Myths and legends in high-performance computing
In this thought-provoking article, we discuss certain myths and legends that are folklore
among members of the high-performance computing community. We gathered these myths …
among members of the high-performance computing community. We gathered these myths …
Extracting clean performance models from tainted programs
Performance models are well-known instruments to understand the scaling behavior of
parallel applications. They express how performance changes as key execution parameters …
parallel applications. They express how performance changes as key execution parameters …
Learning cost-effective sampling strategies for empirical performance modeling
M Ritter, A Calotoiu, S Rinke, T Reimann… - 2020 IEEE …, 2020 - ieeexplore.ieee.org
Identifying scalability bottlenecks in parallel applications is a vital but also laborious and
expensive task. Empirical performance models have proven to be helpful to find such …
expensive task. Empirical performance models have proven to be helpful to find such …
Software Resource Disaggregation for HPC with Serverless Computing
Aggregated HPC resources have rigid allocation systems and programming models which
struggle to adapt to diverse and changing workloads. Consequently, HPC systems fail to …
struggle to adapt to diverse and changing workloads. Consequently, HPC systems fail to …
Performance-detective: automatic deduction of cheap and accurate performance models
The many configuration options of modern applications make it difficult for users to select a
performance-optimal configuration. Performance models help users in understanding …
performance-optimal configuration. Performance models help users in understanding …
[PDF][PDF] Extrapeak: Advanced automatic performance modeling for HPC applications
Performance models are powerful tools allowing developers to understand the behavior of
their applications, and empower them to address performance issues already during the …
their applications, and empower them to address performance issues already during the …
Building a fine-grained analytical performance model for complex scientific simulations
Analytical performance models are powerful for understanding and predicting the
performance of large-scale simulations. As such, they can help identify performance …
performance of large-scale simulations. As such, they can help identify performance …
[PDF][PDF] Modern vector architectures for high-performance computing
A Poenaru - 2022 - research-information.bris.ac.uk
Recent generations of general-purpose central processing units (CPUs) for the high-
performance segment have had to adopt new approaches in order to deliver increasing …
performance segment have had to adopt new approaches in order to deliver increasing …
The effects of wide vector operations on processor caches
A Poenaru, S McIntosh-Smith - 2020 IEEE International …, 2020 - ieeexplore.ieee.org
In this paper we investigate the effects of wide vector instructions on modern processor
caches. On the one hand, contemporary processors have large, highly associative caches …
caches. On the one hand, contemporary processors have large, highly associative caches …
[PDF][PDF] perf-taint: Taint Analysis for Automatic Many-Parameter Performance Modeling
The design process of a massively parallel program requires a deep understanding of
computational kernels and communication patterns that are present in the application …
computational kernels and communication patterns that are present in the application …