Handle concrete values in CodeFolding (#7117)

CodeFolding previously only worked on blocks that did not produce
values. It worked on Ifs that produced values, but only by accident; the
logic for folding matching tails was not written to support tails
producing concrete values, but it happened to work for Ifs because
subsequent ReFinalize runs fixed all the incorrect types it produced.

Improve the power of the optimization by explicitly handling tails that
produce concrete values for both blocks and ifs. Now that the core logic
handles concrete values correctly, remove the unnecessary ReFinalize
run.

Also remove the separate optimization of Ifs with identical arms; this
optimization requires ReFinalize and is already performed by
OptimizeInstructions.

1 files changed, 210 insertions, 228 deletions

diff --git a/test/passes/O3_low-memory-unused_metrics.txt b/test/passes/O3_low-memory-unused_metrics.txt
index 8806e9a04..3117d7778 100644
--- a/test/passes/O3_low-memory-unused_metrics.txt
+++ b/test/passes/O3_low-memory-unused_metrics.txt
@@ -9,23 +9,23 @@ total
  [table-data]   : 0       
  [tables]       : 0       
  [tags]         : 0       
- [total]        : 1964    
+ [total]        : 1953    
  [vars]         : 9       
- Binary         : 240     
+ Binary         : 238     
  Block          : 68      
  Break          : 90      
  Call           : 22      
  CallIndirect   : 1       
- Const          : 175     
+ Const          : 174     
  Drop           : 8       
  If             : 27      
- Load           : 313     
- LocalGet       : 633     
- LocalSet       : 181     
+ Load           : 311     
+ LocalGet       : 629     
+ LocalSet       : 180     
  Loop           : 3       
  Return         : 3       
  Select         : 11      
- Store          : 160     
+ Store          : 159     
  Unary          : 29      
 (module
  (type $0 (func (param i32 i32 i32) (result i32)))
@@ -2718,307 +2718,289 @@ total
        (local.get $0)
       )
      )
-     (i32.store8
-      (block $label$68 (result i32)
-       (if
-        (i32.eq
-         (local.get $4)
-         (i32.const 2)
-        )
-        (then
-         (i32.store offset=20
-          (local.get $2)
-          (i32.add
-           (local.tee $3
-            (i32.load offset=20
-             (local.get $2)
-            )
-           )
-           (i32.const 1)
-          )
-         )
-         (i32.store8
-          (i32.add
-           (local.get $3)
-           (i32.load offset=8
+     (block $label$68
+      (if
+       (i32.eq
+        (local.get $4)
+        (i32.const 2)
+       )
+       (then
+        (i32.store offset=20
+         (local.get $2)
+         (i32.add
+          (local.tee $3
+           (i32.load offset=20
             (local.get $2)
            )
           )
-          (local.get $1)
+          (i32.const 1)
          )
-         (local.set $1
-          (i32.load offset=48
-           (local.get $0)
+        )
+        (i32.store8
+         (i32.add
+          (local.get $3)
+          (i32.load offset=8
+           (local.get $2)
           )
          )
-         (i32.store offset=20
-          (local.get $2)
-          (i32.add
-           (local.tee $3
-            (i32.load offset=20
-             (local.get $2)
-            )
-           )
-           (i32.const 1)
-          )
+         (local.get $1)
+        )
+        (local.set $1
+         (i32.load offset=48
+          (local.get $0)
          )
-         (i32.store8
-          (i32.add
-           (local.get $3)
-           (i32.load offset=8
+        )
+        (i32.store offset=20
+         (local.get $2)
+         (i32.add
+          (local.tee $3
+           (i32.load offset=20
             (local.get $2)
            )
           )
-          (i32.shr_u
-           (local.get $1)
-           (i32.const 8)
-          )
-         )
-         (local.set $1
-          (i32.load16_u offset=50
-           (local.get $0)
-          )
+          (i32.const 1)
          )
-         (i32.store offset=20
-          (local.get $2)
-          (i32.add
-           (local.tee $3
-            (i32.load offset=20
-             (local.get $2)
-            )
-           )
-           (i32.const 1)
+        )
+        (i32.store8
+         (i32.add
