SlideShare a Scribd company logo
11
LCN : Design and Implementation of a Contention-LCN : Design and Implementation of a Contention-
Aware SchedulerAware Scheduler
Raptis Dimos – DimitriosRaptis Dimos – Dimitrios
88thth
SFHMMY Conference 2015SFHMMY Conference 2015
April 4, 2015April 4, 2015
April 4, 2015April 4, 2015 11National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering88thth
SFHMMY ConferenceSFHMMY Conference
22April 4, 2015April 4, 2015 22National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Outline

Motivation

Background

Similar Research

Scheduler Overview

Classification Scheme

Prediction Model

Scheduling Algorithm

Comparison with Similar Research

Conclusion

Future Work
88thth
SFHMMY ConferenceSFHMMY Conference
33April 4, 2015April 4, 2015 33National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Motivation
Memory Wall
Protocols
SMPs & CMPs
Multithreaded
Cache Coherency
Programming
Parallel Processing
88thth
SFHMMY ConferenceSFHMMY Conference
44April 4, 2015April 4, 2015 44National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Motivation
Cache Coherence Problems

Legacy PC
applications
(not benefiting)

Applications
benefiting from
multithreaded
environments

“Embarassingly
parallel” applications
(GPU etc.)
Leveraging
Parallelism
88thth
SFHMMY ConferenceSFHMMY Conference
55April 4, 2015April 4, 2015 55National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Motivation
Problems Approaches

Memory Contention
Problem

Cache Coherence
Problem

Missing existing
infrastructure to detect
and restrict system
resources contention

What if it was not
programmer's
responsibility to
“allocate”
resources ?

What if Operating
System was
responsible for
judging applications'
parallelism ?
Contention – Aware Scheduling
88thth
SFHMMY ConferenceSFHMMY Conference
66April 4, 2015April 4, 2015 66National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Contention – Aware Scheduling
Classification
(based on locality and
degree of contention)
Background
Scheduling Algorithm
HPC Monitoring
++ Our approach contains an additional
component : a prediction model
88thth
SFHMMY ConferenceSFHMMY Conference
77April 4, 2015April 4, 2015 77National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Similar Research
Various Approaches

Simple Heuristic approaches
(LLC misses & Memory bandwidth)

Stack Distance Profiling approaches

Dynamic Scheduling approaches using supervised learning
(linear regression, fuzzy-rule models, K-nearest neighbour)
Differences

Simple Heuristic approaches
(LLC misses & Memory bandwidth)

Stack Distance Profiling approaches

Dynamic Scheduling approaches using supervised learning
(linear regression, fuzzy-rule models, K-nearest neighbour)
Not covering the whole memory hierarchy
Using additional hardware not available currently in OS
Targeting the same problem from a different view
Pre-defined allocated resources in applications
88thth
SFHMMY ConferenceSFHMMY Conference
88April 4, 2015April 4, 2015 88National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Scheduler Overview
Scheduler Main Components

Classification Scheme
4 categories of applications based on memory hierarchy

Prediction Model
prediction of contention in varying resources allocations

Scheduling Algorithm
scheduling a workload of applications based on

classification scheme (co-scheduling combinations)

prediction model (for ideal resource management)
88thth
SFHMMY ConferenceSFHMMY Conference
99April 4, 2015April 4, 2015 99National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Classification Scheme
4 main categories of applications
L LC
C N
88thth
SFHMMY ConferenceSFHMMY Conference
1010April 4, 2015April 4, 2015 1010National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Classification Scheme
Co-scheduling interference

N - * : no interference

L - L : contention on same resource, bandwidth “divided”

L - C : contention in different resources

severe performance degradation in C

no impact in L

L - LC : performance degradation for both

LC faces bigger degradation than L

LC - LC : contention in 2 resources (memory link and LLC)

Both have degradation but in low levels

LC - C : mediocre contention, mainly in C

C - C : most difficult to predict - based on data access
patterns (MESI protocol)
88thth
SFHMMY ConferenceSFHMMY Conference
1111April 4, 2015April 4, 2015 1111National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Classification Scheme
Co-scheduling interference
Analysis from
workload of 16
applications
4 applications
belonging to each
class
Co-scheduling of all
possible
combinations
Average slowdown
calculated for each
combinationTable : Average slowdown in co-execution
88thth
SFHMMY ConferenceSFHMMY Conference
1212April 4, 2015April 4, 2015 1212National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Classification Scheme
Classification tree
88thth
SFHMMY ConferenceSFHMMY Conference
1313April 4, 2015April 4, 2015 1313National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Prediction Model

Linear Regression Model

Target : Prediction of scaling

possess HPC monitored for 1 core allocation

capability to predict scaling for any possible allocation

use of threshold value for defining optimal scaling

Use the suitable counters for each class

Class L : memory link (bandwidth)

Class LC : LLC reuse (MESI protocol)

Class C : L2 and LLC reuse (MESI protocol)

Class N : private part of memory hierarchy
88thth
SFHMMY ConferenceSFHMMY Conference
1414April 4, 2015April 4, 2015 1414National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Prediction Model
L class
Rp = (Mem1 p)/(Maximum Memory Bandwidth)∗
poptimum = max{p}, Rp < 1.15
LC class
Completion(LC) = 0.01799 ∗ fLC
+ 0.50119 (p = 2cores)
= 0.02516 ∗ fLC
+ 0.34286 (p = 3 cores)
= 0.02846 ∗ fLC
+ 0.26028 (p = 4 cores)
= 0.03199 ∗ fLC
+ 0.21584 (p = 5 cores)
= 0.03404 ∗ fLC
+ 0.18296 (p = 6 cores)
= 0.03621 ∗ fLC
+ 0.16410 (p = 7 cores)
= 0.03751 ∗ fLC
+ 0.13969 (p = 8 cores)
Ideal_Completionp
= 1/p , fLC
= L2 RFO Requests/(L3 reuse*105
)
Rp = (Ideal_Completionp
/Completionp
) 100∗
poptimum
= max{p}, Rp > 70
88thth
SFHMMY ConferenceSFHMMY Conference
1515April 4, 2015April 4, 2015 1515National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Prediction Model
C class
Completion(C) = 0.3447 ∗ fC
+ 0.4947 (2cores)
= 0.46974 ∗ fC
+ 0.34415 (p = 3 cores)
= 0.5155 ∗ fC
+ 0.2478 (p = 4 cores)
= 0.63609 ∗ fC
+ 0.22492 (p = 5 cores)
= 0.61403 ∗ fC
+ 0.18127 (p = 6 cores)
= 0.65915 ∗ fC
+ 0.15864 (p = 7 cores)
= 0.6095 ∗ fC
+ 0.1263 (p = 8 cores)
Ideal_Completionp
= 1/p , fC
= (L2 Shared*104
)/Inst.Retired
Rp = (Ideal_Completionp
/Completionp
) 100∗
poptimum
= max{p}, Rp > 70
N class
Completion(N)p
= Completion_idealp
poptimum
= max{p}
88thth
SFHMMY ConferenceSFHMMY Conference
April 4, 2015April 4, 2015 National Technical University of AthensNational Technical University of Athens 1616
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Prediction Model
Example
L class LC class
Mem1
= 4GB/sec
Memmax
= 13.5
GB/sec
R1
= 4/13.5 = 0.29
R2
= (4*2)/13.5 = 0.59
R3
= (4*3)/13.5 = 0.88
R4
= (4*4)/13.5 =
1.185
R5
= (4*5)/13.5 = 1.48
R6
= (4*6)/13.5 = 1.77
R7
= (4*7)/13.5 = 2.07
R8
= (4*8)/13.5 = 2.37
poptimum
= 3 cores
RFO1
= 319106 per second , L3 reuse = 1.51
fLC
= 319106/(1.51*105
) = 2.10
Completion(LC)2
= 0.01799*2.10 + 0.50119 = 0.53 →
R2
=0.5/0.53*100= 92.792.7
Completion(LC)3
= 0.02516*2.10 + 0.34286 = 0.39 →
R3
=0.33/0.39*100= 84.284.2
Completion(LC)4
= 0.02846*2.10 + 0.26028 = 0.32 →
R4
=0.25/0.32*100= 78.078.0
Completion(LC)5
= 0.03199*2.10 + 0.21584 = 0.28 →
R5
=0.2/0.28*100= 70.670.6
Completion(LC)6
= 0.03404*2.10 + 0.18296 =0.25 →
R6
=0.166/0.25*100= 65.465.4
Completion(LC)7
= 0.03621*2.10 + 0.16410 = 0.24 →
R7
=0.142/0.24*100= 59.059.0
Completion(LC)8
= 0.03751*2.10 + 0.13969 = 0.21 →
R8
=0.125/0.21*100= 57.157.1
Poptimum
= 5 cores
88thth
SFHMMY ConferenceSFHMMY Conference
1717April 4, 2015April 4, 2015 1717National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Prediction Model
Evaluation – Verification
Relative Errors in Predictions of C class
88thth
SFHMMY ConferenceSFHMMY Conference
1818April 4, 2015April 4, 2015 1818National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Prediction Model
Evaluation – Verification
Relative Errors in Predictions of LC class
88thth
SFHMMY ConferenceSFHMMY Conference
1919April 4, 2015April 4, 2015 1919National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Prediction Model
LC - C prediction model improvement

