================
@@ -449,6 +449,10 @@ Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned
BuiltinID,
llvm::Function *F = CGM.getIntrinsic(IID, {Value->getType()});
return Builder.CreateCall(F, {Value, Strategy});
}
+ case AMDGPU::BI__builtin_amdgcn_wave_shuffle:
+ // TODO: can we unify this with wave_reduce?
----------------
easyonaadit wrote:
I didn't really understand this comment, what idea did you have to unify
wave_reduce and shuffle?
https://github.com/llvm/llvm-project/pull/179492
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
