diff options
| author | michaelselehov <michael.selehov@amd.com> | 2025-09-29 17:57:07 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-09-30 00:57:07 +0900 |
| commit | 617854f81900d1776c11796dd4aacc82375e56ba (patch) | |
| tree | 7668468df6bb087d45f4b803068d58842f25b48a /llvm/lib/CodeGen/ModuloSchedule.cpp | |
| parent | 2e3f2523e624a4a922c386f6f1264c19f25a2e26 (diff) | |
| download | llvm-617854f81900d1776c11796dd4aacc82375e56ba.zip llvm-617854f81900d1776c11796dd4aacc82375e56ba.tar.gz llvm-617854f81900d1776c11796dd4aacc82375e56ba.tar.bz2 | |
[AMDGPU] LRO: allow same-BB non-lookthrough users for PHI (#160909)
Loop headers frequently consume the loop-carried value in the header
block via non-lookthrough ops (e.g. byte-wise vector binops).
LiveRegOptimizer’s same-BB filter currently prunes these users, so the
loop-carried PHI is not coerced to i32 and the intended packed form is
lost.
Relax the filter: when the def is a PHI, allow same-BB non-lookthrough
users. Also fix the check to look at the user (CII) rather than the def
(II) so the walk does not terminate prematurely.
Diffstat (limited to 'llvm/lib/CodeGen/ModuloSchedule.cpp')
0 files changed, 0 insertions, 0 deletions