SlideShare a Scribd company logo
1 of 1
Download to read offline
Roman Atachiants
Supervised by Dr. Gavin Doherty
Collaborators Dr. David Gregg, Dr. Bérenger Arnaud
Project Title MANYCORE: Understanding Software
Performance on Many-Core Systems
Colour
Photo
6 x 4 cm
Visualising Data Locality Performance
In order to take advantage of the multi-core and many-core
hardware of today and tomorrow, programmers are faced with a
need to parallelize the code to distribute work across multiple CPUs.
User Evaluation
To evaluate the tool,
we have conducted an
experiment with a total
of 33 participants from
industry and academia.
To analyze the results
of the experiment, we
adopted a hybrid quali-
tative and quantitative
approach.
Fieldwork, Taxonomy, Modelling and Validation
While the visualisation itself is being the final step of this research, it
is based on the significant amount of analytical work and an
observational model we’ve created and validated to bridge the gap
The process of paralle-
lization is very complex
and in order to assist
programmers in identi-
fying the performance
of parallel programs re-
lated to poor data loca-
lity, we have designed
an interactive visualis-
ation tool.
3-Step Visualisation
 Summary View
 Timeline View
 Threads View
Our Publications
 R. Atachiants, D. Gregg and
G. Doherty. Design
Considerations for
Parallel Performance
Tools. ACM SIG-CHI’14
 R. Atachiants, D. Gregg and
G. Doherty. 2015. An
Observational Model for
Identifying Parallel
Performance Problems.
Journal paper submitted and
under revision
 R. Atachiants, D. Gregg and
G. Doherty. Visualising
Data Locality Performance
for Parallel Programming.
Submitted for revision.
 R. Atachiants. Ph.D.
Thesis: Supporting Visual
Diagnosis of Performance
Problems in Multi-Threaded
Software. [Draft]
Some Results
 The participants' correctness in data locality problem identifica-
tion has significantly increased when they used the visualisation.
 We received a significant amount of feedback which suggests
that the visualization effectively supports programmers and
reduced the cognitive load of performance problem diagnosis.
 Programmers with less than 10
years of experience in the field
rated their diagnosis answers
with significantly more confi-
dence when they used our
visualisation.
between the events and
counters we can collect
and the actual parallel
performance problems.
We have also created a
taxonomy of problems
comprised of 23 parallel
problems and ran two
experiments with the
help of 81 programmers
to validate the taxono-
my and our model.

More Related Content

What's hot

A Novel Optimization towards Higher Reliability in Predictive Modelling towar...
A Novel Optimization towards Higher Reliability in Predictive Modelling towar...A Novel Optimization towards Higher Reliability in Predictive Modelling towar...
A Novel Optimization towards Higher Reliability in Predictive Modelling towar...IJECEIAES
 
Seminar VU Amsterdam 2015
Seminar VU Amsterdam 2015Seminar VU Amsterdam 2015
Seminar VU Amsterdam 2015Philipp Leitner
 
Co-ordination Support for Managing Progress of Distributed Agile Projects
Co-ordination Support for Managing Progress of Distributed Agile ProjectsCo-ordination Support for Managing Progress of Distributed Agile Projects
Co-ordination Support for Managing Progress of Distributed Agile ProjectsSultan Alyahya
 
Iceemas 119- state of art of metrics of aspect oriented programming
Iceemas 119- state of art of metrics of aspect oriented programmingIceemas 119- state of art of metrics of aspect oriented programming
Iceemas 119- state of art of metrics of aspect oriented programmingMazen Ghareb
 
Productivity Factors in Software Development for PC Platform
Productivity Factors in Software Development for PC PlatformProductivity Factors in Software Development for PC Platform
Productivity Factors in Software Development for PC PlatformIJERA Editor
 
Review on cost estimation technque for web application [part 1]
Review on cost estimation technque for web application [part 1]Review on cost estimation technque for web application [part 1]
Review on cost estimation technque for web application [part 1]Sayed Mohsin Reza
 
Supporting Change Impact Analysis Using a Recommendation System - An Industri...
Supporting Change Impact Analysis Using a Recommendation System - An Industri...Supporting Change Impact Analysis Using a Recommendation System - An Industri...
Supporting Change Impact Analysis Using a Recommendation System - An Industri...Markus Borg
 

What's hot (8)

A Novel Optimization towards Higher Reliability in Predictive Modelling towar...
A Novel Optimization towards Higher Reliability in Predictive Modelling towar...A Novel Optimization towards Higher Reliability in Predictive Modelling towar...
A Novel Optimization towards Higher Reliability in Predictive Modelling towar...
 
