ComNet-IoT 2016 international workshop

Our work about run-time optimization for Wireless Sensor Network has been presented and published in the 5th International Workshop on Computing and Networking for Internet of Things.

Safae DAHMANI PhD defense

I was happy to be part of the PhD defense of Safae DAHMANI. Her PhD title is :

2015-12-14-Safae-4

During the introduction to the defense

« Modèles et protocoles de cohérence de données, décision et optimisation à la compilation pour des architectures massivement parallèles. »

devant le jury composé de :

  • Henri-Pierre Charles Directeur de recherche au CEA Grenoble) / Président
  • Raymond Namyst Professeur à l’Université de Bordeaux / Rapporteur
  • Gilles Sassatelli Directeur de recherche CNRS, Montpellier / Rapporteur
  • Gabriel Antoniu Directeur de recherche à l’INRIA, Rennes /
    2015-12-14-Safae-30

    Safae Dahmani during the defense

    Examinateur

  • Guy Gogniat Professeur à l’Université de Bretagne Sud /
    Directeur de thèse
  • Loïc Cudennec
    Ingénieur chercheur au CEA Saclay / Encadrant de thèse

The PhD abstract is :

Manycœurs architectures consist of hundreds to thousands of embedded cores, distributed memories and a dedicated network on a single chip. In this context, and because of the scale of the processor, providing a shared memory system has to rely on efficient hardware and software mechanisms and data consistency protocols. Numerous works explored consistency mechanisms designed for highly parallel architectures. They lead to the conclusion that there won’t exist one protocol that fits to all applications and hardware contexts. In order to deal with consistency issues for this kind of architectures, we propose in this work a multi-protocol compilation toolchain, in which shared data of the application can

2015-12-14-Safae-120

4 PhD generation together ! Raymond Namyst, Gabriel Antoniu, Loic Cudennec and Safae Dahmani

be managed by different protocols. Protocols are chosen and configured at compile time, following the application behavior and the targeted architecture specifications. The application behavior is characterized with a static analysis process that helps to guide the protocols assignment to each data access. The platform offers a protocol library where each protocol is characterized by one or more parameters. The range of possible values of each parameter depends on some constraints mainly related to the targeted platform. The protocols configuration relies on a genetic-based engine that allows to instantiate each protocol with appropriate parameters values according to multiple performance objectives. In order to evaluate the quality of each proposed solution, we use different evaluation models. We first use a traffic analytical model which gives some NoC communication statistics but no timing information. Therefore, we propose two cycle-based evaluation models that provide more accurate performance metrics while taking into account contention effect due to the consistency protocols communications. We also propose a cooperative cache consistency protocol improving the cache miss rate by sliding data to less stressed neighbors. An extension of this protocol is proposed in order to dynamically define the sliding radius assigned to each data migration. This extension is based on the mass-spring physical model. Experimental validation of different contributions uses the sliding based protocols versus a four-state directory-based protocol.

Teaching at Grenoble Alpes University

I’ve done a seminar in the master of the Grenoble Alpes University. during the compilation course done by Jean-Claude Fernandez.

The subject was « Dynamic Compilation Everywhere », computer architecture and dynamic compilation. The course outline was :

  • State of the art in
    • Computer architecture
    • Compilation chains
  • Why optimize : Memory herarchy, Out of Order, microcontroller, MPSoC
  • Classicals law
  • How to profile, mesure performances
  • Example of Intermediate representation (LLVM, Javascript, ART)

Here are the slides of the presentation

PhD defense of M. Aravind SUKUMARAN RAJAM

I was happy to participate to the committee of the PhD defense of M. Aravind SUKUMARAN2015-11-04-DuringDefense RAJAM at the Strasbourg University. The defense was on Thursday Nov 5. 2015. The abstract of his thesis is :

