Search NASA⌕ Search

SEARCH · Search NASA

Results for “GPU Programming”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

The Multiphysics on Advanced Platforms Project

In 2015, the Lawrence Livermore National Laboratory started development of next-generation multiphysics simulation capabilities for the National Nuclear Security Administration under the Advanced Technologies Development and Mitigation (ATDM) element of the Advanced Simulation and Computing program in collaboration with the Exascale Computing Project (ECP). A key driver for this effort across the NNSA tri-lab was the emergence of advanced high performance computing (HPC) architectures based on heterogeneous compute capabilities, including GPU based systems, as part of the national drive toward exascale computing platforms at multiple Department of Energy (DOE) facilities. Developing a multiphysics code capable of meeting the various simulation needs of the NNSA as defined by the current generation of integrated codes (or ICs), initially developed as part of the Accelerated Strategic Computing Initiative (ASCI) program beginning in 1996, and able to scale to the current 100 petaflop class pre-exascale systems, as well the forthcoming exaflop class computers, is a daunting challenge. To accomplish this ambitious goal, LLNL has embraced two key themes: use of high-order numerical methods and a modular approach to code development. The LLNL next generation effort is organized under the Multi-Physics on Advanced Platforms Project (MAPP). A foundational component of MAPP is the Axom computer science (CS) toolkit which provides infrastructure for the development of modular, performance portable, multi-physics application codes. MARBL is a next-generation application code built on the Axom base to address the modeling needs of the high energy density physics (HEDP) community for simulating high-explosive, magnetic or laser driven experiments such as inertial confinement fusion (ICF), pulsed-power magneto-hydrodynamics (MHD), equation of state (EOS) and material strength studies as part of the NNSA’s stockpile stewardship program (SSP).

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

ADEPT: a domain independent sequence alignment strategy for gpu architectures

Bioinformatic workflows frequently make use of automated genome assembly and protein clustering tools. At the core of most of these tools, a significant portion of execution time is spent in determining optimal local alignment between two sequences. This task is performed with the Smith-Waterman algorithm, which is a dynamic programming based method. With the advent of modern sequencing technologies and increasing size of both genome and protein databases, a need for faster Smith-Waterman implementations has emerged. Multiple SIMD strategies for the Smith-Waterman algorithm are available for CPUs. However, with the move of HPC facilities towards accelerator based architectures, a need for an efficient GPU accelerated strategy has emerged. Existing GPU based strategies have either been optimized for a specific type of characters (Nucleotides or Amino Acids) or for only a handful of application use-cases. In this paper, we present ADEPT, a new sequence alignment strategy for GPU architectures that is domain independent, supporting alignment of sequences from both genomes and proteins. Our proposed strategy uses GPU specific optimizations that do not rely on the nature of sequence. We demonstrate the feasibility of this strategy by implementing the Smith-Waterman algorithm and comparing it to similar CPU strategies as well as the fastest known GPU methods for each domain. ADEPT’s driver enables it to scale across multiple GPUs and allows easy integration into software pipelines which utilize large scale computational systems. We have shown that the ADEPT based Smith-Waterman algorithm demonstrates a peak performance of 360 GCUPS and 497 GCUPs for protein based and DNA based datasets respectively on a single GPU node (8 GPUs) of the Cori Supercomputer. Overall ADEPT shows 10x faster performance in a node-to-node comparison against a corresponding SIMD CPU implementation. ADEPT demonstrates a performance that is either comparable or better than existing GPU strategies. We demonstrated the efficacy of ADEPT in supporting existing bionformatics software pipelines by integrating ADEPT in MetaHipMer a high-performance denovo metagenome assembler and PASTIS a high-performance protein similarity graph construction pipeline. Our results show 10% and 30% boost of performance in MetaHipMer and PASTIS respectively.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

SYCL for Performance Portability: Application Experience with Coupled Cluster Formalism in Quantum Chemistry on Exascale Systems

The exascale computing has brought unprecedented heterogeneity in node architectures, with systems such as Frontier and Aurora featuring diverse GPU accelerators, network connectivity among others. Ensuring performance portability across these platforms is a key challenge. To address this, we employ the SYCL programming model to develop portable, high-performance quantum chemistry workloads. As a representative application, we focus on the non-iterative Triples component of the coupled-cluster CCSD(T) method, a key driver in quantum chemistry. In this work, we report on our experience deploying SYCL-based implementations using both DPC++ and AdaptiveCPP across two flagship exascale platforms: OLCF Frontier with AMD MI250X GPUs and ALCF Aurora with Intel GPUs. Our results demonstrate that SYCL enables efficient, single-source implementations that scale to thousands of nodes, delivering performance on par with vendor-optimized HIP solutions. We highlight key insights into runtime behavior, kernel portability, and scaling characteristics, showing that SYCL offers a viable path for performance-portable computing.