Seminar VU Amsterdam 2015
Seminar VU Amsterdam 2015Seminar VU Amsterdam 2015
Seminar VU Amsterdam 2015
 
Co-ordination Support for Managing Progress of Distributed Agile Projects
Co-ordination Support for Managing Progress of Distributed Agile ProjectsCo-ordination Support for Managing Progress of Distributed Agile Projects
Co-ordination Support for Managing Progress of Distributed Agile Projects
 
Iceemas 119- state of art of metrics of aspect oriented programming
Iceemas 119- state of art of metrics of aspect oriented programmingIceemas 119- state of art of metrics of aspect oriented programming
Iceemas 119- state of art of metrics of aspect oriented programming
 
Productivity Factors in Software Development for PC Platform
Productivity Factors in Software Development for PC PlatformProductivity Factors in Software Development for PC Platform
Productivity Factors in Software Development for PC Platform
 
Promise Keynote
Promise KeynotePromise Keynote
Promise Keynote
 
Review on cost estimation technque for web application [part 1]
Review on cost estimation technque for web application [part 1]Review on cost estimation technque for web application [part 1]
Review on cost estimation technque for web application [part 1]
 
Supporting Change Impact Analysis Using a Recommendation System - An Industri...
Supporting Change Impact Analysis Using a Recommendation System - An Industri...Supporting Change Impact Analysis Using a Recommendation System - An Industri...
Supporting Change Impact Analysis Using a Recommendation System - An Industri...
 

Viewers also liked

Requerimientos
RequerimientosRequerimientos
RequerimientosAlex Rojas
 
On the Fly Award for James Nemo GE, 112014
On the Fly Award for James Nemo GE, 112014On the Fly Award for James Nemo GE, 112014
On the Fly Award for James Nemo GE, 112014Jim Nemo
 
Age span of human development
Age span of human developmentAge span of human development
Age span of human developmentmanica tewatia
 
Ethics of space exploration lecture
Ethics of space exploration lectureEthics of space exploration lecture
Ethics of space exploration lecturePeter Household
 
XILEMA ARTFIFICIAL
XILEMA ARTFIFICIALXILEMA ARTFIFICIAL
XILEMA ARTFIFICIALFelipe
 
Birth and Rebirth
Birth and RebirthBirth and Rebirth
Birth and RebirthStephen Sia
 
Growth&development of school age
Growth&development of school ageGrowth&development of school age
Growth&development of school ageMadiha Deeda
 
Synthesis of Proteins or the Formation of the Conga Line
Synthesis of Proteins or the Formation of the Conga LineSynthesis of Proteins or the Formation of the Conga Line
Synthesis of Proteins or the Formation of the Conga LineAndrea Sánchez del Rio
 

Viewers also liked (11)

Requerimientos
RequerimientosRequerimientos
Requerimientos
 
On the Fly Award for James Nemo GE, 112014
On the Fly Award for James Nemo GE, 112014On the Fly Award for James Nemo GE, 112014
On the Fly Award for James Nemo GE, 112014
 
Why it's important to Sweat
Why it's important to SweatWhy it's important to Sweat
Why it's important to Sweat
 
Hanbit | baedal
Hanbit | baedalHanbit | baedal
Hanbit | baedal
 
Age span of human development
Age span of human developmentAge span of human development
Age span of human development
 
Ethics of space exploration lecture
Ethics of space exploration lectureEthics of space exploration lecture
Ethics of space exploration lecture
 
XILEMA ARTFIFICIAL
XILEMA ARTFIFICIALXILEMA ARTFIFICIAL
XILEMA ARTFIFICIAL
 
Birth and Rebirth
Birth and RebirthBirth and Rebirth
Birth and Rebirth
 
FET
FETFET
FET
 
Growth&development of school age
Growth&development of school ageGrowth&development of school age
Growth&development of school age
 
Synthesis of Proteins or the Formation of the Conga Line
Synthesis of Proteins or the Formation of the Conga LineSynthesis of Proteins or the Formation of the Conga Line
Synthesis of Proteins or the Formation of the Conga Line
 