Integration of 7 relationships to a single one

Coefficients follow logarithmic trendline

Results after analysis
Completion(LC)p = [0.0139536 log(p) + 0.0090562] f∗ ∗ LC + [−0.252533 log(p) + 0.6407058]∗
Completion(C)p = [0.2151318 log(p) + 0.2239032] f∗ ∗ C + [−0.25468 log(p) + 0.6397947]∗
Ideal_Completionp = 1/p
Rp = (Ideal_Completionp /Completionp ) 100∗
poptimum = max{p}, Rp > 70
88thth
SFHMMY ConferenceSFHMMY Conference
2020April 4, 2015April 4, 2015 2020National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Prediction Model
Evaluation – Verification of Refinement
Deviation in C coefficients Deviation in LC coefficients
88thth
SFHMMY ConferenceSFHMMY Conference
Prediction Model
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
April 4, 2015April 4, 2015 National Technical University of AthensNational Technical University of Athens 2121
Experimentation Platform

cores : 8

L1D,I: 32KB
8-way

L2 : 256KB
8-way

L3 : 16 MB
16-way

64bytes line

Mem :64GB
DDR3 1.3GHZ

Debian 6.06
*(Prediction
Model also
tested on
Nehalem
architecture)
88thth
SFHMMY ConferenceSFHMMY Conference
2222April 4, 2015April 4, 2015 2222National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Scheduling Algorithm

Executed after first 2 steps are finished for each application

Step 1 has classified each application

Step 2 has predicted the optimum number of cores that
should be allocated by the scheduler to each application

The algorithm tries to co-schedule the applications in pairs
so that

Sum of cores does not exceed package cores

Contention is avoided as much as possible
(using conclusions from Classification step)

The approach can be extended for co-execution of more
than 2 applications

N applications are allocated half cores and scheduled twice
(their profile implies that they are not affected by this)
88thth
SFHMMY ConferenceSFHMMY Conference
2323April 4, 2015April 4, 2015 2323National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Scheduling Algorithm
Lists of applications separated by class : L, LC, C, N
while(N not empty){
x = current N application ;
y = popMatchFromTheEnd(C, L, LC, N);
coschedule(x, y);
}
while( LC not empty){
x = current LC application;
y = popMatchFromTheEnd(C, LC, L);
coschedule(x, y);
}
while(L not empty){
x = current L application;
y = popMatchFromTheEnd(L);
coschedule(x, y);
}
while(C not empty){
x = current C application;
y = popMatchFromTheEnd(C);
coschedule(x, y);
}
scheduleRemainingApplications();
88thth
SFHMMY ConferenceSFHMMY Conference
2424April 4, 2015April 4, 2015 2424National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Comparison with Similar Research
The other state-of-the-art schedulers

Sorting by heuristic

Distributing load

Combining
application from the
top with application
from the bottom

LLC – MRB
LLC misses

LBB
memory bandwidth
88thth
SFHMMY ConferenceSFHMMY Conference
2525April 4, 2015April 4, 2015 2525National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Comparison with Similar Research
Experiments – Comparison Process

Linux CFS, LCN, LLC-MRB, LLB to be compared

Workload of 17 applications (equally shared among classes)

Whole workload executed for 1 hour

Time quantums of 1 second defined in all schedulers

When application finishes, it gets respawn to re-execute

Comparison between schedulers with 2 criteria

Throughput

Total number of executions of all applications

Number of improved applications

Fairness

Standard Deviation between gain of each application
*gain compared to Gang scheduler
88thth
SFHMMY ConferenceSFHMMY Conference
2626April 4, 2015April 4, 2015 2626National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Comparison with Similar Research
Most Improved
Applications
Linux : 5
LLC – Balance : 7
MEM-Balance : 5
LCN : 8
88thth
SFHMMY ConferenceSFHMMY Conference
2727April 4, 2015April 4, 2015 2727National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Comparison with Similar Research
Criteria :
- Throughput
LCNLCN
- Fairness
LLC-BalanceLLC-Balance **
* fairness can be* fairness can be
misinterpretedmisinterpreted
88thth
SFHMMY ConferenceSFHMMY Conference
2828April 4, 2015April 4, 2015 2828National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Comparison with Similar Research
Major Drawbacks of other schedulers

Linux Scheduler CFS

Cannot locate contention

Does not identify threads of the same application
parallelism benefits lost

MEM - Balance Scheduler

Uses over-generic heuristic

Does not take into account all memory hierarchy parts

LLC - Balance Scheduler

Cannot differentiate between class N and C applications,
since they both exhibit low LLC misses

Results co-scheduling L with C applications → contention
88thth
SFHMMY ConferenceSFHMMY Conference
2929April 4, 2015April 4, 2015 2929National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Conclusion

Proposed contention-aware schedulers that

Does not require additional OS hardware adjustments

Simple, easily integratable as component in modern OS

Consisted of 3 parts

Compared to other state-of-the-art schedulers and the CFS

Presents the best throughput

Presents equal fairness to CFS
(and lower than the other contention-aware schedulers)

Can be integrated to real-life scheduling with 2 approaches:

Applications executed when inserted in queue for 2-3 quantums

Start scheduling and monitoring simultaneously (dynamic adaptation)
88thth
SFHMMY ConferenceSFHMMY Conference
3030April 4, 2015April 4, 2015 3030National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
Future Work
Major Improvements

Improvements in the prediction model

Stepwise regresion models to add more variables

Decrease error

Caution : limitation in number of monitored counters

Other methods, such as machine learning

Investigation of added overhead

Extension of approach to NUMA architectures

Implemented and tested for 1 package only

Extensible to multiple packages, using thread migrations
• Initially try to allocate threads of the same application in the
same package
• Thread migrations executed when class change is observed
along with memory migrations
88thth
SFHMMY ConferenceSFHMMY Conference
3131April 4, 2015April 4, 2015 3131National Technical University of AthensNational Technical University of Athens
School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering
THE END
Thank you !!!
Any Questions ??
88thth
SFHMMY ConferenceSFHMMY Conference

More Related Content

What's hot

Area, Delay and Power Comparison of Adder Topologies
Area, Delay and Power Comparison of Adder TopologiesArea, Delay and Power Comparison of Adder Topologies
Area, Delay and Power Comparison of Adder Topologies
VLSICS Design
 
CHI 2014 talk by Antti Oulasvirta: Automated Nonlinear Regression Modeling fo...
CHI 2014 talk by Antti Oulasvirta: Automated Nonlinear Regression Modeling fo...CHI 2014 talk by Antti Oulasvirta: Automated Nonlinear Regression Modeling fo...
CHI 2014 talk by Antti Oulasvirta: Automated Nonlinear Regression Modeling fo...
Aalto University
 
MATLAB and Simulink for Communications System Design (Design Conference 2013)
MATLAB and Simulink for Communications System Design (Design Conference 2013)MATLAB and Simulink for Communications System Design (Design Conference 2013)
MATLAB and Simulink for Communications System Design (Design Conference 2013)
Analog Devices, Inc.
 