Bagusetty, Abhishek [Argonne National Laboratory (↗
DOE OSTI2022

Unified Language Frontend for Physic-Informed AI/ML

Artificial intelligence and machine learning (AI/ML) are becoming important tools for scientific modeling and simulation as in several other fields such as image analysis and natural language processing. ML techniques can leverage the computing power available in modern systems and reduce the human effort needed to configure experiments, interpret and visualize results, draw conclusions from huge quantities of raw data, and build surrogates for physics based models. Domain scientists in fields like fluid dynamics, microelectronics and chemistry can automate many of their most difficult and repetitive tasks or improve the design times by use of the faster ML-surrogates. However, modern ML and traditional scientific highperformance computing (HPC) tend to use completely different software ecosystems. While ML frameworks like PyTorch and TensorFlow provide Python APIs, most HPC applications and libraries are written in C++. Direct interoperability between the two languages is possible but is tedious and error-prone. In this work, we show that a compiler-based approach can bridge the gap between ML frameworks and scientific software with less developer effort and better efficiency. We use the MLIR (multi-level intermediate representation) ecosystem to compile a pre-trained convolutional neural network (CNN) in PyTorch to freestanding C++ source code in the Kokkos programming model. Kokkos is a programming model widely used in HPC to write portable, shared-memory parallel code that can natively target a variety of CPU and GPU architectures. Our compiler-generated source code can be directly integrated into any Kokkosbased application with no dependencies on Python or cross-language interfaces.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Celeritas: GPU-accelerated particle transport for detector simulation in High Energy Physics experiments

Within the next decade, experimental High Energy Physics (HEP) will enter a new era of scientific discovery through a set of targeted programs recommended by the Particle Physics Project Prioritization Panel (P5), including the upcoming High Luminosity Large Hadron Collider (LHC) HL-LHC upgrade and the Deep Underground Neutrino Experiment (DUNE). These efforts in the Energy and Intensity Frontiers will require an unprecedented amount of computational capacity on many fronts including Monte Carlo (MC) detector simulation. In order to alleviate this impending computational bottleneck, the Celeritas MC particle transport code is designed to leverage the new generation of heterogeneous computer architectures, including the exascale computing power of U.S. Department of Energy (DOE) Leadership Computing Facilities (LCFs), to model targeted HEP detector problems at the full fidelity of Geant4. This paper presents the planned roadmap for Celeritas, including its proposed code architecture, physics capabilities, and strategies for integrating it with existing and future experimental HEP computing workflows.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Distributed out-of-memory NMF on CPU/GPU architectures

We propose an efficient distributed out-of-memory implementation of the non-negative matrix factorization (NMF) algorithm for heterogeneous high-performance-computing systems. The proposed implementation is based on prior work on NMFk, which can perform automatic model selection and extract latent variables and patterns from data. In this work, we extend NMFk by adding support for dense and sparse matrix operation on multi-node, multi-GPU systems. The resulting algorithm is optimized for out-of-memory problems where the memory required to factorize a given matrix is greater than the available GPU memory. Memory complexity is reduced by batching/tiling strategies, and sparse and dense matrix operations are significantly accelerated with GPU cores (or tensor cores when available). Input/output latency associated with batch copies between host and device is hidden using CUDA streams to overlap data transfers and compute asynchronously, and latency associated with collective communications (both intra-node and inter-node) is reduced using optimized NVIDIA Collective Communication Library (NCCL) based communicators. Benchmark results show significant improvement, from 32X to 76x speedup, with the new implementation using GPUs over the CPU-based NMFk. Good weak scaling was demonstrated on up to 4096 multi-GPU cluster nodes with approximately 25,000 GPUs when decomposing a dense 340 Terabyte-size matrix and an 11 Exabyte-size sparse matrix of density 10 -6 .

