diff options
| author | Luke Lau <luke@igalia.com> | 2025-07-30 13:14:28 +0800 |
|---|---|---|
| committer | Luke Lau <luke@igalia.com> | 2025-07-30 13:29:47 +0800 |
| commit | 2a5ac19605ae49d6628ac3af55d6b528cb13ed2e (patch) | |
| tree | a88f1be3bb85acf7ea143a76b8ad10dc9c0e5b9a /clang/lib/CodeGen/CodeGenModule.cpp | |
| parent | f527b319e377202e44b14b6875584a558a628803 (diff) | |
| download | llvm-2a5ac19605ae49d6628ac3af55d6b528cb13ed2e.zip llvm-2a5ac19605ae49d6628ac3af55d6b528cb13ed2e.tar.gz llvm-2a5ac19605ae49d6628ac3af55d6b528cb13ed2e.tar.bz2 | |
Revert "[RISCV] Cost bf16/f16 vector non-unit memory accesses as legal without zvfhmin/zvfbfmin (#150882)"
This reverts commit fe4f6c1a58ab4f00a88a97af01000b6783b573ee, but leaves
the tests that were added.
The original commit mistakenly assumed that if regular bf16/f16 loads
and stores could be lowered without zvfbfmin/zvfhmin, then so too could
masked loads/stores and gathers/scatters.
However SelectionDAG can't actually type-legalize masked.load/stores
since it needs to be done in ScalarizeMaskedMemIntrinPass.
This was causing crashes on IREE because we now returned true for
isLegalMaskedLoadStore.
The original intent of this was to remove a discrepancy in the loop
vectorizer tests whenever predication was enabled, but this has gone
away after 92d09245d61dce80d3e68a27cc34d5fc6f062c93. So I don't think we
need to reapply this patch.
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
0 files changed, 0 insertions, 0 deletions