Adrián Castelló

Publication Activity (10 Years)

Years Active: 2022-2024
Publications (10 Years): 23

Top Topics

Instruction Set

Matrix Multiplication

Efficient Inference

Top Venues

J. Supercomput.

J. Syst. Archit.

Publications

Adrián Castelló, Julian Bellavita, Grace Dinh, Yuka Ikarashi, Héctor Martínez
Tackling the Matrix Multiplication Micro-Kernel Generation with Exo. CGO (2024)
Cristián Ramírez, Adrián Castelló, Héctor Martínez, Enrique S. Quintana-Ortí
Parallel GEMM-based convolution for deep learning on multicore RISC-V processors. J. Supercomput. 80 (9) (2024)
Rafael Rodríguez-Sánchez, Adrián Castelló, Sandra Catalán, Francisco D. Igual, Enrique S. Quintana-Ortí
Experiences with nested parallelism in task-parallel applications using malleable BLAS on multicore processors. Int. J. High Perform. Comput. Appl. 38 (2) (2024)
Guillermo Alaejos, Adrián Castelló, Pedro Alonso-Jordá, Francisco D. Igual, Héctor Martínez, Enrique S. Quintana-Ortí
Algorithm 1039: Automatic Generators for a Family of Matrix Multiplication Routines with Apache TVM. ACM Trans. Math. Softw. 50 (1) (2024)
Cristián Ramírez, Adrián Castelló, Héctor Martínez, Enrique S. Quintana-Ortí
Performance Analysis of Matrix Multiplication for Deep Learning on the Edge. CoRR (2024)
Guillermo Alaejos, Héctor Martínez, Adrián Castelló, Manuel F. Dolz, Francisco D. Igual, Pedro Alonso-Jordá, Enrique S. Quintana-Ortí
Automatic generation of ARM NEON micro-kernels for matrix multiplication. J. Supercomput. 80 (10) (2024)
Héctor Martínez, Sandra Catalán, Adrián Castelló, Enrique S. Quintana-Ortí
Parallel GEMM-based convolutions for deep learning on multicore ARM and RISC-V architectures. J. Syst. Archit. 153 (2024)
Guillermo Alaejos, Adrián Castelló, Héctor Martínez, Pedro Alonso-Jordá, Francisco D. Igual, Enrique S. Quintana-Ortí
Micro-kernels for portable and efficient matrix multiplication in deep learning. J. Supercomput. 79 (7) (2023)
Manuel F. Dolz, Sergio Barrachina, Héctor Martínez, Adrián Castelló, Antonio-Manuel Vidal-Maciá, Germán Fabregat, Andrés E. Tomás
Performance-energy trade-offs of deep learning convolution algorithms on ARM processors. J. Supercomput. 79 (9) (2023)
Manuel F. Dolz, Héctor Martínez, Adrián Castelló, Pedro Alonso-Jordá, Enrique S. Quintana-Ortí
Efficient and portable Winograd convolutions for multi-core processors. J. Supercomput. 79 (10) (2023)
Adrián Castelló, Mar Catalán, Manuel F. Dolz, Enrique S. Quintana-Ortí, José Duato
Analyzing the impact of the MPI allreduce in distributed training of convolutional neural networks. Computing 105 (5) (2023)
Adrián Castelló, Julian Bellavita, Grace Dinh, Yuka Ikarashi, Héctor Martínez
Tackling the Matrix Multiplication Micro-kernel Generation with Exo. CoRR (2023)
Guillermo Alaejos, Adrián Castelló, Pedro Alonso-Jordá, Francisco D. Igual, Héctor Martínez, Enrique S. Quintana-Ortí
Automatic Generators for a Family of Matrix Multiplication Routines with Apache TVM. CoRR (2023)
Francisco D. Igual, Luis Piñuel, Sandra Catalán, Héctor Martínez, Adrián Castelló, Enrique S. Quintana-Ortí
Automatic Generation of Micro-kernels for Performance Portability of Matrix Multiplication on RISC-V Vector Processors. SC Workshops (2023)
Sergio Barrachina, Adrián Castelló, Manuel F. Dolz, Tze Meng Low, Héctor Martínez, Enrique S. Quintana-Ortí, Upasana Sridhar, Andrés E. Tomás
Reformulating the direct convolution for high-performance deep learning inference on ARM processors. J. Syst. Archit. 135 (2023)
Sergio Barrachina, Adrián Castelló, Mar Catalán, Manuel F. Dolz, José I. Mestre
Using machine learning to model the training scalability of convolutional neural networks on clusters of GPUs. Computing 105 (5) (2023)
Adrián Castelló, Enrique S. Quintana-Ortí, Francisco D. Igual
Anatomy of the BLIS Family of Algorithms for Matrix Multiplication. PDP (2022)
Cristián Ramírez, Adrián Castelló, Enrique S. Quintana-Ortí
A BLIS-like matrix multiplication for machine learning in the RISC-V ISA-based GAP8 processor. J. Supercomput. 78 (16) (2022)
Adrián Castelló, Sergio Barrachina, Manuel F. Dolz, Enrique S. Quintana-Ortí, Pau San Juan, Andrés E. Tomás
High performance and energy efficient inference for deep learning on multicore ARM processors using general optimization techniques and BLIS. J. Syst. Archit. 125 (2022)
Adrián Castelló, Sandra Catalán, Francisco D. Igual, Enrique S. Quintana-Ortí, Rafael Rodríguez-Sánchez
QR Factorization Using Malleable BLAS on Multicore Processors. ISC Workshops (2022)
Cristián Ramírez, Adrián Castelló, Héctor Martínez, Enrique S. Quintana-Ortí
Performance Analysis of Matrix Multiplication for Deep Learning on the Edge. ISC Workshops (2022)
Manuel F. Dolz, Adrián Castelló, Enrique S. Quintana-Ortí
Towards Portable Realizations of Winograd-based Convolution with Vector Intrinsics and OpenMP. PDP (2022)
Sergio Barrachina, Adrián Castelló, Manuel F. Dolz, Andrés E. Tomás
BestOf: an online implementation selector for the training and inference of deep neural networks. J. Supercomput. 78 (16) (2022)