Skip to content

Conversation

@mayeut
Copy link
Contributor

@mayeut mayeut commented Nov 23, 2025

The compinv function is invalid when building for BFLOAT16 and leads to the following warning: taking the absolute value of unsigned type 'bfloat16' (aka 'unsigned short') has no effect.
Update pre-processor conditions to remove its definition when building for BFLOAT16.

The compinv function is invalid when building for BFLOAT16 and leads to the following warning:
`taking the absolute value of unsigned type 'bfloat16' (aka 'unsigned short') has no effect`.
Update pre-processor conditions to remove its definition when building for BFLOAT16.
@martin-frbg martin-frbg added this to the 0.3.31 milestone Nov 23, 2025
@martin-frbg martin-frbg merged commit 88c1899 into OpenMathLib:develop Nov 23, 2025
100 of 102 checks passed
@mayeut mayeut deleted the warn-bfloat16 branch November 23, 2025 19:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants