Ph.D
Group : Parallel Architecture

Erbium: Reconciling languages, runtimes, compilation and optimizations for streaming applications

Starts on 01/10/1997
Advisor : COHEN, Albert

Funding : Bourse pour étudiant étranger
Affiliation : Université Paris-Saclay
Laboratory : INRIA alchemy

Defended on 11/02/2013, committee :

Research activities :

Abstract :
As diminishing returns in single-thread performance and power
limitations hit the microprocessor industry, chip-multiprocessors became
ubiquitous. It brought old, difficult problems back into the software
equation. Compilers regain attention by being one of the critical
"puzzle pieces" in the quest for translating Moore's law into the
expected performance improvements, which cannot be achieved without
thread-level parallelism. Nevertheless, parallel systems research has
mainly focused on the language and architectural aspects, and much
potential remains to be explored to compile parallel programs, to
optimize them and to adapt them for the efficient exploitation of
parallel hardware.
This thesis addresses these problems by presenting Erbium, a low level
streaming data-flow language, supporting multiple producer and consumer
task communication; a very efficient runtime implementation for x86
architectures and variants to address other types of architectures; a
compiler integration of the language as an intermediate representation
in GCC; a study of the language primitives dependences, allowing
compilers to further optimise the Erbium code through specific parallel
optimisations as well as through generalized forms of classical compiler
optimisations, such as partial redundancy elimination and dead code
elimination.

CAUSAL LEARNING FOR DIAGNOSTIC SUPPORT


CAUSAL UNCERTAINTY QUANTIFICATION UNDER PARTIAL KNOWLEDGE AND LOW DATA REGIMES


MICRO VISUALIZATIONS: DESIGN AND ANALYSIS OF VISUALIZATIONS FOR SMALL DISPLAY SPACES
The topic of this habilitation is the study of very small data visualizations, micro visualizations, in display contexts that can only dedicate minimal rendering space for data representations. For several years, together with my collaborators, I have been studying human perception, interaction, and analysis with micro visualizations in multiple contexts. In this document I bring together three of my research streams related to micro visualizations: data glyphs, where my joint research focused on studying the perception of small-multiple micro visualizations, word-scale visualizations, where my joint research focused on small visualizations embedded in text-documents, and small mobile data visualizations for smartwatches or fitness trackers. I consider these types of small visualizations together under the umbrella term ``micro visualizations.'' Micro visualizations are useful in multiple visualization contexts and I have been working towards a better understanding of the complexities involved in designing and using micro visualizations. Here, I define the term micro visualization, summarize my own and other past research and design guidelines and outline several design spaces for different types of micro visualizations based on some of the work I was involved in since my PhD.