[AMDGPU][True16][CodeGen] update wwm reg sorting check condition (llvm#135053)

We currently just need to shift down 32bit wwm registers. 

Previous check condition mistakenly select 16bit registers in true16
mode. Update check condition to skip the 16bit register in wmm reg
sorting

Author: broxigarchen

llvm/lib/Target/AMDGPU/SIFrameLowering.cpp

@@ -1650,7 +1650,7 @@ void SIFrameLowering::determineCalleeSaves(MachineFunction &MF,
     // are of 32-bit size. SIPreAllocateWWMRegs pass can add tuples into WWM
     // reserved registers.
     const TargetRegisterClass *RC = TRI->getPhysRegBaseClass(Reg);
-    if (TRI->getRegSizeInBits(*RC) > 32)
+    if (TRI->getRegSizeInBits(*RC) != 32)
       continue;
     SortedWWMVGPRs.push_back(Reg);
   }

llvm/test/CodeGen/AMDGPU/wwm-reg-shift-down-gfx11plus.mir

@@ -0,0 +1,28 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn-- -mcpu=gfx1100 -mattr=+real-true16 -run-pass=prologepilog %s -o - | FileCheck -check-prefix=GCN %s
+
+---
+name:            wwm_reg_skip_sort_16bit
+tracksRegLiveness: true
+machineFunctionInfo:
+  isEntryFunction: true
+body:             |
+  bb.0:
+    ; GCN-LABEL: name: wwm_reg_skip_sort_16bit
+    ; GCN: renamable $sgpr0 = ENTER_STRICT_WWM -1, implicit-def $exec, implicit-def $scc, implicit $exec
+    ; GCN-NEXT: $vgpr0 = IMPLICIT_DEF
+    ; GCN-NEXT: renamable $sgpr1 = V_READLANE_B32 $vgpr0, 31
+    ; GCN-NEXT: renamable $sgpr2 = S_MOV_B32 0
+    ; GCN-NEXT: undef $vgpr0_lo16 = V_CNDMASK_B16_t16_e64 0, 0, 0, killed $sgpr1, killed $sgpr2, 0, implicit $exec
+    ; GCN-NEXT: $exec_lo = EXIT_STRICT_WWM killed renamable $sgpr0
+    ; GCN-NEXT: early-clobber renamable $vgpr1 = V_MOV_B32_e32 $vgpr0, implicit $exec
+    ; GCN-NEXT: S_ENDPGM 0, implicit killed renamable $vgpr1
+    renamable $sgpr0 = ENTER_STRICT_WWM -1, implicit-def $exec, implicit-def $scc, implicit $exec
+    $vgpr0 = IMPLICIT_DEF
+    renamable $sgpr1 = V_READLANE_B32 $vgpr0, 31
+    renamable $sgpr2 = S_MOV_B32 0
+    undef $vgpr0_lo16 = V_CNDMASK_B16_t16_e64 0, 0, 0, killed $sgpr1, killed $sgpr2, 0, implicit $exec
+    $exec_lo = EXIT_STRICT_WWM killed renamable $sgpr0
+    early-clobber renamable $vgpr1 = V_MOV_B32_e32 $vgpr0, implicit $exec
+    S_ENDPGM 0, implicit killed renamable $vgpr1
+...