Dynamic precision autotuning with TAFFO

S Cherubin, D Cattaneo, M Chiari… - ACM Transactions on …, 2020 - dl.acm.org
Many classes of applications, both in the embedded and high performance domains, can
trade off the accuracy of the computed results for computation performance. One way to …

The Italian research on HPC key technologies across EuroHPC

M Aldinucci, G Agosta, A Andreini… - Proceedings of the 18th …, 2021 - dl.acm.org
High-Performance Computing (HPC) is one of the strategic priorities for research and
innovation worldwide due to its relevance for industrial and scientific applications. We …

The ANTAREX domain specific language for high performance computing

C Silvano, G Agosta, A Bartolini, AR Beccari… - Microprocessors and …, 2019 - Elsevier
The ANTAREX project relies on a Domain Specific Language (DSL) based on Aspect
Oriented Programming (AOP) concepts to allow applications to enforce extra functional …

Autotuning and adaptivity in energy efficient HPC systems: the ANTAREX toolbox

C Silvano, G Palermo, G Agosta, AH Ashouri… - Proceedings of the 15th …, 2018 - dl.acm.org
Designing and optimizing applications for energy-efficient High Performance Computing
systems up to the Exascale era is an extremely challenging problem. This paper presents …

Predictive resource management for next-generation high-performance computing heterogeneous platforms

G Massari, A Pupykina, G Agosta… - … , Modeling, and Simulation …, 2019 - Springer
Abstract High-Performance Computing (HPC) is rapidly moving towards the adoption of
nodes characterized by an heterogeneous set of processing resources. This has already …

Antarex: A dsl-based approach to adaptively optimizing and enforcing extra-functional properties in high performance computing

C Silvano, G Agosta, A Bartolini… - 2018 21st Euromicro …, 2018 - ieeexplore.ieee.org
The ANTAREX project relies on a Domain Specific Language (DSL) based on Aspect
Oriented Programming (AOP) concepts to allow applications to enforce extra functional …

Dynamically-tunable dataflow architectures based on Markov queuing models

M Tibaldi, G Palermo, C Pilato - Electronics, 2022 - mdpi.com
Dataflow architectures are fundamental to achieve high performance in data-intensive
applications. They must be optimized to elaborate input data arriving at an expected rate …

Continuous program optimization via advanced dynamic compilation techniques

M Festa, N Gervasoni, S Cherubin… - Proceedings of the 10th …, 2019 - dl.acm.org
In High Performance Computing, it is often useful to fine tune an application code via
recompilation of specific computational intensive code fragments to leverage runtime …

Feedback-driven performance and precision tuning for automatic fixed point exploitation

D Cattaneo, M Chiari, S Cherubin… - Parallel Computing …, 2020 - ebooks.iospress.nl
Precision tuning is an emerging class of techniques that leverage the trade-off between
accuracy and performance in a wide range of numerical applications. We employ TAFFO, a …

Supporting the scale-up of high performance application to pre-exascale systems: The antarex approach

C Silvano, G Agosta, A Bartolini… - 2019 27th Euromicro …, 2019 - ieeexplore.ieee.org
The ANTAREX project developed an approach to the performance tuning of High
Performance applications based on an Aspect-oriented Domain Specific Language (DSL) …