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Application Experiences on a GPU-Accelerated Arm-based HPC Testbed

This paper assesses and reports the experience of ten teams working to port, validate, and benchmark several High Performance Computing applications on a novel GPU-accelerated Arm testbed system. The testbed consists of eight NVIDIA Arm HPC Developer Kit systems, each one equipped with a server-class Arm CPU from Ampere Computing and two data center GPUs from NVIDIA Corp. The systems are connected together using InfiniBand interconnect. The selected applications and mini-apps are written using several programming languages and use multiple accelerator-based programming models for GPUs such as CUDA, OpenACC, and OpenMP offloading. Working on application porting requires a robust and easy-to-access programming environment, including a variety of compilers and optimized scientific libraries. The goal of this work is to evaluate platform readiness and assess the effort required from developers to deploy well-established scientific workloads on current and future generation Arm-based GPU-accelerated HPC systems. The reported case studies demonstrate that the current level of maturity and diversity of software and tools is already adequate for large-scale production deployments.

Elwasif, Wael↗
DOE OSTI2020

TChem v2.0 - A Software Toolkit for the Analysis of Complex Kinetic Models

TChem is an open source software library for solving complex computational chemistry problems and analyzing detailed chemical kinetic models. The software provides support for: complex kinetic models for gas-phase and surface chemistry; thermodynamic properties based on NASA polynomials; species production/consumption rates; stable time integrator for solving stiff time ordinary differential equations; and, reactor models such as homogenous gas-phase ignition (with analytical Jacobian matrices), continuously stirred tank reactor, plug-flow reactor. This toolkit builds upon earlier versions that were written in C and featured tools for gas-phase chemistry only. The current version of the software was completely refactored in C++, uses an object-oriented programming model, and adopts Kokkos as its portability layer to make it ready for the next generation computing architectures i.e., multi/many core computing platforms with GPU accelerators. We have expanded the range of kinetic models to include surface chemistry and have added examples pertaining to Continuously Stirred Tank Reactors (CSTR) and Plug Flow Reactor (PFR) models to complement the homogenous ignition examples present in the earlier versions. To exploit the massive parallelism available from modern computing platforms, the current software interface is designed to evaluate samples in parallel, which enables large scale parametric studies, e.g. for sensitivity analysis and model calibration.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

GenASiS Mathematics: Object-oriented manifolds, operations, and solvers for large-scale physics simulations (version 2)

We report GenASiS Mathematics provides modern Fortran classes furnishing extensible object-oriented functionality for the solution of fields governed by selected partial differential equations. The initial release included extensible object-oriented implementations of simple meshes and the evolution of generic conserved currents thereon. This revision - Version 2 of Mathematics - includes significant reorganization and streamlining of these classes, higher-order reconstruction by a different method, a Poisson solver, coarsening to avoid Courant time step limitations near coordinate singularities, and the offloading of computational kernels to GPUs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

NEthing v0.1

The program extends the analysis capabilities of existing profilers through additional analysis to provide insights about communication computation overlap, communication modeling, and broad performance summaries of CPU, GPU and memory. This allows users to understand how their applications are spending time and where performance bottlenecks are.

Groves, Taylor↗
DOE OSTI2025

Improving the Capabilities and Computational Efficiency of the RTE+RRTMGP Radiation Code (Final Report)

This report details progress on the RTE+RRTMGP radiation codes made during the period of performance. RTE+RRTMGP is a set of codes for computing radiative fluxes in planetary atmospheres. RRTMGP uses a k-distribution to provide an optical description (absorption and possibly Rayleigh optical depth) of the gaseous atmosphere, along with the relevant source functions, on a pre-determined spectral grid given temperatures, pressures, and gas concentration. RTE computes fluxes given spectrally-resolved optical descriptions and source functions. Spectrally-resolved fluxes are summarized (“reduced”) via a user extensible class. The initial release of the code and the design choices are described in Pincus et al. 2019; the codes are available on Github. Although RRTMGP was based on current (at the time) empirical spectroscopic data, RTE and RRTMGP were developed in large part to modernize software practices. The design focused on flexibility broadly interpreted: by separating code from data and allowing data to drive computation; in coupling to the host model (e.g. the coupling of clouds to radiative fluxes is user-controlled); with respect to programming languages (computational tasks are accessed via widely-compatible C interfaces); and with respect to hardware (the codes run on a range of CPU and GPU architectures). The code also puts an emphasis on modularity and clarity. RTE+RRTMGP v1.0 was released in September 20219. This award supported the evolution of the RTE+RRTMGP code base to support greater flexibility, accuracy, and efficiency.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Performance Analysis of PIConGPU: Particle-in-Cell on GPUs using NVIDIA’s NSight Systems and NSight Compute

