[clang] [libcxx] [libc] [lld] [llvm] [flang] [clang-tools-extra] [lldb] [compiler-rt] [AMDGPU][GFX12] VOP encoding and codegen - add support for v_cvt fp8/… (PR #78414)

[Ivan Kosarev via cfe-commits]

Mirko =?utf-8?q?Brkušanin?= <Mirko.Brkusanin at amd.com>
Message-ID:
In-Reply-To: <llvm.org/llvm/llvm-project/pull/78414 at github.com>


================
@@ -305,6 +305,11 @@ class VOP3OpSel_gfx10<bits<10> op, VOPProfile p> : VOP3e_gfx10<op, p> {
 
 class VOP3OpSel_gfx11_gfx12<bits<10> op, VOPProfile p> : VOP3OpSel_gfx10<op, p>;
 
+class VOP3FP8OpSel_gfx11_gfx12<bits<10> op, VOPProfile p> : VOP3e_gfx10<op, p> {
+  let Inst{11} = !if(p.HasSrc0, src0_modifiers{2}, 0);
+  let Inst{12} = !if(p.HasSrc0, src0_modifiers{3}, 0);
----------------
kosarev wrote:

Yes, thanks Mirko. Can we also avoid adding the other dummy operands in `cvtVOP3DPP()` and `cvtDPP()`?

https://github.com/llvm/llvm-project/pull/78414