[CodeGenPrepare] Fold br(freeze(icmp x, const)) to br(icmp(freeze x, const))

Summary:
This patch helps CodeGenPrepare move freeze into the icmp when it is used by branch.
It reenables generation of efficient conditional jumps.

This is only done when at least one of icmp's operands is constant to prevent the transformation from increasing # of freeze instructions.

Performance degradation of MultiSource/Benchmarks/Ptrdist/yacr2/yacr2.test is resolved with this patch.

Checked with Alive2

Reviewers: reames, fhahn, nlopes

Reviewed By: reames

Subscribers: jdoerfert, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D75859

diff --git a/llvm/lib/CodeGen/CodeGenPrepare.cpp b/llvm/lib/CodeGen/CodeGenPrepare.cpp
index 052316f..2620364 100644 (file)
--- a/llvm/lib/CodeGen/CodeGenPrepare.cpp
+++ b/llvm/lib/CodeGen/CodeGenPrepare.cpp
@@ -7191,6 +7191,26 @@ bool CodeGenPrepare::optimizeInst(Instruction *I, bool &ModifiedDT) {
     return false;
   }
 
+  if (FreezeInst *FI = dyn_cast<FreezeInst>(I)) {
+    // br(freeze(icmp a, const)) -> br(icmp (freeze a), const)
+    // This helps generate efficient conditional jumps.
+    if (ICmpInst *II = dyn_cast<ICmpInst>(FI->getOperand(0))) {
+      auto Op0 = II->getOperand(0), Op1 = II->getOperand(1);
+      bool Const0 = isa<ConstantInt>(Op0), Const1 = isa<ConstantInt>(Op1);
+      if (II->hasOneUse() && (Const0 || Const1)) {
+        if (!Const0 || !Const1) {
+          auto *F = new FreezeInst(Const0 ? Op1 : Op0, "", II);
+          F->takeName(FI);
+          II->setOperand(Const0 ? 1 : 0, F);
+        }
+        FI->replaceAllUsesWith(II);
+        FI->eraseFromParent();
+        return true;
+      }
+    }
+    return false;
+  }
+
   if (tryToSinkFreeOperands(I))
     return true;
 

diff --git a/llvm/test/Transforms/CodeGenPrepare/X86/freeze-icmp.ll b/llvm/test/Transforms/CodeGenPrepare/X86/freeze-icmp.ll
new file mode 100644 (file)
index 0000000..e4febc1
--- /dev/null
+++ b/llvm/test/Transforms/CodeGenPrepare/X86/freeze-icmp.ll
@@ -0,0 +1,75 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -codegenprepare < %s | FileCheck %s
+
+target triple = "x86_64-unknown-linux-gnu"
+
+define void @f1(i32 %a) {
+; CHECK-LABEL: @f1(
+; CHECK-NEXT:    [[FR1:%.*]] = freeze i32 [[A:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = icmp eq i32 [[FR1]], 0
+; CHECK-NEXT:    br i1 [[C]], label [[A:%.*]], label [[B:%.*]]
+; CHECK:       A:
+; CHECK-NEXT:    call void @g1()
+; CHECK-NEXT:    ret void
+; CHECK:       B:
+; CHECK-NEXT:    call void @g2()
+; CHECK-NEXT:    ret void
+;
+  %c = icmp eq i32 %a, 0
+  %fr = freeze i1 %c
+  br i1 %fr, label %A, label %B
+A:
+  call void @g1()
+  ret void
+B:
+  call void @g2()
+  ret void
+}
+
+define void @f2(i32 %a) {
+; CHECK-LABEL: @f2(
+; CHECK-NEXT:    [[FR1:%.*]] = freeze i32 [[A:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = icmp eq i32 0, [[FR1]]
+; CHECK-NEXT:    br i1 [[C]], label [[A:%.*]], label [[B:%.*]]
+; CHECK:       A:
+; CHECK-NEXT:    call void @g1()
+; CHECK-NEXT:    ret void
+; CHECK:       B:
+; CHECK-NEXT:    call void @g2()
+; CHECK-NEXT:    ret void
+;
+  %c = icmp eq i32 0, %a
+  %fr = freeze i1 %c
+  br i1 %fr, label %A, label %B
+A:
+  call void @g1()
+  ret void
+B:
+  call void @g2()
+  ret void
+}
+
+define void @f3(i32 %a) {
+; CHECK-LABEL: @f3(
+; CHECK-NEXT:    [[C:%.*]] = icmp eq i32 0, 1
+; CHECK-NEXT:    br i1 [[C]], label [[A:%.*]], label [[B:%.*]]
+; CHECK:       A:
+; CHECK-NEXT:    call void @g1()
+; CHECK-NEXT:    ret void
+; CHECK:       B:
+; CHECK-NEXT:    call void @g2()
+; CHECK-NEXT:    ret void
+;
+  %c = icmp eq i32 0, 1
+  %fr = freeze i1 %c
+  br i1 %fr, label %A, label %B
+A:
+  call void @g1()
+  ret void
+B:
+  call void @g2()
+  ret void
+}
+
+declare void @g1()
+declare void @g2()