Learning intermediate representations using graph neural networks for numa and prefetchers optimization
There is a large space of NUMA and hardware prefetcher configurations that can
significantly impact the performance of an application. Previous studies have demonstrated …
significantly impact the performance of an application. Previous studies have demonstrated …
Modeling and optimizing numa effects and prefetching with machine learning
Both NUMA thread/data placement and hardware prefetcher configuration have significant
impacts on HPC performance. Optimizing both together leads to a large and complex design …
impacts on HPC performance. Optimizing both together leads to a large and complex design …
Adapt burstable containers to variable CPU resources
In the age of the cloud-native, container technology, referred as OS-level virtualization, is
increasingly adopted to deploy cloud applications. Compared with virtual machines …
increasingly adopted to deploy cloud applications. Compared with virtual machines …
Using machine learning to optimize graph execution on numa machines
HMG de A. Rocha, J Schwarzrock… - Proceedings of the 59th …, 2022 - dl.acm.org
This paper proposes PredG, a Machine Learning framework to enhance the graph
processing performance by finding the ideal thread and data mapping on NUMA systems …
processing performance by finding the ideal thread and data mapping on NUMA systems …
Compoff: A compiler cost model using machine learning to predict the cost of openmp offloading
The HPC industry is inexorably moving towards an era of extremely heterogeneous
architectures, with more devices configured on any given HPC platform and potentially more …
architectures, with more devices configured on any given HPC platform and potentially more …
Adaptive load balancing based on machine learning for iterative parallel applications
The performance of irregular scientific applications can be easily affected by an uneven
distribution of work among the computing resources. In this context, Load Balancing (LB) …
distribution of work among the computing resources. In this context, Load Balancing (LB) …
ParaGraph: Weighted Graph Representation for Performance Optimization of HPC Kernels
GPU-based HPC clusters are attracting more sci-entific application developers due to their
extensive parallelism and energy efficiency. In order to achieve portability among a variety of …
extensive parallelism and energy efficiency. In order to achieve portability among a variety of …
Divide&Content: A fair OS-level resource manager for contention balancing on NUMA multicores
Chip multicore processors (CMPs) constitute the cherry-picked architecture for high-
performance servers employed in supercomputers and cloud datacenters. In the last few …
performance servers employed in supercomputers and cloud datacenters. In the last few …
WASP: Workload-Aware Self-Replicating Page-Tables for NUMA Servers
H Qu, Z Yu - Proceedings of the 29th ACM International Conference …, 2024 - dl.acm.org
Recently, page-table self-replication (PTSR) has been proposed to reduce the page-table
caused NUMA effect for large-memory workloads on NUMA servers. However, PTSR may …
caused NUMA effect for large-memory workloads on NUMA servers. However, PTSR may …
[HTML][HTML] Performance Study of an MRI Motion-Compensated Reconstruction Program on Intel CPUs, AMD EPYC CPUs, and NVIDIA GPUs
Motion-compensated image reconstruction enables new clinical applications of Magnetic
Resonance Imaging (MRI), but it relies on computationally intensive algorithms. This study …
Resonance Imaging (MRI), but it relies on computationally intensive algorithms. This study …