X86 Peephole: fix PR13475 in optimizeCompare.

It is possible that an instruction can use and update EFLAGS.
When checking the safety, we should check the usage of EFLAGS first before
declaring it is safe to optimize due to the update.

llvm-svn: 160912

2 files changed, 23 insertions, 3 deletions

diff --git a/llvm/lib/Target/X86/X86InstrInfo.cpp b/llvm/lib/Target/X86/X86InstrInfo.cpp
index 69493bc2070..89a57b53f3c 100644
--- a/llvm/lib/Target/X86/X86InstrInfo.cpp
+++ b/llvm/lib/Target/X86/X86InstrInfo.cpp
@@ -3221,12 +3221,15 @@ optimizeCompareInstr(MachineInstr *CmpInstr, unsigned SrcReg, unsigned SrcReg2,
   MachineBasicBlock::iterator E = CmpInstr->getParent()->end();
   for (++I; I != E; ++I) {
     const MachineInstr &Instr = *I;
-    if (Instr.modifiesRegister(X86::EFLAGS, TRI)) {
+    bool ModifyEFLAGS = Instr.modifiesRegister(X86::EFLAGS, TRI);
+    bool UseEFLAGS = Instr.readsRegister(X86::EFLAGS, TRI);
+    // We should check the usage if this instruction uses and updates EFLAGS.
+    if (!UseEFLAGS && ModifyEFLAGS) {
       // It is safe to remove CmpInstr if EFLAGS is updated again.
       IsSafe = true;
       break;
     }
-    if (!Instr.readsRegister(X86::EFLAGS, TRI))
+    if (!UseEFLAGS && !ModifyEFLAGS)
       continue;
 
     // EFLAGS is used by this instruction.
@@ -3281,7 +3284,8 @@ optimizeCompareInstr(MachineInstr *CmpInstr, unsigned SrcReg, unsigned SrcReg2,
       // instructions will be modified.
       OpsToUpdate.push_back(std::make_pair(&*I, NewOpc));
     }
-    if (Instr.killsRegister(X86::EFLAGS, TRI)) {
+    if (ModifyEFLAGS || Instr.killsRegister(X86::EFLAGS, TRI)) {
+      // It is safe to remove CmpInstr if EFLAGS is updated again or killed.
       IsSafe = true;
       break;
     }
diff --git a/llvm/test/CodeGen/X86/jump_sign.ll b/llvm/test/CodeGen/X86/jump_sign.ll
index 5fb6ee52548..61792d3253c 100644
--- a/llvm/test/CodeGen/X86/jump_sign.ll
+++ b/llvm/test/CodeGen/X86/jump_sign.ll
@@ -214,3 +214,19 @@ entry:
   %add. = select i1 %cmp, i32 %add, i32 0
   ret i32 %add.
 }
+; PR13475
+; If we have sub a, b and cmp b, a and the result of cmp is used
+; by sbb, we should not optimize cmp away.
+define i32 @q(i32 %j.4, i32 %w, i32 %el) {
+; CHECK: q:
+; CHECK: sub
+; CHECK: cmp
+; CHECK-NEXT: sbb
+  %tmp532 = add i32 %j.4, %w
+  %tmp533 = icmp ugt i32 %tmp532, %el
+  %tmp534 = icmp ult i32 %w, %el
+  %or.cond = and i1 %tmp533, %tmp534
+  %tmp535 = sub i32 %el, %w
+  %j.5 = select i1 %or.cond, i32 %tmp535, i32 %j.4
+  ret i32 %j.5
+}