cmd/compile: emit OffPtr for first field in SSA'd structs

Given

  (Store [c] (OffPtr <T1> [0] (Addr <T> _)) _
    (Store [c] (Addr <T> _) _ _))

dead store elimination doesn't eliminate the inner
Store, because it addresses a type of a different width
than the first store.

When decomposing StructMake operations, always generate
an OffPtr to address struct fields so that dead stores to
the first field of the struct can be optimized away.

benchmarks affected on darwin/amd64:
HTTPClientServer-8        73.2µs ± 1%    72.7µs ± 1%  -0.69%  (p=0.022 n=9+10)
TimeParse-8                304ns ± 1%     300ns ± 0%  -1.61%  (p=0.000 n=9+9)
RegexpMatchEasy1_32-8     80.1ns ± 0%    79.5ns ± 1%  -0.84%  (p=0.000 n=8+9)
GobDecode-8               6.78ms ± 0%    6.81ms ± 1%  +0.46%  (p=0.000 n=9+10)
Gunzip-8                  36.1ms ± 1%    36.2ms ± 0%  +0.37%  (p=0.019 n=10+10)
JSONEncode-8              15.6ms ± 0%    15.7ms ± 0%  +0.69%  (p=0.000 n=9+10)

Change-Id: Ia80d73fd047f9400c616ca64fdee4f438a0e7f21
Reviewed-on: https://go-review.googlesource.com/37769
Run-TryBot: Brad Fitzpatrick <bradfitz@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>

src/cmd/compile/internal/ssa/gen/generic.rules

@@ -772,19 +772,19 @@
   (StructMake0)
 (Load <t> ptr mem) && t.IsStruct() && t.NumFields() == 1 && config.fe.CanSSA(t) ->
   (StructMake1
-    (Load <t.FieldType(0)> ptr mem))
+    (Load <t.FieldType(0)> (OffPtr <t.FieldType(0).PtrTo()> [0] ptr) mem))
 (Load <t> ptr mem) && t.IsStruct() && t.NumFields() == 2 && config.fe.CanSSA(t) ->
   (StructMake2
-    (Load <t.FieldType(0)> ptr mem)
+    (Load <t.FieldType(0)> (OffPtr <t.FieldType(0).PtrTo()> [0]             ptr) mem)
     (Load <t.FieldType(1)> (OffPtr <t.FieldType(1).PtrTo()> [t.FieldOff(1)] ptr) mem))
 (Load <t> ptr mem) && t.IsStruct() && t.NumFields() == 3 && config.fe.CanSSA(t) ->
   (StructMake3
-    (Load <t.FieldType(0)> ptr mem)
+    (Load <t.FieldType(0)> (OffPtr <t.FieldType(0).PtrTo()> [0]             ptr) mem)
     (Load <t.FieldType(1)> (OffPtr <t.FieldType(1).PtrTo()> [t.FieldOff(1)] ptr) mem)
     (Load <t.FieldType(2)> (OffPtr <t.FieldType(2).PtrTo()> [t.FieldOff(2)] ptr) mem))
 (Load <t> ptr mem) && t.IsStruct() && t.NumFields() == 4 && config.fe.CanSSA(t) ->
   (StructMake4
-    (Load <t.FieldType(0)> ptr mem)
+    (Load <t.FieldType(0)> (OffPtr <t.FieldType(0).PtrTo()> [0]             ptr) mem)
     (Load <t.FieldType(1)> (OffPtr <t.FieldType(1).PtrTo()> [t.FieldOff(1)] ptr) mem)
     (Load <t.FieldType(2)> (OffPtr <t.FieldType(2).PtrTo()> [t.FieldOff(2)] ptr) mem)
     (Load <t.FieldType(3)> (OffPtr <t.FieldType(3).PtrTo()> [t.FieldOff(3)] ptr) mem))
@@ -794,12 +794,14 @@
 
 (Store _ (StructMake0) mem) -> mem
 (Store dst (StructMake1 <t> f0) mem) ->
-  (Store [t.FieldType(0).Size()] dst f0 mem)
+  (Store [t.FieldType(0).Size()] (OffPtr <t.FieldType(0).PtrTo()> [0] dst) f0 mem)
 (Store dst (StructMake2 <t> f0 f1) mem) ->
   (Store [t.FieldType(1).Size()]
     (OffPtr <t.FieldType(1).PtrTo()> [t.FieldOff(1)] dst)
     f1
-    (Store [t.FieldType(0).Size()] dst f0 mem))
+    (Store [t.FieldType(0).Size()]
+      (OffPtr <t.FieldType(0)> [0] dst)
+        f0 mem))
 (Store dst (StructMake3 <t> f0 f1 f2) mem) ->
   (Store [t.FieldType(2).Size()]
     (OffPtr <t.FieldType(2).PtrTo()> [t.FieldOff(2)] dst)
@@ -807,7 +809,9 @@
     (Store [t.FieldType(1).Size()]
       (OffPtr <t.FieldType(1).PtrTo()> [t.FieldOff(1)] dst)
       f1
-      (Store [t.FieldType(0).Size()] dst f0 mem)))
+      (Store [t.FieldType(0).Size()]
+        (OffPtr <t.FieldType(0).PtrTo()> [0] dst)
+          f0 mem)))
 (Store dst (StructMake4 <t> f0 f1 f2 f3) mem) ->
   (Store [t.FieldType(3).Size()]
     (OffPtr <t.FieldType(3).PtrTo()> [t.FieldOff(3)] dst)
@@ -818,7 +822,9 @@
       (Store [t.FieldType(1).Size()]
         (OffPtr <t.FieldType(1).PtrTo()> [t.FieldOff(1)] dst)
         f1
-        (Store [t.FieldType(0).Size()] dst f0 mem))))
+        (Store [t.FieldType(0).Size()]
+          (OffPtr <t.FieldType(0).PtrTo()> [0] dst)
+            f0 mem))))
 
 // Putting struct{*byte} and similar into direct interfaces.
 (IMake typ (StructMake1 val)) -> (IMake typ val)