Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “NVIDIA GPUs”

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 217 records · Page 12
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

The Minos Computing Library: Efficient Parallel Programming for Extremely Heterogeneous Systems

Hardware specialization has become the silver bullet to achieve efficient high performance, from Systems-on-Chip systems, where hardware specialization can be ``extreme'', to large-scale HPC systems. As the complexity of the systems increases, so does the complexity of programming such architectures in a portable way. This work introduces the Minos Computing Library (MCL), as system software, programming model, and programming model runtime that facilitate programming extremely heterogeneous systems. MCL supports the execution of several multi-threaded applications within the same compute node, performs asynchronous execution of application tasks, efficiently balances computation across hardware resources, and provides performance portability. We show that code developed on a personal desktop automatically scales up to fully utilize powerful workstations with 8 GPUs and down to power-efficient embedded systems. MCL provides up to 17.5x speedup over OpenCL on NVIDIA DGX-1 systems and up to 1.88x speedup on single-GPU systems. In multi-application workloads, MCL dynamically resource allocation provides up to 2.43x performance improvement over manual, static allocation of computing resources.

Gioiosa, Roberto↗
DOE OSTI2020

ddcMD: A fully GPU-accelerated molecular dynamics program for the Martini force field

We have implemented the Martini force field within Lawrence Livermore National Laboratory’s molecular dynamics program, ddcMD. The program is extended to a heterogeneous programming model so that it can exploit graphics processing unit (GPU) accelerators. In addition to the Martini force field being ported to the GPU, the entire integration step, including thermostat, barostat, and constraint solver, is ported as well, which speeds up the simulations to 278-fold using one GPU vs one central processing unit (CPU) core. A benchmark study is performed with several test cases, comparing ddcMD and GROMACS Martini simulations. The average performance of ddcMD for a protein–lipid simulation system of 136k particles achieves 1.04 µs/day on one NVIDIA V100 GPU and aggregates 6.19 µs/day on one Summit node with six GPUs. The GPU implementation in ddcMD offloads all computations to the GPU and only requires one CPU core per simulation to manage the inputs and outputs, freeing up remaining CPU resources on the compute node for alternative tasks often required in complex simulation campaigns.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2023

Porting fragmentation methods to GPUs using an OpenMP API: Offloading the resolution-of-the-identity second-order Møller–Plesset perturbation method

Here, using an OpenMP Application Programming Interface, the resolution-of-the-identity second-order Møller–Plesset perturbation (RI-MP2) method has been off-loaded onto graphical processing units (GPUs), both as a standalone method in the GAMESS electronic structure program and as an electron correlation energy component in the effective fragment molecular orbital (EFMO) framework. First, a new scheme has been proposed to maximize data digestion on GPUs that subsequently linearizes data transfer from central processing units (CPUs) to GPUs. Second, the GAMESS Fortran code has been interfaced with GPU numerical libraries (e.g., NVIDIA cuBLAS and cuSOLVER) for efficient matrix operations (e.g., matrix multiplication, matrix decomposition, and matrix inversion). The standalone GPU RI-MP2 code shows an increasing speedup of up to 7.5× using one NVIDIA V100 GPU with one IBM 42-core P9 CPU for calculations on fullerenes of increasing size from 40 to 260 carbon atoms using the 6-31G(d)/cc-pVDZ-RI basis sets. A single Summit node with six V100s can compute the RI-MP2 correlation energy of a cluster of 175 water molecules using the correlation consistent basis sets cc-pVDZ/cc-pVDZ-RI containing 4375 atomic orbitals and 14 700 auxiliary basis functions in ~0.85 h. In the EFMO framework, the GPU RI-MP2 component shows near linear scaling for a large number of V100s when computing the energy of an 1800-atom mesoporous silica nanoparticle in a bath of 4000 water molecules. The parallel efficiencies of the GPU RI-MP2 component with 2304 and 4608 V100s are 98.0% and 96.1%, respectively.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2018

Standardizing GPU Radiation Test Approaches

While some Graphical Processing Units (GPUs) are discrete components (i.e.GTX1050), others take the form of an IP block or embedded engine within a System on Chip (SoC) device such as the Qualcomm Snapdragon"TM" 820 which contains a Qualcomm Adreno"TM" 530 GPU. Within this device are various functional blocks which can be exercised with software payloads. NVidia's Jetson"TM" TX1 SoC is provided on a System on Module (SOM). Within it are Central Processing Unit (CPU) cores and an nVidia GPU which can be accessed similarly to a discrete GPU coprocessor. While the packaging is different, each one of these GPUs needs to be tested using the same standardized code.

