L
Lluís-Miquel Munguía
Researcher at Georgia Institute of Technology
Publications - 9
Citations - 236
Lluís-Miquel Munguía is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Parallel algorithm & Solver. The author has an hindex of 7, co-authored 9 publications receiving 202 citations. Previous affiliations of Lluís-Miquel Munguía include Polytechnic University of Catalonia.
Papers
More filters
Proceedings ArticleDOI
Fast triangle counting on the GPU
TL;DR: This paper shows the first scalable GPU implementation for triangle counting using a new list intersection algorithm called Intersect Path (named after the Merge Path algorithm), which has two levels of parallelism.
Posted Content
Carbon Emissions and Large Neural Network Training.
David A. Patterson,Joseph E. Gonzalez,Quoc V. Le,Chen Liang,Lluís-Miquel Munguía,Daniel Rothchild,David R. So,Maud Texier,Jeffrey Dean +8 more
TL;DR: In this article, the authors calculate the energy use and carbon footprint of several recent large models, including T5, Meena, GShard, Switch Transformer, and GPT-3, and refine earlier estimates for the neural architecture search that found evolved transformer.
Journal ArticleDOI
Alternating criteria search: a parallel large neighborhood search algorithm for mixed integer programs
TL;DR: A parallel large neighborhood search framework for finding high quality primal solutions for general mixed-integer programs (MIPs) with the dual objective of reducing infeasibility and optimizing with respect to the original objective.
Proceedings ArticleDOI
Load balanced clustering coefficients
TL;DR: This work shows two scalable approaches that load balance clustering coefficients and achieves optimal load balancing with an Ο(|E|) storage requirement and a lower storage requirement at the cost of some imbalance.
Proceedings ArticleDOI
Task-based parallel breadth-first search in heterogeneous environments
TL;DR: This study shows high processing rates are achievable with hybrid environments despite the GPU communication latency and memory coherence, and uses a fine-grained task-based parallelization scheme and the OmpSs programming model to achieve that goal.