SoftNum · Software-Defined Number Formats: Bridging the Gap between Performance, Accuracy, and Security
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2022-09-01 → 2025-01-16
- EU contribution
- €224,934
- Participants
- 1
- Scheme
- MSCA-IF
Lines connect the coordinator with its partners.
Results in brief
Software-Defined Number Formats: Bridging the Gap between Performance, Accuracy, and Security
Nearly all computing devices implement the same standardized hardware-supported number formats to aid software portability. The MSCA SOFTNUM project attempts to answer the question of whether using the same standardized number formats for all applications is still the best approach to achieve high performance. The efficiency benefits of low-precision number formats suggest that a single format may no longer be sufficient for all diverse computing applications. In fact, a single application might benefit from using multiple software-implemented compact number formats, making the use of a single hardwired format no longer effective. The main objective of the SOFTNUM is to explore software-defined number formats, an innovative approach which transforms number formats, generally considered to be hard-wired functionality, software-defined. These software-defined number formats are designed at the software level to meet the numeric needs of the computation and are more compact representations of the data. They reduce memory footprint and bandwidth requirements without sacrificing accuracy, which results in a speedup compared to the purely use of conventional hardwired number formats. This new approach can have significant positive outcomes for society. Reducing computations and memory storage using flexible software-level small numbers leads to sustainable computing. This means a smaller carbon footprint and lower energy requirements while still providing better speed and the same accuracy as traditional methods.
Data: CORDIS, © European Union
Project objective
All computing devices implement computer arithmetic as a core functionality. Nearly all computing devices moreover implement the same, standardized number formats in order to aid software portability. However, with Moore’s Law ending, we question whether it remains the best approach to achieve high performance and low energy consumption by applying the same standardized number formats for all applications. Among others, the Internet-of-Things (IoT) presents a proliferation of compute devices with a wide variety of functionality, among others in data sensing, data analytics, and inference of machine-learned models. Additionally, security mechanisms, which are essential for internet-connected devices, are compute-intensive workloads. We posit that each of these workloads will see improved performance and energy-efficiency from distinct, specialized computer arithmetic. The SoftNum Marie Curie Fellowship will explore how to make number formats, generally considered to be hard-wired functionality, software-defined. Software-defined number formats have the advantage of high performance, low energy consumption, and ensure sufficient while not excessive precision. For instance, with SoftNum it will be possible to design a data sensing device that pre-processes data streams at the minimal precision possible to minimize energy consumption, embeds a watermark to prove ownership and origin of the data, all while achieving the required application-level accuracy. This project, if successful, will have a major impact on how we perceive the design of computing devices. It will create an unprecedented degree of virtualization of the core computing hardware, with an estimated system-level speedup of 50% and reduction of energy consumption by 70%. This novel proposition promises to accelerate the Fellow’s career, who brings prior expertise in computer arithmetic to the project, under the mentorship of an expert in transprecise computing and runtime system software.
Original text from CORDIS.
Participants
- THE QUEEN'S UNIVERSITY OF BELFAST · BELFASTCoordinatorUnited Kingdom
Links
Data: CORDIS, © European Union