A High-Level Programming Approach for using FPGAs in HPC using Functional Des...
A High-Level Programming Approach for using FPGAs in HPC using Functional Des...A High-Level Programming Approach for using FPGAs in HPC using Functional Des...
A High-Level Programming Approach for using FPGAs in HPC using Functional Des...
waqarnabi
 
Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue L...
Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue L...Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue L...
Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue L...
Weikun Wang
 
Why i need to learn so much math for my phd research
Why i need to learn so much math for my phd researchWhy i need to learn so much math for my phd research
Why i need to learn so much math for my phd research
Crypto Cg
 
Introducation of CPLDS and Design of Combinational circuit using CPLD
Introducation of CPLDS and Design of Combinational circuit using CPLDIntroducation of CPLDS and Design of Combinational circuit using CPLD
Introducation of CPLDS and Design of Combinational circuit using CPLD
HemantChaurasia8
 
A DISTRIBUTED ALGORITHM FOR THE DEAD-END PROBLEM IN WSNs
A DISTRIBUTED ALGORITHM FOR THE DEAD-END PROBLEM IN WSNsA DISTRIBUTED ALGORITHM FOR THE DEAD-END PROBLEM IN WSNs
A DISTRIBUTED ALGORITHM FOR THE DEAD-END PROBLEM IN WSNs
Priyanka Jacob
 
Chapter 3 instruction level parallelism and its exploitation
Chapter 3 instruction level parallelism and its exploitationChapter 3 instruction level parallelism and its exploitation
Chapter 3 instruction level parallelism and its exploitation
subramaniam shankar
 
MATLAB LTE Toolbox Projects Research Help
MATLAB LTE Toolbox Projects Research HelpMATLAB LTE Toolbox Projects Research Help
MATLAB LTE Toolbox Projects Research Help
Matlab Simulation
 
Abstractions and Directives for Adapting Wavefront Algorithms to Future Archi...
Abstractions and Directives for Adapting Wavefront Algorithms to Future Archi...Abstractions and Directives for Adapting Wavefront Algorithms to Future Archi...
Abstractions and Directives for Adapting Wavefront Algorithms to Future Archi...
inside-BigData.com
 
20120140506024
2012014050602420120140506024
20120140506024
IAEME Publication
 
Vehicular Ad-hoc network (VANET)
Vehicular Ad-hoc network (VANET)Vehicular Ad-hoc network (VANET)
Vehicular Ad-hoc network (VANET)
Limon Prince
 
The new integer factorization algorithm based on fermat’s factorization algor...
The new integer factorization algorithm based on fermat’s factorization algor...The new integer factorization algorithm based on fermat’s factorization algor...
The new integer factorization algorithm based on fermat’s factorization algor...
IJECEIAES
 
Hardware simulation for exponential blind equal throughput algorithm using sy...
Hardware simulation for exponential blind equal throughput algorithm using sy...Hardware simulation for exponential blind equal throughput algorithm using sy...
Hardware simulation for exponential blind equal throughput algorithm using sy...
IJECEIAES
 
Simulation of Wireless Communication Systems
Simulation of Wireless Communication SystemsSimulation of Wireless Communication Systems
Simulation of Wireless Communication Systems
Bernd-Peter Paris
 
Strel streaming
Strel streamingStrel streaming
Strel streaming
Vincenzo Gulisano
 
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...
Pooyan Jamshidi
 
IRJET- Artificial Algorithms Comparative Study
IRJET-  	  Artificial Algorithms Comparative StudyIRJET-  	  Artificial Algorithms Comparative Study
IRJET- Artificial Algorithms Comparative Study
IRJET Journal
 
Automated Piecewise-Linear Fitting of S-Parameters step-response (PWLFIT) for...
Automated Piecewise-Linear Fitting of S-Parameters step-response (PWLFIT) for...Automated Piecewise-Linear Fitting of S-Parameters step-response (PWLFIT) for...
Automated Piecewise-Linear Fitting of S-Parameters step-response (PWLFIT) for...
Piero Belforte
 

What's hot (20)

Area, Delay and Power Comparison of Adder Topologies
Area, Delay and Power Comparison of Adder TopologiesArea, Delay and Power Comparison of Adder Topologies
Area, Delay and Power Comparison of Adder Topologies
 
CHI 2014 talk by Antti Oulasvirta: Automated Nonlinear Regression Modeling fo...
CHI 2014 talk by Antti Oulasvirta: Automated Nonlinear Regression Modeling fo...CHI 2014 talk by Antti Oulasvirta: Automated Nonlinear Regression Modeling fo...
CHI 2014 talk by Antti Oulasvirta: Automated Nonlinear Regression Modeling fo...
 
MATLAB and Simulink for Communications System Design (Design Conference 2013)
MATLAB and Simulink for Communications System Design (Design Conference 2013)MATLAB and Simulink for Communications System Design (Design Conference 2013)
MATLAB and Simulink for Communications System Design (Design Conference 2013)
 
A High-Level Programming Approach for using FPGAs in HPC using Functional Des...
A High-Level Programming Approach for using FPGAs in HPC using Functional Des...A High-Level Programming Approach for using FPGAs in HPC using Functional Des...
A High-Level Programming Approach for using FPGAs in HPC using Functional Des...
 
Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue L...
Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue L...Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue L...
Maximum Likelihood Estimation of Closed Queueing Network Demands from Queue L...
 
Why i need to learn so much math for my phd research
Why i need to learn so much math for my phd researchWhy i need to learn so much math for my phd research
Why i need to learn so much math for my phd research
 
Introducation of CPLDS and Design of Combinational circuit using CPLD
Introducation of CPLDS and Design of Combinational circuit using CPLDIntroducation of CPLDS and Design of Combinational circuit using CPLD
Introducation of CPLDS and Design of Combinational circuit using CPLD
 
A DISTRIBUTED ALGORITHM FOR THE DEAD-END PROBLEM IN WSNs
A DISTRIBUTED ALGORITHM FOR THE DEAD-END PROBLEM IN WSNsA DISTRIBUTED ALGORITHM FOR THE DEAD-END PROBLEM IN WSNs
A DISTRIBUTED ALGORITHM FOR THE DEAD-END PROBLEM IN WSNs
 
Chapter 3 instruction level parallelism and its exploitation
Chapter 3 instruction level parallelism and its exploitationChapter 3 instruction level parallelism and its exploitation
Chapter 3 instruction level parallelism and its exploitation
 
MATLAB LTE Toolbox Projects Research Help
MATLAB LTE Toolbox Projects Research HelpMATLAB LTE Toolbox Projects Research Help
MATLAB LTE Toolbox Projects Research Help
 
Abstractions and Directives for Adapting Wavefront Algorithms to Future Archi...
Abstractions and Directives for Adapting Wavefront Algorithms to Future Archi...Abstractions and Directives for Adapting Wavefront Algorithms to Future Archi...
Abstractions and Directives for Adapting Wavefront Algorithms to Future Archi...
 
20120140506024
2012014050602420120140506024
20120140506024
 
Vehicular Ad-hoc network (VANET)
Vehicular Ad-hoc network (VANET)Vehicular Ad-hoc network (VANET)
Vehicular Ad-hoc network (VANET)
 
The new integer factorization algorithm based on fermat’s factorization algor...
The new integer factorization algorithm based on fermat’s factorization algor...The new integer factorization algorithm based on fermat’s factorization algor...
The new integer factorization algorithm based on fermat’s factorization algor...
 
Hardware simulation for exponential blind equal throughput algorithm using sy...
Hardware simulation for exponential blind equal throughput algorithm using sy...Hardware simulation for exponential blind equal throughput algorithm using sy...
Hardware simulation for exponential blind equal throughput algorithm using sy...
 
