FTTN: Feature-Targeted Testing for Numerical Properties of NVIDIA & AMD Matrix Accelerators
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- University of Utah
FTTN is a test suite to evaluate the numerical behaviors of matrix accelerators of GPUs (NVIDIA Tensor Cores and AMD Matrix Cores) in a quick and simple setting. Matrix accelerators are heavily used in today's computationally intense applications to speed up matrix multiplications. This test suite provides a comprehensive study on the numerical behaviors of these accelerators, including support for subnormals, rounding modes, extra precision bits and FMA features. Is there
- Short Name / Acronym:
- FTTN
- Site Accession Number:
- LLNL-CODE-2000523
- Software Type:
- Scientific
- License(s):
- MIT License
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)Primary Award/Contract Number:AC52-07NA27344
- DOE Contract Number:
- AC52-07NA27344
- Code ID:
- 145775
- OSTI ID:
- code-145775
- Country of Origin:
- United States
Similar Records
FTTN: Feature-Targeted Testing for Numerical Properties of NVIDIA & AMD Matrix Accelerators
Optimization and Portability of a Fusion OpenACC-based FORTRAN HPC Code from NVIDIA to AMD GPUs
Moment Representation of Regularized Lattice Boltzmann Methods on NVIDIA and AMD GPUs
Conference
·
Tue Oct 08 00:00:00 EDT 2024
·
OSTI ID:2539787
Optimization and Portability of a Fusion OpenACC-based FORTRAN HPC Code from NVIDIA to AMD GPUs
Conference
·
Sat Jul 01 00:00:00 EDT 2023
·
OSTI ID:2301616
Moment Representation of Regularized Lattice Boltzmann Methods on NVIDIA and AMD GPUs
Conference
·
Wed Nov 01 00:00:00 EDT 2023
·
OSTI ID:2224172