FPBench includes a suite of benchmarks, drawn
from published floating-point research.
These benchmarks have been contributed by multiple research
groups. These contributions are listed here in chronological order.
Each listed paper has all its evaluation examples incorporated into
For each benchmark, FPBench records its name (preferably as used
in a paper), descriptive information such as citations, and finally
semantic metadata such as the precision used and preconditions.
The CPU group at the University of Utah
Center for Parallel
Computing at Utah group's FPTaylor project contributed 21
benchmarks, many short textbook examples and mathematical
Rigorous Estimation of Floating-Point Round-off Errors with Symbolic Taylor Expansions
Alexey Solovyev, Charlie Jacobsen, Zvonimir Rakamaric, Ganesh Gopalakrishnan, FM'15
The AVA group at the Max Plank Institute for Software Systems
The Automated Verification and Approximation group's Rosa project
contributed 37 benchmarks, mostly drawn from scientific
computations and control theory.
Sound Compilation of the Reals
Eva Darulova, Viktor Kuncak, POPL'14
The LAMPS group at the Université de Perpignan Via Domitia
de Mathématiques et de Physique group's Salsa project
contributed 25 benchmarks, all programs with loops drawn from
mathematical algorithms and control theory.
Intra-procedural Optimization of the Numerical Accuracy of Programs
Nasrine Damouche, Matthieu Martel, Alexandre Chapoutot, FMICS'15
Transformation of a PID Controller for Numerical Accuracy
Nasrine Damouche, Matthieu Martel, Alexandre Chapoutot, NSV'15
Optimizing the Accuracy of a Rocket Trajectory Simulation by Program Transformation
Nasrine Damouche, Matthieu Martel, Alexandre Chapoutot, CF'15
The PLSE group at the University of Washington
Programming Languages and
group's Herbie project
contributed 28 benchmarks, mostly drawn from Richard
Hamming's Numerical Methods for Scientists and Engineers.