+          (local.get $3)
+          (i32.load offset=8
+           (local.get $2)
           )
          )
-         (i32.store8
-          (i32.add
-           (local.get $3)
-           (i32.load offset=8
-            (local.get $2)
-           )
-          )
+         (i32.shr_u
           (local.get $1)
+          (i32.const 8)
          )
-         (local.set $1
-          (i32.load8_u offset=51
-           (local.get $0)
-          )
-         )
-         (i32.store offset=20
-          (local.get $2)
-          (i32.add
-           (local.tee $3
-            (i32.load offset=20
-             (local.get $2)
-            )
-           )
-           (i32.const 1)
-          )
+        )
+        (local.set $1
+         (i32.load16_u offset=50
+          (local.get $0)
          )
-         (i32.store8
-          (i32.add
-           (local.get $3)
-           (i32.load offset=8
+        )
+        (i32.store offset=20
+         (local.get $2)
+         (i32.add
+          (local.tee $3
+           (i32.load offset=20
             (local.get $2)
            )
           )
-          (local.get $1)
+          (i32.const 1)
          )
-         (local.set $1
+        )
+        (i32.store8
+         (i32.add
+          (local.get $3)
           (i32.load offset=8
-           (local.get $0)
+           (local.get $2)
           )
          )
-         (i32.store offset=20
-          (local.get $2)
-          (i32.add
-           (local.tee $3
-            (i32.load offset=20
-             (local.get $2)
-            )
-           )
-           (i32.const 1)
-          )
+         (local.get $1)
+        )
+        (local.set $1
+         (i32.load8_u offset=51
+          (local.get $0)
          )
-         (i32.store8
-          (i32.add
-           (local.get $3)
-           (i32.load offset=8
+        )
+        (i32.store offset=20
+         (local.get $2)
+         (i32.add
+          (local.tee $3
+           (i32.load offset=20
             (local.get $2)
            )
           )
-          (local.get $1)
+          (i32.const 1)
          )
-         (local.set $1
+        )
+        (i32.store8
+         (i32.add
+          (local.get $3)
           (i32.load offset=8
-           (local.get $0)
+           (local.get $2)
           )
          )
-         (i32.store offset=20
-          (local.get $2)
-          (i32.add
-           (local.tee $3
-            (i32.load offset=20
-             (local.get $2)
-            )
-           )
-           (i32.const 1)
-          )
+         (local.get $1)
+        )
+        (local.set $1
+         (i32.load offset=8
+          (local.get $0)
          )
-         (i32.store8
-          (i32.add
-           (local.get $3)
-           (i32.load offset=8
+        )
+        (i32.store offset=20
+         (local.get $2)
+         (i32.add
+          (local.tee $3
+           (i32.load offset=20
             (local.get $2)
            )
           )
-          (i32.shr_u
-           (local.get $1)
-           (i32.const 8)
-          )
+          (i32.const 1)
          )
-         (local.set $1
-          (i32.load16_u offset=10
-           (local.get $0)
+        )
+        (i32.store8
+         (i32.add
+          (local.get $3)
+          (i32.load offset=8
+           (local.get $2)
           )
          )
-         (i32.store offset=20
-          (local.get $2)
-          (i32.add
-           (local.tee $3
-            (i32.load offset=20
-             (local.get $2)
-            )
-           )
-           (i32.const 1)
-          )
+         (local.get $1)
+        )
+        (local.set $1
+         (i32.load offset=8
+          (local.get $0)
          )
-         (i32.store8
-          (i32.add
-           (local.get $3)
-           (i32.load offset=8
+        )
+        (i32.store offset=20
+         (local.get $2)
+         (i32.add
+          (local.tee $3
+           (i32.load offset=20
             (local.get $2)
            )
           )
-          (local.get $1)
+          (i32.const 1)
          )
-         (local.set $3
-          (i32.load8_u offset=11
-           (local.get $0)
+        )
+        (i32.store8
+         (i32.add
+          (local.get $3)
+          (i32.load offset=8
+           (local.get $2)