Similar to Manycore - Roman Atachiants

TOWARDS PREDICTING SOFTWARE DEFECTS WITH CLUSTERING TECHNIQUES
TOWARDS PREDICTING SOFTWARE DEFECTS WITH CLUSTERING TECHNIQUESTOWARDS PREDICTING SOFTWARE DEFECTS WITH CLUSTERING TECHNIQUES
TOWARDS PREDICTING SOFTWARE DEFECTS WITH CLUSTERING TECHNIQUESijaia
 
Andrea Mocci: Beautiful Design, Beautiful Coding at I T.A.K.E. Unconference 2015
Andrea Mocci: Beautiful Design, Beautiful Coding at I T.A.K.E. Unconference 2015Andrea Mocci: Beautiful Design, Beautiful Coding at I T.A.K.E. Unconference 2015
Andrea Mocci: Beautiful Design, Beautiful Coding at I T.A.K.E. Unconference 2015Mozaic Works
 
Improved Knowledge from Data: Building an Immersive Data Analysis Platform
Improved Knowledge from Data: Building an Immersive Data Analysis PlatformImproved Knowledge from Data: Building an Immersive Data Analysis Platform
Improved Knowledge from Data: Building an Immersive Data Analysis PlatformFelipe Pedroso
 
A Model To Compare The Degree Of Refactoring Opportunities Of Three Projects ...
A Model To Compare The Degree Of Refactoring Opportunities Of Three Projects ...A Model To Compare The Degree Of Refactoring Opportunities Of Three Projects ...
A Model To Compare The Degree Of Refactoring Opportunities Of Three Projects ...acijjournal
 
A MODEL TO COMPARE THE DEGREE OF REFACTORING OPPORTUNITIES OF THREE PROJECTS ...
A MODEL TO COMPARE THE DEGREE OF REFACTORING OPPORTUNITIES OF THREE PROJECTS ...A MODEL TO COMPARE THE DEGREE OF REFACTORING OPPORTUNITIES OF THREE PROJECTS ...
A MODEL TO COMPARE THE DEGREE OF REFACTORING OPPORTUNITIES OF THREE PROJECTS ...acijjournal
 
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...csandit
 
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...cscpconf
 
An approach for software effort estimation using fuzzy numbers and genetic al...
An approach for software effort estimation using fuzzy numbers and genetic al...An approach for software effort estimation using fuzzy numbers and genetic al...
An approach for software effort estimation using fuzzy numbers and genetic al...csandit
 
Application of Genetic Algorithm in Software Engineering: A Review
Application of Genetic Algorithm in Software Engineering: A ReviewApplication of Genetic Algorithm in Software Engineering: A Review
Application of Genetic Algorithm in Software Engineering: A ReviewIRJESJOURNAL
 
The Medium of Visualization for Software Comprehension
The Medium of Visualization for Software ComprehensionThe Medium of Visualization for Software Comprehension
The Medium of Visualization for Software ComprehensionLeonel Merino
 
Knowledge and Data Engineering IEEE 2015 Projects
Knowledge and Data Engineering IEEE 2015 ProjectsKnowledge and Data Engineering IEEE 2015 Projects
Knowledge and Data Engineering IEEE 2015 ProjectsVijay Karan
 
ENSEMBLE REGRESSION MODELS FOR SOFTWARE DEVELOPMENT EFFORT ESTIMATION: A COMP...
ENSEMBLE REGRESSION MODELS FOR SOFTWARE DEVELOPMENT EFFORT ESTIMATION: A COMP...ENSEMBLE REGRESSION MODELS FOR SOFTWARE DEVELOPMENT EFFORT ESTIMATION: A COMP...
ENSEMBLE REGRESSION MODELS FOR SOFTWARE DEVELOPMENT EFFORT ESTIMATION: A COMP...ijseajournal
 
IRJET- Data Reduction in Bug Triage using Supervised Machine Learning
IRJET- Data Reduction in Bug Triage using Supervised Machine LearningIRJET- Data Reduction in Bug Triage using Supervised Machine Learning
IRJET- Data Reduction in Bug Triage using Supervised Machine LearningIRJET Journal
 
