SU‐E‐T‐423: Fast Photon Convolution Calculation with a 3D‐Ideal Kernel On the GPU

GPU acceleration of MPAS microphysics WSM6 using OpenACC directives: Performance and verification

Heterogeneous systems with both Central Processing Units (CPUs) and Graphics Processing Units (GPUs) are frequently used to accelerate short-ranged Molecular Dynamics (MD) simulations. The most time-consuming task in short-ranged MD simulations is the computation of particle-to-particle interactions. Beyond a certain distance, these interactions decrease to zero. To minimize the operations to investigate distance, previous works have tiled interactions by employing the spatial attribute, which increases the memory access and GPU computations, hence decreasing performance. Other studies ignore the spatial attribute and construct an all-versus-all interaction matrix, which has poor scalability. This paper presents an improved algorithm. The algorithm first bins particles into voxels according to the spatial attributes, and then tiles the all-versus-all matrix into voxel-versus-voxel sub-matrixes. Only the sub-matrixes between neighboring voxels are computed on the GPU. Therefore, the algorithm reduces the distance examine operations and limits additional memory access and GPU computations. This paper also adopts a multi-level programming model to implement the algorithm on multi-nodes of Tianhe-lA. By employing (1) a patch design to exploit parallelism across the simulation domain, (2) a communication overlapping method to overlap the communications between CPUs and GPUs, and (3) a dynamic workload balancing method to adjust the workloads among compute nodes, the implementation achieves a speedup of 4.16× on one NVIDIA Tesla M2050 GPU compared to a 2.93 GHz six-core Intel Xeon X5670 CPU. In addition, it runs 2.41× faster on 256 compute nodes of Tianhe-lA (with two CPUs and one GPU inside a node) than on 256 GPU-excluded nodes.

Monte Carlo (MC) simulation is commonly considered to be the most accurate dose calculation method in radiotherapy. However, its efficiency still requires improvement for many routine clinical applications. In this paper, we present our recent progress toward the development of a graphics processing unit (GPU)-based MC dose calculation package, gDPM v2.0. It utilizes the parallel computation ability of a GPU to achieve high efficiency, while maintaining the same particle transport physics as in the original dose planning method (DPM) code and hence the same level of simulation accuracy. In GPU computing, divergence of execution paths between threads can considerably reduce the efficiency. Since photons and electrons undergo different physics and hence attain different execution paths, we use a simulation scheme where photon transport and electron transport are separated to partially relieve the thread divergence issue. A high-performance random number generator and a hardware linear interpolation are also utilized. We have also developed various components to handle the fluence map and linac geometry, so that gDPM can be used to compute dose distributions for realistic IMRT or VMAT treatment plans. Our gDPM package is tested for its accuracy and efficiency in both phantoms and realistic patient cases. In all cases, the average relative uncertainties are less than 1%. A statistical t-test is performed and the dose difference between the CPU and the GPU results is not found to be statistically significant in over 96% of the high dose region and over 97% of the entire region. Speed-up factors of 69.1 ∼ 87.2 have been observed using an NVIDIA Tesla C2050 GPU card against a 2.27 GHz Intel Xeon CPU processor. For realistic IMRT and VMAT plans, MC dose calculation can be completed with less than 1% standard deviation in 36.1 ∼ 39.6 s using gDPM.

Nowadays graphics processing units (GPUs) have become popular parallel computing platforms known as General-Purpose GPU (GPGPU) computing. GPUs thereby are chosen by some security researchers as cryptographic accelerators to secure massive volumes of transactions. However, their security issues are ignored in spite of their popularity and performance. There are some possible information leakages faced with malicious attacks or even in the normal GPU computing. Our objective is to secure the confidentiality of cryptographic keys in GPU computing environments and provide easy-to-use programming with few constraints. In this paper, we propose a prototype in Linux, a system of GPGPU computing solution empowered by GPU virtualization technology, which keeps encrypted keys in guest machine to protect secret keys from leakage even in the event of full system compromise. With the API interception and redirection of CUDA, applications in Virtual Machines (VMs) can access the GPU device in a transparent way. Besides, we use virtio, a dedicated virtual I/O device, to transfer data between virtual and host machines in high performance. In our current study, we evaluate our prototype with the GPU implementation of ECC. We show that it can protect private keys of GPU cryptographic computation and it also incurs low performance penalty compared with the native environment, therefore demonstrating the prototype is secure and requires reasonable overhead.

