124 citations · 666 across the 43 of their papers we have counts for
8 papers · 1 filter
Reducing shared memory footprint to leverage high throughput on Tensor Cores and its flexible API extension library
Hiroyuki Ootomo, Rio Yokota
NVIDIA Tensor Core is a mixed-precision matrix-matrix multiplication and addition computing unit, where the theoretical peak performance is more than 300 TFlop/s on NVIDIA A100 GPU…
DGEMM on Integer Matrix Multiplication Unit
Hiroyuki Ootomo, Katsuhisa Ozaki, Rio Yokota
Deep learning hardware achieves high throughput and low power consumption by reducing computing precision and specializing in matrix multiplication. For machine learning inference,…
Mixed-Precision Random Projection for RandNLA on Tensor Cores
Hiroyuki Ootomo, Rio Yokota
Random projection can reduce the dimension of data while capturing its structure and is a fundamental tool for machine learning, signal processing, and information retrieval, which…
Recovering single precision accuracy from Tensor Cores while surpassing the FP32 theoretical peak performance
Hiroyuki Ootomo, Rio Yokota
Tensor Core is a mixed-precision matrix-matrix multiplication unit on NVIDIA GPUs with a theoretical peak performance of more than 300 TFlop/s on Ampere architectures. Tensor Cores…
Communication Reducing Algorithms for Distributed Hierarchical N-Body Problems with Boundary Distributions
Mustafa Abduljabbar, George Markomanolis, Huda Ibeid +2
Reduction of communication and efficient partitioning are key issues for achieving scalability in hierarchical -Body algorithms like FMM. In the present work, we propose four in…
Communication Complexity of the Fast Multipole Method and its Algebraic Variants
Rio Yokota, George Turkiyyah, David Keyes
A combination of hierarchical tree-like data structures and data access patterns from fast multipole methods and hierarchical low-rank approximation of linear operators from H-matr…
Asynchronous Execution of the Fast Multipole Method Using Charm++
Mustafa AbdulJabbar, Rio Yokota, David Keyes
Fast multipole methods (FMM) on distributed mem- ory have traditionally used a bulk-synchronous model of com- municating the local essential tree (LET) and overlapping it with comp…
A Performance Model for the Communication in Fast Multipole Methods on HPC Platforms
Huda Ibeid, Rio Yokota, David Keyes
Exascale systems are predicted to have approximately one billion cores, assuming Gigahertz cores. Limitations on affordable network topologies for distributed memory systems of suc…