Guillaume Papaure

dblp:17/4368 · DBLP profile ↗
← Back
1ranked-venue papers
0as first author
0since 2021 · last 2006
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Systems, architecture and hardware · 1

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Computer architecture, parallel and distributed computing, and storage systems
1 paper
Processor architecture and microarchitecture · 56% Integrated circuit design · 44%
Software engineering, system software, and programming languages
1 paper
Compilers and program optimization · 100%

Topics — the 3 heaviest of 4, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Compilers and program optimization › parallelization
thread-level speculation
0.112006
Poster reception - ASTEX: a hot path based thread extractor for distributed memory system on a chip · SC 2006
Integrated circuit design
system-on-chip
0.112006
Poster reception - ASTEX: a hot path based thread extractor for distributed memory system on a chip · SC 2006
Processor architecture and microarchitecture
thread partitioning
0.112006
Poster reception - ASTEX: a hot path based thread extractor for distributed memory system on a chip · SC 2006

Methods — techniques the papers use, named apart from their topics

speculative execution · 0.1hot path detection · 0.1
YearPublicationVenuePosition
2006 Poster reception - ASTEX: a hot path based thread extractor for distributed memory system on a chip
abstract
The Automatic Speculative Thread Extractor, ASTEX, addresses the problem of partitioning C code into threads at compile time in order to map them onto System on Chip (SoC). The startpoint of thread extraction is to find the code region to implement as thread. In ASTEX it is based on program hot-paths detection. Then ASTEX construct a thread speculative model for each hot-path. Since ASTEX, contrary to previous work, doesn't assume shared memory, the speculation is performed on control flow and data layout also. The output is a set of threads characterized by their execution time, the code coverage, the amount of memory and communication required, etc. Our Experiments show that the approach is able to capture and to characterize the main computation kernels of embedded applications and how the hot path detection algorithm paremeter influence the final output layout.
Éric Petit 0003, François Bodin, Guillaume Papaure, Florence Dru
SC3