Simulation of Wireless Communication Systems
Simulation of Wireless Communication SystemsSimulation of Wireless Communication Systems
Simulation of Wireless Communication Systems
 
Strel streaming
Strel streamingStrel streaming
Strel streaming
 
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Aut...
 
IRJET- Artificial Algorithms Comparative Study
IRJET-  	  Artificial Algorithms Comparative StudyIRJET-  	  Artificial Algorithms Comparative Study
IRJET- Artificial Algorithms Comparative Study
 
Automated Piecewise-Linear Fitting of S-Parameters step-response (PWLFIT) for...
Automated Piecewise-Linear Fitting of S-Parameters step-response (PWLFIT) for...Automated Piecewise-Linear Fitting of S-Parameters step-response (PWLFIT) for...
Automated Piecewise-Linear Fitting of S-Parameters step-response (PWLFIT) for...
 

Viewers also liked

Speed Up Synchronization Locks: How and Why?
Speed Up Synchronization Locks: How and Why?Speed Up Synchronization Locks: How and Why?
Speed Up Synchronization Locks: How and Why?
psteinb
 
Get More Out of MongoDB with TokuMX
Get More Out of MongoDB with TokuMXGet More Out of MongoDB with TokuMX
Get More Out of MongoDB with TokuMX
Tim Callaghan
 
Lock free programming - pro tips devoxx uk
Lock free programming - pro tips devoxx ukLock free programming - pro tips devoxx uk
Lock free programming - pro tips devoxx uk
Jean-Philippe BEMPEL
 
Wait Events 10g
Wait Events 10gWait Events 10g
Wait Events 10g
sagai
 
Programmation lock free - les techniques des pros (2eme partie)
Programmation lock free - les techniques des pros (2eme partie)Programmation lock free - les techniques des pros (2eme partie)
Programmation lock free - les techniques des pros (2eme partie)
Jean-Philippe BEMPEL
 
Design of highway (Flexible pavement)
Design of highway (Flexible pavement)Design of highway (Flexible pavement)
Design of highway (Flexible pavement)
Raz Gupta
 
UKOUG, Oracle Transaction Locks
UKOUG, Oracle Transaction LocksUKOUG, Oracle Transaction Locks
UKOUG, Oracle Transaction Locks
Kyle Hailey
 
Aceleracion de aplicacione 2
Aceleracion de aplicacione 2Aceleracion de aplicacione 2
Aceleracion de aplicacione 2
jfth
 
Inference Path Flash 20 Letter
Inference Path Flash 20 LetterInference Path Flash 20 Letter
Inference Path Flash 20 Letter
jlaronge
 
" Design of Flexible Pavement "
" Design of Flexible Pavement "" Design of Flexible Pavement "
" Design of Flexible Pavement "
Nishant Pandey
 
Construction of flexible pavement in brief.
Construction of flexible pavement in brief.Construction of flexible pavement in brief.
Construction of flexible pavement in brief.
AJINKYA THAKRE
 
Runway orientation
Runway orientationRunway orientation
Runway orientation
rehan5c
 
Airpot design
Airpot designAirpot design
Airpot design
pradip dangar
 
10-Runway Design ( Highway and Airport Engineering Dr. Sherif El-Badawy )
10-Runway Design ( Highway and Airport Engineering Dr. Sherif El-Badawy )10-Runway Design ( Highway and Airport Engineering Dr. Sherif El-Badawy )
10-Runway Design ( Highway and Airport Engineering Dr. Sherif El-Badawy )
Hossam Shafiq I
 
Runways
RunwaysRunways
Runways
Akash Waghani
 
Construction of flexible pavement
Construction of flexible pavementConstruction of flexible pavement
Construction of flexible pavement
UTU Dehradun
 
Design Of Flexible Pavements
Design Of Flexible PavementsDesign Of Flexible Pavements
Design Of Flexible Pavements
whutton1
 
Pavements PPT
 Pavements PPT  Pavements PPT
Pavements PPT
Amol Pawar
 
Flexible and-rigid-pavements
Flexible and-rigid-pavementsFlexible and-rigid-pavements
Flexible and-rigid-pavements
HARITSEHRAWAT
 

Viewers also liked (19)

Speed Up Synchronization Locks: How and Why?
Speed Up Synchronization Locks: How and Why?Speed Up Synchronization Locks: How and Why?
Speed Up Synchronization Locks: How and Why?
 
Get More Out of MongoDB with TokuMX
Get More Out of MongoDB with TokuMXGet More Out of MongoDB with TokuMX
Get More Out of MongoDB with TokuMX
 
Lock free programming - pro tips devoxx uk
Lock free programming - pro tips devoxx ukLock free programming - pro tips devoxx uk
Lock free programming - pro tips devoxx uk
 
Wait Events 10g
Wait Events 10gWait Events 10g
Wait Events 10g
 
Programmation lock free - les techniques des pros (2eme partie)
Programmation lock free - les techniques des pros (2eme partie)Programmation lock free - les techniques des pros (2eme partie)
Programmation lock free - les techniques des pros (2eme partie)
 
Design of highway (Flexible pavement)
Design of highway (Flexible pavement)Design of highway (Flexible pavement)
Design of highway (Flexible pavement)
 
UKOUG, Oracle Transaction Locks
UKOUG, Oracle Transaction LocksUKOUG, Oracle Transaction Locks
UKOUG, Oracle Transaction Locks
 
Aceleracion de aplicacione 2
Aceleracion de aplicacione 2Aceleracion de aplicacione 2
Aceleracion de aplicacione 2
 
Inference Path Flash 20 Letter
Inference Path Flash 20 LetterInference Path Flash 20 Letter
Inference Path Flash 20 Letter
 
" Design of Flexible Pavement "
" Design of Flexible Pavement "" Design of Flexible Pavement "
" Design of Flexible Pavement "
 
Construction of flexible pavement in brief.
Construction of flexible pavement in brief.Construction of flexible pavement in brief.
Construction of flexible pavement in brief.
 
Runway orientation
Runway orientationRunway orientation
Runway orientation
 
Airpot design
Airpot designAirpot design
Airpot design
 
10-Runway Design ( Highway and Airport Engineering Dr. Sherif El-Badawy )
10-Runway Design ( Highway and Airport Engineering Dr. Sherif El-Badawy )10-Runway Design ( Highway and Airport Engineering Dr. Sherif El-Badawy )
10-Runway Design ( Highway and Airport Engineering Dr. Sherif El-Badawy )
 
Runways
RunwaysRunways
Runways
 
Construction of flexible pavement
Construction of flexible pavementConstruction of flexible pavement
Construction of flexible pavement
 
Design Of Flexible Pavements
Design Of Flexible PavementsDesign Of Flexible Pavements
Design Of Flexible Pavements
 
Pavements PPT
 Pavements PPT  Pavements PPT
Pavements PPT
 
Flexible and-rigid-pavements
Flexible and-rigid-pavementsFlexible and-rigid-pavements
Flexible and-rigid-pavements
 

Similar to Contention - Aware Scheduling (a different approach)

Cost-effective software reliability through autonomic tuning of system resources
Cost-effective software reliability through autonomic tuning of system resourcesCost-effective software reliability through autonomic tuning of system resources
Cost-effective software reliability through autonomic tuning of system resources
Vincenzo De Florio
 
EENC: Energy Efficient Nested Clustering in Underwater Acoustic Sensor Network
EENC: Energy Efficient Nested Clustering in Underwater Acoustic Sensor NetworkEENC: Energy Efficient Nested Clustering in Underwater Acoustic Sensor Network
EENC: Energy Efficient Nested Clustering in Underwater Acoustic Sensor Network
Syed Hassan Ahmed
 
Gene's law
Gene's lawGene's law
Gene's law
Hoopeer Hoopeer
 
Topic2-Network_FlexRayCommBus_20111013.ppt
Topic2-Network_FlexRayCommBus_20111013.pptTopic2-Network_FlexRayCommBus_20111013.ppt
Topic2-Network_FlexRayCommBus_20111013.ppt
jacu123
 
