[GlobalISel] Combine G_SELECTs of the form (cond ? x : x) into x

When we find something like this:

```
%a:_(s32) = G_SOMETHING ...
...
%select:_(s32) = G_SELECT %cond(s1), %a, %a
```

We can remove the select and just replace it entirely with `%a` because it's
always going to result in `%a`.

Same if we have

```
%select:_(s32) = G_SELECT %cond(s1), %a, %b
```

where we can deduce that `%a == %b`.

This implements the following cases:

- `%select:_(s32) = G_SELECT %cond(s1), %a, %a` -> `%a`

- `%select:_(s32) = G_SELECT %cond(s1), %a, %some_copy_from_a` -> `%a`

- `%select:_(s32) = G_SELECT %cond(s1), %a, %b` -> `%a` when `%a` and `%b`
   are defined by identical instructions

This gives a few minor code size improvements on CTMark at -O3 for AArch64.

Differential Revision: https://reviews.llvm.org/D76523

include/llvm/CodeGen/GlobalISel/CombinerHelper.h

@@ -210,6 +210,16 @@ public:
   /// Replace an instruction with a G_IMPLICIT_DEF.
   bool replaceInstWithUndef(MachineInstr &MI);
 
+  /// Delete \p MI and replace all of its uses with its \p OpIdx-th operand.
+  bool replaceSingleDefInstWithOperand(MachineInstr &MI, unsigned OpIdx);
+
+  /// Return true if \p MOP1 and \p MOP2 are register operands are defined by
+  /// equivalent instructions.
+  bool matchEqualDefs(const MachineOperand &MOP1, const MachineOperand &MOP2);
+
+  /// Optimize (cond ? x : x) -> x
+  bool matchSelectSameVal(MachineInstr &MI);
+
   /// Try to transform \p MI by using all of the above
   /// combine functions. Returns true if changed.
   bool tryCombine(MachineInstr &MI);

include/llvm/Target/GlobalISel/Combine.td

@@ -184,6 +184,14 @@ def propagate_undef_shuffle_mask: GICombineRule<
          [{ return Helper.matchUndefShuffleVectorMask(*${root}); }]),
   (apply [{ Helper.replaceInstWithUndef(*${root}); }])>;
 
+// Fold (cond ? x : x) -> x
+def select_same_val: GICombineRule<
+  (defs root:$root),
+  (match (wip_match_opcode G_SELECT):$root,
+    [{ return Helper.matchSelectSameVal(*${root}); }]),
+  (apply [{ return Helper.replaceSingleDefInstWithOperand(*${root}, 2); }])
+>;
+
 // FIXME: These should use the custom predicate feature once it lands.
 def undef_combines : GICombineGroup<[undef_to_fp_zero, undef_to_int_zero,
                                      undef_to_negative_one,
@@ -191,6 +199,9 @@ def undef_combines : GICombineGroup<[undef_to_fp_zero, undef_to_int_zero,
                                      propagate_undef_all_ops,
                                      propagate_undef_shuffle_mask]>;
 
+def identity_combines : GICombineGroup<[select_same_val]>;
+
 def trivial_combines : GICombineGroup<[copy_prop, mul_to_shl]>;
 def all_combines : GICombineGroup<[trivial_combines, ptr_add_immed_chain,
-    combines_for_extload, combine_indexed_load_store, undef_combines]>;
+    combines_for_extload, combine_indexed_load_store, undef_combines,
+    identity_combines]>;

lib/CodeGen/GlobalISel/CombinerHelper.cpp

@@ -1503,6 +1503,41 @@ bool CombinerHelper::matchUndefShuffleVectorMask(MachineInstr &MI) {
   return all_of(Mask, [](int Elt) { return Elt < 0; });
 }
 
+bool CombinerHelper::matchEqualDefs(const MachineOperand &MOP1,
+                                    const MachineOperand &MOP2) {
+  if (!MOP1.isReg() || !MOP2.isReg())
+    return false;
+  MachineInstr *I1 = getDefIgnoringCopies(MOP1.getReg(), MRI);
+  if (!I1)
+    return false;
+  MachineInstr *I2 = getDefIgnoringCopies(MOP2.getReg(), MRI);
+  if (!I2)
+    return false;
+
+  // On the off-chance that there's some target instruction feeding into the
+  // select, let's use produceSameValue instead of isIdenticalTo.
+  return Builder.getTII().produceSameValue(*I1, *I2, &MRI);
+}
+
+bool CombinerHelper::replaceSingleDefInstWithOperand(MachineInstr &MI,
+                                                     unsigned OpIdx) {
+  assert(MI.getNumExplicitDefs() == 1 && "Expected one explicit def?");
+  Register OldReg = MI.getOperand(0).getReg();
+  Register Replacement = MI.getOperand(OpIdx).getReg();
+  assert(canReplaceReg(OldReg, Replacement, MRI) && "Cannot replace register?");
+  MI.eraseFromParent();
+  replaceRegWith(MRI, OldReg, Replacement);
+  return true;
+}
+
+bool CombinerHelper::matchSelectSameVal(MachineInstr &MI) {
+  assert(MI.getOpcode() == TargetOpcode::G_SELECT);
+  // Match (cond ? x : x)
+  return matchEqualDefs(MI.getOperand(2), MI.getOperand(3)) &&
+         canReplaceReg(MI.getOperand(0).getReg(), MI.getOperand(2).getReg(),
+                       MRI);
+}
+
 bool CombinerHelper::replaceInstWithFConstant(MachineInstr &MI, double C) {
   assert(MI.getNumDefs() == 1 && "Expected only one def?");
   Builder.setInstr(MI);

