Numerical Behavior of NVIDIA Tensor Cores

Fasi, Massimiliano and Higham, Nicholas J. and Mikaitis, Mantas and Pranesh, Srikara (2020) Numerical Behavior of NVIDIA Tensor Cores. [MIMS Preprint] (In Press)

This is the latest version of this item.

[thumbnail of fhmp20.pdf] Text

Download (198kB)


We explore the floating-point arithmetic implemented in the NVIDIA tensor cores, which are hardware accelerators for mixed-precision matrix multiplication available on the Volta, Turing, and Ampere microarchitectures. Using Volta V100, Turing T4 and Ampere A100 graphics cards, we determine what precision is used for the intermediate results, whether subnormal numbers are supported, what rounding mode is used, in which order the operations underlying the matrix multiplication are performed, and whether partial sums are normalized. These aspects are not documented by NVIDIA, and we gain insight by running carefully designed numerical experiments on these hardware units. Knowing the answers to these questions is important if one wishes to: 1) accurately simulate NVIDIA tensor cores on conventional hardware; 2) understand the differences between results produced by code that utilizes tensor cores and code that uses only IEEE 754-compliant arithmetic operations; and 3) build custom hardware whose behavior matches that of NVIDIA tensor cores. As part of this work we provide a test suite that can be easily adapted to test newer versions of the NVIDIA tensor cores as well as similar accelerators from other vendors, as they become available. Moreover, we identify a non-monotonicity issue affecting floating point multi-operand adders if the intermediate results are not normalized after each step.

Item Type: MIMS Preprint
Subjects: MSC 2010, the AMS's Mathematics Subject Classification > 65 Numerical analysis
MSC 2010, the AMS's Mathematics Subject Classification > 68 Computer science
Depositing User: Mr Mantas Mikaitis
Date Deposited: 12 Nov 2020 21:21
Last Modified: 12 Nov 2020 21:21

Available Versions of this Item

Actions (login required)

View Item View Item