OPAL-RT RT14 Conference: State-Space Nodal
OPAL-RT RT14 Conference: State-Space NodalOPAL-RT RT14 Conference: State-Space Nodal
OPAL-RT RT14 Conference: State-Space Nodal
OPAL-RT TECHNOLOGIES
 
IRJET - Fault Detection and Classification in Transmission Line by using KNN ...
IRJET - Fault Detection and Classification in Transmission Line by using KNN ...IRJET - Fault Detection and Classification in Transmission Line by using KNN ...
IRJET - Fault Detection and Classification in Transmission Line by using KNN ...
IRJET Journal
 
xiangyuzhang
xiangyuzhangxiangyuzhang
xiangyuzhang
xiangyu zhang
 
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
CloudLightning
 
ScilabTEC 2015 - KIT
ScilabTEC 2015 - KITScilabTEC 2015 - KIT
ScilabTEC 2015 - KIT
Scilab
 
Towards processing and reasoning streams of events in knowledge driven manufa...
Towards processing and reasoning streams of events in knowledge driven manufa...Towards processing and reasoning streams of events in knowledge driven manufa...
Towards processing and reasoning streams of events in knowledge driven manufa...
FAST-Lab. Factory Automation Systems and Technologies Laboratory, Tampere University of Technology
 
PERFORMANCE VEHICULAR AD-HOC NETWORK (VANET)
PERFORMANCE VEHICULAR AD-HOC NETWORK (VANET) PERFORMANCE VEHICULAR AD-HOC NETWORK (VANET)
PERFORMANCE VEHICULAR AD-HOC NETWORK (VANET)
Limon Prince
 
Reliability analysis of wireless automotive applications with transceiver red...
Reliability analysis of wireless automotive applications with transceiver red...Reliability analysis of wireless automotive applications with transceiver red...
Reliability analysis of wireless automotive applications with transceiver red...
rchulyada
 
cis97003
cis97003cis97003
cis97003
perfj
 
Evolutionary Algorithms and Self-Organised Systems
Evolutionary Algorithms and Self-Organised SystemsEvolutionary Algorithms and Self-Organised Systems
Evolutionary Algorithms and Self-Organised Systems
Natalio Krasnogor
 
Short Term Electrical Load Forecasting by Artificial Neural Network
Short Term Electrical Load Forecasting by Artificial Neural NetworkShort Term Electrical Load Forecasting by Artificial Neural Network
Short Term Electrical Load Forecasting by Artificial Neural Network
IJERA Editor
 
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P..."Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
Edge AI and Vision Alliance
 
power electronics manual
power electronics manualpower electronics manual
power electronics manual
m.pal pandian
 
Hardback solution to accelerate multimedia computation through mgp in cmp
Hardback solution to accelerate multimedia computation through mgp in cmpHardback solution to accelerate multimedia computation through mgp in cmp
Hardback solution to accelerate multimedia computation through mgp in cmp
eSAT Publishing House
 
Naidu_Sumit_Resume
Naidu_Sumit_ResumeNaidu_Sumit_Resume
Naidu_Sumit_Resume
S R Naidu
 
Performance prediction of PV & PV/T systems using Artificial Neural Networks ...
Performance prediction of PV & PV/T systems using Artificial Neural Networks ...Performance prediction of PV & PV/T systems using Artificial Neural Networks ...
Performance prediction of PV & PV/T systems using Artificial Neural Networks ...
Ali Al-Waeli
 

Similar to Contention - Aware Scheduling (a different approach) (20)

Cost-effective software reliability through autonomic tuning of system resources
Cost-effective software reliability through autonomic tuning of system resourcesCost-effective software reliability through autonomic tuning of system resources
Cost-effective software reliability through autonomic tuning of system resources
 
EENC: Energy Efficient Nested Clustering in Underwater Acoustic Sensor Network
EENC: Energy Efficient Nested Clustering in Underwater Acoustic Sensor NetworkEENC: Energy Efficient Nested Clustering in Underwater Acoustic Sensor Network
EENC: Energy Efficient Nested Clustering in Underwater Acoustic Sensor Network
 
Gene's law
Gene's lawGene's law
Gene's law
 
Topic2-Network_FlexRayCommBus_20111013.ppt
Topic2-Network_FlexRayCommBus_20111013.pptTopic2-Network_FlexRayCommBus_20111013.ppt
Topic2-Network_FlexRayCommBus_20111013.ppt
 
OPAL-RT RT14 Conference: State-Space Nodal
OPAL-RT RT14 Conference: State-Space NodalOPAL-RT RT14 Conference: State-Space Nodal
OPAL-RT RT14 Conference: State-Space Nodal
 
IRJET - Fault Detection and Classification in Transmission Line by using KNN ...
IRJET - Fault Detection and Classification in Transmission Line by using KNN ...IRJET - Fault Detection and Classification in Transmission Line by using KNN ...
IRJET - Fault Detection and Classification in Transmission Line by using KNN ...
 
xiangyuzhang
xiangyuzhangxiangyuzhang
xiangyuzhang
 
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
 
ScilabTEC 2015 - KIT
ScilabTEC 2015 - KITScilabTEC 2015 - KIT
ScilabTEC 2015 - KIT
 
Towards processing and reasoning streams of events in knowledge driven manufa...
Towards processing and reasoning streams of events in knowledge driven manufa...Towards processing and reasoning streams of events in knowledge driven manufa...
Towards processing and reasoning streams of events in knowledge driven manufa...
 
PERFORMANCE VEHICULAR AD-HOC NETWORK (VANET)
PERFORMANCE VEHICULAR AD-HOC NETWORK (VANET) PERFORMANCE VEHICULAR AD-HOC NETWORK (VANET)
PERFORMANCE VEHICULAR AD-HOC NETWORK (VANET)
 
Reliability analysis of wireless automotive applications with transceiver red...
Reliability analysis of wireless automotive applications with transceiver red...Reliability analysis of wireless automotive applications with transceiver red...
Reliability analysis of wireless automotive applications with transceiver red...
 
cis97003
cis97003cis97003
cis97003
 
Evolutionary Algorithms and Self-Organised Systems
Evolutionary Algorithms and Self-Organised SystemsEvolutionary Algorithms and Self-Organised Systems
Evolutionary Algorithms and Self-Organised Systems
 
Short Term Electrical Load Forecasting by Artificial Neural Network
Short Term Electrical Load Forecasting by Artificial Neural NetworkShort Term Electrical Load Forecasting by Artificial Neural Network
Short Term Electrical Load Forecasting by Artificial Neural Network
 
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P..."Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
"Approaches for Energy Efficient Implementation of Deep Neural Networks," a P...
 
power electronics manual
power electronics manualpower electronics manual
power electronics manual
 
Hardback solution to accelerate multimedia computation through mgp in cmp
Hardback solution to accelerate multimedia computation through mgp in cmpHardback solution to accelerate multimedia computation through mgp in cmp
Hardback solution to accelerate multimedia computation through mgp in cmp
 
Naidu_Sumit_Resume
Naidu_Sumit_ResumeNaidu_Sumit_Resume
Naidu_Sumit_Resume
 
Performance prediction of PV & PV/T systems using Artificial Neural Networks ...
Performance prediction of PV & PV/T systems using Artificial Neural Networks ...Performance prediction of PV & PV/T systems using Artificial Neural Networks ...
Performance prediction of PV & PV/T systems using Artificial Neural Networks ...
 

