10 citations · 26 across the 12 of their papers we have counts for
13 papers
HCCL: Collective Communication for Meta Training and Inference Accelerators
Wesley Bland, Tiago Antunes, Lars Paul Huse +63
We present HCCL, a collective communication library co-designed with Meta's MTIA 300 accelerator, the first Meta chip to integrate backend networking directly on chip package. MTIA…
Generating wall-bounded turbulent inflows at high Reynolds numbers
Ronith Stanly, Timofey Mukha, Martin Karp +2
One of the main challenges in simulating high Reynolds number () turbulent boundary layers (TBLs) is the long streamwise distance required for large-scale outer-layer structure…
Portable High-Performance Kernel Generation for a Computational Fluid Dynamics Code with DaCe
Måns I. Andersson, Martin Karp, Niclas Jansson +1
With the emergence of new high-performance computing (HPC) accelerators, such as Nvidia and AMD GPUs, efficiently targeting diverse hardware architectures has become a major challe…
Effects of lower floating-point precision on scale-resolving numerical simulations of turbulence
Martin Karp, Ronith Stanly, Timofey Mukha +11
Modern computing clusters offer specialized hardware for reduced-precision arithmetic that can speed up the time to solution significantly. This is possible due to a decrease in da…
Robustness and uncertainty of direct numerical simulation under the influence of rounding and noise
Martin Karp, Niclas Jansson, Saleh Rezaeiravesh +2
Numerical precision in large-scale scientific computations has become an emerging topic due to recent developments in computer hardware. Lower floating point precision offers the p…
Experience and Analysis of Scalable High-Fidelity Computational Fluid Dynamics on Modular Supercomputing Architectures
Martin Karp, Estela Suarez, Jan H. Meinke +4
The never-ending computational demand from simulations of turbulence makes computational fluid dynamics (CFD) a prime application use case for current and future exascale systems.…
Supercomputers as a Continous Medium
Martin Karp, Niclas Jansson, Philipp Schlatter +1
As supercomputers' complexity has grown, the traditional boundaries between processor, memory, network, and accelerators have blurred, making a homogeneous computer model, in which…
Large-Scale Direct Numerical Simulations of Turbulence Using GPUs and Modern Fortran
Martin Karp, Daniele Massaro, Niclas Jansson +4
We present our approach to making direct numerical simulations of turbulence with applications in sustainable shipping. We use modern Fortran and the spectral element method to lev…
Strong Scaling of OpenACC enabled Nek5000 on several GPU based HPC systems
Jonathan Vincent, Jing Gong, Martin Karp +11
We present new results on the strong parallel scaling for the OpenACC-accelerated implementation of the high-order spectral element fluid dynamics solver Nek5000. The test case con…
A High-Fidelity Flow Solver for Unstructured Meshes on Field-Programmable Gate Arrays
Martin Karp, Artur Podobas, Tobias Kenter +4
The impending termination of Moore's law motivates the search for new forms of computing to continue the performance scaling we have grown accustomed to. Among the many emerging Po…
Neko: A Modern, Portable, and Scalable Framework for High-Fidelity Computational Fluid Dynamics
Niclas Jansson, Martin Karp, Artur Podobas +2
Recent trends and advancement in including more diverse and heterogeneous hardware in High-Performance Computing is challenging software developers in their pursuit for good perfor…
High-Performance Spectral Element Methods on Field-Programmable Gate Arrays
Martin Karp, Artur Podobas, Niclas Jansson +4
Improvements in computer systems have historically relied on two well-known observations: Moore's law and Dennard's scaling. Today, both these observations are ending, forcing comp…
Optimization of Tensor-product Operations in Nekbone on GPUs
Martin Karp, Niclas Jansson, Artur Podobas +2
In the CFD solver Nek5000, the computation is dominated by the evaluation of small tensor operations. Nekbone is a proxy app for Nek5000 and has previously been ported to GPUs with…