Browse

Building a Reusable and Extensible Automatic Compiler Infrastructure for reconfigurable devices (2023)
Conference Proceeding
Zang, Z., Dolinsky, U., Ghiglio, P., Cherubin, S., Goli, M., & Yang, S. (in press). Building a Reusable and Extensible Automatic Compiler Infrastructure for reconfigurable devices.

Multi-Level Intermediate Representation (MLIR) is gaining increasing attention in reconfigurable hardware communities due to its capability to represent various abstract levels for software compilers. This project aims to be the first to provide an e... Read More about Building a Reusable and Extensible Automatic Compiler Infrastructure for reconfigurable devices.

TAFFO: The compiler-based precision tuner (2022)
Journal Article
Cattaneo, D., Chiari, M., Agosta, G., & Cherubin, S. (2022). TAFFO: The compiler-based precision tuner. SoftwareX, 20, Article 101238. https://doi.org/10.1016/j.softx.2022.101238

We present taffo, a framework that automatically performs precision tuning to exploit the performance/accuracy trade-off. In order to avoid expensive dynamic analyses, taffo leverages programmer annotations which encapsulate domain knowledge about th... Read More about TAFFO: The compiler-based precision tuner.

Ahead-Of-Real-Time (ART): A Methodology for Static Reduction of Worst-Case Execution Time (2022)
Conference Proceeding
Cattaneo, D., Magnani, G., Cherubin, S., & Agosta, G. (2022). Ahead-Of-Real-Time (ART): A Methodology for Static Reduction of Worst-Case Execution Time. In Third Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2022) (4:1-4:10). https://doi.org/10.4230/OASIcs.NG-RES.2022.4

Precision tuning is an approximate computing technique for trading precision with lower execution time, and it has been increasingly important in embedded and high-performance computing applications. In particular, embedded applications benefit from... Read More about Ahead-Of-Real-Time (ART): A Methodology for Static Reduction of Worst-Case Execution Time.

Front Matter, Table of Contents, Preface, Conference Organization (2022)
Conference Proceeding
Palumbo, F., Bispo, J., & Cherubin, S. (2022). Front Matter, Table of Contents, Preface, Conference Organization. In F. Palumbo, J. Bispo, & S. Cherubin (Eds.), 13th Workshop on Parallel Programming and Run-Time Management Techniques for Many-Core Architectures and 11th Workshop on Design Tools and Architectures for Multicore Embedded Computing Platforms (PARMA-DITAM 2022). https://doi.org/10.4230/OASIcs.PARMA-DITAM.2022.0

Architecture-aware Precision Tuning with Multiple Number Representation Systems (2021)
Conference Proceeding
Cattaneo, D., Chiari, M., Fossati, N., Cherubin, S., & Agosta, G. (2021). Architecture-aware Precision Tuning with Multiple Number Representation Systems. In 2021 58th ACM/IEEE Design Automation Conference (DAC). https://doi.org/10.1109/dac18074.2021.9586303

Precision tuning trades accuracy for speed and energy savings, usually by reducing the data width, or by switching from floating point to fixed point representations. However, comparing the precision across different representations is a difficult ta... Read More about Architecture-aware Precision Tuning with Multiple Number Representation Systems.

FixM: Code generation of fixed point mathematical functions (2020)
Journal Article
Cattaneo, D., Chiari, M., Magnani, G., Fossati, N., Cherubin, S., & Agosta, G. (2021). FixM: Code generation of fixed point mathematical functions. Sustainable Computing, 29, part B, Article 100478. https://doi.org/10.1016/j.suscom.2020.100478

Approximate computing has seen significant interest as a design philosophy oriented to performance and energy efficiency [1]. Precision tuning is an approximate computing technique that trades off the accuracy of operations for performance and energy... Read More about FixM: Code generation of fixed point mathematical functions.

Dynamic Precision Autotuning with TAFFO (2020)
Journal Article
Cherubin, S., Cattaneo, D., Chiari, M., & Agosta, G. (2020). Dynamic Precision Autotuning with TAFFO. ACM transactions on architecture and code optimization, 17(2), Article 10. https://doi.org/10.1145/3388785

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 achieve such a trade-off is precision tuning—that is, to modify the data types... Read More about Dynamic Precision Autotuning with TAFFO.

