Development of a hardware-accelerated simulation kernel for ultra-high vacuum with Nvidia RTX GPUs

2021 ◽  
pp. 109434202110566
Author(s):  
Pascal R Bähr ◽  
Bruno Lang ◽  
Peer Ueberholz ◽  
Marton Ady ◽  
Roberto Kersevan
Keyword(s):  
Ray Tracing ◽  
Graphics Processing Units ◽  
High Vacuum ◽  
Simulation Software ◽  
Ultra High Vacuum ◽  
Particle Accelerators ◽  
Accelerated Simulation ◽  
Mc Simulation ◽  
Graphics Processing ◽  
Simulation Unit

Molflow+ is a Monte Carlo (MC) simulation software for ultra-high vacuum, mainly used to simulate pressure in particle accelerators. In this article, we present and discuss the design choices arising in a new implementation of its ray-tracing–based simulation unit for Nvidia RTX Graphics Processing Units (GPUs). The GPU simulation kernel was designed with Nvidia’s OptiX 7 API to make use of modern hardware-accelerated ray-tracing units, found in recent RTX series GPUs based on the Turing and Ampere architectures. Even with the challenges posed by switching to 32 bit computations, our kernel runs much faster than on comparable CPUs at the expense of a marginal drop in calculation precision.

scholarly journals Acceleration of ray tracing method using predictive evaluation and GPGPU technology

2014 ◽  
Vol 4 (3) ◽  
Author(s):  
Branislav Sobota ◽  
Štefan Korečko ◽  
Csaba Szabó ◽  
František Hrozek
Keyword(s):  
Ray Tracing ◽  
Graphics Processing Units ◽  
Computation Time ◽  
General Purpose ◽  
Ray Tracing Method ◽  
Parallel Solution ◽  
Graphics Processing ◽  
Tracing Method ◽  
Selection Of ◽  
Parallel Ray Tracing

AbstractRay tracing is one of computer graphics methods for achieving the most realistic outputs. Its main disadvantage is high computation demands. Removal of this disadvantage is possible using parallelization due to the fact that the ray tracing method is inherently parallel. Solution presented in this article uses GPGPU (general-purpose computing on graphics processing units) technology and a predictive evaluation for the acceleration of ray tracing method. The CUDA C was selected as a GPGPU language and it was used for a conversion of a raytracer core. The main reason for choosing this language was usage of the Tesla C1060 graphics card. The predictive evaluation of a scene was based on the fact that total computation time increases proportionally with resolution. This evaluation allows selection of the optimal scene division for the parallel ray tracing. In tests, proposed GPGPU solution reached accelerations up to 28.3× comparing to CPU.

scholarly journals MadFlow: towards the automation of Monte Carlo simulation on GPU for particle physics processes

2021 ◽  
Vol 251 ◽  
pp. 03022
Author(s):  
Stefano Carrazza ◽  
Juan Cruz-Martinez ◽  
Marco Rossi ◽  
Marco Zaro
Keyword(s):  
Monte Carlo ◽  
Particle Physics ◽  
Graphics Processing Units ◽  
Hardware Acceleration ◽  
Matrix Elements ◽  
Analytic Expressions ◽  
Mc Simulation ◽  
Graphics Processing ◽  
Full Simulation ◽  
New Framework

In this proceedings we present MadFlow, a new framework for the automation of Monte Carlo (MC) simulation on graphics processing units (GPU) for particle physics processes. In order to automate MC simulation for a generic number of processes, we design a program which provides to the user the possibility to simulate custom processes through the Mad-Graph5_aMC@NLO framework. The pipeline includes a first stage where the analytic expressions for matrix elements and phase space are generated and exported in a GPU-like format. The simulation is then performed using the VegasFlow and PDFFlow libraries which deploy automatically the full simulation on systems with different hardware acceleration capabilities, such as multi-threading CPU, single-GPU and multi-GPU setups. We show some preliminary results for leading-order simulations on different hardware configurations.

USE OF MULTIPROCESSOR COMPUTING PLATFORM WITH HETEROGENEOUS ARCHITECTURE FOR SOLVING THE PROBLEMS OF HYDROACOUSTICS AND RADIOLOCATION

2018 ◽  
pp. 7-16 ◽  
Author(s):  
L. D. Baranov ◽  
V. N. Lobanov ◽  
M. I. Cheldiev
Keyword(s):  
Graphics Processing Units ◽  
Low Cost ◽  
Simulation Software ◽  
Actual Problem ◽  
Computing Systems ◽  
Computing Technique ◽  
Computing Platform ◽  
Massively Parallel Computing ◽  
Graphics Processing ◽  
Task Oriented

One of the main directions to increasing efficiency of computing systems related with making of heterogeneous platform which allow more effectively to use computing resources of conventional processors, graphics processing units and coprocessors based on FPGA for performance of massively-parallel computing oriented tasks. The creation of task-oriented solutions, allowing the user to configure computing technique for solving specific application tasks and giving a chance to quickly and with a low cost to reconfigure the system to another type of task is an actual problem. The domestic computing platform that can simultaneously use modules with different architectures in different configurations to solve a common problem is described in the article. The description and results of the simulation software aimed at solving problems in the field of hydroacoustics and radiolocation in order to implement the joint interaction of computing resources of different architecture and to assess the prospects of further application of the platform in resource-intensive applications are presented in the article.