In this thesis, we present our contributions to APOLLO (Automatic speculative POLyhedral Loop Optimizer), which is an automated compiler combining Thread Level Speculation (TLS) and the polyhedral model to optimize codes on the fly. By doing partial instrumentation at runtime, and subjecting it to interpolation, Apollo is able to construct a speculative polyhedral model dynamically. The speculative model is then passed to Pluto -a static polyhedral scheduler-. Apollo then selects one of the statically generated code optimization skeletons and instantiates it. The runtime continuously monitors the code for any dependence violation in a decentralized manner.
Another important contribution of this thesis is our extension of the polyhedral model to codes exhibiting a non linear behavior. Thanks to the dynamic and speculative context offered by Apollo, non-linear behaviors are either modeled using linear regression hyperplanes forming tubes, or using ranges of reached values. Our approach enables the application of polyhedral transformations to non-linear codes thanks to an hybrid centralized-decentralized speculation verification system.

The defense committee was composed by :

  • M. P. Sadayappan Professor, Ohio State University, USA
  • M. Erven ROHOU Directeur de Recherche Inria, Équipe Alf, Rennes,  France
  • M. Henri Pierre CHARLES Directeur de Recherche informatique au CEA,  Grenoble, France
  • Philippe CLAUSS Professeur, Université de Strasboug2015-11-04-AfterDefense

Conference ACIVS in Catania, Italy.

I’ve done a talk at the conference ACIVS in Catania, Italy. It was during a special session for the COPCAMS european project

This talk was « Binary Code Generation for Multimedia Application on 20151102-133438Embedded Platforms »

The abstract was :

<< Multimedia applications such as video compression, image processing, face recognition, run now on embedded platforms. The huge computing power
needed is provided by the  evolution of the transistor density  and by using specialized   accelerators. Theses accelerators are supported by multimedia
instructions set.
Using theses complex instructions can be a nightmare for the engineer
because there is many way to program it, quality of the compiler support
can be random depending on the couple compiler/platform and worse,
performances can be data dependent. Using libraries can be an option if
such library exist and provide enough performances.
In this talk I’ll illustrate the difficulty to generate binary code for this
application domain by practical example of code generation. Then I’ll
show a tool deGoal which is developed in house to resolve these problems. >>

What a wonderfull conference room for a conference on Vision Systems.20151102-133530

IoT symposium during ESWEEK

I attended to the ESWEEK conference, in Amsterdam, mainly the CASES conference.

I’ve done a talk during the IoT symposium. « Self-optimisation using runtime code generation for Wireless Sensor Networks« , Caroline Quéva, Damien Couroussé and Henri-Pierre Charles.

My slides are now online on the HAL website : https://hal-cea.archives-ouvertes.fr/cea-01240865

« Compilation day » at Saclay

Today, compilation day ! October 1, 2015 CEA NanoInnov, Amphitéatre 33, Av. de la Vauve, 91120 Palaiseau. It was announced on the labex persyval web site.

Agenda and CV :

  • 10:30-11:30 : Benoit Dupont de Dinechin Séminaire : « Revisiting DSP Acceleration with the Kalray MPPA Manycore Processor »
  • 14:00-16:00 : Alexandre Aminot Soutenance de thèse : « Placement de tâches dynamique et flexible sur processeur multi‐coeur asymétrique en fonctionnalités»
  • The thesis committee was composed by
    • Guy GOGNIAT Professeur Université de Bretagne-Sud – UEB Rapporteur
    • Alain PEGATOQUET Maître de conférences Univ. de Nice Sophia Antipolis Rapporteur
    • Albert COHEN Directeur de recherche INRIA – ENS Examinateur
    • Karine HEYDEMANN Maître de conférences Univ. Pierre et Marie Curie Examinateur
    • Vivien QUEMA Professeur Grenoble INP / ENSIMAG Examinateur
    • Benoit DUPONT de DINECHIN Directeur de la technologie Kalray Examinateur
    • Henri-Pierre CHARLES Directeur Recherche CEA LIST Directeur de thèse
    • Yves LHUILLIER Ingénieur Recherche CEA LIST Encadrant de thèse
    • Andrea CASTAGNETTI Ingénieur Recherche CEA LIST Encadrant de thèse (invité)

« Compilation day » in Grenoble

« Compilation day » in Grenoble. A compilation day is a mini workshop which include a talk given by a thesis comittee member followed by the PhD defense.