SummaryMany e‐business or social network servers have been constructed on cloud. On such open environments, private data of massive users have to be protected by encrypting, such as using Advanced Encryption Standard (AES), and furthermore, this process must be finished in a short time for users' better experience. This gives huge pressure on cloud servers, especially common servers, such as web servers. We urgently need an inexpensive and highly efficient method to relieve cloud servers' pressure. Fortunately, many cores of a graphics processing unit (GPU) can undertake this hard mission because of stronger computing power and lower price. The GPU environments can be virtualized on demand by cloud through the vCUDA technology. Of course, for those clouds not equipped with a GPU, a central processing unit (CPU) can still work as multithreads in parallel. Thus, in a cloud, AES can be parallelized using many cores of a GPU or multicores of a CPU with high efficiency and low cost. For typical cloud applications, such as web services, there are massive users and each one has short plaintext. If we simply parallelize AES in such an application, we cannot obtain better performance because of the GPU's extra data transferring cost. Thus, we coalesce the massive users' data and cut these data into same‐length slices for improving the performance of parallel AES as much as possible. So we design six parallel AES algorithms using GPU parallelism or CPU parallelism, which differ in parallel scope and whether data are coalesced or cut to slices. Specifically, they are coalescent and sliced GPU (GCS), coalescent and unsliced GPU, uncoalescent GPU, coalescent and sliced CPU, coalescent and unsliced CPU, and uncoalescent CPU. Moreover, we implement them on two representative platforms and evaluate their performance. Through comparing their performance, GCS has the best performance among these algorithms. In a cloud with Nvidia GPUs, GCS is a more powerful algorithm for massive users' data encrypting, relatively. Copyright © 2015 John Wiley & Sons, Ltd.

Efficient methods for implementation of multi-level nonrigid mass-preserving image registration on GPUs and multi-threaded CPUs

Bioinspired methods usually need a high amount of computational resources. For this reason, parallelization is an interesting alternative in order to decrease the execution time and to provide accurate results. In this sense, recently there has been a growing interest in developing parallel algorithms using graphic processing units (GPU) also refered as GPU computation. Advances in the video gaming industry have led to the production of low-cost, high-performance graphics processing units (GPUs) that possess more memory bandwidth and computational capability than central processing units (CPUs). As GPUs are available in personal computers, and they are easy to use and manage through several GPU programming languages (CUDA, OpenCL, etc.), graphics engines are being adopted widely in scientific computing applications, particularly in the fields of computational biology and bioinformatics. This paper reviews the use of GPUs to solve scientific problems, giving an overview of current software systems.

Evaluation of a new hybrid VMAT-IMRT multi-criteria optimization plan generation algorithm

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. The ddcMD code has been made open source and is available on GitHub at https://github.com/LLNL/ddcMD.

Objective.Deep learning (DL) methods enable photon dose calculation under two main coordinate representations: Beam's Eye View (BEV) and patient coordinates. We evaluate dose calculation accuracy and speed under these coordinate paradigms and with representative DL models within a unified dataset and pipeline, and introduce two lightweight models for fast photon dose calculation.Approach.Planning computed tomography (CT) scans and volumetric modulated arc therapy plans from 24 prostate cancer patients were used. Monte Carlo simulation generated 5940, 540, and 3053 segment doses for training (11 patients), validation (3), and testing (10), respectively. For BEV, we used a combination of convolutional neural network (CNN) and convolutional long short-term memory network (ConvLSTM) called CNN-ConvLSTM, a CNN-Mamba combination (CNN-Mamba), a transformer-based architecture (DoTA), and a cascaded 3D UNet (C3D). These were trained on CT and segment-projection BEV cuboids. For patient coordinates, the DeepDose individual segment dose prediction framework implemented with C3D (DeepDose-C3D) was trained on cropped CT volumes with four physical inputs. Segment and plan dose accuracy were assessed using local gamma passing ratesγPR(2%/3 mm and 1%/3 mm) and dose-volume histogram metrics. Dose calculation times (inference plus pre/post-processing) were measured on three different graphics processing unit (GPUs).Results.All five models achieved mean localγPRvalues⩾91.0% (2%/3 mm) for segment doses and⩾99.0% (1%/3 mm) for plan doses. Mean per-segment dose calculation times were 79, 67, 298, 490, 356 ms for CNN-ConvLSTM, CNN-Mamba, DoTA, C3D, and DeepDose-C3D, respectively. On the latest-generation GPU available, the corresponding per-plan (average 305 segments) dose calculation times were 5.5, 6.2, 33.6, 38.7, 35.4 s.Significance.Both BEV- and patient-coordinate DL methods achieved accurate photon plan dose calculation, with BEV-based approaches showing more robust segment performance. CNN-ConvLSTM and CNN-Mamba retain comparable accuracy at lower computational cost, enabling fast photon dose calculation.

MSA Probs is a parallel algorithm developed to align multiple sequence alignment using a central processing unit (CPU). Whereas the CPU has some limitations, such as the inability to parallelize tasks in the processor (latency-oriented). To overcome these limitations, this paper proposes an improved version of MSA Probs that is compatible with a graphical Processing Unit (GPU). This idea helps in enhancing the performance of our algorithm (MSAprobs). To parallelize the sequential algorithm, Compute Unified Device Architecture (CUDA) or OpenCL is commonly used on GPUs. The NIVIDIA API is used to investigate the GPU's computing power. The results of using CPU only in MSAprobs versus the CPU and GPU are compared using two data sets from the Bali Base and OX Bench. The evaluation of the CPU and GPU is done using Threads 1,2 and 4. The results showed that by combining CPU and GPU, performance is improved and execution time is reduced.

