Sitemap

A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.

Pages

Posts

portfolio

ERIS Permalink

ERIS (short for ERIS is a Resource Interference Suite) is a tool for performance bottleneck analysis based on the injection of performance noise. Noise is defined as additional assembly instructions inserted into performance-critical sections of a code, with the goal to stress specific hardware bottleneck sources.
I develop ERIS as part of my ongoing PhD.

Verificarlo Permalink

A tool for debugging and assessing floating point precision and reproducibility.
I have contributed to Verificarlo in the context of the TREX European CoE.

MAQAO Permalink

MAQAO (Modular Assembly Quality Analyzer and Optimizer) is a performance analysis and optimization framework operating at binary level with a focus on core performance. Its main goal of is to guide application developpers along the optimization process through synthetic reports and hints.

CERE Permalink

Codelet Extractor and REplayer (CERE) is an open source framework for code isolation developped jointly at UVSQ Li-PaRAD lab and ECR lab. CERE finds and extracts the hotspots of an application as isolated fragments of code, called codelets. Codelets can be modified, compiled, run, and measured independently from the original application. Code isolation reduces benchmarking cost and allows piecewise optimization of an application.
I have contributed to CERE in the context of the EMOPASS project.

QMCkl Permalink

The domain of quantum chemistry needs a library in which the main kernels of Quantum Monte Carlo (QMC) methods are implemented. In the library proposed in this project, we expose the main algorithms in a simple language and provide a standard API and tests to enable the development of high-performance QMCkl implementations taking advantage of modern hardware.
I have contributed to QMCkl in the context of the TREX European CoE.

publications

Noise Injection for Performance Botleneck Analysis

Published in 31st International European Conference on Parallel and Distributed Computing, Dresden, Germany, 2025

Conference Best Paper Award

Recommended citation: Delval, A.; de Oliveira Castro, P.; Jalby, W.; Renault E. (2025)."Noise Injection for Performance Bottleneck Analysis".
Download Paper

talks

teaching

Compilation (STICO)

Graduate course, Université de Versailles-Saint-Quentin-en-Yvelines, IATIC, 2021

Compilation course and labs around the Tiger language by Pablo de Oliveira Castro and Samuel Tardieu. I have taught the labs where students build a compiler step-by-step using flex, bison and LLVM. Material can be found here.

Numerical Programming Projects (PPN)

Graduate course, Université de Versailles-Saint-Quentin-en-Yvelines, CHPS, 2022

Group projects around various topics, often related to parallel computing.

Parallel Architectures (AP)

Graduate course, Université de Versailles-Saint-Quentin-en-Yvelines, CHPS, 2024

Course exploring different aspects of parallel computing and dependence analysis taught by Pr. William Jalby.