Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “CUDA”

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 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2015

SU-E-T-112: An OpenCL-Based Cross-Platform Monte Carlo Dose Engine (oclMC) for Coupled Photon-Electron Transport

Purpose: Low computational efficiency of Monte Carlo (MC) dose calculation impedes its clinical applications. Although a number of MC dose packages have been developed over the past few years, enabling fast MC dose calculations, most of these packages were developed under NVidia’s CUDA environment. This limited their code portability to other platforms, hindering the introduction of GPU-based MC dose engines to clinical practice. To solve this problem, we developed a cross-platform fast MC dose engine named oclMC under OpenCL environment for external photon and electron radiotherapy. Methods: Coupled photon-electron simulation was implemented with standard analogue simulation scheme for photon transport and Class II condensed history scheme for electron transport. We tested the accuracy and efficiency of oclMC by comparing the doses calculated using oclMC and gDPM, a previously developed GPU-based MC code on NVidia GPU platform, for a 15MeV electron beam and a 6MV photon beam in a homogenous water phantom, a water-bone-lung-water slab phantom and a half-slab phantom. We also tested code portability of oclMC on different devices, including an NVidia GPU, two AMD GPUs and an Intel CPU. Results: Satisfactory agreements were observed in all photon and electron cases, with ∼0.48%–0.53% average dose differences at regions within 10% isodose line for electron beam cases and ∼0.15%–0.17% for photon beam cases. It took oclMC 3–4 sec to perform transport simulation for electron beam on NVidia Titan GPU and 35–51 sec for photon beam, both with ∼0.5% statistical uncertainty. The computation was 6%–17% slower than gDPM due to the differences in both physics model and development environment, which is considered not significant for clinical applications. In terms of code portability, gDPM only runs on NVidia GPUs, while oclMC successfully runs on all the tested devices. Conclusion: oclMC is an accurate and fast MC dose engine. Its high cross-platform portability makes it clinically attractive.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

A GPU-accelerated Monte Carlo dose calculation platform and its application toward validating an MRI-guided radiation therapy beam model

Purpose: The clinical commissioning of IMRT subject to a magnetic field is challenging. The purpose of this work is to develop a GPU-accelerated Monte Carlo dose calculation platform based on PENELOPE and then use the platform to validate a vendor-provided MRIdian head model toward quality assurance of clinical IMRT treatment plans subject to a 0.35 T magnetic field. Methods: PENELOPE was first translated from FORTRAN to C++ and the result was confirmed to produce equivalent results to the original code. The C++ code was then adapted to CUDA in a workflow optimized for GPU architecture. The original code was expanded to include voxelized transport with Woodcock tracking, faster electron/positron propagation in a magnetic field, and several features that make gPENELOPE highly user-friendly. Moreover, the vendor-provided MRIdian head model was incorporated into the code in an effort to apply gPENELOPE as both an accurate and rapid dose validation system. A set of experimental measurements were performed on the MRIdian system to examine the accuracy of both the head model and gPENELOPE. Ultimately, gPENELOPE was applied toward independent validation of patient doses calculated by MRIdian’s KMC. Results: An acceleration factor of 152 was achieved in comparison to the original single-thread FORTRAN implementation with the original accuracy being preserved. For 16 treatment plans including stomach (4), lung (2), liver (3), adrenal gland (2), pancreas (2), spleen(1), mediastinum (1), and breast (1), the MRIdian dose calculation engine agrees with gPENELOPE with a mean gamma passing rate of 99.1% ± 0.6% (2%/2 mm). Conclusions: A Monte Carlo simulation platform was developed based on a GPU- accelerated version of PENELOPE. This platform was used to validate that both the vendor-provided head model and fast Monte Carlo engine used by the MRIdian system are accurate in modeling radiation transport in a patient using 2%/2 mm gamma criteria. Future applications of this platform will include dose validation and accumulation, IMRT optimization, and dosimetry system modeling for next generation MR-IGRT systems.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