In magnetic resonance imaging, the fidelity of image reconstruction is an important criterion. It has been suggested that the infinite-extent sinc kernel is the ideal interpolation kernel for ensuring the reconstruction quality of non-Cartesian trajectories. However, the application of the sinc function has been limited owing to its computational overheads. Recently, graphics processing units (GPUs) have been employed as fast computation tools because of their efficient and versatile parallel computation abilities. We implemented an accelerated convolution function with the sinc kernel using GPUs computing and evaluated the reconstruction performance. The computation time was significantly improved: Computation using the proposed method was approximately 270 times faster than that on a central processing unit (CPU) and approximately 4.6 times faster than that on a CPU optimized by level-3 Basic Linear Algebra Subprograms. The images reconstructed using the fast sinc function exhibited no adverse errors at all matrix sizes (resolutions). The total reconstruction time was approximately 0.3–3 s for all matrices, indicating that the sinc function could be a practical option for image reconstruction. Ultimately, its application would present a fundamental improvement to the performance of image reconstruction, and the GPU implementation of the convolution function with the sinc kernel could resolve various challenges in image data processing.


 
 
 With the development of the Big Data sphere, as well as those fields of study that we can relate to artificial intelligence, the need for fast and efficient computing has become one of the most important tasks nowadays. That is why in the recent decade, graphics processing unit computations have been actively developing to provide an ability for scientists and developers to use thousands of cores GPUs have in order to perform intensive computations. The goal of this research is to implement orthogonal decomposition of a matrix by applying a series of Householder transformations in Java language using JCuda library to conduct a research on its benefits. Several related papers were examined. Malaschonok and Savchenko in their work have introduced an improved version of QR algorithm for this purpose [4] and achieved better results, however Householder algorithm is more promising for GPUs according to another team of researchers – Lahabar and Narayanan [6]. However, they were using Float numbers, while we are using Double, and apart from that we are working on a new BigDecimal type for CUDA. Apart from that, there is still no solution for handling huge matrices where errors in calculations might occur.
 The algorithm of orthogonal matrix decomposition, which is the first part of SVD algorithm, is researched and implemented in this work. The implementation of matrix bidiagonalization and calculation of orthogonal factors by the Hausholder method in the jCUDA environment on a graphics processor is presented, and the algorithm for the central processor for comparisons is also implemented. Research of the received results where we experimentally measured acceleration of calculations with the use of the graphic processor in comparison with the implementation on the central processor are carried out. We show a speedup up to 53 times compared to CPU implementation on a big matrix size, specifically 2048, and even better results when using more advanced GPUs. At the same time, we still experience bigger errors in calculations while using graphic processing units due to synchronization problems. We compared execution on different platforms (Windows 10 and Arch Linux) and discovered that they are almost the same, taking the computation speed into account. The results have shown that on GPU we can achieve better performance, however there are more implementation difficulties with this approach.
 
 

This study aims to employ both central processing units (CPUs) and graphics processing units (GPUs) to collaboratively generate contour lines from a large-scale digital elevation model (DEM). The performance was improved with regard to three aspects. First, the original DEM data were decomposed and assigned according to the GPU’s limited memory so that large-scale data could be correctly addressed. Second, different types of computational tasks between the CPUs and GPUs were dynamically scheduled to ensure that both accelerators cooperate for performance improvement. Third, parallel processing on GPUs and CPUs was separately optimized for more efficient acceleration. Experimental results indicated that applying the parallel algorithm to data with a volume of 37.81 GB and area of 5,975,625.16 km2 reduced the total execution time from 332.84 min to 8.29 min for an optimal speedup of 40.15. In addition, we investigated the effects of the computational intensity, decomposition granularity, and task scheduling on parallel efficiency and performance improvement. We also discussed its degree of effectiveness, broader application, and the future direction of research in the field of geographic information systems.

A high-order spectral difference (SD) method has been developed with graphics processing units (GPUs) using compute unified device architecture (CUDA). It solves the three-dimensional Navier-Stokes equations on unstructured hexahedral grids with RungeKutta time integration. The method is efficient since operations are completed in a onedimensional fashion and the equations are solved in differential form, removing explicit surface and volume integral calculations. Additionally, solution and flux reconstructions are completed locally per cell, increasing the parallelization of the implementation. Due to this efficiency, the application of GPU computing is appealing. This paper presents the SD method implementation with GPU CUDA computing and presents accuracy studies with isotropic vortex propagation and Couette flow, verifies the high-order accuracy of the solver with a numerical sensitive aero-acoustic problem, and compares the developed solver and a high-order finite difference solver with a case presented in the 1st International Workshop on High-Order CFD Methods. Finally, the GPU solver is compared to a similar central processing unit (CPU) solver, where speed-ups ranging from 20-40x faster are illustrated.