diff options
| author | Nikita Popov <npopov@redhat.com> | 2022-02-22 17:53:14 +0100 |
|---|---|---|
| committer | Nikita Popov <npopov@redhat.com> | 2022-02-23 09:37:30 +0100 |
| commit | 65dc78d63ee2eb20fbed54401091f08a685ef8c1 (patch) | |
| tree | 6455faf9eda1dc963799472ffb537d285829e8c2 /llvm/lib/CodeGen/MachineModuleInfo.cpp | |
| parent | 79353f940cf441e69f32af0a78a48baee89e8517 (diff) | |
| download | llvm-65dc78d63ee2eb20fbed54401091f08a685ef8c1.zip llvm-65dc78d63ee2eb20fbed54401091f08a685ef8c1.tar.gz llvm-65dc78d63ee2eb20fbed54401091f08a685ef8c1.tar.bz2 | |
[InstCombine] Remove one-use limitation from X-Y==0 fold
This one-use limitation is artificial, we do not increase
instruction count if we perform the fold with multiple uses. The
motivating case is shown in @sub_eq_zero_select, where the one-use
limitation causes us to miss a subsequent select fold.
I believe the backend is pretty good about reusing flag-producing
subs for cmps with same operands, so I think doing this is fine.
Differential Revision: https://reviews.llvm.org/D120337
Diffstat (limited to 'llvm/lib/CodeGen/MachineModuleInfo.cpp')
0 files changed, 0 insertions, 0 deletions