[llvm] [AMDGPU] Support merging 16-bit and 8-bit TBUFFER load/store instruction (PR #145078)

[Harrison Hao via llvm-commits]

================
@@ -839,8 +839,16 @@ void SILoadStoreOptimizer::CombineInfo::setMI(MachineBasicBlock::iterator MI,
     Offset = I->getOperand(OffsetIdx).getImm();
   }
 
-  if (InstClass == TBUFFER_LOAD || InstClass == TBUFFER_STORE)
+  if (InstClass == TBUFFER_LOAD || InstClass == TBUFFER_STORE) {
     Format = LSO.TII->getNamedOperand(*I, AMDGPU::OpName::format)->getImm();
+    const AMDGPU::GcnBufferFormatInfo *Info =
+        AMDGPU::getGcnBufferFormatInfo(Format, *LSO.STM);
+
+    // Use 2-byte element size if the tbuffer format is 16-bit.
+    // Use 1-byte element size if the tbuffer format is 8-bit.
+    if (Info)
----------------
harrisonGPU wrote:

I think separating merge-tbuffer.mir makes sense, but we still have these lit tests that need to be separated:
```
Failed Tests (6):
  LLVM :: CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.tbuffer.load.ll
  LLVM :: CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.tbuffer.store.ll
  LLVM :: CodeGen/AMDGPU/llvm.amdgcn.raw.tbuffer.load.ll
  LLVM :: CodeGen/AMDGPU/llvm.amdgcn.raw.tbuffer.store.ll
  LLVM :: CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.tbuffer.load.ll
  LLVM :: CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer.load.ll
```
Should I continue to do this?

https://github.com/llvm/llvm-project/pull/145078