SU-C-BRC-07: Parametrized GPU Accelerated Electron Monte Carlo Second Check

Purpose: I am presenting a parameterized 3D GPU accelerated electron Monte Carlo second check program. Method: I wrote the 3D grid dose calculation algorithm in CUDA and utilized an NVIDIA GeForce GTX 780 Ti to run all of the calculations. The electron path beyond the distal end of the cone is governed by four parameters: the amplitude of scattering (AMP), the mean and width of a Gaussian energy distribution (E and α), and the percentage of photons. In my code, I adjusted all parameters until the calculated PDD and profile fit the measured 10×10 open beam data within 1%/1mm. I then wrote a user interface for reading the DICOM treatment plan and images in Python. In order to verify the algorithm, I calculated 3D dose distributions on a variety of phantoms and geometries, and compared them with the Eclipse eMC calculations. I also calculated several patient specific dose distributions, including a nose and an ear. Finally, I compared my algorithm’s computation times to Eclipse’s. Results: The calculated MU for all of the investigated geometries agree with the TPS within the TG-114 action level of 5%. The MU for the nose was < 0.5 % different while the MU for the ear at 105 SSD was ∼2 %. Calculation times for a 12MeV 10×10 open beam ranged from 1 second for a 2.5 mm grid resolution with ∼15 million particles to 33 seconds on a 1 mm grid with ∼460 million particles. Eclipse calculation runtimes distributed over 10 FAS workers were 9 seconds to 15 minutes respectively. Conclusion: The GPU accelerated second check allows quick MU verification while accounting for patient specific geometry and heterogeneity.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

SU-F-T-256: 4D IMRT Planning Using An Early Prototype GPU-Enabled Eclipse Workstation

Purpose: True 4D IMRT planning, based on simultaneous spatiotemporal optimization has been shown to significantly improve plan quality in lung radiotherapy. However, the high computational complexity associated with such planning represents a significant barrier to widespread clinical deployment. We introduce an early prototype GPU-enabled Eclipse workstation for inverse planning. To our knowledge, this is the first GPUintegrated Eclipse system demonstrating the potential for clinical translation of GPU computing on a major commercially-available TPS. Methods: The prototype system comprised of four NVIDIA Tesla K80 GPUs, with a maximum processing capability of 8.5 Tflops per K80 card. The system architecture consisted of three key modules: (i) a GPU-based inverse planning module using a highly-parallelizable, swarm intelligence-based global optimization algorithm, (ii) a GPU-based open-source b-spline deformable image registration module, Elastix, and (iii) a CUDA-based data management module. For evaluation, aperture fluence weights in an IMRT plan were optimized over 9 beams,166 apertures and 10 respiratory phases (14940 variables) for a lung cancer case (GTV = 95 cc, right lower lobe, 15 mm cranio-caudal motion). Sensitivity of the planning time and memory expense to parameter variations was quantified. Results: GPU-based inverse planning was significantly accelerated compared to its CPU counterpart (36 vs 488 min, for 10 phases, 10 search agents and 10 iterations). The optimized IMRT plan significantly improved OAR sparing compared to the original internal target volume (ITV)-based clinical plan, while maintaining prescribed tumor coverage. The dose-sparing improvements were: Esophagus Dmax 50%, Heart Dmax 42% and Spinal cord Dmax 25%. Conclusion: Our early prototype system demonstrates that through massive parallelization, computationally intense tasks such as 4D treatment planning can be accomplished in clinically feasible timeframes. With further optimization, such systems are expected to enable the eventual clinical translation of higher-dimensional and complex treatment planning strategies to significantly improve plan quality. This work was partially supported through research funding from National Institutes of Health (R01CA169102) and Varian Medical Systems, Palo Alto, CA, USA.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

SU-G-TeP1-15: Toward a Novel GPU Accelerated Deterministic Solution to the Linear Boltzmann Transport Equation

