MAHMOUDI – A3SI Laboratory– 2009 April
25 R. MAHMOUDI – A3SI Laboratory– 2009 April

Weitere ähnliche Inhalte

Was ist angesagt?

Parallel and distributed Computing
Parallel and distributed Computing Parallel and distributed Computing
Parallel and distributed Computing MIANSHOAIB10
 
Shared Memory Multi Processor
Shared Memory Multi ProcessorShared Memory Multi Processor
Shared Memory Multi Processorbabuece
 
Lecture 4 principles of parallel algorithm design updated
Lecture 4   principles of parallel algorithm design updatedLecture 4   principles of parallel algorithm design updated
Lecture 4 principles of parallel algorithm design updatedVajira Thambawita
 
Multithreading
MultithreadingMultithreading
MultithreadingA B Shinde
 
Cpu scheduling in operating System.
Cpu scheduling in operating System.Cpu scheduling in operating System.
Cpu scheduling in operating System.Ravi Kumar Patel
 
Introduction to Distributed System
Introduction to Distributed SystemIntroduction to Distributed System
Introduction to Distributed SystemSunita Sahu
 
Process synchronization in Operating Systems
Process synchronization in Operating SystemsProcess synchronization in Operating Systems
Process synchronization in Operating SystemsRitu Ranjan Shrivastwa
 
15 puzzle problem using branch and bound
15 puzzle problem using branch and bound15 puzzle problem using branch and bound
15 puzzle problem using branch and boundAbhishek Singh
 
Algorithm and pseudocode conventions
Algorithm and pseudocode conventionsAlgorithm and pseudocode conventions
Algorithm and pseudocode conventionssaranyatdr
 
Chapter 11 - File System Implementation
Chapter 11 - File System ImplementationChapter 11 - File System Implementation
Chapter 11 - File System ImplementationWayne Jones Jnr
 
Distributed DBMS - Unit 8 - Distributed Transaction Management & Concurrency ...
Distributed DBMS - Unit 8 - Distributed Transaction Management & Concurrency ...Distributed DBMS - Unit 8 - Distributed Transaction Management & Concurrency ...
Distributed DBMS - Unit 8 - Distributed Transaction Management & Concurrency ...Gyanmanjari Institute Of Technology
 
deadlock avoidance
deadlock avoidancedeadlock avoidance
deadlock avoidancewahab13
 

Was ist angesagt? (20)

Parallel and distributed Computing
Parallel and distributed Computing Parallel and distributed Computing
Parallel and distributed Computing
 
Deadlock ppt
Deadlock ppt Deadlock ppt
Deadlock ppt
 
Shared memory
Shared memoryShared memory
Shared memory
 
Minimum spanning tree
Minimum spanning treeMinimum spanning tree
Minimum spanning tree
 
Shared Memory Multi Processor
Shared Memory Multi ProcessorShared Memory Multi Processor
Shared Memory Multi Processor
 
Aca11 bk2 ch9
Aca11 bk2 ch9Aca11 bk2 ch9
Aca11 bk2 ch9
 
Lecture 4 principles of parallel algorithm design updated
Lecture 4   principles of parallel algorithm design updatedLecture 4   principles of parallel algorithm design updated
Lecture 4 principles of parallel algorithm design updated
 
Multithreading
MultithreadingMultithreading
Multithreading
 
Parallel Algorithms
Parallel AlgorithmsParallel Algorithms
Parallel Algorithms
 
Cpu scheduling in operating System.
Cpu scheduling in operating System.Cpu scheduling in operating System.
Cpu scheduling in operating System.
 
Introduction to Distributed System
Introduction to Distributed SystemIntroduction to Distributed System
Introduction to Distributed System
 
Process synchronization in Operating Systems
Process synchronization in Operating SystemsProcess synchronization in Operating Systems
Process synchronization in Operating Systems
 
Divide and conquer
Divide and conquerDivide and conquer
Divide and conquer
 
15 puzzle problem using branch and bound
15 puzzle problem using branch and bound15 puzzle problem using branch and bound
15 puzzle problem using branch and bound
 
Functional modeling
Functional modelingFunctional modeling
Functional modeling
 
Algorithm and pseudocode conventions
Algorithm and pseudocode conventionsAlgorithm and pseudocode conventions
Algorithm and pseudocode conventions
 
