Related papers: Evaluation of Portable Acceleration Solutions for …
Leading HPC systems achieve their status through use of highly parallel devices such as NVIDIA GPUs or Intel Xeon Phi many-core CPUs. The concept of performance portability across such architectures, as well as traditional CPUs, is vital…
The Large Hadron Collider (LHC) at CERN will see an upgraded hardware configuration which will bring a new era of physics data taking and related computational challenges. To this end, it is necessary to exploit the ever increasing variety…
The four 10 kt Liquid Argon Time Projection Chambers (LArTPCs) of the future DUNE experiment will enable precise measurements of the oscillation parameters and the discovery of CP violation for leptons, thanks to their excellent 3D imaging…
Neural Networks (NN) provide a solid and reliable way of executing different types of applications, ranging from speech recognition to medical diagnosis, speeding up onerous and long workloads. The challenges involved in their…
It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed…
Numerical codes using the Lattice Boltzmann Methods (LBM) for simulating one- or two-phase flows are widely compiled and run on graphical process units. However, those computational units necessitate to re-write the program by using a…
Transformers have revolutionized deep learning and generative modeling to enable unprecedented advancements in natural language processing tasks and beyond. However, designing hardware accelerators for executing transformer models is…
Deep learning (DL) models are piquing high interest and scaling at an unprecedented rate. To this end, a handful of tiled accelerators have been proposed to support such large-scale training tasks. However, these accelerators often…
As LLMs grow in complexity, achieving state-of-the-art performance requires tight co-design across algorithms, software, and hardware. Today's reliance on a single dominant platform limits portability, creates vendor lock-in, and raises…
Evaluating architectural ideas on realistic workloads is increasingly challenging due to the prohibitive cost of detailed simulation and the lack of portable sampling tools. Existing targeted sampling techniques are often tied to specific…
The modern trend in High-Performance Computing (HPC) involves the use of accelerators such as Graphics Processing Units (GPUs) alongside Central Processing Units (CPUs) to speed up numerical operations in various applications. Leading…
In this dissertation, a fully object-oriented, fully relativistic, multi-dimensional Particle-In-Cell code was developed and applied to answer key questions in plasma-based accelerator research. The simulations increase the understanding of…
In recent years, artificial intelligence (AI) technologies have found industrial applications in various fields. AI systems typically possess complex software and heterogeneous CPU/GPU hardware architecture, making it difficult to answer…
This document describes a new package to compute high performance simulations of a module of superconducting accelerating cavities from the LLRF controller perspective. The reason to make a dedicated C++/Python package is to simulate all…
A computer simulation has to be fast to be helpful, if it is employed to study the behavior of a multicomponent dynamic system. This paper discusses modeling concepts and algorithmic techniques useful for creating such fast simulations.…
Nonlinear time-history evolution problems employing high-fidelity physical models are essential in numerous scientific domains. However, these problems face a critical dual bottleneck: the immense computational cost of time-stepping and the…
This study evaluates AoS-to-SoA transformations over reduced-precision data layouts for a particle simulation code on several GPU platforms: We hypothesize that SoA fits particularly well to SIMT, while AoS is the preferred storage format…
The complexity of combustion simulations demands the latest high-performance computing tools to accelerate its time-to-solution results. A current trend on HPC systems is the utilization of CPUs with SIMD or vector extensions to exploit…
The introduction of accelerator devices such as graphics processing units (GPUs) has had profound impact on molecular dynamics simulations and has enabled order-of-magnitude performance advances using commodity hardware. To fully reap these…
We introduce a practical real-time neural video codec (NVC) designed to deliver high compression ratio, low latency and broad versatility. In practice, the coding speed of NVCs depends on 1) computational costs, and 2) non-computational…