Single Event Effects (SEE)↗
NASA NTRS2020

NASA GPU Hackathon Yields Significant Code Improvements

The NASA GPU Hackathon 2020 brought together application developers and computer experts to help get important NASA applications running effectively on graphics processing unit (GPU) nodes. Nine teams of application developers participated in this virtual event, a major impetus for teams to modernize codes of interest for NASA missions to CPU nodes containing GPU accelerators, with a focus on hands-on problem solving. The photo in Figure1 shows 30 of the more than50 participants. The HECC project and NVIDIA jointly organized the event, and HECC provided five Pleiades nodes each with 4 V100 GPUs for teams to use. The virtual event, which took place over four days from September 28–October 7, 2020, used Microsoft Teams and Slack as collaboration tools. Each team consisted of three to six members from NASA Centers and supporting organizations. The teams were paired with one to two mentors from industry, government, and academia. The experience levels of the teams ranged from being GPU novices to advanced CUDA programming experts. OpenACC and the emerging Kokkos API were used in addition to CUDA for GPU programming. During the event, which focused on accelerating AeroSciences and CFD applications, most teams achieved considerable performance improvements on both GPUs and CPUs. For example, a team with no GPU experience completed a first port of a time-critical loop to a GPU. Another team of expert CUDA programmers were able to restructure their algorithm, yielding a factor of five speed-up. And another team sped up some of their CUDA kernels by a factor of 20, which directly translated into their production code. This article highlights some of the many successes resulting from the event.

HECC↗
DOE OSTI2020

Performance Assessment of AFQMC Implementation (ECP Milestone 5.2 Report)

The auxiliary field quantum Monte Carlo algorithm in QMCPACK was ported to run on AMD GPUs using HIP. Initial performance measurements on early access hardware indicate a 4x slowdown compared to NVIDIA V100s. The slowdown was determined to be a result of suboptimal ROCM libraries for small matrix sizes coupled with some poorly performing hipified CUDA kernels. Through a preliminary analysis of HIP kernel performance we determined a strategy for pro ling and tuning kernels. We request that ROCM libraries are optimized for smaller problem sizes particularly for batched operations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Spy in the GPU-box: Covert and Side Channel Attacks on Multi-GPU System

The deep learning revolution has been enabled in large part by GPUs, and more recently accelerators, which make it possible to carry out computationally demanding training and inference in acceptable times. As the size of machine learning networks and workloads continues to increase, multi-GPU machines have emerged as an important platform offered on High Performance Computing and cloud data centers. Since these machines are shared among multiple users, it becomes increasingly important to protect applications against potential attacks. In this paper, we explore the vulnerability of Nvidia's DGX multi-GPU machines to covert and side channel attacks. These machines consist of a number of discrete GPUs that are interconnected through a combination of custom interconnect (NVLink) and PCIe connections. We reverse engineer the interconnected cache hierarchy and show that it is possible for an attacker on one GPU to cause contention on the L2 cache of another GPU. We use this observation to first develop a covert channel attack across two GPUs, achieving the best bandwidth of around 4 MB/s. We also develop a prime and probe attack on a remote GPU allowing an attacker to recover the cache access pattern of another workload. This access pattern can be used in any number of side channel attacks: we demonstrate a proof of concept attack that fingerprints the application running on the remote GPU, with high accuracy. We also develop a proof of concept attack to extract hyperparameters of a machine learning workload. Our work establishes for the first time the vulnerability of these machines to microarchitectural attacks and can guide future research to improve their security.

