diff options
| author | Brox Chen <guochen2@amd.com> | 2024-10-16 12:26:01 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-10-16 12:26:01 -0400 |
| commit | 35e937b4de1890186347a382f7727ba86441dbda (patch) | |
| tree | 1d8e497fbbf8feee894f05ab7fb3c31954ee2c0b /clang/lib/CodeGen/CodeGenModule.cpp | |
| parent | 7ebe5a1ec00ce463ef421cdb4a3d84500c09e77a (diff) | |
| download | llvm-35e937b4de1890186347a382f7727ba86441dbda.zip llvm-35e937b4de1890186347a382f7727ba86441dbda.tar.gz llvm-35e937b4de1890186347a382f7727ba86441dbda.tar.bz2 | |
[AMDGPU][True16][CodeGen] fp conversion in true/fake16 format (#101678)
fp conversion V_CVT_F_F/V_CVT_F_U instructions true16 format were
previously implemented using fake16 profile.
With the MC support inplace, correct and support these instructions in
true16/fake16 format in CodeGen
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
0 files changed, 0 insertions, 0 deletions