Mark Endrei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mark Endrei has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- David Abramson
The University of Queensland, Brisbane, Australia
4 shared publications Heidi Poxon
Cray Inc., Bloomington, MN, USA
3 shared publicationsLuiz DeRose
Cray Inc., Bloomington, MN, USA
3 shared publications- Minh Ngoc Dinh
RMIT University Australia
3 shared publications Bronis R de Supinski
Lawrence Livermore National Laboratory, Livermore, CA, USA
2 shared publicationsChao Jin
Research Computing Center and School of ITEE, The University of Queensland, Brisbane, QLD, Australia
2 shared publications
Latest Publications
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1564-1573
A Cache Interaction Graph for Data Locality Optimization
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1564-1573
Open AccessA Cache Interaction Graph for Data Locality Optimization
- Open Access
- 1 January 2025
- Published by ScienceOpen
- p. e339
Enhancing Research Through FAIR-Compliant Imaging Data Repositories: The PITSCHI – a solution for Large-Scale/multi-user imaging facilities
Scientific research produces ever-larger and more complicated datasets because of the advancements of imaging technologies, especially in disciplines that demand multi-modal imaging, spectroscopy and high-resolution microscopy. Repositories that follow the FAIR (Findable, Accessible, Interoperable, and Reusable) data principles are necessary for efficiently managing, sharing, and reusing this data. Maximising the usability and accessibility of imaging data requires us to adhere to FAIR principles, which provide easy data integration, long-term preservation, and discovery across a range of research areas. To address these needs, the Centre for Microscopy and Microanalysis (CMM), in partnership with UQ’s Research Computing Centre (RCC), at the University of Queensland implemented PITSCHI (Particle Imaging depoT using Storage CacHing Infrastructure), which offers a reliable, FAIR-compliant solution for handling large imaging datasets with little manual intervention. PITSCHI is an advanced data repository built to handle large imaging datasets. PITSCHI immediately feeds data into a Clowder-based system [ 1] from any sophisticated scientific instruments, such as mass spectrometry devices, x-ray machines, scanning and transmission electron microscopes, and other microscope techniques. Large-scale microscope datasets may be shared, annotated, organised, and analysed with ease thanks to this integration, which also reduces the need for human data processing. PITSCHI is an end-to-end process for capturing and transferring raw data to storage collections, indexing it in an image repository with automated metadata harvesting, and enabling users to view, search, and process their data on external platforms, [ Fig. 1- 2]. Easy access to UQ’s Research Data Manager collections is made possible by PITSCHI’s complete integration with MeDiCI, a high-performance data storage fabric, and the university’s Research Infrastructure Management System (RIMS). Fig. 1: PITSCHI workflow Fig. 2: PITSCHI Email notifications
- 1 January 2025
- Published by ScienceOpen
- p. e339
Open AccessEnhancing Research Through FAIR-Compliant Imaging Data Repositories: The PITSCHI – a solution for Large-Scale/multi-user imaging facilities
Scientific research produces ever-larger and more complicated datasets because of the advancements of imaging technologies, especially in disciplines that demand multi-modal imaging, spectroscopy and high-resolution microscopy. Repositories that follow the FAIR (Findable, Accessible, Interoperable, and Reusable) data principles are necessary for efficiently managing, sharing, and reusing this data. Maximising the usability and accessibility of imaging data requires us to adhere to FAIR principles, which provide easy data integration, long-term preservation, and discovery across a range of research areas. To address these needs, the Centre for Microscopy and Microanalysis (CMM), in partnership with UQ’s Research Computing Centre (RCC), at the University of Queensland implemented PITSCHI (Particle Imaging depoT using Storage CacHing Infrastructure), which offers a reliable, FAIR-compliant solution for handling large imaging datasets with little manual intervention. PITSCHI is an advanced data repository built to handle large imaging datasets. PITSCHI immediately feeds data into a Clowder-based system [ 1] from any sophisticated scientific instruments, such as mass spectrometry devices, x-ray machines, scanning and transmission electron microscopes, and other microscope techniques. Large-scale microscope datasets may be shared, annotated, organised, and analysed with ease thanks to this integration, which also reduces the need for human data processing. PITSCHI is an end-to-end process for capturing and transferring raw data to storage collections, indexing it in an image repository with automated metadata harvesting, and enabling users to view, search, and process their data on external platforms, [ Fig. 1- 2]. Easy access to UQ’s Research Data Manager collections is made possible by PITSCHI’s complete integration with MeDiCI, a high-performance data storage fabric, and the university’s Research Infrastructure Management System (RIMS). Fig. 1: PITSCHI workflow Fig. 2: PITSCHI Email notifications