Fast Cutter Location Surface Computation Using Ray Tracing Cores

2021 ◽  
Author(s):  
Daiki Ishii ◽  
Masatomo Inui ◽  
Nobuyuki Umezu
Keyword(s):  
Computer Graphics ◽  
Ray Tracing ◽  
Graphics Processing Units ◽  
Application Programming Interface ◽  
Computation Method ◽  
Cutter Path ◽  
Depth Buffer ◽  
Stable Computation ◽  
Graphics Processing ◽  
Straight Lines

Abstract By using the cutter location (CL) surface, fast and stable computation of the cutter path for machining complicated molds and dies can be realized. State-of-the-art graphics processing units (GPUs) are equipped with special hardware named ray tracing (RT) cores dedicated to image processing (called ray tracing) for 3D computer graphics. Using RT cores, it is possible to quickly compute the intersection points between a set of straight lines and polygons. In this paper, we propose a novel CL surface computation method using the RT core. The RT core was originally designed to accelerate 3D computer graphics processing. For the development of software using RT cores, it is necessary to use the OptiX application programming interface (API) library for computer graphics. We demonstrate how to use the OptiX API in the development of software for CL surface computations. Computational experiments were carried out, and it was confirmed that it is possible to obtain the CL surface based on a very high-resolution Z-map several times faster than the depth buffer-based method, which has been considered to be the fastest to date.

A virtual-reality subtotal tonsillectomy simulator

2012 ◽  
Vol 126 (S2) ◽  
pp. S8-S13 ◽  
Author(s):  
G S Ruthenbeck ◽  
S B Tan ◽  
A S Carney ◽  
J C Hobson ◽  
K J Reynolds
Keyword(s):  
Virtual Reality ◽  
Surgical Training ◽  
Graphics Processing Units ◽  
Simulation Software ◽  
Tactile Feedback ◽  
Surgical Instrument ◽  
Simulation Technology ◽  
Recent Developments ◽  
Graphics Processing ◽  
Rendering Techniques

AbstractObjectives:To develop a virtual-reality subtotal tonsillectomy simulation for surgical training.Materials and Methods:Computer models of a male patient's head and throat, and the surgical instrument, were created. These models were combined with custom-built simulation software. Recently developed tissue simulation technology that exploits recent developments in programmable graphics processing units was used to model tonsillar tissue in a way that allows surgical interaction whilst providing accurate tactile feedback. Current real-time rendering techniques were used to provide realistic visuals. Iterative refinements were made to the simulation, and in particular the tissue simulation, in consultation with relevantly experienced surgeons.Results:We have used newly developed tissue simulation technology to developed a novel virtual-reality subtotal tonsillectomy simulation for surgical training, the first of its kind.Conclusion:Early feedback suggests that this simulator can help surgeons to rapidly acquire subtotal tonsillectomy surgical skills in a risk-free and realistic virtual environment.

scholarly journals Heuristic based real-time hybrid rendering with the use of rasterization and ray tracing method

Open Physics ◽  
2019 ◽  
Vol 17 (1) ◽  
pp. 527-544 ◽  
Author(s):  
Patryk Walewski ◽  
Tomasz Gałaj ◽  
Dominik Szajerman
Keyword(s):  
Real Time ◽  
Ray Tracing ◽  
Graphics Processing Units ◽  
Hybrid Approach ◽  
Poor Performance ◽  
Complex Environments ◽  
Secondary Effects ◽  
Hybrid Rendering ◽  
Illumination Algorithms ◽  
Graphics Processing

Abstract Nowadays, rasterization is the most common method used to achieve real-time semi-photorealistic effects in games or interactive applications. Some of those effects are not easily achievable, thus require more complicated methods and are difficult to obtain. The appearance of the presented worlds depends to a large extent on the approximation to the physical basis of light behaviour in them. The best effects in this regard are global illumination algorithms. Each of them including ray tracing give the most plausible effects, but at cost of higher computational complexity. Today’s hardware allows usage of ray tracing methods in-real time on Graphics Processing Units (GPU) thanks to its parallel nature. However, using ray tracing as a single rendering method may still result in poor performance, especially when used to create many image effects in complex environments. In this paper we present a hybrid approach for real-time rendering using both rasterization and ray tracing using heuristic, which determines whether to render secondary effects such as shadows, reflections and refractions for individual objects considering their relevancy and cost of rendering those effects for these objects in particular case.

