Category Archives: SoftNum

SoftNum Project Results

Posted on by

The SOFTNUM project, funded by the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 101031148, has introduced a novel paradigm where number formats are software-defined rather than hardwired. This advancement moves beyond traditional computing, which relies on conventional hardware-supported floating-point number formats. In such systems, concerns about portability and compatibility often lead to unnecessary computational and memory overhead for many applications. The project has demonstrated that by leveraging software-defined number formats, computational efficiency can be achieved without sacrificing accuracy. This has been validated through comprehensive theoretical and experimental studies, with findings published in the resulting papers. For more details, please refer to the following key publications of the SoftNum:

A. S. Molahosseini, J. Lee and H. Vandierendonck, “Software-Defined Number Formats for High-Speed Belief Propagation,” in IEEE Transactions on Emerging Topics in Computing, 2025 (Full-Text is available here).

A. S. Molahosseini and H. Vandierendonck, “Exploiting Data Redundancy in CKKS Encoding for High-Speed Homomorphic Encryption,” In Proceedings of the 19th ACM Asia Conference on Computer and Communications Security (ASIA CCS ’24), Singapore, 2024 (Full-Text is available here).

New Paper Accepted in IEEE Transactions on Emerging Topics in Computing

Posted on by

Our group has published a new paper in the IEEE Transactions on Emerging Topics in Computing. In this study, we introduced Software-Defined Floating-Point (SDF) number formats designed to enhance the performance of the Belief Propagation (BP) algorithm, which is widely used in fields like machine learning, communications, and robotics. Traditional floating-point formats, such as single (32-bit) and double precision (64-bit), consume a lot of memory and require high bandwidth, making BP implementations slow especially for large-scale graphs or on devices with limited resources.  Our SDF formats, using more compact 16-bit (half-precision) and 8-bit (mini-precision) representations, significantly reduce memory usage and bandwidth needs without losing the necessary accuracy for BP applications. It should be noted that a standard 8-bit floating-point format (E5M2 or E4M3) are not applicable for BP as they cannot provide convergence. Therefore, software-defined floating-point format design is necessary. 

To ensure that our SDF formats work efficiently on standard CPUs, we developed highly effective software implementations that convert SDF numbers to single-precision arithmetic with minimal overhead. In our experiments using Ising grids sized from 100×100 to 500×500, our 16-bit and 8-bit SDF formats achieved speedups of up to 3.40 times compared to traditional double-precision floating-point formats on an Intel Xeon processor. Importantly, these performance gains did not compromise the accuracy of the BP algorithm, maintaining results equivalent to those obtained with double precision. Larger grid sizes benefited even more from the speed improvements, demonstrating the scalability and effectiveness of our approach.

For more information please visit https://ieeexplore.ieee.org/document/10847799

SoftNum: Software-Defined Number Formats

Posted on by

Computing devices implement computer arithmetic as basic functionality, and they implement the same, standardized number formats in order to support 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. We 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.

SoftNum is Amir’s individual Marie Sklodowska Curie Fellowship, sponsored by the European Commission.