[clang] [AMDGPU] Modifies builtin def to take _Float16('x') for both HIP/C++ and for OpenCL (PR #167652)

Wed, 03 Dec 2025 23:14:27 -0800 

================
@@ -10527,6 +10527,21 @@ bool ASTContext::areCompatibleVectorTypes(QualType 
FirstVec,
       Second->getVectorKind() != VectorKind::RVVFixedLengthMask_4)
     return true;
 
+  // In OpenCL, treat half and _Float16 vector types as compatible.
----------------
ranapratap55 wrote:

Created a separate PR for: https://github.com/llvm/llvm-project/pull/170605

https://github.com/llvm/llvm-project/pull/167652
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to