arsenm added inline comments.
================
Comment at: lib/CodeGen/CGBuiltin.cpp:11313-11315
+ case AMDGPU::BI__builtin_amdgcn_update_dpp: {
+ llvm::SmallVector<llvm::Value *, 6> Args;
+ for (unsigned I = 0; I != 6; ++I)
----------------
b-sumner wrote:
> arsenm wrote:
> > The only difference between this and mov_dpp is the argument count and the
> > intrinsic ID, so you can combine the cases
> We should really drop mov_dpp. It will be easier to do so if we keep the
> cases separate.
We could also emit the mov_dpp with the new intrinsic, using I think undef for
the extra operand?
https://reviews.llvm.org/D52320
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
