Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “GPU acceleration”

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 847 records · Page 47

3D-ReG: A 3D ReRAM-based Heterogeneous Architecture for Training Deep Neural Networks

Deep neural network (DNN) models are being expanded to a broader range of applications. The computational capability of traditional hardware platforms cannot accommodate the growth of model complexity. Among recent technologies to accelerate DNN, resistive memory (ReRAM)-based processing-in-memory (PIM) emerged as a promising solution for DNN inference due to its high efficiency for matrix-based computation. We face two major technical challenges in extending the use of ReRAM-based accelerators for training: (1) full-precision data is essential in back-propagation; (2) the need to support both feed-forward and back-propagation aggravates the data-movement burden. We propose a heterogeneous architecture named as 3D-ReG, which leverages full-precision GPU to ensure training accuracy and low-overhead 3D integration to provide low-cost data movements. Moreover, we introduce conservative and aggressive task-mapping schemes, which partition the computation phases in different ways to balance execution efficiency and training accuracy. We evaluate 3D-ReG implemented with two 3D integration technologies, through-silicon vias (TSVs) and monolithic inter-tier vias (MIVs), and compare them with GPU-only and PIM-only counterparts. Various GPU-only platforms using two main-memory technologies (DRAM, ReRAM) and three interconnect technologies (2D, TSV, MIV) are evaluated as well. Experimental results show that 3D-ReG can achieve on average 5.64× training speedup and 3.56× higher energy efficiency compared with the GPU with DRAM as main memory, at the cost of 0.05%–3.39% accuracy drop. We define a new metric, gain-loss ratio (GLR), which quantitatively evaluates the capability of a DNN training hardware in terms of the model accuracy and hardware efficiency. The results of our comparison show that the aggressive task-mapping scheme on MIV-based 3D-ReG outperforms the other methods.

Computer Science↗

Massively parallel GPU enabled third-order cluster perturbation excitation energies for cost-effective large scale excitation energy calculations

We present here a massively parallel implementation of the recently developed CPS(D-3) excitation energy model that is based on cluster perturbation theory. The new algorithm extends the one developed in Baudin et al. [J. Chem. Phys., 150, 134110 (2019)] to leverage multiple nodes and utilize graphical processing units for the acceleration of heavy tensor contractions. Furthermore, we show that the extended algorithm scales efficiently with increasing amounts of computational resources and that the developed code enables CPS(D-3) excitation energy calculations on large molecular systems with a low time-to-solution. More specifically, calculations on systems with over 100 atoms and 1000 basis functions are possible in a few hours of wall clock time. This establishes CPS(D-3) excitation energies as a computationally efficient alternative to those obtained from the coupled-cluster singles and doubles model.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

GPU-optimized Code for Long-term Simulations of Beam-beam Effects in Colliders

We report on the development of the new code for long-term simulation of beam-beam effects in particle colliders. The underlying physical model relies on a matrix-based arbitrary-order symplectic particle tracking for beam transport and the Bassetti-Erskine approximation for beam-beam interaction. The computations are accelerated through a parallel implementation on a hybrid GPU/CPU platform. With the new code, a previously computationally prohibitive long-term simulations become tractable. We use the new code to model the proposed medium-energy electron-ion collider (MEIC) at Jefferson Lab.

43 PARTICLE ACCELERATORS↗

TU-AB-BRC-11: Moving a GPU-OpenCL-Based Monte Carlo (MC) Dose Engine Towards Routine Clinical Use: Automatic Beam Commissioning and Efficient Source Sampling

Purpose: We have previously developed a GPU-OpenCL-based MC dose engine named goMC with built-in analytical linac beam model. To move goMC towards routine clinical use, we have developed an automatic beam-commissioning method, and an efficient source sampling strategy to facilitate dose calculations for real treatment plans. Methods: Our commissioning method is to automatically adjust the relative weights among the sub-sources, through an optimization process minimizing the discrepancies between calculated dose and measurements. Six models built for Varian Truebeam linac photon beams (6MV, 10MV, 15MV, 18MV, 6MVFFF, 10MVFFF) were commissioned using measurement data acquired at our institution. To facilitate dose calculations for real treatment plans, we employed inverse sampling method to efficiently incorporate MLC leaf-sequencing into source sampling. Specifically, instead of sampling source particles control-point by control-point and rejecting the particles blocked by MLC, we assigned a control-point index to each sampled source particle, according to MLC leaf-open duration of each control-point at the pixel where the particle intersects the iso-center plane. Results: Our auto-commissioning method decreased distance-to-agreement (DTA) of depth dose at build-up regions by 36.2% averagely, making it within 1mm. Lateral profiles were better matched for all beams, with biggest improvement found at 15MV for which root-mean-square difference was reduced from 1.44% to 0.50%. Maximum differences of output factors were reduced to less than 0.7% for all beams, with largest decrease being from1.70% to 0.37% found at 10FFF. Our new sampling strategy was tested on a Head&Neck VMAT patient case. Achieving clinically acceptable accuracy, the new strategy could reduce the required history number by a factor of ∼2.8 given a statistical uncertainty level and hence achieve a similar speed-up factor. Conclusion: Our studies have demonstrated the feasibility and effectiveness of our auto-commissioning approach and new efficient source sampling strategy, implying the potential of our GPU-based MC dose engine goMC for routine clinical use.