- 5 February 2020
- Published by University of Queensland Library
Energy Efficiency Models for Scientific Applications on Supercomputers
- 5 February 2020
- Published by University of Queensland Library
Energy Efficiency Models for Scientific Applications on Supercomputers
- 25 April 2019
- Published by SAGE Publications in The International Journal of High Performance Computing Applications
- Vol. 33 (6) , 1079-1097
Statistical and machine learning models for optimizing energy in parallel applications
Rising power costs and constraints are driving a growing focus on the energy efficiency of high performance computing systems. The unique characteristics of a particular system and workload and their effect on performance and energy efficiency are typically difficult for application users to assess and to control. Settings for optimum performance and energy efficiency can also diverge, so we need to identify trade-off options that guide a suitable balance between energy use and performance. We present statistical and machine learning models that only require a small number of runs to make accurate Pareto-optimal trade-off predictions using parameters that users can control. We study model training and validation using several parallel kernels and more complex workloads, including Algebraic Multigrid (AMG), Large-scale Atomic Molecular Massively Parallel Simulator, and Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. We demonstrate that we can train the models using as few as 12 runs, with prediction error of less than 10%. Our AMG results identify trade-off options that provide up to 45% improvement in energy efficiency for around 10% performance loss. We reduce the sample measurement time required for AMG by 90%, from 13 h to 74 min.
- 25 April 2019
- Published by SAGE Publications in The International Journal of High Performance Computing Applications
- Vol. 33 (6) , 1079-1097
Statistical and machine learning models for optimizing energy in parallel applications
Rising power costs and constraints are driving a growing focus on the energy efficiency of high performance computing systems. The unique characteristics of a particular system and workload and their effect on performance and energy efficiency are typically difficult for application users to assess and to control. Settings for optimum performance and energy efficiency can also diverge, so we need to identify trade-off options that guide a suitable balance between energy use and performance. We present statistical and machine learning models that only require a small number of runs to make accurate Pareto-optimal trade-off predictions using parameters that users can control. We study model training and validation using several parallel kernels and more complex workloads, including Algebraic Multigrid (AMG), Large-scale Atomic Molecular Massively Parallel Simulator, and Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. We demonstrate that we can train the models using as few as 12 runs, with prediction error of less than 10%. Our AMG results identify trade-off options that provide up to 45% improvement in energy efficiency for around 10% performance loss. We reduce the sample measurement time required for AMG by 90%, from 13 h to 74 min.
- 1 January 2019
- Published by University of Queensland Library
Artefacts archive for energy efficiency models for scientific applications on supercomputers
The University of Queensland's institutional repository, UQ eSpace, aims to create global visibility and accessibility of UQ’s scholarly research.
- 1 January 2019
- Published by University of Queensland Library
Artefacts archive for energy efficiency models for scientific applications on supercomputers
The University of Queensland's institutional repository, UQ eSpace, aims to create global visibility and accessibility of UQ’s scholarly research.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 212-224
Energy Efficiency Modeling of Parallel Applications
Energy efficiency has become increasingly important in high performance computing (HPC), as power constraints and costs escalate. Workload and system characteristics form a complex optimization search space in which optimal settings for energy efficiency and performance often diverge. Thus, we must identify trade-off options for performance and energy efficiency to find the desired balance between them. We present an innovative statistical model that accurately predicts the Pareto optimal performance and energy efficiency trade-off options using only user-controllable parameters. Our approach can also tolerate both measurement and model errors. We study model training and validation using several HPC kernels, then explore the feasibility of applying the model to more complex workloads, including AMG and LAMMPS. We can calibrate an accurate model from as few as 12 runs, with prediction error of less than 10%. Our results identify trade-off options allowing up to 40% improvement in energy efficiency at the cost of under 20% performance loss. For AMG, we reduce the required sample measurement time from 13 hours to 74 minutes (about 90%).
