Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

FTTN: Feature-Targeted Testing for Numerical Properties of NVIDIA & AMD Matrix Accelerators

Software ·
DOI:https://doi.org/10.11578/dc.20241018.1· OSTI ID:code-145775 · Code ID:145775
 [1];  [2];  [2]
  1. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
  2. 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
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

Related Subjects