LIBSHALOM: Optimizing small and irregular-shaped matrix multiplications on ARMv8 multi-cores
General Matrix Multiplication (GEMM) is a key subroutine in highperformance computing.
While the mainstream linear algebra libraries can deliver high performance on large and …
While the mainstream linear algebra libraries can deliver high performance on large and …
Evaluating fft-based algorithms for strided convolutions on armv8 architectures?
X Huang, Q Wang, S Lu, R Hao, S Mei… - ACM SIGMETRICS …, 2022 - dl.acm.org
Convolutional Neural Networks (CNNs) have been widely adopted in all kinds of artificial
intelligence applications. Most of the computational overhead of CNNs is mainly spent on …
intelligence applications. Most of the computational overhead of CNNs is mainly spent on …
Automatic code generation and optimization of large-scale stencil computation on many-core processors
Stencil computation is an indispensable building block of many scientific applications and is
widely used by the numerical solvers of partial differential equations (PDEs). Due to the …
widely used by the numerical solvers of partial differential equations (PDEs). Due to the …
Performance evaluation of memory-centric armv8 many-core architectures: A case study with phytium 2000+
This article presents a comprehensive performance evaluation of Phytium 2000+, an ARMv8-
based 64-core architecture. We focus on the cache and memory subsystems, analyzing the …
based 64-core architecture. We focus on the cache and memory subsystems, analyzing the …
Deploying and scaling distributed parallel deep neural networks on the Tianhe-3 prototype system
Due to the increase in computing power, it is possible to improve the feature extraction and
data fitting capabilities of DNN networks by increasing their depth and model complexity …
data fitting capabilities of DNN networks by increasing their depth and model complexity …
Optimizing Attention by Exploiting Data Reuse on ARM Multi-core CPUs
X Fu, W Yang, D Dong, X Su - Proceedings of the 38th ACM International …, 2024 - dl.acm.org
Transformers reign supreme in natural language processing, representing a milestone
innovation in deep learning. For high-performance model inference, optimizing the time …
innovation in deep learning. For high-performance model inference, optimizing the time …
Performance evaluation of convolutional neural network on Tianhe-3 prototype
W Chen, X Dong, H Chen, Q Wang, X Yu… - The Journal of …, 2021 - Springer
Exascale supercomputers will greatly support the expanding computational resource
demand of convolutional neural networks (CNNs). At present, the prototype cluster of Tianhe …
demand of convolutional neural networks (CNNs). At present, the prototype cluster of Tianhe …
Characterizing small-scale matrix multiplications on ARMv8-based many-core architectures
General Matrix Multiplication (GEMM) is a key subroutine in high-performance computing.
There is a large body of work on evaluating and optimizing large-scale matrix multiplication …
There is a large body of work on evaluating and optimizing large-scale matrix multiplication …
GraphCube: Interconnection Hierarchy-aware Graph Processing
Processing large-scale graphs with billions to trillions of edges requires efficiently utilizing
parallel systems. However, current graph processing engines do not scale well beyond a …
parallel systems. However, current graph processing engines do not scale well beyond a …
An empirical study of hpc workloads on huawei kunpeng 916 processor
YC Wang, JK Chen, BR Li, SC Zuo… - 2019 IEEE 25th …, 2019 - ieeexplore.ieee.org
The ARM-based server processors have been gaining momentum in high performance
computing (HPC). While not designed specifically for HPC, Huawei Kunpeng 916 processor …
computing (HPC). While not designed specifically for HPC, Huawei Kunpeng 916 processor …