[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:

Yes, it will cause some lit tests to fail. I think this is a problem with the test itself, for example, if we run it with gfx900 but the test is meant to target gfx10, the format won't be found and Info will be null. This will trigger failures, like in `gfx10_tbuffer_load_x_xyz` when run on gfx900.
So I think it makes sense to keep the null check for compatibility. right?

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