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 212-224
Energy Efficiency Modeling of Parallel Applications
Energy efficiency has become increasingly important in high performance computing (HPC), as power constraints and costs escalate. Workload and system characteristics form a complex optimization search space in which optimal settings for energy efficiency and performance often diverge. Thus, we must identify trade-off options for performance and energy efficiency to find the desired balance between them. We present an innovative statistical model that accurately predicts the Pareto optimal performance and energy efficiency trade-off options using only user-controllable parameters. Our approach can also tolerate both measurement and model errors. We study model training and validation using several HPC kernels, then explore the feasibility of applying the model to more complex workloads, including AMG and LAMMPS. We can calibrate an accurate model from as few as 12 runs, with prediction error of less than 10%. Our results identify trade-off options allowing up to 40% improvement in energy efficiency at the cost of under 20% performance loss. For AMG, we reduce the required sample measurement time from 13 hours to 74 minutes (about 90%).
- 1 January 2018
- Published by University of Queensland Library
HPC Model
The University of Queensland's institutional repository, UQ eSpace, aims to create global visibility and accessibility of UQ’s scholarly research.
- 1 January 2018
- Published by University of Queensland Library
HPC Model
The University of Queensland's institutional repository, UQ eSpace, aims to create global visibility and accessibility of UQ’s scholarly research.
- 9 September 2016
- Published by SAGE Publications in The International Journal of High Performance Computing Applications
- Vol. 31 (6) , 517-549
A survey on software methods to improve the energy efficiency of parallel computing
Energy consumption is one of the top challenges for achieving the next generation of supercomputing. Codesign of hardware and software is critical for improving energy efficiency (EE) for future large-scale systems. Many architectural power-saving techniques have been developed, and most hardware components are approaching physical limits. Accordingly, parallel computing software, including both applications and systems, should exploit power-saving hardware innovations and manage efficient energy use. In addition, new power-aware parallel computing methods are essential to decrease energy usage further. This article surveys software-based methods that aim to improve EE for parallel computing. It reviews the methods that exploit the characteristics of parallel scientific applications, including load imbalance and mixed precision of floating-point (FP) calculations, to improve EE. In addition, this article summarizes widely used methods to improve power usage at different granularities, such as the whole system and per application. In particular, it describes the most important techniques to measure and to achieve energy-efficient usage of various parallel computing facilities, including processors, memories, and networks. Overall, this article reviews the state-of-the-art of energy-efficient methods for parallel computing to motivate researchers to achieve optimal parallel computing under a power budget constraint.
- 9 September 2016
- Published by SAGE Publications in The International Journal of High Performance Computing Applications
- Vol. 31 (6) , 517-549
A survey on software methods to improve the energy efficiency of parallel computing
Energy consumption is one of the top challenges for achieving the next generation of supercomputing. Codesign of hardware and software is critical for improving energy efficiency (EE) for future large-scale systems. Many architectural power-saving techniques have been developed, and most hardware components are approaching physical limits. Accordingly, parallel computing software, including both applications and systems, should exploit power-saving hardware innovations and manage efficient energy use. In addition, new power-aware parallel computing methods are essential to decrease energy usage further. This article surveys software-based methods that aim to improve EE for parallel computing. It reviews the methods that exploit the characteristics of parallel scientific applications, including load imbalance and mixed precision of floating-point (FP) calculations, to improve EE. In addition, this article summarizes widely used methods to improve power usage at different granularities, such as the whole system and per application. In particular, it describes the most important techniques to measure and to achieve energy-efficient usage of various parallel computing facilities, including processors, memories, and networks. Overall, this article reviews the state-of-the-art of energy-efficient methods for parallel computing to motivate researchers to achieve optimal parallel computing under a power budget constraint.