OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-06 12:20:52 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity

Minor doc fix: change truncating to rounding in TF32 docs (#49625)

Browse Source 
Summary:
Minor doc fix in clarifying that the input data is rounded not truncated.

CC zasdfgbnm ngimel

Pull Request resolved: https://github.com/pytorch/pytorch/pull/49625

Reviewed By: mruberry

Differential Revision: D25668244

Pulled By: ngimel

fbshipit-source-id: ac97e41e0ca296276544f9e9f85b2cf1790d9985
This commit is contained in:
pbialecki 2020-12-22 13:44:41 -08:00 committed by Facebook GitHub Bot
parent 21398fb6cb
commit 1451d84766
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/notes/cuda.rst
View File

@ -65,7 +65,7 @@ available on new NVIDIA GPUs since Ampere, internally to compute matmul (matrix
and batched matrix multiplies) and convolutions. and batched matrix multiplies) and convolutions.
TF32 tensor cores are designed to achieve better performance on matmul and convolutions on TF32 tensor cores are designed to achieve better performance on matmul and convolutions on
`torch.float32` tensors by truncating input data to have 10 bits of mantissa, and accumulating `torch.float32` tensors by rounding input data to have 10 bits of mantissa, and accumulating
results with FP32 precision, maintaining FP32 dynamic range. results with FP32 precision, maintaining FP32 dynamic range.
matmuls and convolutions are controlled separately, and their corresponding flags can be accessed at: matmuls and convolutions are controlled separately, and their corresponding flags can be accessed at: