[llvm] [AMDGPU] Fix VGPR lowering for V_DUAL_FMAMK_F32 (PR #170567)

[Stanislav Mekhanoshin via llvm-commits]

================
@@ -283,11 +283,11 @@ body:             |
     ; GCN-NEXT: v_dual_mov_b32 v2, v3 /*v259*/ :: v_dual_add_f32 v3, v1 /*v257*/, v2 /*v258*/
     $vgpr2, $vgpr3 = V_DUAL_MOV_B32_e32_X_ADD_F32_e32_gfx1250 undef $vgpr259, undef $vgpr257, undef $vgpr258, implicit $exec, implicit $mode
 
-    ; GCN-NEXT: s_set_vgpr_msb 0x544
+    ; GCN-NEXT: s_set_vgpr_msb 0x554
     ; GCN-NEXT: v_dual_fmamk_f32 v244 /*v500*/, v0, 0xa, v44 /*v300*/ :: v_dual_fmac_f32 v3 /*v259*/, v1, v1 /*v257*/
     $vgpr500, $vgpr259 = V_DUAL_FMAMK_F32_X_FMAC_F32_e32_gfx1250 undef $vgpr0, 10, undef $vgpr300, undef $vgpr1, undef $vgpr257, $vgpr259, implicit $mode, implicit $exec
 
-    ; GCN-NEXT: s_set_vgpr_msb 0x4410
+    ; GCN-NEXT: s_set_vgpr_msb 0x5410
----------------
rampitec wrote:

As a side note I wish a better asm syntax here. The test can be improved by adding asm comments, but ideally asm syntax shall show src0/1/2/vdst components individually.

https://github.com/llvm/llvm-project/pull/170567