Robust and Energy-Efficient Numerical Solvers Towards Reliable and Sustainable Scientific Computations

ended

Computations in parallel environments, like the emerging Exascale systems, are usually orchestrated by complex runtimes that employ various strategies to uniformly and efficiently distribute computations and data. However, these strategies, pursuing excellent performance scalability, may also impair numerical reliability (accuracy and reproducibility) of final results due to the dynamic and, thus, non-deterministic execution as well as non-associativity of floating-point operations. Additionally, scientific computations frequently rely upon only one working precision for computing problems with various complexities, which leads to the significant underutilization of the floating-point representation or the lack of accuracy. The Robust project aims to address the issue of reliable and sustainable scientific computations through developing robust, energy-efficient, and high performing algorithmic solutions for underlying numerical linear algebra solvers and libraries as well as applying these solutions in applications and kernels at scale. The fellow, Roman Iakymchuk, is an expert in numerical linear algebra and high-performance computing and will collaborate with the research team of Prof. Stef Graillat at the Sorbonne University, who are experts in numerical analysis and computer arithmetic. This unique collaboration and combination of skill sets are crucial to embed numerical reliability and sustainability in algorithmic solutions for linear algebra operations and solvers. The derivation of novel robust algorithmic solutions, which will lead to either faster or more energy-efficient execution, will also grant a user an opportunity to specify the expected output accuracy of computations while ensuring optimal intermediate precisions. This ambitious research project in conjunction with formal training and bespoke mentoring will enhance the fellow's academic profile, research experience, and broaden skill set in numerical analysis and computer arithmetic.