Recently uploaded

Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Need for Speed: Removing speed bumps from your Symfony projects ⚡️Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Łukasz Chruściel
 
SMS API Integration in Saudi Arabia| Best SMS API Service
SMS API Integration in Saudi Arabia| Best SMS API ServiceSMS API Integration in Saudi Arabia| Best SMS API Service
SMS API Integration in Saudi Arabia| Best SMS API Service
Yara Milbes
 
Artificia Intellicence and XPath Extension Functions
Artificia Intellicence and XPath Extension FunctionsArtificia Intellicence and XPath Extension Functions
Artificia Intellicence and XPath Extension Functions
Octavian Nadolu
 
How to write a program in any programming language
How to write a program in any programming languageHow to write a program in any programming language
How to write a program in any programming language
Rakesh Kumar R
 
Oracle 23c New Features For DBAs and Developers.pptx
Oracle 23c New Features For DBAs and Developers.pptxOracle 23c New Features For DBAs and Developers.pptx
Oracle 23c New Features For DBAs and Developers.pptx
Remote DBA Services
 
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit ParisNeo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j
 
原版定制美国纽约州立大学奥尔巴尼分校毕业证学位证书原版一模一样
原版定制美国纽约州立大学奥尔巴尼分校毕业证学位证书原版一模一样原版定制美国纽约州立大学奥尔巴尼分校毕业证学位证书原版一模一样
原版定制美国纽约州立大学奥尔巴尼分校毕业证学位证书原版一模一样
mz5nrf0n
 
Oracle Database 19c New Features for DBAs and Developers.pptx
Oracle Database 19c New Features for DBAs and Developers.pptxOracle Database 19c New Features for DBAs and Developers.pptx
Oracle Database 19c New Features for DBAs and Developers.pptx
Remote DBA Services
 
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdf
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdfAutomated software refactoring with OpenRewrite and Generative AI.pptx.pdf
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdf
timtebeek1
 
Using Xen Hypervisor for Functional Safety
Using Xen Hypervisor for Functional SafetyUsing Xen Hypervisor for Functional Safety
Using Xen Hypervisor for Functional Safety
Ayan Halder
 
What is Master Data Management by PiLog Group
What is Master Data Management by PiLog GroupWhat is Master Data Management by PiLog Group
What is Master Data Management by PiLog Group
aymanquadri279
 
UI5con 2024 - Keynote: Latest News about UI5 and it’s Ecosystem
UI5con 2024 - Keynote: Latest News about UI5 and it’s EcosystemUI5con 2024 - Keynote: Latest News about UI5 and it’s Ecosystem
UI5con 2024 - Keynote: Latest News about UI5 and it’s Ecosystem
Peter Muessig
 
E-Invoicing Implementation: A Step-by-Step Guide for Saudi Arabian Companies
E-Invoicing Implementation: A Step-by-Step Guide for Saudi Arabian CompaniesE-Invoicing Implementation: A Step-by-Step Guide for Saudi Arabian Companies
E-Invoicing Implementation: A Step-by-Step Guide for Saudi Arabian Companies
Quickdice ERP
 
8 Best Automated Android App Testing Tool and Framework in 2024.pdf
8 Best Automated Android App Testing Tool and Framework in 2024.pdf8 Best Automated Android App Testing Tool and Framework in 2024.pdf
8 Best Automated Android App Testing Tool and Framework in 2024.pdf
kalichargn70th171
 
Atelier - Innover avec l’IA Générative et les graphes de connaissances
Atelier - Innover avec l’IA Générative et les graphes de connaissancesAtelier - Innover avec l’IA Générative et les graphes de connaissances
Atelier - Innover avec l’IA Générative et les graphes de connaissances
Neo4j
 
E-commerce Application Development Company.pdf
E-commerce Application Development Company.pdfE-commerce Application Development Company.pdf
E-commerce Application Development Company.pdf
Hornet Dynamics
 
openEuler Case Study - The Journey to Supply Chain Security
openEuler Case Study - The Journey to Supply Chain SecurityopenEuler Case Study - The Journey to Supply Chain Security
openEuler Case Study - The Journey to Supply Chain Security
Shane Coughlan
 
Webinar On-Demand: Using Flutter for Embedded
Webinar On-Demand: Using Flutter for EmbeddedWebinar On-Demand: Using Flutter for Embedded
Webinar On-Demand: Using Flutter for Embedded
ICS
 
Microservice Teams - How the cloud changes the way we work
Microservice Teams - How the cloud changes the way we workMicroservice Teams - How the cloud changes the way we work
Microservice Teams - How the cloud changes the way we work
Sven Peters
 
SWEBOK and Education at FUSE Okinawa 2024
SWEBOK and Education at FUSE Okinawa 2024SWEBOK and Education at FUSE Okinawa 2024
SWEBOK and Education at FUSE Okinawa 2024
Hironori Washizaki
 

Recently uploaded (20)

Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Need for Speed: Removing speed bumps from your Symfony projects ⚡️Need for Speed: Removing speed bumps from your Symfony projects ⚡️
Need for Speed: Removing speed bumps from your Symfony projects ⚡️
 
SMS API Integration in Saudi Arabia| Best SMS API Service
SMS API Integration in Saudi Arabia| Best SMS API ServiceSMS API Integration in Saudi Arabia| Best SMS API Service
SMS API Integration in Saudi Arabia| Best SMS API Service
 
Artificia Intellicence and XPath Extension Functions
Artificia Intellicence and XPath Extension FunctionsArtificia Intellicence and XPath Extension Functions
Artificia Intellicence and XPath Extension Functions
 
How to write a program in any programming language
How to write a program in any programming languageHow to write a program in any programming language
How to write a program in any programming language
 
Oracle 23c New Features For DBAs and Developers.pptx
Oracle 23c New Features For DBAs and Developers.pptxOracle 23c New Features For DBAs and Developers.pptx
Oracle 23c New Features For DBAs and Developers.pptx
 
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit ParisNeo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
Neo4j - Product Vision and Knowledge Graphs - GraphSummit Paris
 
原版定制美国纽约州立大学奥尔巴尼分校毕业证学位证书原版一模一样
原版定制美国纽约州立大学奥尔巴尼分校毕业证学位证书原版一模一样原版定制美国纽约州立大学奥尔巴尼分校毕业证学位证书原版一模一样
原版定制美国纽约州立大学奥尔巴尼分校毕业证学位证书原版一模一样
 
Oracle Database 19c New Features for DBAs and Developers.pptx
Oracle Database 19c New Features for DBAs and Developers.pptxOracle Database 19c New Features for DBAs and Developers.pptx
Oracle Database 19c New Features for DBAs and Developers.pptx
 
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdf
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdfAutomated software refactoring with OpenRewrite and Generative AI.pptx.pdf
Automated software refactoring with OpenRewrite and Generative AI.pptx.pdf
 
Using Xen Hypervisor for Functional Safety
Using Xen Hypervisor for Functional SafetyUsing Xen Hypervisor for Functional Safety
Using Xen Hypervisor for Functional Safety
 
What is Master Data Management by PiLog Group
What is Master Data Management by PiLog GroupWhat is Master Data Management by PiLog Group
What is Master Data Management by PiLog Group
 
UI5con 2024 - Keynote: Latest News about UI5 and it’s Ecosystem
UI5con 2024 - Keynote: Latest News about UI5 and it’s EcosystemUI5con 2024 - Keynote: Latest News about UI5 and it’s Ecosystem
UI5con 2024 - Keynote: Latest News about UI5 and it’s Ecosystem
 
E-Invoicing Implementation: A Step-by-Step Guide for Saudi Arabian Companies
E-Invoicing Implementation: A Step-by-Step Guide for Saudi Arabian CompaniesE-Invoicing Implementation: A Step-by-Step Guide for Saudi Arabian Companies
E-Invoicing Implementation: A Step-by-Step Guide for Saudi Arabian Companies
 
8 Best Automated Android App Testing Tool and Framework in 2024.pdf
8 Best Automated Android App Testing Tool and Framework in 2024.pdf8 Best Automated Android App Testing Tool and Framework in 2024.pdf
8 Best Automated Android App Testing Tool and Framework in 2024.pdf
 
Atelier - Innover avec l’IA Générative et les graphes de connaissances
Atelier - Innover avec l’IA Générative et les graphes de connaissancesAtelier - Innover avec l’IA Générative et les graphes de connaissances
Atelier - Innover avec l’IA Générative et les graphes de connaissances
 
E-commerce Application Development Company.pdf
E-commerce Application Development Company.pdfE-commerce Application Development Company.pdf
E-commerce Application Development Company.pdf
 
openEuler Case Study - The Journey to Supply Chain Security
openEuler Case Study - The Journey to Supply Chain SecurityopenEuler Case Study - The Journey to Supply Chain Security
openEuler Case Study - The Journey to Supply Chain Security
 
