Add an early `TailMerge` pass (#2721)

* Add an early `TailMerge` pass

Some translations can have a lot of guest calls and since for each guest
call there is a call guard which may return. This can produce a lot of
epilogue code for returns. This pass merges the epilogue into a single
block.

```
Using filter 'hcq'.
Using metric 'code size'.

Total diff: -1648111 (-7.19 %) (bytes):
  Base: 22913847
  Diff: 21265736

Improved: 4567, regressed: 14, unchanged: 144
```

* Set PTC version

* Address feedback

* Handle `void` returning functions

* Actually handle `void` returning functions

* Fix `RegisterToLocal` logging

1 files changed, 22 insertions, 10 deletions

diff --git a/ARMeilleure/Translation/RegisterUsage.cs b/ARMeilleure/Translation/RegisterUsage.cs
index 035d4540..775fa3ab 100644
--- a/ARMeilleure/Translation/RegisterUsage.cs
+++ b/ARMeilleure/Translation/RegisterUsage.cs
@@ -203,12 +203,18 @@ namespace ARMeilleure.Translation
                 // It always needs a context load as it is the first block to run.
                 if (block.Predecessors.Count == 0 || hasContextLoad)
                 {
-                    arg = Local(OperandType.I64);
+                    long vecMask = globalInputs[block.Index].VecMask;
+                    long intMask = globalInputs[block.Index].IntMask;
 
-                    Operation loadArg = block.Operations.AddFirst(Operation(Instruction.LoadArgument, arg, Const(0)));
+                    if (vecMask != 0 || intMask != 0)
+                    {
+                        arg = Local(OperandType.I64);
+
+                        Operation loadArg = block.Operations.AddFirst(Operation(Instruction.LoadArgument, arg, Const(0)));
 
-                    LoadLocals(block, globalInputs[block.Index].VecMask, RegisterType.Vector, mode, loadArg, arg);
-                    LoadLocals(block, globalInputs[block.Index].IntMask, RegisterType.Integer, mode, loadArg, arg);
+                        LoadLocals(block, vecMask, RegisterType.Vector, mode, loadArg, arg);
+                        LoadLocals(block, intMask, RegisterType.Integer, mode, loadArg, arg);
+                    }
                 }
 
                 bool hasContextStore = HasContextStore(block);
@@ -220,15 +226,21 @@ namespace ARMeilleure.Translation
 
                 if (EndsWithReturn(block) || hasContextStore)
                 {
-                    if (arg == default)
+                    long vecMask = globalOutputs[block.Index].VecMask;
+                    long intMask = globalOutputs[block.Index].IntMask;
+
+                    if (vecMask != 0 || intMask != 0)
                     {
-                        arg = Local(OperandType.I64);
+                        if (arg == default)
+                        {
+                            arg = Local(OperandType.I64);
 
-                        block.Append(Operation(Instruction.LoadArgument, arg, Const(0)));
-                    }
+                            block.Append(Operation(Instruction.LoadArgument, arg, Const(0)));
+                        }
 
-                    StoreLocals(block, globalOutputs[block.Index].IntMask, RegisterType.Integer, mode, arg);
-                    StoreLocals(block, globalOutputs[block.Index].VecMask, RegisterType.Vector, mode, arg);
+                        StoreLocals(block, intMask, RegisterType.Integer, mode, arg);
+                        StoreLocals(block, vecMask, RegisterType.Vector, mode, arg);
+                    }
                 }
             }
         }