Ph.D
Group : Parallel Architecture

Decoupled approaches to Register and Software-controlled memory allocations

Starts on 01/10/2007
Advisor : COHEN, Albert

Funding : AM
Affiliation : Université Paris-Saclay
Laboratory : INRIA Saclay

Defended on 15/12/2011, committee :

Research activities :

Abstract :
Register and local memory allocation are two important optimizations performed during compilation. The former optimization maps the variables of a program to either machine registers or main memory locations. The
latter one maps arrays to either local memory or main memory locations. Recent work in register allocation leverages the complexity and performance benefits of decoupling its allocation and assignment phases.

In this thesis, we exploit the decoupled approach to propose a split register allocator,showing that linear complexity does not imply reduced code quality in just-in-time compilation, and to address the spill minimization problem. Considering the similarities between the register and local memory allocation problems, we study how a decoupled approach could be applied to the local memory allocation problem. We propose
theoretical basis of such an approach, validate it experimentally and reset a bridge between the register and local memory allocation problems.

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.