diff options
| author | YixingZhang007 <yixing.zhang@intel.com> | 2025-09-16 06:21:43 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-09-16 12:21:43 +0200 |
| commit | 3a5cc953dce0e142e935335a4cdbc5821ddf6d11 (patch) | |
| tree | f89f31d12d2de510e22c99c284c09bf80166bd65 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 46fcece2a8015980fa51bece0d87311af10da553 (diff) | |
| download | llvm-3a5cc953dce0e142e935335a4cdbc5821ddf6d11.zip llvm-3a5cc953dce0e142e935335a4cdbc5821ddf6d11.tar.gz llvm-3a5cc953dce0e142e935335a4cdbc5821ddf6d11.tar.bz2 | |
[SPIRV] Add FPEncoding operand support for OpTypeFloat (#156871)
This PR introduces support for `FPEncoding` operand for SPIR-V
instruction `OpTypeFloat`, with the following main changes:
1. Introduces `FPEncoding` enum class to represent floating-point
encodings, such as `BFloat16KHR`, in SPIR-V.
2. Updates SPIR-V instruction `OpTypeFloat` to accept `FPEncoding` as
its second input operand.
3. Updates SPIR-V type creation to handle new encoding requirements.
This PR enables support for the BFloat floating-point type in SPIR-V.
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions