Related papers: cuSten -- CUDA Finite Difference and Stencil Libra…
Large language models show promise for automated CUDA programming, however even the strongest coding models (e.g., Claude-Opus-4.6) may still fall short of expert-level, architecture-aware optimization. We introduce CUDAHercules, a…
Finite element schemes based on discontinuous Galerkin methods possess features amenable to massively parallel computing accelerated with general purpose graphics processing units (GPUs). However, the computational performance of such…
This work presents the efficient, matrix-free finite-element library hyper.deal for solving partial differential equations in two to six dimensions with high-order discontinuous Galerkin methods. It builds upon the low-dimensional…
The acceleration of sparse matrix computations on modern many-core processors, such as the graphics processing units (GPUs), has been recognized and studied over a decade. Significant performance enhancements have been achieved for many…
Efficient GPU execution of convolution operators is governed by memory-access efficiency, on-chip data reuse, and execution mapping rather than arithmetic throughput alone. This paper presents a controlled operator-level study of CUDA…
Distributed training is a novel approach to accelerate Deep Neural Networks (DNN) training, but common training libraries fall short of addressing the distributed cases with heterogeneous processors or the cases where the processing nodes…
Although QUDA allows for an efficient computation of many QCD quantities, it is surprinsingly lacking tools to evaluate disconnected diagrams, for which GPUs are specially well suited. We aim to fill this gap by creating our own branch of…
The numerical integration of stochastic trajectories to estimate the time to pass a threshold is an interesting physical quantity, for instance in Josephson junctions and atomic force microscopy, where the full trajectory is not accessible.…
Convolutions are the core operation of deep learning applications based on Convolutional Neural Networks (CNNs). Current GPU architectures are highly efficient for training and deploying deep CNNs, and hence, these are largely used in…
Automatic code generation is frequently used to create implementations of algorithms specifically tuned to particular hardware and application parameters. The code generation process involves the selection of adequate code transformations,…
The MuST package is a computational software designed for ab initio electronic structure calculations for solids. The Locally Self-consistent Multiple Scattering (LSMS) method implemented in MuST allows to perform the electronic structure…
We present MIST, the Molecular Integration Simulation Toolkit, a lightweight and efficient software library written in C++ which provides an abstract in- terface to common molecular dynamics codes, enabling rapid and portable development of…
Motivated by the increasing availability of low- and mixed-precision arithmetic on modern hardware, we develop mixed-precision variants of Lloyd's algorithm for k-means clustering. The main ingredient is a family of mixed-precision kernels…
Linear Programs (LPs) appear in a large number of applications and offloading them to the GPU is viable to gain performance. Existing work on offloading and solving an LP on GPU suggests that performance is gained from large sized LPs…
Fuzzing is a powerful technique for finding bugs in software libraries, but scaling it remains difficult. Automated harness generation commits to fixed API sequences at synthesis time, limiting the behaviors each harness can test.…
We present automatic horizontal fusion, a novel optimization technique that complements the standard kernel fusion techniques for GPU programs. Unlike the standard fusion, whose goal is to eliminate intermediate data round trips, our…
Computing platforms equipped with accelerators like GPUs have proven to provide great computational power. However, exploiting such platforms for existing scientific applications is not a trivial task. Current GPU programming frameworks…
Stencil algorithms on regular lattices appear in many fields of computational science, and much effort has been put into optimized implementations. Such activities are usually not guided by performance models that provide estimates of…
High-Order, High-Dimension, and Sparse Tensor (HOHDST) data originates from real industrial applications, i.e., social networks, recommender systems, bio-information, and traffic information. Sparse Tensor Decomposition (STD) can project…
Numerical simulations are ubiquitous in mathematics and computational science. Several industrial and clinical applications entail modeling complex multiphysics systems that evolve over a variety of spatial and temporal scales. This study…