Chapter 11 - File System Implementation
Chapter 11 - File System ImplementationChapter 11 - File System Implementation
Chapter 11 - File System Implementation
 
Distributed DBMS - Unit 8 - Distributed Transaction Management & Concurrency ...
Distributed DBMS - Unit 8 - Distributed Transaction Management & Concurrency ...Distributed DBMS - Unit 8 - Distributed Transaction Management & Concurrency ...
Distributed DBMS - Unit 8 - Distributed Transaction Management & Concurrency ...
 
deadlock avoidance
deadlock avoidancedeadlock avoidance
deadlock avoidance
 
Greedy method
Greedy methodGreedy method
Greedy method
 

Andere mochten auch

Parallel programming
Parallel programmingParallel programming
Parallel programmingAnshul Sharma
 
الديسلكسيا العسر القرائي
الديسلكسيا العسر القرائيالديسلكسيا العسر القرائي
الديسلكسيا العسر القرائيLAILAF_M
 
Introduction to multi core
Introduction to multi coreIntroduction to multi core
Introduction to multi coremukul bhardwaj
 
Multi core-architecture
Multi core-architectureMulti core-architecture
Multi core-architecturePiyush Mittal
 
Servers Technologies and Enterprise Data Center Trends 2014 - Thailand
Servers Technologies and Enterprise Data Center Trends 2014 - ThailandServers Technologies and Enterprise Data Center Trends 2014 - Thailand
Servers Technologies and Enterprise Data Center Trends 2014 - ThailandAruj Thirawat
 
Multi core processors
Multi core processorsMulti core processors
Multi core processorsAdithya Bhat
 

Andere mochten auch (9)

Multicore
MulticoreMulticore
Multicore
 
Parallel programming
Parallel programmingParallel programming
Parallel programming
 
ER_appreciation
ER_appreciationER_appreciation
ER_appreciation
 
Introduction to multicore .ppt
Introduction to multicore .pptIntroduction to multicore .ppt
Introduction to multicore .ppt
 
الديسلكسيا العسر القرائي
الديسلكسيا العسر القرائيالديسلكسيا العسر القرائي
الديسلكسيا العسر القرائي
 
Introduction to multi core
Introduction to multi coreIntroduction to multi core
Introduction to multi core
 
Multi core-architecture
Multi core-architectureMulti core-architecture
Multi core-architecture
 
Servers Technologies and Enterprise Data Center Trends 2014 - Thailand
Servers Technologies and Enterprise Data Center Trends 2014 - ThailandServers Technologies and Enterprise Data Center Trends 2014 - Thailand
Servers Technologies and Enterprise Data Center Trends 2014 - Thailand
 
Multi core processors
Multi core processorsMulti core processors
Multi core processors
 

Ähnlich wie parallelization strategy

2014 valat-phd-defense-slides
2014 valat-phd-defense-slides2014 valat-phd-defense-slides
2014 valat-phd-defense-slidesSébastien Valat
 
fdocuments.in_metamorphic-robots.ppt
fdocuments.in_metamorphic-robots.pptfdocuments.in_metamorphic-robots.ppt
fdocuments.in_metamorphic-robots.pptYagnaSri8
 
Moim a novel design of cryptographic hash function
Moim a novel design of cryptographic hash functionMoim a novel design of cryptographic hash function
Moim a novel design of cryptographic hash functionIAEME Publication
 
Browser-Based Collaborative Modeling in Near Real-Time
Browser-Based Collaborative Modeling in Near Real-TimeBrowser-Based Collaborative Modeling in Near Real-Time
Browser-Based Collaborative Modeling in Near Real-TimeNicolaescu Petru
 
Cloud Era Transactional Processing -- Problems, Strategies and Solutions
Cloud Era Transactional Processing -- Problems, Strategies and SolutionsCloud Era Transactional Processing -- Problems, Strategies and Solutions
Cloud Era Transactional Processing -- Problems, Strategies and SolutionsYu Liu
 
Tuple-Based Coordination in Large-Scale Situated Systems
Tuple-Based Coordination in Large-Scale Situated SystemsTuple-Based Coordination in Large-Scale Situated Systems
Tuple-Based Coordination in Large-Scale Situated SystemsRoberto Casadei
 