ManganoHoeeg - Virtual Supermarket Designer POSTER
ManganoHoeeg - Virtual Supermarket Designer POSTERManganoHoeeg - Virtual Supermarket Designer POSTER
ManganoHoeeg - Virtual Supermarket Designer POSTEREmil Rosenlund Høeg
 
Proceedings of the 2015 Industrial and Systems Engineering Res.docx
Proceedings of the 2015 Industrial and Systems Engineering Res.docxProceedings of the 2015 Industrial and Systems Engineering Res.docx
Proceedings of the 2015 Industrial and Systems Engineering Res.docxwkyra78
 
Knowledge and Data Engineering IEEE 2015 Projects
Knowledge and Data Engineering IEEE 2015 ProjectsKnowledge and Data Engineering IEEE 2015 Projects
Knowledge and Data Engineering IEEE 2015 ProjectsVijay Karan
 

Similar to Manycore - Roman Atachiants (20)

TOWARDS PREDICTING SOFTWARE DEFECTS WITH CLUSTERING TECHNIQUES
TOWARDS PREDICTING SOFTWARE DEFECTS WITH CLUSTERING TECHNIQUESTOWARDS PREDICTING SOFTWARE DEFECTS WITH CLUSTERING TECHNIQUES
TOWARDS PREDICTING SOFTWARE DEFECTS WITH CLUSTERING TECHNIQUES
 
Andrea Mocci: Beautiful Design, Beautiful Coding at I T.A.K.E. Unconference 2015
Andrea Mocci: Beautiful Design, Beautiful Coding at I T.A.K.E. Unconference 2015Andrea Mocci: Beautiful Design, Beautiful Coding at I T.A.K.E. Unconference 2015
Andrea Mocci: Beautiful Design, Beautiful Coding at I T.A.K.E. Unconference 2015
 
Improved Knowledge from Data: Building an Immersive Data Analysis Platform
Improved Knowledge from Data: Building an Immersive Data Analysis PlatformImproved Knowledge from Data: Building an Immersive Data Analysis Platform
Improved Knowledge from Data: Building an Immersive Data Analysis Platform
 
A Model To Compare The Degree Of Refactoring Opportunities Of Three Projects ...
A Model To Compare The Degree Of Refactoring Opportunities Of Three Projects ...A Model To Compare The Degree Of Refactoring Opportunities Of Three Projects ...
A Model To Compare The Degree Of Refactoring Opportunities Of Three Projects ...
 
A MODEL TO COMPARE THE DEGREE OF REFACTORING OPPORTUNITIES OF THREE PROJECTS ...
A MODEL TO COMPARE THE DEGREE OF REFACTORING OPPORTUNITIES OF THREE PROJECTS ...A MODEL TO COMPARE THE DEGREE OF REFACTORING OPPORTUNITIES OF THREE PROJECTS ...
A MODEL TO COMPARE THE DEGREE OF REFACTORING OPPORTUNITIES OF THREE PROJECTS ...
 
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
 
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
AN APPROACH FOR SOFTWARE EFFORT ESTIMATION USING FUZZY NUMBERS AND GENETIC AL...
 
An approach for software effort estimation using fuzzy numbers and genetic al...
An approach for software effort estimation using fuzzy numbers and genetic al...An approach for software effort estimation using fuzzy numbers and genetic al...
An approach for software effort estimation using fuzzy numbers and genetic al...
 
Application of Genetic Algorithm in Software Engineering: A Review
Application of Genetic Algorithm in Software Engineering: A ReviewApplication of Genetic Algorithm in Software Engineering: A Review
Application of Genetic Algorithm in Software Engineering: A Review
 
The Medium of Visualization for Software Comprehension
The Medium of Visualization for Software ComprehensionThe Medium of Visualization for Software Comprehension
The Medium of Visualization for Software Comprehension
 
Knowledge and Data Engineering IEEE 2015 Projects
Knowledge and Data Engineering IEEE 2015 ProjectsKnowledge and Data Engineering IEEE 2015 Projects
Knowledge and Data Engineering IEEE 2015 Projects
 
ENSEMBLE REGRESSION MODELS FOR SOFTWARE DEVELOPMENT EFFORT ESTIMATION: A COMP...
ENSEMBLE REGRESSION MODELS FOR SOFTWARE DEVELOPMENT EFFORT ESTIMATION: A COMP...ENSEMBLE REGRESSION MODELS FOR SOFTWARE DEVELOPMENT EFFORT ESTIMATION: A COMP...
ENSEMBLE REGRESSION MODELS FOR SOFTWARE DEVELOPMENT EFFORT ESTIMATION: A COMP...
 
