| commit | 45a334d31cc3a22b1aa28ba463130eb8622abad7 | |
| author | Philip Reames <preames@rivosinc.com> | |
| Wed, 4 Oct 2023 17:30:47 +0000 (4 10:30 -0700) | ||
| committer | Philip Reames <listmail@philipreames.com> | |
| Wed, 4 Oct 2023 17:41:29 +0000 (4 10:41 -0700) | ||
| tree | e87bfd5be577065c4e16c57e86d1f82c9f15af1a | treesnapshot (tar.gz zip) |
| parent | 7a73a2c241211ad8b492aa13bb8908589c378d16 | commitdiff |
[RISCV] Generaize reduction tree matching to all integer reductions (#68014) (reapply)
This was reverted in 824251c9b349d859a9169196cd9533c619a715ce exposed by this change in a previous patch. Fixed in 199cbec987ee68d70611db8e7961b43c3dbad83e. Original commit message follows.
This builds on the transform introduced in
https://github.com/llvm/llvm-project/pull/67821, and generalizes it for
all integer reduction types.
A couple of notes:
* This will only form smax/smin/umax/umin reductions when zbb is
enabled. Otherwise, we lower the min/max expressions early. I don't care
about this case, and don't plan to address this further.
* This excludes floating point. Floating point introduces concerns about
associativity. I may or may not do a follow up patch for that case.
* The explodevector test change is mildly undesirable from a clarity
perspective. If anyone sees a good way to rewrite that to stablize the
test, please suggest.
This was reverted in 824251c9b349d859a9169196cd9533c619a715ce exposed by this change in a previous patch. Fixed in 199cbec987ee68d70611db8e7961b43c3dbad83e. Original commit message follows.
This builds on the transform introduced in
https://github.com/llvm/llvm-project/pull/67821, and generalizes it for
all integer reduction types.
A couple of notes:
* This will only form smax/smin/umax/umin reductions when zbb is
enabled. Otherwise, we lower the min/max expressions early. I don't care
about this case, and don't plan to address this further.
* This excludes floating point. Floating point introduces concerns about
associativity. I may or may not do a follow up patch for that case.
* The explodevector test change is mildly undesirable from a clarity
perspective. If anyone sees a good way to rewrite that to stablize the
test, please suggest.