Purpose: To develop a Graphic Processor Unit (GPU) accelerated deterministic solution to the Linear Boltzmann Transport Equation (LBTE) for accurate dose calculations in radiotherapy (RT). A deterministic solution yields the potential for major speed improvements due to the sparse matrix-vector and vector-vector multiplications and would thus be of benefit to RT. Methods: In order to leverage the massively parallel architecture of GPUs, the first order LBTE was reformulated as a second order self-adjoint equation using the Least Squares Finite Element Method (LSFEM). This produces a symmetric positive-definite matrix which is efficiently solved using a parallelized conjugate gradient (CG) solver. The LSFEM formalism is applied in space, discrete ordinates is applied in angle, and the Multigroup method is applied in energy. The final linear system of equations produced is tightly coupled in space and angle. Our code written in CUDA-C was benchmarked on an Nvidia GeForce TITAN-X GPU against an Intel i7-6700K CPU. A spatial mesh of 30,950 tetrahedral elements was used with an S4 angular approximation. Results: To avoid repeating a full computationally intensive finite element matrix assembly at each Multigroup energy, a novel mapping algorithm was developed which minimized the operations required at each energy. Additionally, a parallelized memory mapping for the kronecker product between the sparse spatial and angular matrices, including Dirichlet boundary conditions, was created. Atomicity is preserved by graph-coloring overlapping nodes into separate kernel launches. The one-time mapping calculations for matrix assembly, kronecker product, and boundary condition application took 452±1ms on GPU. Matrix assembly for 16 energy groups took 556±3s on CPU, and 358±2ms on GPU using the mappings developed. The CG solver took 93±1s on CPU, and 468±2ms on GPU. Conclusion: Three computationally intensive subroutines in deterministically solving the LBTE have been formulated on GPU, resulting in two orders of magnitude speedup. Funding support from Natural Sciences and Engineering Research Council and Alberta Innovates Health Solutions. Dr. Fallone is a co-founder and CEO of MagnetTx Oncology Solutions (under discussions to license Alberta bi-planar linac MR for commercialization).

60 APPLIED LIFE SCIENCES↗
DOE OSTI2016

TH-AB-BRA-07: PENELOPE-Based GPU-Accelerated Dose Calculation System Applied to MRI-Guided Radiation Therapy

Purpose: The clinical commissioning of IMRT subject to a magnetic field is challenging. The purpose of this work is to develop a GPU-accelerated Monte Carlo dose calculation platform based on PENELOPE and then use the platform to validate a vendor-provided MRIdian head model toward quality assurance of clinical IMRT treatment plans subject to a 0.35 T magnetic field. Methods: We first translated PENELOPE from FORTRAN to C++ and validated that the translation produced equivalent results. Then we adapted the C++ code to CUDA in a workflow optimized for GPU architecture. We expanded upon the original code to include voxelized transport boosted by Woodcock tracking, faster electron/positron propagation in a magnetic field, and several features that make gPENELOPE highly user-friendly. Moreover, we incorporated the vendor-provided MRIdian head model into the code. We performed a set of experimental measurements on MRIdian to examine the accuracy of both the head model and gPENELOPE, and then applied gPENELOPE toward independent validation of patient doses calculated by MRIdian’s KMC. Results: We achieve an average acceleration factor of 152 compared to the original single-thread FORTRAN implementation with the original accuracy preserved. For 16 treatment plans including stomach (4), lung (2), liver (3), adrenal gland (2), pancreas (2), spleen (1), mediastinum (1) and breast (1), the MRIdian dose calculation engine agrees with gPENELOPE with a mean gamma passing rate of 99.1% ± 0.6% (2%/2 mm). Conclusions: We developed a Monte Carlo simulation platform based on a GPU-accelerated version of PENELOPE. We validated that both the vendor provided head model and fast Monte Carlo engine used by the MRIdian system are accurate in modeling radiation transport in a patient using 2%/2 mm gamma criteria. Future applications of this platform will include dose validation and accumulation, IMRT optimization, and dosimetry system modeling for next generation MR-IGRT systems.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2014

Features of the application of the Monte Carlo method to calculations for large RBMK reactors and to model correction on the basis of data from in-core detectors

Statistical errors in sampling neutron fields in physically large systems like an RBMK are analyzed both qualitatively and quantitatively. Recommendations concerning the choice of parameters for calculations are given. A new procedure for Monte Carlo RBMK calculations with model corrections on the basis of data from in-core detectors is proposed. Dedicated software based on the CUDA software and hardware platform is developed for computational research. Results of testing the procedure and software in question via calculations for real RBMK reactors are discussed.

74 ATOMIC AND MOLECULAR PHYSICS↗
DOE OSTI2023

GPU acceleration of Swendsen–Wang dynamics

When simulating a lattice system near its critical temperature, local algorithms for modeling the system’s evolution can introduce very large autocorrelation times into sampled data. Here, this critical slowing down places restrictions on the analysis that can be completed in a timely manner of the behavior of systems around the critical point. Because it is often desirable to study such systems around this point, a new algorithm must be introduced. Therefore, we turn to cluster algorithms, such as the Swendsen–Wang algorithm and the Wolff clustering algorithm. They incorporate global updates which generate new lattice configurations with little correlation to previous states, even near the critical point. We look to accelerate the rate at which these algorithm are capable of running by implementing and benchmarking a parallel implementation of each algorithm designed to run on GPUs under NVIDIA’s CUDA framework. A 17 and 90 fold increase in the computational rate was, respectively, experienced when measured against the equivalent algorithm implemented in serial code.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2013

