search

giaf / blasfeo

Basic linear algebra subroutines for embedded optimization
Other
321 stars 88 forks source link

Replace AVX instructions in SSE3 kernel by <=SSE3 equivalents. #166

Closed nielsvd closed 2 years ago

nielsvd commented 2 years ago

Hi Gianluca, we have found some AVX instructions being used in the SS3 kernel that obviously don't work on SSE3-only hardware. These changes should fix the issue.

giaf commented 2 years ago

Hey Niels, thanks for spotting these AVX instructions where they should have not been :p