Though a majority of current processor architectures relies on shared, cache-coherent memory, current prototypes that integrate large amounts of cores, connected through a message-passing substrate, indicate that architectures of the near future may have these characteristics. Either of those tendencies requires that processes execute in parallel, making concurrent programming a necessary tool. The inherent difficulty of reasoning about concurrency, however, may make the new processor architectures hard to program. In order to deal with issues such as this, we explore approaches for providing ease of programmability. We propose WFR-TM, an approach based on transactional memory (TM), which is a concurrent programming paradigm that employs tr...
In this paper we describe an architecture and implementation of the ACTOR model of concurrent comput...
The continuous proliferation of multicore architectures has placeddevelopers under great pressure to...
This thesis explores co-scheduling problems in the context of large-scale applications with two main...
Though a majority of current processor architectures relies on shared, cache-coherent memory, curren...
Multicore architectures are changing the way we write programs. Writing concurrent programs is well ...
This document is presented in fulfilment of the degree of \emph{Habilitation \`{a} Diriger des Reche...
To use the computational power of modern computing machines, we have to deal with concurrent program...
The increase in the number of cores in processors has been an important trend over the past decade. ...
Modern concurrent programming benefits from a large variety of synchronization techniques. These inc...
The arrival of multiprocessor chips rises again some questions about the way of writing programs, wh...
Modern automated services rely on concurrent software where multiple requests are processed by diffe...
The Single-chip Cloud Computer (SCC) is an experimental multicore processor created by Intel Labs fo...
Parallel programming presents an efficient solution to exploit future multicore processors. Unfortu...
Arguably, one of the biggest deterrants for software developers who might otherwise choose to write ...
In this paper we describe an architecture and implementation of the ACTOR model of concurrent comput...
The continuous proliferation of multicore architectures has placeddevelopers under great pressure to...
This thesis explores co-scheduling problems in the context of large-scale applications with two main...
Though a majority of current processor architectures relies on shared, cache-coherent memory, curren...
Multicore architectures are changing the way we write programs. Writing concurrent programs is well ...
This document is presented in fulfilment of the degree of \emph{Habilitation \`{a} Diriger des Reche...
To use the computational power of modern computing machines, we have to deal with concurrent program...
The increase in the number of cores in processors has been an important trend over the past decade. ...
Modern concurrent programming benefits from a large variety of synchronization techniques. These inc...
The arrival of multiprocessor chips rises again some questions about the way of writing programs, wh...
Modern automated services rely on concurrent software where multiple requests are processed by diffe...
The Single-chip Cloud Computer (SCC) is an experimental multicore processor created by Intel Labs fo...
Parallel programming presents an efficient solution to exploit future multicore processors. Unfortu...
Arguably, one of the biggest deterrants for software developers who might otherwise choose to write ...
In this paper we describe an architecture and implementation of the ACTOR model of concurrent comput...
The continuous proliferation of multicore architectures has placeddevelopers under great pressure to...
This thesis explores co-scheduling problems in the context of large-scale applications with two main...