Webinar On-Demand: Using Flutter for Embedded
Webinar On-Demand: Using Flutter for EmbeddedWebinar On-Demand: Using Flutter for Embedded
Webinar On-Demand: Using Flutter for Embedded
 
Microservice Teams - How the cloud changes the way we work
Microservice Teams - How the cloud changes the way we workMicroservice Teams - How the cloud changes the way we work
Microservice Teams - How the cloud changes the way we work
 
SWEBOK and Education at FUSE Okinawa 2024
SWEBOK and Education at FUSE Okinawa 2024SWEBOK and Education at FUSE Okinawa 2024
SWEBOK and Education at FUSE Okinawa 2024
 

Contention - Aware Scheduling (a different approach)

  • 1. 11 LCN : Design and Implementation of a Contention-LCN : Design and Implementation of a Contention- Aware SchedulerAware Scheduler Raptis Dimos – DimitriosRaptis Dimos – Dimitrios 88thth SFHMMY Conference 2015SFHMMY Conference 2015 April 4, 2015April 4, 2015 April 4, 2015April 4, 2015 11National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering88thth SFHMMY ConferenceSFHMMY Conference
  • 2. 22April 4, 2015April 4, 2015 22National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Outline  Motivation  Background  Similar Research  Scheduler Overview  Classification Scheme  Prediction Model  Scheduling Algorithm  Comparison with Similar Research  Conclusion  Future Work 88thth SFHMMY ConferenceSFHMMY Conference
  • 3. 33April 4, 2015April 4, 2015 33National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Motivation Memory Wall Protocols SMPs & CMPs Multithreaded Cache Coherency Programming Parallel Processing 88thth SFHMMY ConferenceSFHMMY Conference
  • 4. 44April 4, 2015April 4, 2015 44National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Motivation Cache Coherence Problems  Legacy PC applications (not benefiting)  Applications benefiting from multithreaded environments  “Embarassingly parallel” applications (GPU etc.) Leveraging Parallelism 88thth SFHMMY ConferenceSFHMMY Conference
  • 5. 55April 4, 2015April 4, 2015 55National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Motivation Problems Approaches  Memory Contention Problem  Cache Coherence Problem  Missing existing infrastructure to detect and restrict system resources contention  What if it was not programmer's responsibility to “allocate” resources ?  What if Operating System was responsible for judging applications' parallelism ? Contention – Aware Scheduling 88thth SFHMMY ConferenceSFHMMY Conference
  • 6. 66April 4, 2015April 4, 2015 66National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Contention – Aware Scheduling Classification (based on locality and degree of contention) Background Scheduling Algorithm HPC Monitoring ++ Our approach contains an additional component : a prediction model 88thth SFHMMY ConferenceSFHMMY Conference
  • 7. 77April 4, 2015April 4, 2015 77National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Similar Research Various Approaches  Simple Heuristic approaches (LLC misses & Memory bandwidth)  Stack Distance Profiling approaches  Dynamic Scheduling approaches using supervised learning (linear regression, fuzzy-rule models, K-nearest neighbour) Differences  Simple Heuristic approaches (LLC misses & Memory bandwidth)  Stack Distance Profiling approaches  Dynamic Scheduling approaches using supervised learning (linear regression, fuzzy-rule models, K-nearest neighbour) Not covering the whole memory hierarchy Using additional hardware not available currently in OS Targeting the same problem from a different view Pre-defined allocated resources in applications 88thth SFHMMY ConferenceSFHMMY Conference
  • 8. 88April 4, 2015April 4, 2015 88National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Scheduler Overview Scheduler Main Components  Classification Scheme 4 categories of applications based on memory hierarchy  Prediction Model prediction of contention in varying resources allocations  Scheduling Algorithm scheduling a workload of applications based on  classification scheme (co-scheduling combinations)  prediction model (for ideal resource management) 88thth SFHMMY ConferenceSFHMMY Conference
  • 9. 99April 4, 2015April 4, 2015 99National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Classification Scheme 4 main categories of applications L LC C N 88thth SFHMMY ConferenceSFHMMY Conference
  • 10. 1010April 4, 2015April 4, 2015 1010National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Classification Scheme Co-scheduling interference  N - * : no interference  L - L : contention on same resource, bandwidth “divided”  L - C : contention in different resources  severe performance degradation in C  no impact in L  L - LC : performance degradation for both  LC faces bigger degradation than L  LC - LC : contention in 2 resources (memory link and LLC)  Both have degradation but in low levels  LC - C : mediocre contention, mainly in C  C - C : most difficult to predict - based on data access patterns (MESI protocol) 88thth SFHMMY ConferenceSFHMMY Conference
  • 11. 1111April 4, 2015April 4, 2015 1111National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Classification Scheme Co-scheduling interference Analysis from workload of 16 applications 4 applications belonging to each class Co-scheduling of all possible combinations Average slowdown calculated for each combinationTable : Average slowdown in co-execution 88thth SFHMMY ConferenceSFHMMY Conference
  • 12. 1212April 4, 2015April 4, 2015 1212National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Classification Scheme Classification tree 88thth SFHMMY ConferenceSFHMMY Conference
  • 13. 1313April 4, 2015April 4, 2015 1313National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Prediction Model  Linear Regression Model  Target : Prediction of scaling  possess HPC monitored for 1 core allocation  capability to predict scaling for any possible allocation  use of threshold value for defining optimal scaling  Use the suitable counters for each class  Class L : memory link (bandwidth)  Class LC : LLC reuse (MESI protocol)  Class C : L2 and LLC reuse (MESI protocol)  Class N : private part of memory hierarchy 88thth SFHMMY ConferenceSFHMMY Conference
  • 14. 1414April 4, 2015April 4, 2015 1414National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Prediction Model L class Rp = (Mem1 p)/(Maximum Memory Bandwidth)∗ poptimum = max{p}, Rp < 1.15 LC class Completion(LC) = 0.01799 ∗ fLC + 0.50119 (p = 2cores) = 0.02516 ∗ fLC + 0.34286 (p = 3 cores) = 0.02846 ∗ fLC + 0.26028 (p = 4 cores) = 0.03199 ∗ fLC + 0.21584 (p = 5 cores) = 0.03404 ∗ fLC + 0.18296 (p = 6 cores) = 0.03621 ∗ fLC + 0.16410 (p = 7 cores) = 0.03751 ∗ fLC + 0.13969 (p = 8 cores) Ideal_Completionp = 1/p , fLC = L2 RFO Requests/(L3 reuse*105 ) Rp = (Ideal_Completionp /Completionp ) 100∗ poptimum = max{p}, Rp > 70 88thth SFHMMY ConferenceSFHMMY Conference
  • 15. 1515April 4, 2015April 4, 2015 1515National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Prediction Model C class Completion(C) = 0.3447 ∗ fC + 0.4947 (2cores) = 0.46974 ∗ fC + 0.34415 (p = 3 cores) = 0.5155 ∗ fC + 0.2478 (p = 4 cores) = 0.63609 ∗ fC + 0.22492 (p = 5 cores) = 0.61403 ∗ fC + 0.18127 (p = 6 cores) = 0.65915 ∗ fC + 0.15864 (p = 7 cores) = 0.6095 ∗ fC + 0.1263 (p = 8 cores) Ideal_Completionp = 1/p , fC = (L2 Shared*104 )/Inst.Retired Rp = (Ideal_Completionp /Completionp ) 100∗ poptimum = max{p}, Rp > 70 N class Completion(N)p = Completion_idealp poptimum = max{p} 88thth SFHMMY ConferenceSFHMMY Conference