Agenda and CV

  • 10:30-11:30h : Invited talk : Paul Kelly, Imperial College icimagesLondon « Compiler technology for solving PDEs with performance portability« 
  • 14-16h : PhD defense : Fernando A. Endo « Online auto-tuning for performance and energy through micro-architecture dependent code generation. »
    • Fernando thesis dissertation
    • Fernando Thesis Slides
    • The thesis committee was composed by1d5dc55
      • M. Florent de DINECHIN professeur, INSA de Lyon, Rapporteur
      • M. Paul KELLY, professeur, Imperial College London, Rapporteur
      • M. Frédéric PÉTROT, professeur, Grenoble Institute of Technology, Examinateur
      • Mme Karine HEYDEMANN, maître de conférences, Univ. Pierre et Marie Curie, Examinatrice
      • M. Henri-Pierre CHARLES, directeur de recherche au CEA, Directeur de thèse
      • M. Damien COUROUSSÉ, ingénieur chercheur au CEA, Grenoble, Encadrant de thèse

 

« Dynamic compilation day » in Grenoble

Wedenesday 12 november 2014 Salle 320 UFR IM2A20141112-ForHiPEACG, a dynamic compilation organized thanks to the « PERSYVAL-Lab ». Here is the announcement on the Dynamic Compilation Day

  • 10h-12h : Séminaire :Dynamic Compilation in OpenCL : – Potential and Practice by Ayal Zacks Manager of the Intel OpenCL compiler in Haifa
    • Abstract: OpenCL (Open Computing Language) is designed for portable heterogeneous computing across a wide spectrum of platforms and architectures. OpenCL’s portability is supported by dynamic compilation – every OpenCL driver must be able to compile portable (C99-based) OpenCL-C code for its device at runtime. Such dynamic compilation by design provides attractive opportunities, which surprisingly have not been fully leveraged yet. In this talk we will review several recent dynamic optimizations for OpenCL, focusing on how they involve compilation.
  • 14-16h : Soutenance de thèse : Victor Lomüller 2014-vl-thesis / 2014-vl-thesis-defense

    « Multi-Time Code Generation and Multi-Objective Code Optimisation« 

    • Abstract: Compilation is an essential step to create efficient applications. This step allows the use of high-level and target independent languages while 20141112-143832maintaining good performances. However, many obstacle prevent compilers to fully optimize applications. For static compilers, the major obstacle is the poor knowledge of the execution context, particularly knowledge on the architecture and data. This knowledge is progressively known during the application life cycle. Compilers progressively integrated dynamic code generation techniques to be
      able to use this knowledge. However, those techniques usually focuses on improvement of hardware capabilities usage but don’t take data into account. In this thesis, we investigate data usage in applications optimization process on Nvidia GPU.We present a method that uses different moments in the application life cycle to create adaptive libraries able to take into account data size. Those libraries can therefore provide more adapted kernels. With the GEMM algorithm, the method is able to provide gains up to 100 % while avoiding code size explosion.The thesis also investigate runtime code generation gains and costs from the execution speed, memory footprint and energy consumption point of view. We present and study 2 light-weight runtime code generation approaches that can specialize code. We show that those 2 approaches can obtain comparable, and even superior, gains compared to LLVM but at a lower cost.
    • The PhD committee was composed by
      • M. Gaël Thomas : Professeur à Télécom Sud Paris, Rapporteur
      • M. François Bodin : Professeur à l’Université de Rennes I, Rapporteur
      • M. Albert Cohen : Directeur de recherche à l’INRIA, Examinateur
      • Mme Karine Heydemann : Maître de Conférences à l’UPMC Paris, Examinatrice
      • M. Jean-François Méhaut : Professeur à l’Université Joseph Fourier, Examinateur
      • M. Thierry Lepley : Ingénieur recherche senior à Nvidia, Examinateur
      • M. Ayal Zaks :Ingénieur recherche senior à Intel Israël, Examinateur
      • M. Henri-Pierre Charles : Directeur de recherche au CEA LIST, Directeur de thèse

20141112-Jury