HeAT -- a Distributed and GPU-accelerated Tensor Framework for Data Analytics
German Aerospace Center (DLR)（德国航空航天中心）；Forschungszentrum Jülich (FZJ)（于利希研究中心）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）
Markus Götz, Daniel Coquelin, Charlotte Debus, Kai Krajsek, Claudia Comito, Philipp Knechtges, Björn Hagemeier, Michael Tarnawa, Simon Hanselmann, Martin Siggel… 展开作者
Markus Götz, Daniel Coquelin, Charlotte Debus, Kai Krajsek, Claudia Comito, Philipp Knechtges, Björn Hagemeier, Michael Tarnawa, Simon Hanselmann, Martin Siggel, Achim Basermann, Achim Streit
To cope with the rapid growth in available data, the efficiency of data analysis and machine learning libraries has recently received increased attention. Although great advancements have been made in traditional array-based computations, most are limited by the resources available on a single computation node. Consequently, novel approaches must be made to exploit distributed resources, e.g. distributed memory architectures. To this end, we introduce HeAT, an array-based numerical programming framework for large-scale parallel processing with an easy-to-use NumPy-like API. HeAT utilizes PyTorch as a node-local eager execution engine and distributes the workload on arbitrarily large high-performance computing systems via MPI. It provides both low-level array computations, as well as assorted higher-level algorithms. With HeAT, it is possible for a NumPy user to take full advantage of their available resources, significantly lowering the barrier to distributed data analysis. When compared to similar frameworks, HeAT achieves speedups of up to two orders of magnitude.
In this paper, we present GATSPI, a novel GPU accelerated logic gate simulator that enables ultra-fast power estimation for industry sized ASIC designs with millions of gates. GATSPI is written in PyTorch with custom CUDA kernels for ease of coding and maintainability. It achieves simulation kernel speedup of up to 1668X on a single-GPU system and up to 7412X on a multiple-GPU system when compared to a commercial gate-level simulator running on a single CPU core. GATSPI supports a range of simple to complex cell types from an industry standard cell library and SDF conditional delay statements …
As part of the Exascale Computing Project (ECP), a recent focus of development efforts for the SUite of Nonlinear and DIfferential/ALgebraic equation Solvers (SUNDIALS) has been to enable GPU-accelerated time integration in scientific applications at extreme scales. This effort has resulted in several new GPU-enabled implementations of core SUNDIALS data structures, support for programming paradigms which are aware of the heterogeneous architectures, and the introduction of utilities to provide new points of flexibility. In this paper, we discuss our considerations, both internal and external,…
Most, if not all the modern scientific simulation packages utilize matrix algebra operations. Among the operation of the linear algebra, one of the most important kernels is the multiplication of matrices, dense and sparse. Examples of application of such a kernel are in electronic structure calculations, machine learning, data mining, graph processing, and digital signal processing. Several optimized libraries exist that can achieve high-performance on distributed systems. Only a few of them target distributed GPU-accelerated systems. In most of the cases, these libraries are provided and opt…
To address the challenge of performance analysis on the US DOE's forthcoming exascale supercomputers, Rice University has been extending its HPCToolkit performance tools to support measurement and analysis of GPU-accelerated applications. To help developers understand the performance of accelerated applications as a whole, HPCToolkit's measurement and analysis tools attribute metrics to calling contexts that span both CPUs and GPUs. To measure GPU-accelerated applications efficiently, HPCToolkit employs a novel wait-free data structure to coordinate monitoring and attribution of GPU performanc…
We present an MPI + OpenACC implementation of the kernel-independent barycentric Lagrange treecode (BLTC) for fast summation of particle interactions on GPUs. The distributed memory parallelization uses recursive coordinate bisection for domain decomposition and MPI remote memory access to build locally essential trees on each rank. The particle interactions are organized into target batch/source cluster interactions which efficiently map onto the GPU; target batching provides an outer level of parallelism, while the direct sum form of the barycentric particle-cluster approximation provides an…
Processing large graphs with memory-limited GPU needs to resolve issues of host-GPU data transfer, which is a key performance bottleneck. Existing GPU-accelerated graph processing frameworks reduce the data transfers by managing the active subgraph transfer at runtime. Some frameworks adopt explicit transfer management approaches based on explicit memory copy with filter or compaction. In contrast, others adopt implicit transfer management approaches based on on-demand access with zero-copy or unified-memory. Having made intensive analysis, we find that as the active vertices evolve, the perfo…
Hash functions like SHA-1 or MD5 are one of the most important cryptographic primitives, especially in the field of information integrity. Considering the fact that increasing methods have been proposed to break these hash algorithms, a competition for a new family of hash functions was held by the US National Institute of Standards and Technology. Keccak was the winner and selected to be the next generation of hash function standard, named SHA-3. We aim to implement and optimize Batch mode based Keccak algorithms on NVIDIA GPU platform. Our work consider the case of processing multiple hash t…
This chapter introduces GPU-accelerated image processing in ImageJ/FIJI. The reader is expected to have some pre-existing knowledge of ImageJ Macro programming. Core concepts such as variables, for-loops, and functions are essential. The chapter provides basic guidelines for improved performance in typical image processing workflows. We present in a step-by-step tutorial how to translate a pre-existing ImageJ macro into a GPU-accelerated macro.