scholarly journals Constructing K-d Tree on GPU through Treelet Restructuring

2020 ◽  
pp. short56-1-short56-8
Author(s):  
Vadim Bulavintsev ◽  
Dmitry Zhdanov
Keyword(s):  
Ray Tracing ◽  
Graphics Processing Units ◽  
Global Illumination ◽  
Mapping Method ◽  
Bounding Volume ◽  
Illumination Algorithms ◽  
Graphics Processing ◽  
New Generation ◽  
Bounding Volume Hierarchies ◽  
Acceleration Structure

With every new generation of graphics processing units (GPUs), offloading ray-tracing algorithms to GPUs becomes more feasible. Software-hardware solutions for ray-tracing focus on implementing its basic components, such as building and traversing bounding volume hierarchies (BVH). However, global illumination algorithms, such as photon mapping method, depend on another kind of acceleration structure, namely k-d trees. In this work, we adapt state-ofthe-art GPU-based BVH-building algorithm of treelet restructuring to k-d trees. By evaluating the performance of the resulting k-d tree, we show that treelet optimisation heuristic suitable for BVHs of triangles is inadequate for k-d trees of points.

scholarly journals Non-Evaporable Getter Ti-V-Hf-Zr Film Coating on Laser-Treated Aluminum Alloy Substrate for Electron Cloud Mitigation

Coatings ◽  
2019 ◽  
Vol 9 (12) ◽  
pp. 839
Author(s):  
Jie Wang ◽  
Yong Gao ◽  
Zhiming You ◽  
Jiakun Fan ◽  
Jing Zhang ◽  
...  
Keyword(s):  
Aluminum Alloy ◽  
Photoelectron Spectroscopy ◽  
High Vacuum ◽  
Film Coating ◽  
High Energy ◽  
Ultra High Vacuum ◽  
Aluminum Surface ◽  
Particle Accelerators ◽  
Xps Spectra ◽  
Alloy Substrate

For improving the vacuum and mitigating the electron clouds in ultra-high vacuum chamber systems of high-energy accelerators, the deposition of Ti-V-Hf-Zr getter film on a laser-treated aluminum alloy substrate was proposed and exploited for the first time in this study. The laser-treated aluminum surface exhibits a low secondary electron yield (SEY), which is even lower than 1 for some selected laser parameters. Non-evaporable getter (NEG) Ti-V-Hf-Zr film coatings were prepared using the direct current (DC) sputtering method. The surface morphology, surface roughness and composition of Ti-V-Hf-Zr getter films were characterized and analyzed. The maximum SEY of unactivated Ti-V-Hf-Zr getter film on laser-treated aluminum alloy substrates ranged from 1.10 to 1.48. The X-ray photoelectron spectroscopy (XPS) spectra demonstrate that the Ti-V-Hf-Zr coated laser-treated aluminum alloy could be partially activated after being heated at 100 and 150 °C, respectively, for 1 h in a vacuum and also used as a pump. The results were demonstrated initially and the potential application should be considered in future particle accelerators.

scholarly journals A hybrid mesh and voxel based Monte Carlo algorithm for accurate and efficient photon transport modeling in complex bio-tissues

2020 ◽  
Author(s):  
Shijie Yan ◽  
Qianqian Fang
Keyword(s):  
Monte Carlo ◽  
Graphics Processing Units ◽  
Light Transport ◽  
Monte Carlo Algorithm ◽  
Brain Atlas ◽  
Simulation Accuracy ◽  
Mc Simulation ◽  
Voxel Data ◽  
Graphics Processing ◽  
Improved Accuracy

AbstractOver the past decade, an increasing body of evidence has suggested that threedimensional (3-D) Monte Carlo (MC) light transport simulations are affected by the inherent limitations and errors of voxel-based domain boundaries. In this work, we specifically address this challenge using a hybrid MC algorithm, namely split-voxel MC or SVMC, that combines both mesh and voxel domain information to greatly improve MC simulation accuracy while remaining highly flexible and efficient in parallel hardware, such as graphics processing units (GPU). We achieve this by applying a marching-cubes algorithm to a pre-segmented domain to extract and encode sub-voxel information of curved surfaces, which is then used to inform ray-tracing computation within boundary voxels. This preservation of curved boundaries in a voxel data structure demonstrates significantly improved accuracy in several benchmarks, including a human brain atlas. The accuracy of the SVMC algorithm is comparable to that of mesh-based MC (MMC), but runs 2x-6x faster and requires only a lightweight preprocessing step. The proposed algorithm has been implemented in our open-source software and is freely available at http://mcx.space.

Sign in / Sign up

Export Citation Format

Share Document