[PATCH] D133723: [AMDGPU][GFX11] Use VGPR_32_F128 for VOP1,2,C

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIRegisterInfo.td:557
+
+def VGPR_32_F128 : SIRegisterClass<"AMDGPU", !listconcat(Reg32Types.types, Reg16Types.types), 32,
+                            (add (sequence "VGPR%u", 0, 127))> {
----------------
arsenm wrote:
> Joe_Nash wrote:
> > arsenm wrote:
> > > I don't know what "_F128" is supposed to mean. I read this as a class for long double
> > It is short for First 128. Is a set with only the first 128 VGPRs. I will add a comment noting this. 
> Lo128 would probably be more consistent terminology over "first"
I probably agree to that. F128 also hints a long double to me.
With that I still hope this class is transitional and will be replaced by a real 16 bit RC.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D133723/new/

https://reviews.llvm.org/D133723