99 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Oak Ridge National LaboratoryUS20 papers
- University of Tennessee at KnoxvilleUS7 papers
- National Institute of Advanced Industrial Science and TechnologyJP2 papers
- RIKEN Center for Computational ScienceJP2 papers
- Shenzhen Institutes of Advanced TechnologyCN2 papers
- Tokyo Institute of TechnologyJP2 papers
- Virginia TechUS2 papers
- Arts et MétiersFR1 paper
- Bar-Ilan UniversityIL1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
- Clemson UniversityUS1 paper
- Florida A&M University - Florida State University College of EngineeringUS1 paper
3 papers · 1 filter
Mojo: MLIR-Based Performance-Portable HPC Science Kernels on GPUs for the Python Ecosystem
William F. Godoy, Tatiana Melnichenko, Pedro Valero-Lara +5
We explore the performance and portability of the novel Mojo language for scientific computing workloads on GPUs. As the first language based on the LLVM's Multi-Level Intermediate…
Revisiting Temporal Blocking Stencil Optimizations
Lingqi Zhang, Mohamed Wahib, Peng Chen +4
Iterative stencils are used widely across the spectrum of High Performance Computing (HPC) applications. Many efforts have been put into optimizing stencil GPU kernels, given the p…
PERKS: a Locality-Optimized Execution Model for Iterative Memory-bound GPU Applications
Lingqi Zhang, Mohamed Wahib, Peng Chen +4
Iterative memory-bound solvers commonly occur in HPC codes. Typical GPU implementations have a loop on the host side that invokes the GPU kernel as much as time/algorithm steps the…