61 RADIATION PROTECTION AND DOSIMETRY↗

Brookhaven Lab Hosts Hackathon Focused on Graphics Processing Units (GPUs)

For five days in June 2017, Brookhaven Lab’s Computational Science Initiative hosted “Brookathon”—a programming workshop where teams of researchers, students, and software developers worked with mentors to accelerate scientific applications on GPUs for high-performance computing.

97 MATHEMATICS AND COMPUTING↗

Towards the clinical implementation of iterative low-dose cone-beam CT reconstruction in image-guided radiation therapy: Cone/ring artifact correction and multiple GPU implementation

Purpose: Compressed sensing (CS)-based iterative reconstruction (IR) techniques are able to reconstruct cone-beam CT (CBCT) images from undersampled noisy data, allowing for imaging dose reduction. However, there are a few practical concerns preventing the clinical implementation of these techniques. On the image quality side, data truncation along the superior–inferior direction under the cone-beam geometry produces severe cone artifacts in the reconstructed images. Ring artifacts are also seen in the half-fan scan mode. On the reconstruction efficiency side, the long computation time hinders clinical use in image-guided radiation therapy (IGRT). Methods: Image quality improvement methods are proposed to mitigate the cone and ring image artifacts in IR. The basic idea is to use weighting factors in the IR data fidelity term to improve projection data consistency with the reconstructed volume. In order to improve the computational efficiency, a multiple graphics processing units (GPUs)-based CS-IR system was developed. The parallelization scheme, detailed analyses of computation time at each step, their relationship with image resolution, and the acceleration factors were studied. The whole system was evaluated in various phantom and patient cases. Results: Ring artifacts can be mitigated by properly designing a weighting factor as a function of the spatial location on the detector. As for the cone artifact, without applying a correction method, it contaminated 13 out of 80 slices in a head-neck case (full-fan). Contamination was even more severe in a pelvis case under half-fan mode, where 36 out of 80 slices were affected, leading to poorer soft tissue delineation and reduced superior–inferior coverage. The proposed method effectively corrects those contaminated slices with mean intensity differences compared to FDK results decreasing from ∼497 and ∼293 HU to ∼39 and ∼27 HU for the full-fan and half-fan cases, respectively. In terms of efficiency boost, an overall 3.1 × speedup factor has been achieved with four GPU cards compared to a single GPU-based reconstruction. The total computation time is ∼30 s for typical clinical cases. Conclusions: The authors have developed a low-dose CBCT IR system for IGRT. By incorporating data consistency-based weighting factors in the IR model, cone/ring artifacts can be mitigated. A boost in computational efficiency is achieved by multi-GPU implementation.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

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↗

FunMC^2: A Filter for Uncertainty Visualization of Marching Cubes on Multi-Core Devices

Visualization is an important tool for scientists to extract understanding from complex scientific data. Scientists need to understand the uncertainty inherent in all scientific data in order to interpret the data correctly. Uncertainty visualization has been an active and growing area of research to address this challenge. Algorithms for uncertainty visualization can be expensive, and research efforts have been focused mainly on structured grid types. Further, support for uncertainty visualization in production tools is limited. In this paper, we adapt an algorithm for computing key metrics for visualizing uncertainty in Marching Cubes (MC) to multi-core devices and present the design, implementation, and evaluation for a Filter for uncertainty visualization of Marching Cubes on Multi-Core devices (FunMC2). FunMC2 accelerates the uncertainty visualization of MC significantly, and it is portable across multi-core CPUs and GPUs. Evaluation results show that FunMC2 based on OpenMP runs around 11× to 41× faster on multi-core CPUs than the corresponding serial version using one CPU core. FunMC2 based on a single GPU is around 5× to 9× faster than FunMC2 running by OpenMP. Moreover, FunMC2 is flexible enough to process ensemble data with both structured and unstructured mesh types. Furthermore, we demonstrate that FunMC2 can be seamlessly integrated as a plugin into ParaView, a production visualization tool for post-processing.

