From b6d9add71b1a7bc77ce504ed09a43288ca67c0cd Mon Sep 17 00:00:00 2001
From: Juneyoung Lee <aqjune@gmail.com>
Date: Fri, 7 Aug 2020 21:12:52 +0900
Subject: [PATCH] [InstCombine] Optimize select(freeze(icmp eq/ne x, y), x, y)

This patch adds an optimization that folds select(freeze(icmp eq/ne x, y), x, y)
to x or y.
This was needed to resolve slowdown after D84940 is applied.

I tried to bake this logic into foldSelectInstWithICmp, but it wasn't clear.
This patch conservatively writes the pattern in a separate function,
foldSelectWithFrozenICmp.

The output does not need freeze; https://alive2.llvm.org/ce/z/X49hNE (from @nikic)

Reviewed By: nikic

Differential Revision: https://reviews.llvm.org/D85533
---
 .../InstCombine/InstCombineSelect.cpp         | 29 +++++++++++++++++++
 llvm/test/Transforms/InstCombine/select.ll    | 27 ++++++++++++-----
 2 files changed, 48 insertions(+), 8 deletions(-)

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
index c14a330542c9..33da3c69ad91 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
@@ -2526,6 +2526,32 @@ static Instruction *foldSelectToPhi(SelectInst &Sel, const DominatorTree &DT,
   return nullptr;
 }
 
+static Value *foldSelectWithFrozenICmp(SelectInst &Sel, InstCombiner::BuilderTy &Builder) {
+  FreezeInst *FI = dyn_cast<FreezeInst>(Sel.getCondition());
+  if (!FI)
+    return nullptr;
+
+  Value *Cond = FI->getOperand(0);
+  Value *TrueVal = Sel.getTrueValue(), *FalseVal = Sel.getFalseValue();
+
+  //   select (freeze(x == y)), x, y --> y
+  //   select (freeze(x != y)), x, y --> x
+  // The freeze should be only used by this select. Otherwise, remaining uses of
+  // the freeze can observe a contradictory value.
+  //   c = freeze(x == y)   ; Let's assume that y = poison & x = 42; c is 0 or 1
+  //   a = select c, x, y   ;
+  //   f(a, c)              ; f(poison, 1) cannot happen, but if a is folded
+  //                        ; to y, this can happen.
+  CmpInst::Predicate Pred;
+  if (FI->hasOneUse() &&
+      match(Cond, m_c_ICmp(Pred, m_Specific(TrueVal), m_Specific(FalseVal))) &&
+      (Pred == ICmpInst::ICMP_EQ || Pred == ICmpInst::ICMP_NE)) {
+    return Pred == ICmpInst::ICMP_EQ ? FalseVal : TrueVal;
+  }
+
+  return nullptr;
+}
+
 Instruction *InstCombinerImpl::visitSelectInst(SelectInst &SI) {
   Value *CondVal = SI.getCondition();
   Value *TrueVal = SI.getTrueValue();
@@ -2977,5 +3003,8 @@ Instruction *InstCombinerImpl::visitSelectInst(SelectInst &SI) {
   if (Instruction *PN = foldSelectToPhi(SI, DT, Builder))
     return replaceInstUsesWith(SI, PN);
 
+  if (Value *Fr = foldSelectWithFrozenICmp(SI, Builder))
+    return replaceInstUsesWith(SI, Fr);
+
   return nullptr;
 }
diff --git a/llvm/test/Transforms/InstCombine/select.ll b/llvm/test/Transforms/InstCombine/select.ll
index 5d1fd76b2709..4c651b7bf145 100644
--- a/llvm/test/Transforms/InstCombine/select.ll
+++ b/llvm/test/Transforms/InstCombine/select.ll
@@ -2540,10 +2540,7 @@ define void @cond_freeze_multipleuses(i8 %x, i8 %y) {
 
 define i32 @select_freeze_icmp_eq(i32 %x, i32 %y) {
 ; CHECK-LABEL: @select_freeze_icmp_eq(
-; CHECK-NEXT:    [[C:%.*]] = icmp eq i32 [[X:%.*]], [[Y:%.*]]
-; CHECK-NEXT:    [[C_FR:%.*]] = freeze i1 [[C]]
-; CHECK-NEXT:    [[V:%.*]] = select i1 [[C_FR]], i32 [[X]], i32 [[Y]]
-; CHECK-NEXT:    ret i32 [[V]]
+; CHECK-NEXT:    ret i32 [[Y:%.*]]
 ;
   %c = icmp eq i32 %x, %y
   %c.fr = freeze i1 %c
@@ -2553,10 +2550,7 @@ define i32 @select_freeze_icmp_eq(i32 %x, i32 %y) {
 
 define i32 @select_freeze_icmp_ne(i32 %x, i32 %y) {
 ; CHECK-LABEL: @select_freeze_icmp_ne(
-; CHECK-NEXT:    [[C:%.*]] = icmp ne i32 [[X:%.*]], [[Y:%.*]]
-; CHECK-NEXT:    [[C_FR:%.*]] = freeze i1 [[C]]
-; CHECK-NEXT:    [[V:%.*]] = select i1 [[C_FR]], i32 [[X]], i32 [[Y]]
-; CHECK-NEXT:    ret i32 [[V]]
+; CHECK-NEXT:    ret i32 [[X:%.*]]
 ;
   %c = icmp ne i32 %x, %y
   %c.fr = freeze i1 %c
@@ -2576,3 +2570,20 @@ define i32 @select_freeze_icmp_else(i32 %x, i32 %y) {
   %v = select i1 %c.fr, i32 %x, i32 %y
   ret i32 %v
 }
+
+declare void @use_i1_i32(i1, i32)
+
+define void @select_freeze_icmp_multuses(i32 %x, i32 %y) {
+; CHECK-LABEL: @select_freeze_icmp_multuses(
+; CHECK-NEXT:    [[C:%.*]] = icmp ne i32 [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[C_FR:%.*]] = freeze i1 [[C]]
+; CHECK-NEXT:    [[V:%.*]] = select i1 [[C_FR]], i32 [[X]], i32 [[Y]]
+; CHECK-NEXT:    call void @use_i1_i32(i1 [[C_FR]], i32 [[V]])
+; CHECK-NEXT:    ret void
+;
+  %c = icmp ne i32 %x, %y
+  %c.fr = freeze i1 %c
+  %v = select i1 %c.fr, i32 %x, i32 %y
+  call void @use_i1_i32(i1 %c.fr, i32 %v)
+  ret void
+}