Dutta, Sankha↗
DOE OSTI2022

VWC-BERT: Scaling Vulnerability–Weakness–Exploit Mapping on Modern AI Accelerators

Defending cybersystems needs accurate mapping of software and hardware vulnerabilities to generalized descriptions of weaknesses, and weaknesses to exploits. These mappings enable cyber defenders to build plans for effective defense and assessment of potential risks to a cybersystem. With close to 170k vulnerabilities, manual mapping is not a feasible option. However, automated mapping is challenging due to limited training data, computational intractability, and limitations in computational natural language processing. Tools based on breakthroughs in Transformer-based language models have been demonstrated to classify vulnerabilities with high accuracy. We make three key contributions in this paper: (1) We present a new framework, \VWCBERT, that augments the Transformer-based hierarchical multi-class classification framework of Das et al. (\textsc{V2W-BERT}) with the ability to map weaknesses to exploits. (2) We implement \VWCBERT~ on modern AI accelerator platforms using two data parallel techniques for the pre-training phase and demonstrate nearly linear speedups across NVIDIA and Graphcore accelerator platforms. We observe nearly linear speedups for up to 16 V100 and 8 A100 GPUs, and about 3.4$\times$ speedup for A100 relative to V100 GPUs. We also observe excellent speedups on Graphcore, with $5.7\times$ speedup on 128 IPUs relative to 16 IPUs. Enabled by scaling, we also demonstrate higher accuracy using a larger language model, RoBERTa-Large. We show up to 87\% accuracy for strict and up to 98\% accuracy for relaxed classification. (3) We develop a novel parallel link manager for the link prediction phase and demonstrate up to 21$\times$ speedup with 16 V100 GPUs relative to one V100 GPU, and thus reducing the runtime from 2.5 hours to 10 minutes. We believe that generalizability and scalability of \VWCBERT~ will benefit both the theoretical development and practical deployment of novel cyberdefense solutions and vulnerability classification.

Das, Siddhartha Shankar↗
NASA NTRS2011

GPU Accelerated Vector Median Filter

Noise reduction is an important step for most image processing tasks. For three channel color images, a widely used technique is vector median filter in which color values of pixels are treated as 3-component vectors. Vector median filters are computationally expensive; for a window size of n x n, each of the n(sup 2) vectors has to be compared with other n(sup 2) - 1 vectors in distances. General purpose computation on graphics processing units (GPUs) is the paradigm of utilizing high-performance many-core GPU architectures for computation tasks that are normally handled by CPUs. In this work. NVIDIA's Compute Unified Device Architecture (CUDA) paradigm is used to accelerate vector median filtering. which has to the best of our knowledge never been done before. The performance of GPU accelerated vector median filter is compared to that of the CPU and MPI-based versions for different image and window sizes, Initial findings of the study showed 100x improvement of performance of vector median filter implementation on GPUs over CPU implementations and further speed-up is expected after more extensive optimizations of the GPU algorithm .

Aras, Rifat↗
DOE OSTI2024

CaTS: Integration of Geant4 and Opticks

CaTS [6]is an advanced example that is part of Geant4 since version 11.0. It demonstrates the use of Opticks to offload the simulation of optical photons to GPUs. Opticks interfaces with the Geant4 toolkit to collect all the necessary information to generate and trace optical photons, re-implements the optical physics processes to be run on the GPU, and automatically translates the Geant4 geometry into a GPU appropriate format. To trace the photons, Opticks uses NVIDIA OptiX®. In this report, we describe CaTS and the integration of Opticks with Geant4. We demonstrate that the generation and tracing of optical photons represents an ideal application to be offloaded to GPUs, fully utilizing the high degree of available parallelism. In a typical liquid argon TPC simulation, a speedup of several hundred times is observed compared to an equivalent simulation using single threaded Geant4.

Wenzel, Hans↗
DOE OSTI2024

Application of performance portability solutions for GPUs and many-core CPUs to track reconstruction kernels

Next generation High-Energy Physics (HEP) experiments are presented with significant computational challenges, both in terms of data volume and processing power. Using compute accelerators, such as GPUs, is one of the promising ways to provide the necessary computational power to meet the challenge. The current programming models for compute accelerators often involve using architecture-specific programming languages promoted by the hardware vendors and hence limit the set of platforms that the code can run on. Developing software with platform restrictions is especially unfeasible for HEP communities as it takes significant effort to convert typical HEP algorithms into ones that are efficient for compute accelerators. Multiple performance portability solutions have recently emerged and provide an alternative path for using compute accelerators, which allow the code to be executed on hardware from different vendors. We apply several portability solutions, such as Kokkos, SYCL, C++17 std::execution::par, Alpaka, and OpenMP/OpenACC, on two mini-apps extracted from the mkFit project: p2z and p2r. These apps include basic kernels for a Kalman filter track fit, such as propagation and update of track parameters, for detectors at a fixed z or fixed r position, respectively. The two mini-apps explore different memory layout formats. We report on the development experience with different portability solutions, as well as their performance on GPUs and many-core CPUs, measured as the throughput of the kernels from different GPU and CPU vendors such as NVIDIA, AMD and Intel.

