Francisco Igual

Profesor Titular de Universidad

Universidad Complutense de Madrid

Spain

Research Interests

Explore related searches

Professors in Spain

Contact this professor

ORCID

Google Scholar

About

Francisco Igual is a Profesore Titular de Universidad at Universidad Complutense de Madrid, Spain. His research interests include multi-instance GPU scheduling, mixed-precision matrix multiplication, and the development of algorithmic frameworks for matrix operations. He has recently published articles on balanced CNN segmentation for multi-TPU inference and dynamic power budget redistribution in multi-application environments.

Francisco Igual

Research Interests

Explore related searches

Contact this professor

About

Articles (17)

Leveraging Multi-Instance GPUs through moldable task scheduling

Balanced segmentation of CNNs for multi-TPU inference

Experience-guided, mixed-precision matrix multiplication with apache TVM for ARM processors

Algorithm 1039: Automatic Generators for a Family of Matrix Multiplication Routines with Apache TVM

Automatic generation of ARM NEON micro-kernels for matrix multiplication

Experiences with nested parallelism in task-parallel applications using malleable BLAS on multicore processors

Algorithm 1033: Parallel Implementations for Computing the Minimum Distance of a Random Linear Code on Distributed-memory Architectures

Dynamic power budget redistribution under a power cap on multi-application environments

Micro-kernels for portable and efficient matrix multiplication in deep learning

Fine-grain task-parallel algorithms for matrix factorizations and inversion on many-threaded CPUs

Algorithm 1022: Efficient Algorithms for Computing a Rank-Revealing UTV Factorization on Parallel Computing Architectures

Low precision matrix multiplication for efficient deep learning in NVIDIA Carmel processors

Integration and exploitation of intra-routine malleability in BLIS

Programming parallel dense matrix factorizations with look-ahead and OpenMP

Leveraging knowledge-as-a-service (KaaS) for QoS-aware resource management in multi-user video transcoding

Resource Management for Power-Constrained HEVC Transcoding Using Reinforcement Learning

STEEL-RT: combining single task–single executor model and expanded scheduling to ease heterogeneity exploitation

Collaborators (6)

Rafael Rodríguez-Sánchez

KATZALIN OLCOZ

Luis Costero

Enrique Quintana-Ortí

Manuel Prieto-Matias

FRANCISCO TIRADO

How do I reach out?

Meet Kite AI