[llvm] [WIP] Optimize S_MOV frame index elimination support (PR #101322)

[Matt Arsenault via llvm-commits]

================
@@ -2568,30 +2568,46 @@ bool SIRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator MI,
                 } else
                   Add.addImm(Offset).addReg(TmpResultReg, RegState::Kill);
               } else {
-                BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_MOV_B32_e32),
-                        TmpResultReg)
-                    .addImm(Offset);
                 assert(Offset > 0 &&
                        isUInt<24>(2 * ST.getMaxWaveScratchSize()) &&
                        "offset is unsafe for v_mad_u32_u24");
-                // We start with a frame pointer with a wave space value, and an
-                // offset in lane-space. We are materializing a lane space
-                // value. We can either do a right shift of the frame pointer to
-                // get to lane space, or a left shift of the offset to get to
-                // wavespace. We can right shift after the computation to get
-                // back to the desired per-lane value.
-                // We are using the mad_u32_u24 primarily as an add with no
-                // carry out clobber.
-                Add = BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_MAD_U32_U24_e64),
+                if (AMDGPU::isInlinableLiteral32(Offset,
+                                                 ST.hasInv2PiInlineImm())) {
----------------
arsenm wrote:

This is further complicating a direct fold. This patch should be really small and simple, and not need to touch the helper function 

```
if (!IsInlineImm)
  BuildMI(V_MOV_B32, OffsetReg)

Mad24 = BuildMI(V_MAD_U24_U32, ...)
if (!IsInlineImm)
  Mad24.addReg(OffsetReg)
else
   Mad24.addImm(Imm)...
```

https://github.com/llvm/llvm-project/pull/101322