Kwok, Ka Hei Martin↗
DOE OSTI2024

Application of performance portability solutions for GPUs and many-core CPUs to track reconstruction kernels

Next generation High-Energy Physics (HEP) experiments are presented with significant computational challenges, both in terms of data volume and processing power. Using compute accelerators, such as GPUs, is one of the promising ways to provide the necessary computational power to meet the challenge. The current programming models for compute accelerators often involve using architecture-specific programming languages promoted by the hardware vendors and hence limit the set of platforms that the code can run on. Developing software with platform restrictions is especially unfeasible for HEP communities as it takes significant effort to convert typical HEP algorithms into ones that are efficient for compute accelerators. Multiple performance portability solutions have recently emerged and provide an alternative path for using compute accelerators, which allow the code to be executed on hardware from different vendors. We apply several portability solutions, such as Kokkos, SYCL, C++17 std::execution::par and Alpaka, on two mini-apps extracted from the mkFit project: p2z and p2r. These apps include basic kernels for a Kalman filter track fit, such as propagation and update of track parameters, for detectors at a fixed z or fixed r position, respectively. The two mini-apps explore different memory layout formats. We report on the development experience with different portability solutions, as well as their performance on GPUs and many-core CPUs, measured as the throughput of the kernels from different GPU and CPU vendors such as NVIDIA, AMD and Intel.

Kwok, Ka Martin↗
DOE OSTI2023

CSPlib: A performance portable parallel software toolkit for analyzing complex kinetic mechanisms

Computational singular perturbation (CSP) is a method to analyze dynamical systems. It targets the decoupling of fast and slow dynamics using an alternate linear expansion of the right-hand side of the governing equations based on eigenanalysis of the associated Jacobian matrix. This representation facilitates diagnostic analysis, detection and control of stiffness, and the development of simplified models. For this work, we have implemented CSP in a C++ open-source library CSPlib using the Kokkos parallel programming model to address portability across diverse heterogeneous computing platforms, i.e., multi/many-core CPUs and GPUs. We describe the CSPlib implementation and present its computational performance across different computing platforms using several test problems. Specifically, we test the CSPlib performance for a constant pressure ignition reactor model on different architectures, including IBM Power 9, Intel Xeon Skylake, and NVIDIA V100 GPU. The size of the chemical kinetic mechanism is varied in these tests. As expected, the Jacobian matrix evaluation, the eigensolution of the Jacobian matrix, and matrix inversion are the most expensive computational tasks. When considering the higher throughput characteristic of GPUs, GPUs performs better for small matrices with higher occupancy rate. CPUs gain more advantages from the higher performance of well-tuned and optimized linear algebra libraries such as OpenBLAS.

97 MATHEMATICS AND COMPUTING↗
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 OSTI2024

Efficient Mixed-Precision Matrix Factorization of the Inverse Overlap Matrix in Electronic Structure Calculations with AI-Hardware and GPUs

In recent years, a new kind of accelerated hardware has gained popularity in the artificial intelligence (AI) community which enables extremely high-performance tensor contractions in reduced precision for deep neural network calculations. In this article, we exploit Nvidia Tensor cores, a prototypical example of such AI-hardware, to develop a mixed precision approach for computing a dense matrix factorization of the inverse overlap matrix in electronic structure theory, S –1 . This factorization of S –1 , written as ZZT = S –1 , is used to transform the general matrix eigenvalue problem into a standard matrix eigenvalue problem. Here we present a mixed precision iterative refinement algorithm where Z is given recursively using matrix–matrix multiplications and can be computed with high performance on Tensor cores. To understand the performance and accuracy of Tensor cores, comparisons are made to GPU-only implementations in single and double precision. Additionally, we propose a nonparametric stopping criteria which is robust in the face of lower precision floating point operations. The algorithm is particularly useful when we have a good initial guess to Z, for example, from previous time steps in quantum-mechanical molecular dynamics simulations or from a previous iteration in a geometry optimization.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Revisiting Huffman Coding: Toward Extreme Performance on Modern GPU Architectures