PIConGPU, Particle In Cell on GPUs, is an open source simulations framework for plasma and laser-plasma physics used to develop advanced particle accelerators for radiation therapy of cancer, high energy physics and photon science. While PIConGPU has been optimized for at least 5 years to run well on NVIDIA GPU-based clusters, there has been limited exploration by the development team of potential scalability bottlenecks using recently updated and new tools including NVIDIA’s NVProf tool and the brand-new NVIDIA NSight Suite (Systems and Compute) tools. PIConGPU is a highly optimized application that runs production jobs at scale on a system Oak Ridge Leadership Facility’s (OLCF) Summit supercomputer (using the full machine at 4600 nodes; at 98% of GPU utilization on all ~28000 NVIDIA Volta GPUs). PIConGPU has been selected as one of the the eight applications for OLCF’s coveted Center for Accelerated Application Readiness (CAAR) program aimed at the facility’s Frontier supercomputer (OLCF’s first exascale system to launch in 2021), to partner with our vendors (primary vendors: AMD and Cray/HPE) ensuring that Frontier will be able to perform large-scale science when it opens to users in 2022. To this effect, performance engineers on the PIConGPU team wanted to dive deep into the application to understand at the finest granularity, which portions of the code could be further optimized to exploit the hardware on Summit at it’s maximum potential and also to elucidate which key kernels should be tracked and optimized for the CAAR effort to port this code to Frontier. Any bottlenecks that are observed via performance profiling on Summit are likely to also impact scalability on the Frontier-dev system and the Frontier Early Access (EA) system. Additionally, the engineers wanted to take a closer look at the newest NVIDIA profiling tools which allows us to identify the most useful features on these tools and will provide an opportunity to compare it to new AMD and Cray’s performance analysis tool releases and provide feedback to our vendor partners on what features are most important and mission critical for CAAR efforts. The primary goal of this report is to focus on the evaluation of PIConGPU’s most time-intensive kernels using NVProf and NSight Suite. Three kernels, Current Deposition (also known as Compute Current), Particle Push (Move and Mark), and Shift Particles are known to be some of the most time-consuming kernels in PIConGPU. The Current xi Deposition kernel and Particle Push kernel both set up the particle attributes for running any physics simulation with PIConGPU, so it is crucial to improve the performance of these two kernels. In this report, we measure single GPU metrics for the three kernels, offer high level takeaways from the conducted analysis, and compare the profiling data from NSight Compute to that of NVProf. This analysis was performed using a grid size of 240 x 272 x 224, and 10 time steps with the Mid-November Figure of Merit (FOM) run setup. The Traveling Wave Electron Acceleration (TWEAC) science case used in this run is a representative science case for PIConGPU. This execution can also be used for baseline analysis on AMD MI50/ MI60 systems. As of the time of writing, the PIConGPU application has limited use for features of NSight Systems, so this report will mainly focus on insights garnered from NSight Compute. For this analysis, we run the “full” metric set available in NSight Compute version 2020.1.2 and use NSight Systems version 2020.3.1 to generate the application timeline.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Evaluating performance and portability of high-level programming models: Julia, Python/Numba, and Kokkos on exascale nodes