Wang, Jay↗

MONTE CARLO CROSS SECTION LOOKUP KERNEL FOR THE CEREBRAS WSE-2 IN CSL

This is a small kernel that was used to collect data for an upcoming paper. We would like to have the code be open source so that the reviewers (and then readers) of the paper can see the whole code, and can reproduce/verify our results. This is not a fully featured application, it cannot produce any useful simulation results, it just executes a small abstracted kernel using synthetic data. The purpose of the kernel is to understand the basic performance characteristics of an HPC kernel on novel AI accelerator architectures. The main kernel is written in the CSL coding language for use with the Cerebras WSE-2 AI accelerator. The kernel represented is the Monte Carlo cross section lookup kernel, which is a small kernel used by the Monte Carlo neutral particle transport algorithm. There is also a baseline kernel written in CUDA that we will include in the repository to form a basis for comparing the WSE-2 to GPU.

Tramm, John↗

Continuous Flow Processing of ZIF-8 Membranes on Polymeric Porous Hollow Fiber Supports for CO 2 Capture

We have utilized an environmentally friendly synthesis approach for the accelerated growth of a selective inorganic membrane on a polymeric hollow fiber support for postcombustion carbon capture. Specifically, continuous defect-free ZIF-8 thin films were grown and anchored using continuous flow synthesis on the outer surface of porous supports using water as solvent. These membranes demonstrated CO 2 permeance of 22 GPU and the highest reported CO 2 /N 2 selectivity of 52 for a continuous flow synthesized ZIF-8 membrane.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Performance Evaluation of Python Based Data Analytics Frameworks in Summit: Early Experiences

The explosion in the volumes of data generated from ever-larger simulation campaigns and experiments or observations necessitates competent tools for data wrangling and analysis). While the Oak Ridge Leadership Computing Facility (OLCF) provides a variety of tools to perform data wrangling and data analysis tasks, Python based tools often lack scalability, or the ability to fully exploit the computational capability of OLCF’s Summit supercomputer. NVIDIA RAPIDS and Dask offer a promising solution to accelerate and distribute data analytics workloads from personal computers to heterogeneous supercomputing systems. We discuss early performance evaluation results of RAPIDS and Dask on Summit to understand their capabilities, scalability, and limitations. Our evaluation includes a subset of RAPIDS libraries, i.e., cuDF, cuML, and cuGraph, and Chainer’s CuPy, and their multi-GPU variants when available.We also draw on the observed trends from the performance evaluation results to discuss best practices for maximizing performance.

Hernandez Arreguin, Benjamin↗

Accelerating Transformer-based Deep Learning Models on FPGAs using Column Balanced Block Pruning

Although Transformer-based language representations achieve state-of-the-art accuracy on various natural language processing (NLP) tasks, the large model size has been challenging the resource constrained computing platforms. Weight pruning, as a popular and effective technique in reducing the number of weight parameters and accelerating the Transformer, has been investigated on GPUs. However, the Transformer acceleration using weight pruning on field-programmable gate array (FPGAs) remains unexplored. This paper investigates the column balanced block-wise pruning on Transformer and designs an FPGA acceleration engine to customize the balanced blockwise matrix multiplication. We implement the Transformer model with proper hardware scheduling, and the experiments show that the Transformer inference on FPGA achieves 10.35 ms latency with the batch size of 32, which is 10.96 × speed up comparing to CPU platform and 2.08 × speed up comparing to GPU platform.

Peng, Hongwu↗

Acceleration of Streamed Tensor Contraction Expressions on GPGPU-based Clusters

Tensor contractions are generalized multidimensional matrix multiplication operations that widely occur in quantum chemistry. Efficient execution of tensor contractions on GPUs requires tackling several challenges to be addressed, including index permutation and small dimension-sizes reducing thread block utilization. In this paper, we present our approach to automatically generate CUDA code to execute tensor contractions on GPUs, including management of data movement between CPU and GPU. GPU-enabled code is generated for the most expensive contractions in CCSD(T) and incorporated into NWChem, a popular computational chemistry suite. We demonstrate speedup over a factor of 8.4 using one core per node and over 2.6 when utilizing the entire system using hybrid CPU+GPU solution with 2 GPUs and 5 cores. We finally analyze the behavior of the application on future GPU systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Design-to-Deployment Continuum Platform for Microscopes and Computing Ecosystems