It has been widely accepted that Graphics Processing Units (GPU) is one of promising schemes for encryption acceleration, in particular, the support of complex mathematical calculations such as integer and logical operations makes the implementation easier; however, complexes such as parallel granularity, memory allocation still imposes a burden on real world implementations. In this paper, we propose a new approach for Advanced Encryption Standard accelerations, including both encryption and decryption. Specifically, we adapt the Electronic Code Book mode for cryptographic transformation, loo…
We present the smoothed-particle hydrodynamics simulation code, Bonsai-SPH, which is a continuation of our previously developed gravity-only hierarchical $N$-body code (called Bonsai). The code is optimized for Graphics Processing Unit (GPU) accelerators which enables researchers to take advantage of these powerful computational resources. Bonsa-SPH produces simulation results comparable with state-of-the-art, CPU based, codes, but using an order of magnitude less computation time. The code is freely available online and the details are described in this work.
This paper gives an analysis and an evaluation of linear algebra operations on Graphics Processing Unit (GPU) with complex number arithmetics with double precision. Knowing the performance of these operations, iterative Krylov methods are considered to solve the acoustic problem efficiently. Numerical experiments carried out on a set of acoustic matrices arising from the modelisation of acoustic phenomena within a cylinder and a car compartment are exposed, exhibiting the performance, robustness and efficiency of our algorithms, with a ratio up to 27x for dot product, 10x for sparse matrix-vec…
A discontinuous Galerkin method for the discretization of the compressible Euler equations, the governing equations of inviscid fluid dynamics, on Cartesian meshes is developed for use of Graphical Processing Units via OCCA, a unified approach to performance portability on multi-threaded hardware architectures. A 30x time-to-solution speedup over CPU-only implementations using non-CUDA-Aware MPI communications is demonstrated up to 1,536 NVIDIA V100 GPUs and parallel strong scalability is shown up to 6,144 NVIDIA V100 GPUs for a problem containing 345 billion unknowns. A comparison of CUDA-Awa…
The development of NekRS, a GPU-oriented thermal-fluids simulation code based on the spectral element method (SEM) is described. For performance portability, the code is based on the open concurrent compute abstraction and leverages scalable developments in the SEM code Nek5000 and in libParanumal, which is a library of high-performance kernels for high-order discretizations and PDE-based miniapps. Critical performance sections of the Navier-Stokes time advancement are addressed. Performance results on several platforms are presented, including scaling to 27,648 V100s on OLCF Summit, for calcu…
WarpX is a general purpose electromagnetic particle-in-cell code that was originally designed to run on many-core CPU architectures. We describe the strategy followed to allow WarpX to use the GPU-accelerated nodes on OLCF's Summit supercomputer, a strategy we believe will extend to the upcoming machines Frontier and Aurora. We summarize the challenges encountered, lessons learned, and give current performance results on a series of relevant benchmark problems.
We present the barycentric Lagrange dual tree traversal (BLDTT) fast summation method for particle interactions. The scheme replaces well-separated particle-particle interactions by adaptively chosen particle-cluster, cluster-particle, and cluster-cluster approximations given by barycentric Lagrange interpolation at proxy particles on a Chebyshev grid in each cluster. The BLDTT is kernel-independent and the approximations can be efficiently mapped onto GPUs, where target particles provide an outer level of parallelism and source particles provide an inner level of parallelism. We present an Op…
We present hipBone, an open source performance-portable proxy application for the Nek5000 (and NekRS) CFD applications. HipBone is a fully GPU-accelerated C++ implementation of the original NekBone CPU proxy application with several novel algorithmic and implementation improvements which optimize its performance on modern fine-grain parallel GPU accelerators. Our optimizations include a conversion to store the degrees of freedom of the problem in assembled form in order to reduce the amount of data moved during the main iteration and a portable implementation of the main Poisson operator kerne…
Sun Yat-sen University（中山大学）；Notheastern University（东北大学）；Peng Cheng Laboratory（鹏城实验室）
Over the last years, a great success of deep neural networks (DNNs) has been witnessed in computer vision and other fields. However, performance and power constraints make it still challenging to deploy DNNs on mobile devices due to their high computational complexity. Binary neural networks (BNNs) have been demonstrated as a promising solution to achieve this goal by using bit-wise operations to replace most arithmetic operations. Currently, existing GPU-accelerated implementations of BNNs are only tailored for desktop platforms. Due to architecture differences, mere porting of such implement…
LISN, CNRS, Université Paris-Saclay（巴黎萨克雷大学国家科学研究中心LISN实验室）；Brno University of Technology（布尔诺理工大学）
We propose to express the forward-backward algorithm in terms of operations between sparse matrices in a specific semiring. This new perspective naturally leads to a GPU-friendly algorithm which is easy to implement in Julia or any programming languages with native support of semiring algebra. We use this new implementation to train a TDNN with the LF-MMI objective function and we compare the training time of our system with PyChain - a recently introduced C++/CUDA implementation of the LF-MMI loss. Our implementation is about two times faster while not having to use any approximation such as …
Multichannel Analysis of Surface Waves (MASW) is a technique frequently used in geotechnical engineering and engineering geophysics to infer layered models of seismic shear wave velocities in the top tens to hundreds of meters of the subsurface. We aim to accelerate MASW calculations by capitalizing on modern computer hardware available in the workstations of most engineers: multiple cores and graphics processing units (GPUs). We propose new parallel and GPU accelerated algorithms for evaluating MASW data, and provide software implementations in C using Message Passing Interface (MPI) and CUDA…