           )
          )
-         (i32.store offset=20
-          (local.get $2)
-          (i32.add
-           (local.tee $1
-            (i32.load offset=20
-             (local.get $2)
-            )
-           )
-           (i32.const 1)
-          )
+         (i32.shr_u
+          (local.get $1)
+          (i32.const 8)
          )
-         (br $label$68
-          (i32.add
-           (local.get $1)
-           (i32.load offset=8
+        )
+        (local.set $1
+         (i32.load16_u offset=10
+          (local.get $0)
+         )
+        )
+        (i32.store offset=20
+         (local.get $2)
+         (i32.add
+          (local.tee $3
+           (i32.load offset=20
             (local.get $2)
            )
           )
+          (i32.const 1)
          )
         )
-       )
-       (i32.store offset=20
-        (local.get $2)
-        (i32.add
-         (local.tee $3
-          (i32.load offset=20
+        (i32.store8
+         (i32.add
+          (local.get $3)
+          (i32.load offset=8
            (local.get $2)
           )
          )
-         (i32.const 1)
-        )
-       )
-       (i32.store8
-        (i32.add
-         (local.get $3)
-         (i32.load offset=8
-          (local.get $2)
-         )
-        )
-        (i32.shr_u
          (local.get $1)
-         (i32.const 24)
         )
-       )
-       (i32.store offset=20
-        (local.get $2)
-        (i32.add
-         (local.tee $3
-          (i32.load offset=20
-           (local.get $2)
-          )
+        (local.set $3
+         (i32.load8_u offset=11
+          (local.get $0)
          )
-         (i32.const 1)
         )
+        (br $label$68)
        )
-       (i32.store8
-        (i32.add
-         (local.get $3)
-         (i32.load offset=8
+      )
+      (i32.store offset=20
+       (local.get $2)
+       (i32.add
+        (local.tee $3
+         (i32.load offset=20
           (local.get $2)
          )
         )
-        (i32.shr_u
-         (local.get $1)
-         (i32.const 16)
-        )
+        (i32.const 1)
        )
-       (local.set $3
-        (i32.load offset=48
-         (local.get $0)
+      )
+      (i32.store8
+       (i32.add
+        (local.get $3)
+        (i32.load offset=8
+         (local.get $2)
         )
        )
-       (i32.store offset=20
-        (local.get $2)
-        (i32.add
-         (local.tee $1
-          (i32.load offset=20
-           (local.get $2)
-          )
-         )
-         (i32.const 1)
-        )
+       (i32.shr_u
+        (local.get $1)
+        (i32.const 24)
        )
-       (i32.store8
-        (i32.add
-         (local.get $1)
-         (i32.load offset=8
+      )
+      (i32.store offset=20
+       (local.get $2)
+       (i32.add
+        (local.tee $3
+         (i32.load offset=20
           (local.get $2)
          )
         )
-        (i32.shr_u
-         (local.get $3)
-         (i32.const 8)
+        (i32.const 1)
+       )
+      )
+      (i32.store8
+       (i32.add
+        (local.get $3)
+        (i32.load offset=8
+         (local.get $2)
         )
        )
-       (i32.store offset=20
-        (local.get $2)
-        (i32.add
-         (local.tee $1
-          (i32.load offset=20
-           (local.get $2)
-          )
+       (i32.shr_u
+        (local.get $1)
+        (i32.const 16)
+       )
+      )
+      (local.set $3
+       (i32.load offset=48
+        (local.get $0)
+       )
+      )
+      (i32.store offset=20
+       (local.get $2)
+       (i32.add
+        (local.tee $1
+         (i32.load offset=20
+          (local.get $2)
          )
-         (i32.const 1)
         )
+        (i32.const 1)
        )
+      )
+      (i32.store8
        (i32.add
         (local.get $1)
         (i32.load offset=8
          (local.get $2)
         )
        )
+       (i32.shr_u
+        (local.get $3)
+        (i32.const 8)
+       )
+      )
+     )
+     (i32.store offset=20
+      (local.get $2)
+      (i32.add
+       (local.tee $1
+        (i32.load offset=20
+         (local.get $2)
+        )
+       )
+       (i32.const 1)
+      )
+     )
+     (i32.store8
+      (i32.add
+       (local.get $1)
+       (i32.load offset=8
+        (local.get $2)
+       )
       )
       (local.get $3)
      )