High-Speed Neural Network Controller for Autonomous Robot Navigation using FPGA
High-Speed Neural Network Controller for Autonomous Robot Navigation using FPGAHigh-Speed Neural Network Controller for Autonomous Robot Navigation using FPGA
High-Speed Neural Network Controller for Autonomous Robot Navigation using FPGAiosrjce
 
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINESISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINESijcseit
 
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINESISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINESijcseit
 
[Gp][1st seminar][presentation]
[Gp][1st seminar][presentation][Gp][1st seminar][presentation]
[Gp][1st seminar][presentation]anas_awad
 
Exploring the capabilities of the tight integration of HyperWorks and ESAComp
Exploring the capabilities of the tight integration of HyperWorks and ESACompExploring the capabilities of the tight integration of HyperWorks and ESAComp
Exploring the capabilities of the tight integration of HyperWorks and ESACompAltair
 

Ähnlich wie parallelization strategy (20)

Cluster Schedulers
Cluster SchedulersCluster Schedulers
Cluster Schedulers
 
2D Thinning
2D Thinning2D Thinning
2D Thinning
 
2014 valat-phd-defense-slides
2014 valat-phd-defense-slides2014 valat-phd-defense-slides
2014 valat-phd-defense-slides
 
PhD Topics
PhD TopicsPhD Topics
PhD Topics
 
fdocuments.in_metamorphic-robots.ppt
fdocuments.in_metamorphic-robots.pptfdocuments.in_metamorphic-robots.ppt
fdocuments.in_metamorphic-robots.ppt
 
Moim a novel design of cryptographic hash function
Moim a novel design of cryptographic hash functionMoim a novel design of cryptographic hash function
Moim a novel design of cryptographic hash function
 
4 Serge Fdida
4   Serge Fdida4   Serge Fdida
4 Serge Fdida
 
Browser-Based Collaborative Modeling in Near Real-Time
Browser-Based Collaborative Modeling in Near Real-TimeBrowser-Based Collaborative Modeling in Near Real-Time
Browser-Based Collaborative Modeling in Near Real-Time
 
Cloud Era Transactional Processing -- Problems, Strategies and Solutions
Cloud Era Transactional Processing -- Problems, Strategies and SolutionsCloud Era Transactional Processing -- Problems, Strategies and Solutions
Cloud Era Transactional Processing -- Problems, Strategies and Solutions
 
Be cse
Be cseBe cse
Be cse
 
Tuple-Based Coordination in Large-Scale Situated Systems
Tuple-Based Coordination in Large-Scale Situated SystemsTuple-Based Coordination in Large-Scale Situated Systems
Tuple-Based Coordination in Large-Scale Situated Systems
 
High-Speed Neural Network Controller for Autonomous Robot Navigation using FPGA
High-Speed Neural Network Controller for Autonomous Robot Navigation using FPGAHigh-Speed Neural Network Controller for Autonomous Robot Navigation using FPGA
High-Speed Neural Network Controller for Autonomous Robot Navigation using FPGA
 
H011114758
H011114758H011114758
H011114758
 
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINESISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
 
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINESISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
ISSUES IN IMPLEMENTATION OF PARALLEL PARSING ON MULTI-CORE MACHINES
 
[Gp][1st seminar][presentation]
[Gp][1st seminar][presentation][Gp][1st seminar][presentation]
[Gp][1st seminar][presentation]
 
Role of locking- cds
Role of locking- cdsRole of locking- cds
Role of locking- cds
 
Rock Overview
Rock OverviewRock Overview
Rock Overview
 
Exploring the capabilities of the tight integration of HyperWorks and ESAComp
Exploring the capabilities of the tight integration of HyperWorks and ESACompExploring the capabilities of the tight integration of HyperWorks and ESAComp
Exploring the capabilities of the tight integration of HyperWorks and ESAComp
 
Lj2419141918
Lj2419141918Lj2419141918
Lj2419141918
 

Kürzlich hochgeladen

Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxLoriGlavin3
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfIngrid Airi González
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxLoriGlavin3
 
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical InfrastructureVarsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructureitnewsafrica
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxLoriGlavin3
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentPim van der Noll
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Farhan Tariq
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
A Framework for Development in the AI Age
A Framework for Development in the AI AgeA Framework for Development in the AI Age
A Framework for Development in the AI AgeCprime
 
