diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2024-03-15 15:51:53 +0530 |
|---|---|---|
| committer | Matt Arsenault <arsenm2@gmail.com> | 2024-03-15 16:08:39 +0530 |
| commit | c7c561ef98ad783d257dab3940dd2378ef8760bf (patch) | |
| tree | 720a9f80a4bd6c3a6d1fdd96ac77eebf43ed2269 /llvm/lib/Bitcode/Reader/BitcodeReader.cpp | |
| parent | fe753f77c35cf236b8aed6b5ebd857973e047925 (diff) | |
| download | llvm-c7c561ef98ad783d257dab3940dd2378ef8760bf.zip llvm-c7c561ef98ad783d257dab3940dd2378ef8760bf.tar.gz llvm-c7c561ef98ad783d257dab3940dd2378ef8760bf.tar.bz2 | |
AMDGPU: Enable ExpandLargeFpConvert for > 64-bit types
Fixes casts between double/float/half and i128. The pass seems to be
broken for bfloat though. I also believe we could have a better implementation
which attempts to make use the native 32-bit conversion instructions like
the 64-bit expansion does.
Diffstat (limited to 'llvm/lib/Bitcode/Reader/BitcodeReader.cpp')
0 files changed, 0 insertions, 0 deletions