test/CodeGen/AArch64/GlobalISel/prelegalizercombiner-select.mir

@@ -0,0 +1,95 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple aarch64 -run-pass=aarch64-prelegalizer-combiner -verify-machineinstrs %s -o - | FileCheck %s
+
+name:            self
+tracksRegLiveness: true
+body:             |
+  bb.1.entry:
+    liveins: $w0, $w1
+    ; Optimize (cond ? %a : %a) -> %a
+    ; CHECK-LABEL: name: self
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK: %a:_(s32) = COPY $w0
+    ; CHECK: $w0 = COPY %a(s32)
+    ; CHECK: RET_ReallyLR implicit $w0
+    %a:_(s32) = COPY $w0
+    %cond_wide:gpr(s32) = COPY $w1
+    %cond:gpr(s1) = G_TRUNC %cond_wide(s32)
+    %select:_(s32) = G_SELECT %cond(s1), %a, %a
+    $w0 = COPY %select(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            self_with_copy
+tracksRegLiveness: true
+body:             |
+  bb.1.entry:
+    liveins: $w0, $w1
+    ; Optimize (cond ? %a : %b) -> %a
+    ;
+    ; This shows that we are looking through copies correctly and deduce that
+    ; %b is a copy from %a.
+    ;
+    ; CHECK-LABEL: name: self_with_copy
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK: %a:_(s32) = COPY $w0
+    ; CHECK: $w0 = COPY %a(s32)
+    ; CHECK: RET_ReallyLR implicit $w0
+    %a:_(s32) = COPY $w0
+    %b:_(s32) = COPY %a
+    %cond_wide:gpr(s32) = COPY $w1
+    %cond:gpr(s1) = G_TRUNC %cond_wide(s32)
+    %select:_(s32) = G_SELECT %cond(s1), %a, %b
+    $w0 = COPY %select(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            self_with_equivalent
+tracksRegLiveness: true
+body:             |
+  bb.1.entry:
+    liveins: $w0, $w1
+    ; Optimize (cond ? %a : %b) -> %a
+    ;
+    ; This shows that we can detect when %a == %b, even though they define
+    ; different virtual registers.
+    ;
+    ; CHECK-LABEL: name: self_with_equivalent
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK: %a:_(s32) = COPY $w0
+    ; CHECK: $w0 = COPY %a(s32)
+    ; CHECK: RET_ReallyLR implicit $w0
+    %a:_(s32) = COPY $w0
+    %b:_(s32) = COPY $w0
+    %cond_wide:gpr(s32) = COPY $w1
+    %cond:gpr(s1) = G_TRUNC %cond_wide(s32)
+    %select:_(s32) = G_SELECT %cond(s1), %a, %b
+    $w0 = COPY %select(s32)
+    RET_ReallyLR implicit $w0
+
+...
+---
+name:            self_not_equivalent
+tracksRegLiveness: true
+body:             |
+  bb.1.entry:
+    liveins: $w0, $w1
+    ; In this case, the copies are not equivalent, so there is no optimization.
+    ; CHECK-LABEL: name: self_not_equivalent
+    ; CHECK: liveins: $w0, $w1
+    ; CHECK: %a:_(s32) = COPY $w0
+    ; CHECK: %b:_(s32) = COPY $w1
+    ; CHECK: %cond_wide:gpr(s32) = COPY $w1
+    ; CHECK: %cond:gpr(s1) = G_TRUNC %cond_wide(s32)
+    ; CHECK: %select:_(s32) = G_SELECT %cond(s1), %a, %b
+    ; CHECK: $w0 = COPY %select(s32)
+    ; CHECK: RET_ReallyLR implicit $w0
+    %a:_(s32) = COPY $w0
+    %b:_(s32) = COPY $w1
+    %cond_wide:gpr(s32) = COPY $w1
+    %cond:gpr(s1) = G_TRUNC %cond_wide(s32)
+    %select:_(s32) = G_SELECT %cond(s1), %a, %b
+    $w0 = COPY %select(s32)
+    RET_ReallyLR implicit $w0