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...Alkin Tezuysal
 
Glenn Lazarus- Why Your Observability Strategy Needs Security Observability
Glenn Lazarus- Why Your Observability Strategy Needs Security ObservabilityGlenn Lazarus- Why Your Observability Strategy Needs Security Observability
Glenn Lazarus- Why Your Observability Strategy Needs Security Observabilityitnewsafrica
 
Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityIES VE
 
Scale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterScale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterMydbops
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
Infrared simulation and processing on Nvidia platforms
Infrared simulation and processing on Nvidia platformsInfrared simulation and processing on Nvidia platforms
Infrared simulation and processing on Nvidia platformsYoss Cohen
 
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotesMuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotesManik S Magar
 
[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality Assurance[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality AssuranceInflectra
 
Microservices, Docker deploy and Microservices source code in C#
Microservices, Docker deploy and Microservices source code in C#Microservices, Docker deploy and Microservices source code in C#
Microservices, Docker deploy and Microservices source code in C#Karmanjay Verma
 
Landscape Catalogue 2024 Australia-1.pdf
Landscape Catalogue 2024 Australia-1.pdfLandscape Catalogue 2024 Australia-1.pdf
Landscape Catalogue 2024 Australia-1.pdfAarwolf Industries LLC
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxLoriGlavin3
 

Kürzlich hochgeladen (20)

Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdf
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
 
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical InfrastructureVarsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
Varsha Sewlal- Cyber Attacks on Critical Critical Infrastructure
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptx
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
 
Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...Genislab builds better products and faster go-to-market with Lean project man...
Genislab builds better products and faster go-to-market with Lean project man...
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
A Framework for Development in the AI Age
A Framework for Development in the AI AgeA Framework for Development in the AI Age
A Framework for Development in the AI Age
 
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
Unleashing Real-time Insights with ClickHouse_ Navigating the Landscape in 20...
 
Glenn Lazarus- Why Your Observability Strategy Needs Security Observability
Glenn Lazarus- Why Your Observability Strategy Needs Security ObservabilityGlenn Lazarus- Why Your Observability Strategy Needs Security Observability
Glenn Lazarus- Why Your Observability Strategy Needs Security Observability
 
Decarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a realityDecarbonising Buildings: Making a net-zero built environment a reality
Decarbonising Buildings: Making a net-zero built environment a reality
 
Scale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterScale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL Router
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
Infrared simulation and processing on Nvidia platforms
Infrared simulation and processing on Nvidia platformsInfrared simulation and processing on Nvidia platforms
Infrared simulation and processing on Nvidia platforms
 
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotesMuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
MuleSoft Online Meetup Group - B2B Crash Course: Release SparkNotes
 
[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality Assurance[Webinar] SpiraTest - Setting New Standards in Quality Assurance
[Webinar] SpiraTest - Setting New Standards in Quality Assurance
 
Microservices, Docker deploy and Microservices source code in C#
Microservices, Docker deploy and Microservices source code in C#Microservices, Docker deploy and Microservices source code in C#
Microservices, Docker deploy and Microservices source code in C#
 
Landscape Catalogue 2024 Australia-1.pdf
Landscape Catalogue 2024 Australia-1.pdfLandscape Catalogue 2024 Australia-1.pdf
Landscape Catalogue 2024 Australia-1.pdf
 
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptxThe Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
The Fit for Passkeys for Employee and Consumer Sign-ins: FIDO Paris Seminar.pptx
 