Tunable approximations to control time-to-solution in an HPC molecular docking Mini-App (2020)
Journal Article
Gadioli, D., Palermo, G., Cherubin, S., Vitali, E., Agosta, G., Manelfi, C., …Silvano, C. (2021). Tunable approximations to control time-to-solution in an HPC molecular docking Mini-App. Journal of Supercomputing, 77(1), 841-869. https://doi.org/10.1007/s11227-020-03295-x

The drug discovery process involves several tasks to be performed in vivo, in vitro and in silico. Molecular docking is a task typically performed in silico. It aims at finding the three-dimensional pose of a given molecule when it interacts with the... Read More about Tunable approximations to control time-to-solution in an HPC molecular docking Mini-App.

Tools for Reduced Precision Computation: A Survey (2020)
Journal Article
Cherubin, S., & Agosta, G. (2020). Tools for Reduced Precision Computation: A Survey. ACM computing surveys, 53(2), Article 33. https://doi.org/10.1145/3381039

The use of reduced precision to improve performance metrics such as computation latency and power consumption is a common practice in the embedded systems field. This practice is emerging as a new trend in High Performance Computing (HPC), especially... Read More about Tools for Reduced Precision Computation: A Survey.

Automated Precision Tuning in Activity Classification Systems: A Case Study (2020)
Conference Proceeding
Fossati, N., Cattaneo, D., Chiari, M., Cherubin, S., & Agosta, G. (2020). Automated Precision Tuning in Activity Classification Systems: A Case Study. In PARMA-DITAM'2020: Proceedings of the 11th Workshop on Parallel Programming and Run-Time Management Techniques for Many-core Architectures. https://doi.org/10.1145/3381427.3381432

The greater availability and reduction in production cost make wearable IoT platforms perfect candidates to continuously monitor people at risk, like elderly people. In particular these platforms, along with the use of artificial intelligence algorit... Read More about Automated Precision Tuning in Activity Classification Systems: A Case Study.

TAFFO: Tuning Assistant for Floating to Fixed Point Optimization (2019)
Journal Article
Cherubin, S., Cattaneo, D., Chiari, M., Bello, A. D., & Agosta, G. (2020). TAFFO: Tuning Assistant for Floating to Fixed Point Optimization. IEEE Embedded Systems Letters, 12(1), 5-8. https://doi.org/10.1109/les.2019.2913774

While many approximate computing methods are quite application-dependent, reducing the size of the data representation used in the computation has a more general applicability. We present a tuning assistant for floating to fixed point optimization (T... Read More about TAFFO: Tuning Assistant for Floating to Fixed Point Optimization.

Towards a High-Performance Modelica Compiler (2019)
Conference Proceeding
Agosta, G., Baldino, E., Casella, F., Cherubin, S., Leva, A., & Terraneo, F. (2019). Towards a High-Performance Modelica Compiler. In Proceedings of the 13th International Modelica Conference, Regensburg, Germany, March 4–6, 2019 (313-320). https://doi.org/10.3384/ecp19157313

The use of Modelica as a modelling and simulation language is progressively replacing hand-tuned simulation code written in traditional imperative programming languages. This adoption is fuelled by the availability of libraries to target different ap... Read More about Towards a High-Performance Modelica Compiler.

libVersioningCompiler: An easy-to-use library for dynamic generation and invocation of multiple code versions (2018)
Journal Article
Cherubin, S., & Agosta, G. (2018). libVersioningCompiler: An easy-to-use library for dynamic generation and invocation of multiple code versions. SoftwareX, 7, 95-100. https://doi.org/10.1016/j.softx.2018.03.006

We present libVersioningCompiler, a C++ library designed to support the dynamic generation of multiple versions of the same compute kernel in a HPC scenario. It can be used to provide continuous optimization, code specialization based on the input da... Read More about libVersioningCompiler: An easy-to-use library for dynamic generation and invocation of multiple code versions.

Array-Aware Matching: Taming the Complexity of Large-Scale Simulation Models
Working Paper
Fioravanti, M., Cattaneo, D., Terraneo, F., Seva, S., Cherubin, S., Agosta, G., …Leva, A. (2022). Array-Aware Matching: Taming the Complexity of Large-Scale Simulation Models

Equation-based modelling is a powerful approach to tame the complexity of large-scale simulation problems. Equation-based tools automatically translate models into imperative languages. When confronted with nowadays' problems, however, well assessed... Read More about Array-Aware Matching: Taming the Complexity of Large-Scale Simulation Models.