IRJET- Data Reduction in Bug Triage using Supervised Machine Learning
IRJET- Data Reduction in Bug Triage using Supervised Machine LearningIRJET- Data Reduction in Bug Triage using Supervised Machine Learning
IRJET- Data Reduction in Bug Triage using Supervised Machine Learning
 
Ijetcas14 533
Ijetcas14 533Ijetcas14 533
Ijetcas14 533
 
ONE HIDDEN LAYER ANFIS MODEL FOR OOS DEVELOPMENT EFFORT ESTIMATION
ONE HIDDEN LAYER ANFIS MODEL FOR OOS DEVELOPMENT EFFORT ESTIMATIONONE HIDDEN LAYER ANFIS MODEL FOR OOS DEVELOPMENT EFFORT ESTIMATION
ONE HIDDEN LAYER ANFIS MODEL FOR OOS DEVELOPMENT EFFORT ESTIMATION
 
ManganoHoeeg - Virtual Supermarket Designer POSTER
ManganoHoeeg - Virtual Supermarket Designer POSTERManganoHoeeg - Virtual Supermarket Designer POSTER
ManganoHoeeg - Virtual Supermarket Designer POSTER
 
Naresh Chirra
Naresh ChirraNaresh Chirra
Naresh Chirra
 
Proceedings of the 2015 Industrial and Systems Engineering Res.docx
Proceedings of the 2015 Industrial and Systems Engineering Res.docxProceedings of the 2015 Industrial and Systems Engineering Res.docx
Proceedings of the 2015 Industrial and Systems Engineering Res.docx
 
Knowledge and Data Engineering IEEE 2015 Projects
Knowledge and Data Engineering IEEE 2015 ProjectsKnowledge and Data Engineering IEEE 2015 Projects
Knowledge and Data Engineering IEEE 2015 Projects
 
Chounta avouris arv2011
Chounta avouris arv2011Chounta avouris arv2011
Chounta avouris arv2011
 

Manycore - Roman Atachiants

  • 1. Roman Atachiants Supervised by Dr. Gavin Doherty Collaborators Dr. David Gregg, Dr. Bérenger Arnaud Project Title MANYCORE: Understanding Software Performance on Many-Core Systems Colour Photo 6 x 4 cm Visualising Data Locality Performance In order to take advantage of the multi-core and many-core hardware of today and tomorrow, programmers are faced with a need to parallelize the code to distribute work across multiple CPUs. User Evaluation To evaluate the tool, we have conducted an experiment with a total of 33 participants from industry and academia. To analyze the results of the experiment, we adopted a hybrid quali- tative and quantitative approach. Fieldwork, Taxonomy, Modelling and Validation While the visualisation itself is being the final step of this research, it is based on the significant amount of analytical work and an observational model we’ve created and validated to bridge the gap The process of paralle- lization is very complex and in order to assist programmers in identi- fying the performance of parallel programs re- lated to poor data loca- lity, we have designed an interactive visualis- ation tool. 3-Step Visualisation  Summary View  Timeline View  Threads View Our Publications  R. Atachiants, D. Gregg and G. Doherty. Design Considerations for Parallel Performance Tools. ACM SIG-CHI’14  R. Atachiants, D. Gregg and G. Doherty. 2015. An Observational Model for Identifying Parallel Performance Problems. Journal paper submitted and under revision  R. Atachiants, D. Gregg and G. Doherty. Visualising Data Locality Performance for Parallel Programming. Submitted for revision.  R. Atachiants. Ph.D. Thesis: Supporting Visual Diagnosis of Performance Problems in Multi-Threaded Software. [Draft] Some Results  The participants' correctness in data locality problem identifica- tion has significantly increased when they used the visualisation.  We received a significant amount of feedback which suggests that the visualization effectively supports programmers and reduced the cognitive load of performance problem diagnosis.  Programmers with less than 10 years of experience in the field rated their diagnosis answers with significantly more confi- dence when they used our visualisation. between the events and counters we can collect and the actual parallel performance problems. We have also created a taxonomy of problems comprised of 23 parallel problems and ran two experiments with the help of 81 programmers to validate the taxono- my and our model.