Effective sampling-driven performance tools for GPU-accelerated supercomputers, In: SC '13 Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis

Performance analysis of GPU-accelerated systems requires a system-wide view that considers both CPU and GPU components. In this paper, we describe how to extend system-wide, sampling-based performance analysis methods to GPU-accelerated systems. Since current GPUs do not support sampling, our implementation required careful coordination of instrumentation-based performance data collection on GPUs with sampling-based methods employed on CPUs. In addition, we also introduce a novel technique for analyzing systemic idleness in CPU/GPU systems. We demonstrate the effectiveness of our techniques with application case studies on Titan and Keeneland. Some of the highlights of our case studies are: 1) we improved performance for LULESH 1.0 by 30%, 2) we identified a hardware performance problem on Keeneland, 3) we identified a scaling problem in LAMMPS derived from CUDA initialization, and 4) we identified a performance problem that is caused by GPU synchronization operations that suffer delays due to blocking system calls.

Computer Science↗
DOE OSTI2017

Improving Uintah's Scalability Through the Use of Portable Kokkos-Based Data Parallel Tasks

The University of Utah’s Carbon Capture Multidisciplinary Simulation Center (CCMSC) is using the Uintah Computational Framework to predict performance of a 1000 MWe ultra-supercritical clean coal boiler. The center aims to utilize the Intel Xeon Phi-based DOE systems, Theta and Aurora, through the Aurora Early Science Program by using the Kokkos C++ library to enable node-level performance portability. This paper describes infrastructure advancements and portability improvements made possible by the integration of Kokkos within Uintah. This integration marks a step towards consolidating Uintah’s MPI+PThreads and MPI+CUDA hybrid parallelism approaches into a single MPI+Kokkos approach. Scalability results are presented that compare serial and data parallel task execution models for a challenging radiative heat transfer calculation, central to the center’s predictive boiler simulations. Here, these results demonstrate both good strong-scaling characteristics to 256 Knights Landing (KNL) processors on the NSF Stampede system, and show the KNL-based calculation to compete with prior GPU-based results for the same calculation.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2017

WIREFRAME: Supporting Data-dependent Parallelism through Dependency Graph Execution in GPUs

GPUs lack fundamental support for data-dependent parallelism and synchronization. While CUDA Dynamic Parallelism signals progress in this direction, many limitations and challenges still re-main. This paper introducesWireframe, a hardware-software solution that enables generalized support for data-dependent parallelism and synchronization. Wireframe enables applications to naturally express execution dependencies across different thread blocks through a dependency graph abstraction at run-time, which is sent to the GPU hardware at kernel launch. At run-time, the hardware enforces the dependencies specified in the dependency graph through a dependency-aware thread block scheduler. Overall, Wireframe is able to improve total execution time up to 65.20% with an average of 45.07%.

Abdolrashidi, AmirAli↗
DOE OSTI2021

PAGANI: a parallel adaptive GPU algorithm for numerical integration

We present a new adaptive parallel algorithm for the challenging problem of multi-dimensional numerical integration on massively parallel architectures. Adaptive algorithms have demonstrated the best performance, but efficient many-core utilization is difficult to achieve because the adaptive work-load can vary greatly across the integration space and is impossible to predict a priori. Existing parallel algorithms utilize sequential computations on independent processors, which results in bottlenecks due to the need for data redistribution and processor synchronization. Our algorithm employs a high-throughput approach in which all existing sub-regions are processed and sub-divided in parallel. Repeated sub-region classification and filtering improves upon a brute-force approach and allows the algorithm to make efficient use of computation and memory resources. A CUDA implementation shows orders of magnitude speedup over the fastest open-source CPU method and extends the achievable accuracy for difficult integrands. Our algorithm typically outperforms other existing deterministic parallel methods.

