Joseph Huber 8cfcdee95e [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
..
AggressiveInstCombine
CFGuard
Coroutines	[coro async] Don't promote allocas to the frame or rewrite swifterror if there are no suspend points	2021-02-16 09:05:38 -08:00
Hello
InstCombine	[InstCombine] fold fcmp-of-copysign idiom	2021-02-17 10:32:33 -05:00
Instrumentation	[PGO] Drop unnecessary const from return types (NFC)	2021-02-11 23:31:29 -08:00
IPO	[WPD] Add an optional checking mode for debugging devirtualization	2021-02-17 16:46:15 -08:00
ObjCARC	[ObjC][ARC] Do not perform code motion on precise release calls	2021-02-15 17:39:37 -08:00
Scalar	[SROA] Propagate correct TBAA/TBAA Struct offsets	2021-02-17 11:59:00 -05:00
Utils	[SampleFDO] Third Try: Refactor SampleProfile.cpp	2021-02-17 15:31:50 -08:00
Vectorize	[LV] Add analysis remark for mixed precision conversions	2021-02-17 21:37:08 -05:00
CMakeLists.txt