We explore the performance and portability of the high-level programming models: the LLVM-based Julia and Python/Numba, and Kokkos on high-performance computing (HPC) nodes: AMD Epyc CPUs and MI250X graphical processing units (GPUs) on Frontier’s test bed Crusher system and Ampere’s Arm-based CPUs and NVIDIA’s A100 GPUs on the Wombat system at the Oak Ridge Leadership Computing Facilities. We compare the default performance of a hand-rolled dense matrix multiplication algorithm on CPUs against vendor-compiled C/OpenMP implementations, and on each GPU against CUDA and HIP. Rather than focusing on the kernel optimization per-se, we select this naive approach to resemble exploratory work in science and as a lower-bound for performance to isolate the effect of each programming model. Julia and Kokkos perform comparably with C/OpenMP on CPUs, while Julia implementations are competitive with CUDA and HIP on GPUs. Performance gaps are identified on NVIDIA A100 GPUs for Julia’s single precision and Kokkos, and for Python/Numba in all scenarios. We also comment on half-precision support, productivity, performance portability metrics, and platform readiness. We expect to contribute to the understanding and direction for high-level, high-productivity languages in HPC as the first-generation exascale systems are deployed.

Godoy, William↗
DOE OSTI2020

Toward a scalable robust security-constrained optimal power flow using a proximal projection bundle method

Robust security-constrained optimal power flow (rSCOPF) aims to find the worst-case contingencies of alternating current optimal power flow (ACOPF) in power systems. With the rise of GPU architectures on the upcoming supercomputer architectures, optimization algorithms that rely on sparse linear algebra and indefinite linear systems are becoming increasingly hard to solve efficiently (e.g. interior-point method). To address this we revisit a maximin optimization formulation of the rSCOPF and the single-level mixed-integer semidefinite programming (MISDP) reformulation, which is obtained by taking the Lagrangian relaxation of the inner minimization ACOPF problem. In this paper, we focus on the development of a proximal projection bundle method (PPBM) for solving continuous relaxation node subproblems of the MISDP problem, based primarily on the well-known alternating direction method of multipliers. Cutting planes reminiscent of bundle method ideas are also applied in coordination with updates of the proximal parameter. The cutting-plane method can generate a large number of linear inequalities, leading to a large scale but decomposable quadratic programming (QP) subproblem that is amenable to GPUs. We present the numerical results on the IEEE 30, 57, 118, and 300-bus systems by using our PBMM method. We discuss the main computational bottleneck of our method, which is the time taken to solve each iteration of a QP subproblem instance of the PPBM, and how GPU architectures can accelerate this solution process.

bundle method↗
DOE OSTI2024

Development of a Performance Portable Non-Equilibrium Plasma Fluid Solver on Adaptive Grids

This presentation will describe the numerical techniques, programming paradigms, verification, and performance of a non-equilibrium plasma fluid solver that can effectively utilize current and upcoming central processing and graphics processing unit (CPU+GPU) architectures. Our plasma fluid model solves the conservation equations for self-consistent electrostatic Poisson, electron and heavy species transport, and electron temperature on adaptive Cartesian grids. Our solver is written using performance portable adaptive mesh management library, AMReX (Zhang et al., JOSS, 4 (37) 1370, 2019), and can be built and run on widely available vendor specific GPU architectures (NVIDIA/AMD/Intel). We utilize a non-subcycled second order semi-implicit time-stepping method where all adaptive mesh refinement (AMR) levels are advanced with the same time step. The composite multi-level multigrid solver from within AMReX is used for each of the governing equations that are cast into a Helmholtz equation form. We have also developed a python based chemical mechanism parser framework that uses a similar format as CANTERA (Goodwin et al., Zenodo, 2018) yaml files as input. Our custom parser reads the yaml file and provides C++ files with transport and production rate functions that can be executed on both host (CPU) and device (GPU). We present verification of our solver using method of manufactured solutions that indicate formal second order accuracy with central diffusion and fifth order weighted-essentially-non-oscillatory (WENO) advection scheme. We also verify our solver with published literature on low-pressure capacitive and high-pressure streamer discharges. Our initial performance studies indicate 10X speed-up using 20 NVIDIA GPUs versus 200 CPUs for an atmospheric streamer discharge problem solved on a 512 x 1024 x 512 grid.

graphics processing units↗
DOE OSTI2021

A compute-bound formulation of Galerkin model reduction for linear time-invariant dynamical systems

