[llvm-branch-commits] [llvm] [AMDGPU] Dynamic VGPR support for llvm.amdgcn.cs.chain (PR #130094)

[Matt Arsenault via llvm-branch-commits]

================
@@ -172,7 +215,12 @@ bool SILateBranchLowering::runOnMachineFunction(MachineFunction &MF) {
 
       case AMDGPU::SI_CS_CHAIN_TC_W32:
       case AMDGPU::SI_CS_CHAIN_TC_W64:
-        expandChainCall(MI);
+        expandChainCall(MI, ST, /*DynamicVGPR*/ false);
+        MadeChange = true;
+        break;
+      case AMDGPU::SI_CS_CHAIN_TC_W32_DVGPR:
+      case AMDGPU::SI_CS_CHAIN_TC_W64_DVGPR:
+        expandChainCall(MI, ST, /*DynamicVGPR*/ true);
----------------
arsenm wrote:

```suggestion
        expandChainCall(MI, ST, /*DynamicVGPR=*/ true);
```

https://github.com/llvm/llvm-project/pull/130094