Joseph Huber c3a3d20093 [LV] Add analysis remark for mixed precision conversions
Floating point conversions inside vectorized loops have performance
implications but are very subtle. The user could specify a floating
point constant, or call a function without realizing that it will
force a change in the vector width. An example of this behaviour is
seen in https://godbolt.org/z/M3nT6c . The vectorizer should indicate
when this happens becuase it is most likely unintended behaviour.

This patch adds a simple check for this behaviour by following floating
point stores in the original loop and checking if a floating point
conversion operation occurs.

Reviewed By: fhahn

Differential Revision: https://reviews.llvm.org/D95539
2021-02-17 21:37:08 -05:00
..
2020-12-04 11:05:01 -08:00
2021-02-02 11:09:31 +00:00
2020-12-14 12:01:19 +00:00
2021-01-05 13:25:42 -08:00
2021-02-17 16:01:32 -08:00