Sakiotis, Ioannis↗
DOE OSTI2023

A Sparse Distributed Gigascale Resolution Material Point Method

In this paper, we present a four-layer distributed simulation system and its adaptation to the Material Point Method (MPM). The system is built upon a performance portable C++ programming model targeting major High-Performance-Computing (HPC) platforms. A key ingredient of our system is a hierarchical block-tile-cell sparse grid data structure that is distributable to an arbitrary number of Message Passing Interface (MPI) ranks. We additionally propose strategies for efficient dynamic load balance optimization to maximize the efficiency of MPI tasks. Our simulation pipeline can easily switch among backend programming models, including OpenMP and CUDA, and can be effortlessly dispatched onto supercomputers and the cloud. Finally, we construct benchmark experiments and ablation studies on supercomputers and consumer workstations in a local network to evaluate the scalability and load balancing criteria. We demonstrate massively parallel, highly scalable, and gigascale resolution MPM simulations of up to 1.01 billion particles for less than 323.25 seconds per frame with 8 OpenSSH-connected workstations.

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 OSTI2023

Performance Evaluation of Heterogeneous GPU Programming Frameworks for Hemodynamic Simulations

Preparing for the deployment of large scientific and engineering codes on upcoming exascale systems with GPU-dense nodes is made challenging by the unprecedented diversity of device architectures and heterogeneous programming models. In this work, we evaluate the process of porting a massively parallel, fluid dynamics code written in CUDA to SYCL, HIP, and Kokkos with a range of backends, using a combination of automated tools and manual tuning. We use a proxy application along with a custom performance model to inform the results and identify additional optimization strategies. At scale performance of the programming model implementations are evaluated on pre-production GPU node architectures for Frontier and Aurora, as well as on current NVIDIA device-based systems Summit and Polaris. Real-world workloads representing 3D blood flow calculations in complex vasculature are assessed. Our analysis highlights critical trade-offs between code performance, portability, and development time.

Martin, Aristotle↗
DOE OSTI2023

Demonstrating Cross-Facility Data Processing at Scale with Laue Microdiffraction

In February and April 2023 live, at-scale data processing demonstrations were conducted between the Advanced Photon Source (APS), a synchrotron light source, and the Argonne Leadership Computing Facility (ALCF). These tests were run as part of a novel beamline technique: coded aperture laue micro-diffraction. This technique requires a significant amount of compute to decode appeture patterns embedded in the detector stream. An autonomous system was able to send data to ALCF during an experiment, utilize 50 nodes of the Polaris supercomputer to process 6-12 hour scans, and return the data back to the APS within 12-15 minutes behind the detector. With scan points arriving every 72 seconds, the system kept up with the beamline, potentially enabling in-experiment analysis. The data processing system utilizes Globus infrastructure and an on-demand queue to dynamically acquire nodes on Polaris. The underlying reconstruction algorithms were parallelized via MPI and accelerated with custom CUDA kernels.

Prince, Michael↗
DOE OSTI2024

CommBench: Micro-Benchmarking Hierarchical Networks with Multi-GPU, Multi-NIC Nodes

Modern high-performance computing systems have multiple GPUs and network interface cards (NICs) per node. The resulting network architectures have multilevel hierarchies of subnetworks with different interconnect and software technologies. These systems offer multiple vendor-provided communication capabilities and library implementations (IPC, MPI, NCCL, RCCL, OneCCL) with APIs providing varying levels of performance across the different levels. Understanding this performance is currently difficult because of the wide range of architectures and programming models (CUDA, HIP, OneAPI). We present CommBench, a library with cross-system portability and a high-level API that enables developers to easily build microbenchmarks relevant to their use cases and gain insight into the performance (bandwidth & latency) of multiple implementation libraries on different networks. We demonstrate CommBench with three sets of microbenchmarks that profile the performance of six systems. Our experimental results reveal the effect of multiple NICs on optimizing the bandwidth across nodes and also present the performance characteristics of four available communication libraries within and across nodes of NVIDIA, AMD, and Intel GPU networks.

Hidayetoglu, Mert↗
DOE OSTI2025

A Study of Performance Portability of Low-bit Fused Matrix-Vector Multiplication Kernels in SYCL

Understanding the causes of performance gaps between a portable programming model and a vendor-specific programming model is important for improving performance portability. This paper studies performance portability of low-bit fused general matrix-vector multiplication kernels in SYCL on vendors’ graphics processing units (GPUs). This work introduces the use case, explains the kernel implementations in detail, evaluates the performance of the CUDA, HIP, and SYCL kernels on datacenter, desktop, and laptop GPUs, and investigates the causes of performance gaps. The results show that loop unrolling, kernel dispatch overhead, and sum reduction contribute to the gaps.

Jin, Zheming [ORNL] (ORCID:000000027197780X)↗