Science ecosystems with networked computing systems and physical instruments are increasingly being deployed with a goal to achieve the productivity promised by AI-supported remote automation. In support of these efforts, the virtual infrastructure twins (VITs) have been successfully utilized to develop the orchestration codes for these ecosystems without requiring physical access to expensive instruments, such as electron microscopes. Currently, the utility of such a VIT is severely limited by the computing capacity and capability of the computing system used as its host. Furthermore, codes developed on the VIT typically need to be transferred and refactored for production use, particularly, on high-performance systems with accelerators. In response, we develop a design-to-deployment continuum platform wherein a VIT runs natively on the ecosystem's own computing system, and thereby facilitates the continual in-situ testing and transition of codes for production use. Here, we describe the development and testing of software for remote microscope steering and GPU-based image reconstruction using this platform on a multi-GPU computing system networked to Nion microscopes. We demonstrate a continual transition of steering and reconstruction codes developed under VIT platform to production ecosystem deployment.

Al-Najjar, Anees [Oak Ridge National Laboratory (O↗

High-Performance Multi-Mode Ptychography Reconstruction on Distributed GPUs

Abstract—Ptychography is an emerging imaging technique that is able to provide wavelength-limited spatial resolution from spec-imen with extended lateral dimensions. As a scanning microscopy method, a typical two-dimensional image requires a number of data frames. As a diffraction-based imaging technique, the real-space image has to be recovered through iterative reconstruction algorithms. Due to these two inherent aspects, a ptychographic reconstruction is generally a computation-intensive and time-consuming process, which limits the throughput of this method. We report an accelerated version of the multi-mode difference map algorithm for ptychography reconstruction using multiple distributed GPUs. This approach leverages available scientific computing packages in Python, including mpi4py and PyCUDA, with the core computation functions implemented in CUDA C. We find that interestingly even with MPI collective communications, the weak scaling in the number of GPU nodes can still remain nearly constant. Most importantly, for realistic diffraction measurements, we observe a speedup ranging from a factor of 10 to 103 depending on the data size, which reduces the reconstruction time remarkably from hours to typically about 1 minute and is thus critical for real-time data processing and visualization.

97 MATHEMATICS AND COMPUTING↗

Accelerating parameter inference with graphics processing units

Gravitational wave Bayesian parameter inference involves repeated comparisons of GW data to generic candidate predictions. Even with algorithmically efficient methods like RIFT or reduced-order quadrature, the time needed to perform these calculations and overall computational cost can be significant compared to the minutes to hours needed to achieve the goals of low-latency multimessenger astronomy. By translating some elements of the RIFT algorithm to operate on graphics processing units (GPU), we demonstrate substantial performance improvements, enabling dramatically reduced overall cost and latency.

97 MATHEMATICS AND COMPUTING↗

Performance tuning of CEED software and 1st and 2nd wave apps

The goal of this milestone was the performance tuning of the CEED software, as well as the use and tuning of CEED to accelerate the first and second wave of targeted ECP applications. In this milestone, the CEED team developed optimization techniques and tuned for performance the CEED software to accelerate the first and second wave target ECP applications. Specifically, the focus was on the following: (1) Efficient use of the memory sub-system for managing data motion and interactions among different physics packages and libraries; this included integration of the new developments in a libCEED 0.5 software release; (2) Enhancing the CEED libraries with GPU and AMD GPU support in close interaction with vendors; (3) Optimal data locality and motion, and enhanced scalability and parallelism; this included vendors interactions for improvements in data motion and making strong scaling easier and more efficient; and (4) Continue boosting performance for the first-wave and second-wave of ECP target applications, including ExaSMR, ExaWind, Urban, MARBL, E3SM, and ExaAM. A main part of this milestone was the performance tuning of the CEED first-wave and second-wave ECP applications. This included the ExaSMR application – Coupled Monte Carlo Neutronics and Fluid Flow Simulation of Small Modular Reactors (ORNL), the MARBL application – Next-Gen Multi-physics Simulation Code (LLNL), and the ExaAM ExaConstit – a miniapp for the Transforming Additive Manufacturing through Exascale Simulation applications project (ExaAM), as well as ExaWind, Urban, and E3SM. The artifacts delivered include performance improvements in CEED’s 1st and 2nd wave of applications, and tuned CEED software for various architectures through a number of backends, freely available in the CEED’s repository on GitHub. See the CEED website, http://ceed.exascaleproject.org and the CEED GitHub organization, http://github.com/ceed for more details. In addition to details and results from the above R&D efforts, in this document we are also reporting on other project-wide activities performed in Q4 of FY19 including: CEED’s third annual meeting, MFEM GPU kernels scaling improvements, libCEED 0.5 and NekRS releases, an overview paper covering latest results on a set of bake-off high-order finite element problems (BPs), and other outreach efforts.

97 MATHEMATICS AND COMPUTING↗