parallelization strategy

  • 1. 1 Is it an open door to common parallelization strategy for topological operators on multi-core multi-thread architecture ? R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 2. 2 Summary General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 3. 3 Summary General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 4. 4 General framework 1. Scientific and technical context (1) Image processingoperators Fourier Transformation Opening Thinning Dynamic redistribution Linear filters Closing Crest restoring Not-linear filters Euclidean Distance Transformation Thresholding Smoothing Attributed Filter Watershed Associated class Topological operators Morphological operators Local operators Point-to-Point operators Global operators R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 5. 5 General framework 1. Scientific and technical context (2) (Associated class) Vs (Parallelizationstrategies) Global operators Topological operators Morphological operators Local operators Point-to-Point operators Sienstra [1] (2002) Wilkinson [2] (2007) Meijster [3] [1] F. J. Seinstra, D. Koelma, and J. M. Geusebroek, “A software architecture for user transparent parallel image processing”. [2] M.H.F. Wilkinson, H. Gao, W.H. Hesselink, “Concurrent Computation of Attribute Filters on Shared Memory Parallel Machines”. [3] A. Meijster, J. B. T. M. Roerdink, and W. H. Hesselink, “A general algorithm for computing distance transforms in linear time” . R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 6. 6 General framework 2. Ph. D. objectives (1) Topological operators Thinning operator [1] common parallelization strategy Crest restoring [1] 2D and 3D smoothing [2] Watershed based on w-thinning [3] Watershed based on graph [4] Homotopic kernel transformation [5] Leveling kernel transformation [5] [1] M. Couprie, F. N. Bezerra, and G. Bertrand, “Topological operators for grayscale image processing”, [2] M. Couprie, and G. Bertrand, “Topology preserving alternating sequential filter for smoothing 2D and 3D objects”. [3] G. Bertrand, “On Topological Watersheds”.   [4] J. Cousty, M. Couprie, L. Najman and G. Betrand “Weighted fusion graphs: Merging properties and watersheds”. [5] G. Bertrand, J. C. Everat, and M. Couprie, "Image segmentation through operators based on topology“ R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 7. 7 General framework 2. Ph. D. objectives (2) Main Architectural Classes SISD machines SIMD machines MISD machines MIMD Machine : (Execute several instruction streams in parallel on different data) Shared Memory Machine Distributed Memory System CPU1 CPU2 CPU3 CPUn Random Access Memory R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 8. 8 General framework 2. Ph. D. objectives (3) Needs Common parallelization strategy of topological operators on multi-core multithread architecture (MIMD Machines – Shared Memory System)? Main Objectives Unifyingparallelizationmethod of topologicaloperators class (Algorithmiclevel) Implementation Methodology and optimization techniques on multi-core multithread architecture (Architecture level). R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 9. 9 General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 10. 10 Parallel thinning operator 1. Theoretical background Filtered thinning method that allows to selectively simplify the topology, based on a local contrast parameter λ. (b) filtered skeleton with λ = 10. (a) After Deriche gradient operator R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 11. 11 Parallel thinning operator 1. Parallelization strategy (1) Definesearch area Startparallelcharacterization Create new shared data structure End parallelcharacterization Mergemodifiedsearch area Restart process until stability R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 12. 12 Parallel thinning operator 1. Parallelization strategy (2) SDM-Strategy (Divide and conquer principle) Up level DATA PARALLELISM MIXED PARALLELISM Down level THREAD PARALLELISM R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 13. 13 Parallel thinning operator 1. Parallelization strategy (3) R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 14. 14 Parallel thinning operator 2. Coordination of threads (1) Thread 1 Thread 2 First implementation using a lock-based shared FIFO queue. Lock() Unlock() Push() Fail Success Blocked R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 15. 15 Parallel thinning operator 2. Coordination of threads (2) Thread 1 Thread 2 Lock() and access semaphore Unlock() and leave semaphore Semaphore Push() Second implementation using a private-shared concurrent FIFO queue R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 16. 16 Parallel thinning operator 3. Performance testing (1) R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 17. 17 Parallel thinning operator 3. Performance testing (2) First implementation using a lock-based shared FIFO queue. R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 18. 18 Parallel thinning operator 3. Performance testing (3) Second implementation using a private-shared concurrent FIFO queue R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 19. 19 Parallel thinning operator 4. Conclusion Non-specific nature of the proposed parallelization strategy. Threads coordination and communication during computing dependently parallel read/write for managing cache-resident data 1 2 R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 20. 20 General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 21. 21 Future work 1. Extension SDM - Strategy Performance enhancement (speed up) Efficiency (work distribution) Cache miss ParallelThinning Operator IMBRICATE TWO Operators Crest restoring R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 22. 22 Future work 2. New parallel topological watershed % Achievement Parallelwatershed Operator SDM - Strategy Performance enhancement (speed up) Efficiency (work distribution) Cache miss 80% R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 23. 23 General framework Parallel thinning operator Future work Discussion R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 24. 24 Discussion Introduce future programming model (make it easy to write programs that execute efficiently on highly parallel C.S) Introduce new “Draft”to design and evaluate parallel programming models (instead of old benchmark) Maximize programmer productivity, future programming model must be more human-centric (than the conventional focus on hardware or application) R. MAHMOUDI – A3SI Laboratory– 2009 April
  • 25. 25 R. MAHMOUDI – A3SI Laboratory– 2009 April