Today's high-performance computing (HPC) applications are producing vast volumes of data, which are challenging to store and transfer efficiently during the execution, such that data compression is becoming a critical technique to mitigate the storage burden and data movement cost. Huffman coding is arguably the most efficient Entropy coding algorithm in information theory, such that it could be found as a fundamental step in many modern compression algorithms such as DEFLATE. On the other hand, today's HPC applications are more and more relying on the accelerators such as GPU on supercomputers, while Huffman encoding suffers from low throughput on GPUs, resulting in a significant bottleneck in the entire data processing. In this paper, we propose and implement an efficient Huffman encoding approach based on modern GPU architectures, which addresses two key challenges: (1) how to parallelize the entire Huffman encoding algorithm, including codebook construction, and (2) how to fully utilize the high memory-bandwidth feature of modern GPU architectures. The detailed contribution is fourfold. (1) We develop an efficient parallel codebook construction on GPUs that scales effectively with the number of input symbols. (2) We propose a novel reduction based encoding scheme that can efficiently merge the codewords on GPUs. (3) We optimize the overall GPU performance by leveraging the state-of-the-art CUDA APIs such as Cooperative Groups. (4) We evaluate our Huffman encoder thoroughly using six real-world application datasets on two advanced GPUs and compare with our implemented multithreaded Huffman encoder. Experiments show that our solution can improve the encoding throughput by up to 5.0× and 6.8× on NVIDIA RTX 5000 and V100, respectively, over the state-of-the-art GPU Huffman encoder, and by up to 3.3× over the multithread encoder on two 28-core Xeon Platinum 8280 CPUs.

Tian, Jiannan↗
DOE OSTI2024

Acceleration of Graph Neural Network-Based Prediction Models in Chemistry via Co-Design Optimization on Intelligence Processing Units

Atomic structure prediction and associated property calculations are the bedrock of chemical physics. Since high-fidelity ab initio modeling techniques for computing the structure and properties can be prohibitively expensive, this motivates the development of machine-learning (ML) models that make these predictions more efficiently. Training graph neural networks over large atomistic databases introduces unique computational challenges such as the need to process millions of small graphs with variable size and support communication patterns that are distinct from learning over large graphs such as social networks. We demonstrate a novel hardware-software co-design approach to scale up the training of atomistic graph neural networks (GNN) for structure and property prediction. First, to eliminate redundant computation and memory associated with alternative padding techniques and to improve throughput via minimizing communication, we formulate the effective coalescing of the batches of variable-size atomistic graphs as the bin packing problem and introduce a hardware-agnostic algorithm to pack these batches. In addition, we propose hardware-specific optimizations including a planner and vectorization for the gather-scatter operations targeted for Graphcore’s Intelligence Processing Unit (IPU), as well as model-specific optimizations such as merged communication collectives and optimized softplus. Putting these all together, we demonstrate the effectiveness of the proposed co-design approach by providing an implementation of a well-established atomistic GNN on the Graphcore IPUs. We evaluate the training performance on multiple atomistic graph databases with varying degrees of graph counts, sizes and sparsity. Here, we demonstrate that such a co-design approach can reduce the training time of atomistic GNNs and can improve the performance by up to 1.5× compared to the baseline implementation of the model on the IPUs. Additionally, we compare our IPU implementation with a Nvidia GPU-based implementation and show that our atomistic GNN implementation on the IPUs can run 1.8× faster on average compared to the execution time on the GPUs.

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

Design and analysis of CXL performance models for tightly-coupled heterogeneous computing

Truly heterogeneous systems enable partitioned workloads to be mapped to the hardware that nets the best performance. However, current practice requires that inter-device communication between different vendors' hardware use host memory as an intermediary step. To date, there are no widely adopted solutions that allow accelerators to directly transfer data. A new cache-coherent protocol, CXL, aims to facilitate easier, fine-grained sharing between accelerators. In this work we analyze existing methods for designing heterogeneous applications that target GPUs and FPGAs working collaboratively, followed by an exploration to show the benefits of a CXL-enabled system. Specifically, we develop a test application that utilizes both an NVIDIA P100 GPU and a Xilinx U250 FPGA to show current communication limitations. From this application, we capture overall execution time and throughput measurements on the FPGA and GPU. We use these measurements as inputs to novel CXL performance models to show that using CXL caching instead of host memory results in a 1.31X speedup, while a more tightly-coupled pipelined implementation using CXL-enabled hardware would result in a speedup of 1.45X.

Cabrera, Anthony↗