  • 16. April 4, 2015April 4, 2015 National Technical University of AthensNational Technical University of Athens 1616 School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Prediction Model Example L class LC class Mem1 = 4GB/sec Memmax = 13.5 GB/sec R1 = 4/13.5 = 0.29 R2 = (4*2)/13.5 = 0.59 R3 = (4*3)/13.5 = 0.88 R4 = (4*4)/13.5 = 1.185 R5 = (4*5)/13.5 = 1.48 R6 = (4*6)/13.5 = 1.77 R7 = (4*7)/13.5 = 2.07 R8 = (4*8)/13.5 = 2.37 poptimum = 3 cores RFO1 = 319106 per second , L3 reuse = 1.51 fLC = 319106/(1.51*105 ) = 2.10 Completion(LC)2 = 0.01799*2.10 + 0.50119 = 0.53 → R2 =0.5/0.53*100= 92.792.7 Completion(LC)3 = 0.02516*2.10 + 0.34286 = 0.39 → R3 =0.33/0.39*100= 84.284.2 Completion(LC)4 = 0.02846*2.10 + 0.26028 = 0.32 → R4 =0.25/0.32*100= 78.078.0 Completion(LC)5 = 0.03199*2.10 + 0.21584 = 0.28 → R5 =0.2/0.28*100= 70.670.6 Completion(LC)6 = 0.03404*2.10 + 0.18296 =0.25 → R6 =0.166/0.25*100= 65.465.4 Completion(LC)7 = 0.03621*2.10 + 0.16410 = 0.24 → R7 =0.142/0.24*100= 59.059.0 Completion(LC)8 = 0.03751*2.10 + 0.13969 = 0.21 → R8 =0.125/0.21*100= 57.157.1 Poptimum = 5 cores 88thth SFHMMY ConferenceSFHMMY Conference
  • 17. 1717April 4, 2015April 4, 2015 1717National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Prediction Model Evaluation – Verification Relative Errors in Predictions of C class 88thth SFHMMY ConferenceSFHMMY Conference
  • 18. 1818April 4, 2015April 4, 2015 1818National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Prediction Model Evaluation – Verification Relative Errors in Predictions of LC class 88thth SFHMMY ConferenceSFHMMY Conference
  • 19. 1919April 4, 2015April 4, 2015 1919National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Prediction Model LC - C prediction model improvement  Integration of 7 relationships to a single one  Coefficients follow logarithmic trendline  Results after analysis Completion(LC)p = [0.0139536 log(p) + 0.0090562] f∗ ∗ LC + [−0.252533 log(p) + 0.6407058]∗ Completion(C)p = [0.2151318 log(p) + 0.2239032] f∗ ∗ C + [−0.25468 log(p) + 0.6397947]∗ Ideal_Completionp = 1/p Rp = (Ideal_Completionp /Completionp ) 100∗ poptimum = max{p}, Rp > 70 88thth SFHMMY ConferenceSFHMMY Conference
  • 20. 2020April 4, 2015April 4, 2015 2020National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Prediction Model Evaluation – Verification of Refinement Deviation in C coefficients Deviation in LC coefficients 88thth SFHMMY ConferenceSFHMMY Conference
  • 21. Prediction Model School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering April 4, 2015April 4, 2015 National Technical University of AthensNational Technical University of Athens 2121 Experimentation Platform  cores : 8  L1D,I: 32KB 8-way  L2 : 256KB 8-way  L3 : 16 MB 16-way  64bytes line  Mem :64GB DDR3 1.3GHZ  Debian 6.06 *(Prediction Model also tested on Nehalem architecture) 88thth SFHMMY ConferenceSFHMMY Conference
  • 22. 2222April 4, 2015April 4, 2015 2222National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Scheduling Algorithm  Executed after first 2 steps are finished for each application  Step 1 has classified each application  Step 2 has predicted the optimum number of cores that should be allocated by the scheduler to each application  The algorithm tries to co-schedule the applications in pairs so that  Sum of cores does not exceed package cores  Contention is avoided as much as possible (using conclusions from Classification step)  The approach can be extended for co-execution of more than 2 applications  N applications are allocated half cores and scheduled twice (their profile implies that they are not affected by this) 88thth SFHMMY ConferenceSFHMMY Conference
  • 23. 2323April 4, 2015April 4, 2015 2323National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Scheduling Algorithm Lists of applications separated by class : L, LC, C, N while(N not empty){ x = current N application ; y = popMatchFromTheEnd(C, L, LC, N); coschedule(x, y); } while( LC not empty){ x = current LC application; y = popMatchFromTheEnd(C, LC, L); coschedule(x, y); } while(L not empty){ x = current L application; y = popMatchFromTheEnd(L); coschedule(x, y); } while(C not empty){ x = current C application; y = popMatchFromTheEnd(C); coschedule(x, y); } scheduleRemainingApplications(); 88thth SFHMMY ConferenceSFHMMY Conference
  • 24. 2424April 4, 2015April 4, 2015 2424National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Comparison with Similar Research The other state-of-the-art schedulers  Sorting by heuristic  Distributing load  Combining application from the top with application from the bottom  LLC – MRB LLC misses  LBB memory bandwidth 88thth SFHMMY ConferenceSFHMMY Conference
  • 25. 2525April 4, 2015April 4, 2015 2525National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Comparison with Similar Research Experiments – Comparison Process  Linux CFS, LCN, LLC-MRB, LLB to be compared  Workload of 17 applications (equally shared among classes)  Whole workload executed for 1 hour  Time quantums of 1 second defined in all schedulers  When application finishes, it gets respawn to re-execute  Comparison between schedulers with 2 criteria  Throughput  Total number of executions of all applications  Number of improved applications  Fairness  Standard Deviation between gain of each application *gain compared to Gang scheduler 88thth SFHMMY ConferenceSFHMMY Conference
  • 26. 2626April 4, 2015April 4, 2015 2626National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Comparison with Similar Research Most Improved Applications Linux : 5 LLC – Balance : 7 MEM-Balance : 5 LCN : 8 88thth SFHMMY ConferenceSFHMMY Conference
  • 27. 2727April 4, 2015April 4, 2015 2727National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Comparison with Similar Research Criteria : - Throughput LCNLCN - Fairness LLC-BalanceLLC-Balance ** * fairness can be* fairness can be misinterpretedmisinterpreted 88thth SFHMMY ConferenceSFHMMY Conference
  • 28. 2828April 4, 2015April 4, 2015 2828National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Comparison with Similar Research Major Drawbacks of other schedulers  Linux Scheduler CFS  Cannot locate contention  Does not identify threads of the same application parallelism benefits lost  MEM - Balance Scheduler  Uses over-generic heuristic  Does not take into account all memory hierarchy parts  LLC - Balance Scheduler  Cannot differentiate between class N and C applications, since they both exhibit low LLC misses  Results co-scheduling L with C applications → contention 88thth SFHMMY ConferenceSFHMMY Conference
  • 29. 2929April 4, 2015April 4, 2015 2929National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Conclusion  Proposed contention-aware schedulers that  Does not require additional OS hardware adjustments  Simple, easily integratable as component in modern OS  Consisted of 3 parts  Compared to other state-of-the-art schedulers and the CFS  Presents the best throughput  Presents equal fairness to CFS (and lower than the other contention-aware schedulers)  Can be integrated to real-life scheduling with 2 approaches:  Applications executed when inserted in queue for 2-3 quantums  Start scheduling and monitoring simultaneously (dynamic adaptation) 88thth SFHMMY ConferenceSFHMMY Conference
  • 30. 3030April 4, 2015April 4, 2015 3030National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering Future Work Major Improvements  Improvements in the prediction model  Stepwise regresion models to add more variables  Decrease error  Caution : limitation in number of monitored counters  Other methods, such as machine learning  Investigation of added overhead  Extension of approach to NUMA architectures  Implemented and tested for 1 package only  Extensible to multiple packages, using thread migrations • Initially try to allocate threads of the same application in the same package • Thread migrations executed when class change is observed along with memory migrations 88thth SFHMMY ConferenceSFHMMY Conference
  • 31. 3131April 4, 2015April 4, 2015 3131National Technical University of AthensNational Technical University of Athens School of Electrical and Computer EngineeringSchool of Electrical and Computer Engineering THE END Thank you !!! Any Questions ?? 88thth SFHMMY ConferenceSFHMMY Conference