Search Results

Conventional wisdom maintains that the interval of time mutually exclusive access is granted to a shared resource (i.e., in a critical section) should be as short as possible. However, the arbitration of shared-resource accesses introduces overhead. As a ...

As part of the US Department of Energy’s Exascale Computing Project (ECP), Rice University has been refining its HPCToolkit performance tools to better support measurement and analysis of applications executing on exascale supercomputers. To efficiently ...

Kronecker Matrix-Matrix Multiplication (Kron-Matmul) is the multiplication of a matrix with the Kronecker Product of several smaller matrices. Kron-Matmul is a core operation for many scientific and machine learning computations. State-of-the-art Kron-...

An approach to accelerating a parallel domain decomposition (DD) solver by graphics processing units (GPUs) is investigated. The solver is based on the Balancing Domain Decomposition Method by Constraints (BDDC), which is a nonoverlapping DD technique. ...

Reacting flow simulations for combustion applications require extensive computing capabilities. Leveraging the AMReX library, the Pele suite of combustion simulation tools targets the largest supercomputers available and future exascale machines. We ...

Krylov methods provide a fast and highly parallel numerical tool for the iterative solution of many large-scale sparse linear systems. To a large extent, the performance of practical realizations of these methods is constrained by the communication ...

Identity-based cryptography is proposed to solve the complicated certificate management of traditional public-key cryptography. The pairing computation and high-level tower extension field arithmetic turn out to be the performance bottleneck of pairing-...

Multi-Chip Module (MCM) designs have emerged as a key technique to scale up a GPU's compute capabilities in the face of slowing transistor technology. However, the disaggregated nature of MCM GPUs with many chiplets connected via in-package ...

Analytical models can greatly help computer architects perform orders of magnitude faster early-stage design space exploration than using cycle-level simulators. To facilitate rapid design space exploration for graphics processing units (GPUs), prior ...

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 ...

Due to their high computational power and internal memory bandwidth, graphic processing units (GPUs) have been extensively studied by the database systems research community. A heterogeneous query processing system that employs CPUs and GPUs at the same ...

Plagiarism is a rapidly rising issue among students during submission of assignments, reports and publications in universities and educational institutions, due to easy accessibility of abundant e-resources on the internet. Existing tools become ...

Skeleton‐based action recognition algorithms have been widely applied to human action recognition. Graph convolutional networks (GCNs) generalize convolutional neural networks (CNNs) to non‐Euclidean graphs and achieve significant performance in ...

A modern GPU is designed with many large thread groups to achieve a high throughput and performance. Within these groups, the threads are grouped into fixed-size SIMD batches in which the same instruction is applied to vectors of data in a lockstep. This ...

Leveraging sparsity in deep neural network (DNN) models is promising for accelerating model inference. Yet existing GPUs can only leverage the sparsity from weights but not activations, which are dynamic, unpredictable, and hence challenging to exploit. ...

Graphics processing units (GPUs) have been the target of a significant body of recent real-time research, but research is often hampered by the “black box” nature of GPU hardware and software. Now that one GPU manufacturer, AMD, has embraced an open-...

A parallel, blocked, one-sided Hari–Zimmermann algorithm for the generalized singular value decomposition (GSVD) of a real or a complex matrix pair ( F , G ) is here proposed, where F and G have the same number of columns, and are both of the ...

Scientific workloads have traditionally exploited high levels of sparsity to accelerate computation and reduce memory requirements. While deep neural networks can be made sparse, achieving practical speedups on GPUs is difficult because these ...

Domain-specific languages that execute image processing pipelines on GPUs, such as Halide and Forma, operate by 1)~dividing the image into overlapped tiles, and 2)~fusing loops to improve memory locality. However, current approaches have limitations: 1)~...

GPUs have emerged as a key computing platform for an ever-growing range of applications. Unlike traditional bulk-synchronous GPU programs, many emerging GPU-accelerated applications, such as graph processing, have irregular interaction among the ...