Related papers: HotQCD on Multi-GPU Systems

The present panorama of HPC architectures is extremely heterogeneous, ranging from traditional multi-core CPU processors, supporting a wide class of applications but delivering moderate computing performance, to many-core GPUs, exploiting…

We describe the construction of a high performance parallel computer composed of PC components, present some physical results for light hadron and hybrid meson masses from lattice QCD. We also show that the smearing technique is very useful…

We present a new set of QCD codes in both message passing and data parallel versions. The message passing package used is PARMACS, although other packages may be used. Data parallel software is written in High Performance fortran, an…

Since the development of the Beowulf project to build a parallel computer from commodity PC components, there have been many such clusters built. The MILC QCD code has been run on a variety of clusters and supercomputers. Key design…

We present cudaclaw, a CUDA-based high performance data-parallel framework for the solution of multidimensional hyperbolic partial differential equation (PDE) systems, equations describing wave motion. cudaclaw allows computational…

Efficient GPU programming is crucial for achieving high performance in deep learning (DL) applications. The performance of GPU programs depends on how data is parallelized across threads and arranged within memory subsystems. The mapping…

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…

Low-discrepancy (LD) sequences have been extensively used as efficient experimental designs across many scientific disciplines. QMCPy (https://qmcsoftware.github.io/QMCSoftware/) is an accessible Python library which provides a unified…

Reducing memory traffic is critical to accelerate Lattice QCD computations on modern processors, given that such computations are memory-bandwidth bound. A commonly used strategy is mixed-precision solvers, however, these require careful…

To address the challenge of performance analysis on the US DOE's forthcoming exascale supercomputers, Rice University has been extending its HPCToolkit performance tools to support measurement and analysis of GPU-accelerated applications.…

Algorithmic formulations of GPU programs provide a high-level alternative to device-specific code by expressing computations as compositions of well-defined parallel primitives (e.g., map, sort, reduce), rather than through handcrafted GPU…

In this work, we present accLB, a high-performance Fortran-based lattice Boltzmann (LB) solver tailored to multiphase turbulent flows on multi-GPU architectures. The code couples a conservative phase-field formulation of the Allen-Cahn…

Lattice computations are the only first principle method capable of quantitatively assessing the topological properties of QCD at high temperature, however the numerical determination of the topological properties of QCD, especially in the…

While multi-GPU (MGPU) systems are extremely popular for compute-intensive workloads, several inefficiencies in the memory hierarchy and data movement result in a waste of GPU resources and difficulties in programming MGPU systems. First,…

We propose an architecture, called NVQLink, for connecting high-performance computing (HPC) resources to the control system of a quantum processing unit (QPU) to accelerate workloads necessary to the operation of the QPU. We aim to support…

Experience shows that on today's high performance systems the utilization of different acceleration cards in conjunction with a high utilization of all other parts of the system is difficult. Future architectures, like exascale clusters,…

The use of reduced and mixed precision computing has gained increasing attention in high-performance computing (HPC) as a means to improve computational efficiency, particularly on modern hardware architectures like GPUs. In this work, we…

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

We present the first open-source, GPU-based code for complex plasmas. The code, OpenDust, aims to provide researchers both experimenters and theorists user-friendly and high-performance tool for self-consistent calculation forces, acting on…

Quantum computers have demonstrated utility in simulating quantum systems beyond brute-force classical approaches. As the community builds on these demonstrations to explore using quantum computing for applied research, algorithms and…