diff options
author | Juneyoung Lee <aqjune@gmail.com> | 2021-01-13 09:33:21 +0900 |
---|---|---|
committer | Juneyoung Lee <aqjune@gmail.com> | 2021-01-13 09:36:52 +0900 |
commit | 25eb7b08ba77a0b7c9c938490444bb8b5121233c (patch) | |
tree | 72efb16420a01172f5cff1ab90d0dfc8621282a5 /llvm/lib/Transforms/Utils/LoopUtils.cpp | |
parent | 76643c48cdddfa220680f1ab4a83829bd83faa7a (diff) | |
download | llvm-25eb7b08ba77a0b7c9c938490444bb8b5121233c.zip llvm-25eb7b08ba77a0b7c9c938490444bb8b5121233c.tar.gz llvm-25eb7b08ba77a0b7c9c938490444bb8b5121233c.tar.bz2 |
[DAGCombiner] Fold BRCOND(FREEZE(COND)) to BRCOND(COND)
This patch resolves the suboptimal codegen described in http://llvm.org/pr47873 .
When CodeGenPrepare lowers select into a conditional branch, a freeze instruction is inserted.
It is then translated to `BRCOND(FREEZE(SETCC))` in SelDag.
The `FREEZE` in the middle of `SETCC` and `BRCOND` was causing a suboptimal code generation however.
This patch adds `BRCOND(FREEZE(cond))` -> `BRCOND(cond)` fold to DAGCombiner to remove the `FREEZE`.
To make this optimization sound, `BRCOND(UNDEF)` simply should nondeterministically jump to the branch or not, rather than raising UB.
It wasn't clear what happens when the condition was undef according to the comments in ISDOpcodes.h, however.
I updated the comments of `BRCOND` to make it explicit (as well as `BR_CC`, which is also a conditional branch instruction).
Note that it diverges from the semantics of `br` instruction in IR, which is explicitly UB.
Since the UB semantics was necessary to explain optimizations that use branching conditions, and SelDag doesn't seem to have such optimization, I think this divergence is okay.
Reviewed By: spatel
Differential Revision: https://reviews.llvm.org/D92015
Diffstat (limited to 'llvm/lib/Transforms/Utils/LoopUtils.cpp')
0 files changed, 0 insertions, 0 deletions