Related papers: Scaling SU(2) to 1000 GPUs using HiRep
The increasing scale and wealth of inter-connected data, such as those accrued by social network applications, demand the design of new techniques and platforms to efficiently derive actionable knowledge from large-scale graphs. However,…
The Monte Carlo method is a powerful technique for computing thermodynamic magnetic states of otherwise unsolvable spin Hamiltonians, but the method becomes computationally prohibitive with increasing number of spins and the simulation of…
Simulating the real-time dynamics of lattice gauge theories, underlying the Standard Model of particle physics, is a notoriously difficult problem where quantum simulators can provide a practical advantage over classical approaches. In this…
We present a hybrid numerical approach to simulate quantum many body problems on two spatial dimensional quantum lattice models via the non-Abelian ab initio version of the density matrix renormalization group method on state-of-the-art…
Scaling up the sparse matrix-vector multiplication kernel on modern Graphics Processing Units (GPU) has been at the heart of numerous studies in both academia and industry. In this article we present a novel non-parametric, self-tunable,…
It has been proposed to abandon the requirement that parallel transporters in gauge theories are unitary (or pseudoorthogonal). This leads to a geometric interpretation of Vierbein fields as parts of gauge fields, and nonunitary parallel…
Training large transformers is slow, but recent innovations on GPU architecture give us an advantage. NVIDIA Ampere GPUs can execute a fine-grained 2:4 sparse matrix multiplication twice as fast as its dense equivalent. In the light of this…
Neural networks have become indispensable for a wide range of applications, but they suffer from high computational- and memory-requirements, requiring optimizations from the algorithmic description of the network to the hardware…
Over the past decade there has been a growing interest in the development of parallel hardware systems for simulating large-scale networks of spiking neurons. Compared to other highly-parallel systems, GPU-accelerated solutions have the…
Surrogate models driven by sizeable datasets and scientific machine-learning methods have emerged as an attractive microstructure simulation tool with the potential to deliver predictive microstructure evolution dynamics with huge savings…
We study the performance of a cloud-based GPU-accelerated inference server to speed up event reconstruction in neutrino data batch jobs. Using detector data from the ProtoDUNE experiment and employing the standard DUNE grid job submission…
We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute accelerators such as GPUs and FPGAs for the training of…
Deep Gaussian processes (DGPs) are increasingly popular as predictive models in machine learning (ML) for their non-stationary flexibility and ability to cope with abrupt regime changes in training data. Here we explore DGPs as surrogates…
Intel Max GPUs are a new option available to CGYRO fusion simulation users. This paper outlines the changes that were needed to successfully run CGYRO on Intel Max 1550 GPUs on TACC's Stampede3 HPC system and presents benchmark results…
The open source HIP platform for GPU computing provides an uniform framework to support both the NVIDIA and AMD GPUs, and also the possibility to porting the CUDA code to the HIP- compatible one. We present the porting progress on the…
We report on simulations with two flavors of O(a) improved degenerate Wilson fermions with Schroedinger functional boundary conditions. The algorithm which is used is Hybrid Monte Carlo with two pseudo-fermion fields as proposed by M.…
Realistic simulations of detailed, biophysics-based, multi-scale models require very high resolution and, thus, large-scale compute facilities. Existing simulation environments, especially for biomedical applications, are designed to allow…
We explore aspects of the phase structure of SU(2) and SU(3) lattice gauge theories at strong coupling with many flavours $N_f$ of Wilson fermions in the fundamental representation. The pseudoscalar meson mass as a function of hopping…
One significant advantage of superconducting processors is their extensive design flexibility, which encompasses various types of qubits and interactions. Given the large number of tunable parameters of a processor, the ability to perform…
We present preliminary results of lattice simulations of SU(2) gauge theory with two Wilson fermions in the adjoint representation. This theory has recently attracted considerable attention because it might possess an infrared fixed point…