aboutsummaryrefslogtreecommitdiff
path: root/clang/lib/Frontend/FrontendAction.cpp
diff options
context:
space:
mode:
authorStanislav Mekhanoshin <rampitec@users.noreply.github.com>2023-11-28 09:07:26 -0800
committerGitHub <noreply@github.com>2023-11-28 09:07:26 -0800
commit87d884b5c8ff3f477b54fcd5a7966df49f1f8111 (patch)
tree9138bd2685f249c7097070ca3e9f2d4ce4431c7d /clang/lib/Frontend/FrontendAction.cpp
parenta1b3b78c55be7e95042e22d83a7f183ae6cc865a (diff)
downloadllvm-87d884b5c8ff3f477b54fcd5a7966df49f1f8111.zip
llvm-87d884b5c8ff3f477b54fcd5a7966df49f1f8111.tar.gz
llvm-87d884b5c8ff3f477b54fcd5a7966df49f1f8111.tar.bz2
[AMDGPU] Fix folding of v2i16/v2f16 splat imms (#72709)
We can use inline constants with packed 16-bit operands, but these should use op_sel. Currently splat of inlinable constants is considered legal, which is not really true if we fail to fold it with op_sel and drop the high half. It may be legal as a literal but not as inline constant, but then usual literal checks must be performed. This patch makes these splat literals illegal but adds additional logic to the operand folding to keep current folds. This logic is somewhat heavy though. This has fixed constant bus violation in the fdot2 test.
Diffstat (limited to 'clang/lib/Frontend/FrontendAction.cpp')
0 files changed, 0 insertions, 0 deletions