This work aims to advance computational methods for projection-based reduced-order models (ROMs) of linear time-invariant (LTI) dynamical systems. For such systems, current practice relies on ROM formulations expressing the state as a rank-1 tensor (i.e., a vector), leading to computational kernels that are memory bandwidth bound and, therefore, ill-suited for scalable performance on modern architectures. This weakness can be particularly limiting when tackling many-query studies, where one needs to run a large number of simulations. This work introduces a reformulation, called rank-2 Galerkin, of the Galerkin ROM for LTI dynamical systems which converts the nature of the ROM problem from memory bandwidth to compute bound. We present the details of the formulation and its implementation, and demonstrate its utility through numerical experiments using, as a test case, the simulation of elastic seismic shear waves in an axisymmetric domain. We quantify and analyze performance and scaling results for varying numbers of threads and problem sizes. In conclusion, we present an end-to-end demonstration of using the rank-2 Galerkin ROM for a Monte Carlo sampling study. We show that the rank-2 Galerkin ROM is one order of magnitude more efficient than the rank-1 Galerkin ROM (the current practice) and about 970 times more efficient than the full-order model, while maintaining accuracy in both the mean and statistics of the field.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

If We Build Them, They Will Run: Automated HPC Apps Deployment and Profiling with eBPF in Cloud

The high performance computing (HPC) community is in a period of transition. The rise of AI/ML coupled with a changing landscape of resources deems portability a new metric of performance, and methods to move between on-premises and cloud environments and assess compatibility are paramount. Here we design and test a strategy for bridging the gap between traditional HPC and Kubernetes environments – first containerizing applications, providing automated orchestration to run studies, and packaging the setup with automated means to assess performance using low overhead eXtended Berkeley Packet Filter (eBPF) programs. We first assess different designs for eBPF collection, demonstrating a tradeoff between number of programs deployed on a node and overhead added. We develop 5 low overhead eBPF programs that combine with streaming ML models to assess CPU, futex, TCP, shared memory, and file access across four different builds of an HPC application for CPU and GPU. We use eBPF data to generate insights into the possible underlying etiology of scaling issues. We then assess compatibility of a well-known benchmark, HPCG, across matrices of micro-architectures and optimization levels (217 containers across 24 instance types and over 7500 runs). We provide to the community 30 applications to deploy in our automated setup and perform a scaling study from 4 to a maximum of 256 nodes for both CPU and GPU applications. Finally, we use our gained knowledge about performance to generate compatibility artifacts that are used by a newly developed Kubernetes controller to intelligently select instance type based on optimizing a figure of merit. Along with insights to scaling in this environment with a collection of applications and templates to work from, we provide an overall strategy for approaching HPC application deployment and image selection based on compatibility in cloud.

Computer science↗
DOE OSTI2019

Accelerating DCA++ (Dynamical Cluster Approximation) Scientific Application on the Summit supercomputer

Optimizing scientific applications on today’s accelerator-based high performance computing systems can be challenging, especially when multiple GPUs and CPUs with heterogeneous memories and persistent non-volatile memories are present. An example is Summit, an accelerator-based system at the Oak Ridge Leadership Computing Facility (OLCF) that is rated as the world’s fastest supercomputer to-date. New strategies are thus needed to expose the parallelism in legacy applications, while being amenable to efficient mapping to the underlying architecture.In this paper we discuss our experiences and strategies to port a scientific application, DCA++, to Summit. DCA++ is a highperformance research application that solves quantum manybody problems with a cutting edge quantum cluster algorithm, the dynamical cluster approximation.Our strategies aim to synergize the strengths of the different programming models in the code. These include: (a) streamlining the interactions between the CPU threads and the GPUs, (b) implementing computing kernels on the GPUs and decreasing CPU-GPU memory transfers, (c) allowing asynchronous GPU communications, and (d) increasing compute intensity by combining linear algebraic operations.Full-scale production runs using all 4600 Summit nodes attained a peak performance of 73.5 PFLOPS with a mixed precision implementation.We observed a perfect strong and weak scaling for the quantum Monte Carlo solver in DCA++, while encountering about 2× input/output (I/O) and MPI communication overhead on the time-to-solution for the full machine run. Our hardware agnostic optimizations are designed to alleviate the communication and I/O challenges observed, while improving the compute intensity and obtaining optimal performance on a complex, hybrid architecture like Summit.

Balduzzi, Giovanni↗