This is another case where instcombine demanded bits optimization created

large immediates. Add dag combine logic to recover in case the large
immediates doesn't fit in cmp immediate operand field.

int foo(unsigned long l) {
  return (l>> 47) == 1;
}

we produce

  %shr.mask = and i64 %l, -140737488355328
  %cmp = icmp eq i64 %shr.mask, 140737488355328
  %conv = zext i1 %cmp to i32
  ret i32 %conv

which codegens to

movq    $0xffff800000000000,%rax
andq    %rdi,%rax
movq    $0x0000800000000000,%rcx
cmpq    %rcx,%rax
sete    %al
movzbl    %al,%eax
ret

TargetLowering::SimplifySetCC would transform
(X & -256) == 256 -> (X >> 8) == 1
if the immediate fails the isLegalICmpImmediate() test. For x86,
that's immediates which are not a signed 32-bit immediate.

Based on a patch by Eli Friedman.

PR10328
rdar://9758774

llvm-svn: 160346

llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp

@@ -2322,6 +2322,27 @@ TargetLowering::SimplifySetCC(EVT VT, SDValue N0, SDValue N1,
           }
         }
       }
+
+    if (!isLegalICmpImmediate(C1.getSExtValue())) {
+      // (X & -256) == 256 -> (X >> 8) == 1
+      if ((Cond == ISD::SETEQ || Cond == ISD::SETNE) &&
+          N0.getOpcode() == ISD::AND && N0.hasOneUse()) {
+        if (ConstantSDNode *AndRHS =
+            dyn_cast<ConstantSDNode>(N0.getOperand(1))) {
+          const APInt &AndRHSC = AndRHS->getAPIntValue();
+          if ((-AndRHSC).isPowerOf2() && (AndRHSC & C1) == C1) {
+            unsigned ShiftBits = AndRHSC.countTrailingZeros();
+            EVT ShiftTy = DCI.isBeforeLegalize() ?
+              getPointerTy() : getShiftAmountTy(N0.getValueType());
+            EVT CmpTy = N0.getValueType();
+            SDValue Shift = DAG.getNode(ISD::SRL, dl, CmpTy, N0.getOperand(0),
+                                        DAG.getConstant(ShiftBits, ShiftTy));
+            SDValue CmpRHS = DAG.getConstant(C1.lshr(ShiftBits), CmpTy);
+            return DAG.getSetCC(dl, VT, Shift, CmpRHS, Cond);
+          }
+        }
+      }
+    }
   }
 
   if (isa<ConstantFPSDNode>(N0.getNode())) {

llvm/lib/Target/X86/X86ISelLowering.cpp

@@ -11384,6 +11384,14 @@ bool X86TargetLowering::isTruncateFree(Type *Ty1, Type *Ty2) const {
   return true;
 }
 
+bool X86TargetLowering::isLegalICmpImmediate(int64_t Imm) const {
+  return Imm == (int32_t)Imm;
+}
+
+bool X86TargetLowering::isLegalAddImmediate(int64_t Imm) const {
+  return Imm == (int32_t)Imm;
+}
+
 bool X86TargetLowering::isTruncateFree(EVT VT1, EVT VT2) const {
   if (!VT1.isInteger() || !VT2.isInteger())
     return false;

llvm/lib/Target/X86/X86ISelLowering.h

@@ -568,6 +568,18 @@ namespace llvm {
     /// by AM is legal for this target, for a load/store of the specified type.
     virtual bool isLegalAddressingMode(const AddrMode &AM, Type *Ty)const;
 
+    /// isLegalICmpImmediate - Return true if the specified immediate is legal
+    /// icmp immediate, that is the target has icmp instructions which can
+    /// compare a register against the immediate without having to materialize
+    /// the immediate into a register.
+    virtual bool isLegalICmpImmediate(int64_t Imm) const;
+
+    /// isLegalAddImmediate - Return true if the specified immediate is legal
+    /// add immediate, that is the target has add instructions which can
+    /// add a register and the immediate without having to materialize
+    /// the immediate into a register.
+    virtual bool isLegalAddImmediate(int64_t Imm) const;
+
     /// isTruncateFree - Return true if it's free to truncate a value of
     /// type Ty1 to type Ty2. e.g. On x86 it's free to truncate a i32 value in
     /// register EAX to i16 by referencing its sub-register AX.

llvm/test/CodeGen/X86/cmp.ll

@@ -91,7 +91,7 @@ F:
 }
 
 ; rdar://11866926
-define i32 @test7(i64 %res) nounwind uwtable readnone ssp {
+define i32 @test7(i64 %res) nounwind {
 entry:
 ; CHECK: test7:
 ; CHECK-NOT: movabsq
@@ -103,7 +103,7 @@ entry:
   ret i32 %lnot.ext
 }
 
-define i32 @test8(i64 %res) nounwind uwtable readnone ssp {
+define i32 @test8(i64 %res) nounwind {
 entry:
 ; CHECK: test8:
 ; CHECK-NOT: movabsq
@@ -114,7 +114,7 @@ entry:
   ret i32 %lnot.ext
 }
 
-define i32 @test9(i64 %res) nounwind uwtable readnone ssp {
+define i32 @test9(i64 %res) nounwind {
 entry:
 ; CHECK: test9:
 ; CHECK-NOT: movabsq
@@ -126,7 +126,7 @@ entry:
   ret i32 %lnot.ext
 }
 
-define i32 @test10(i64 %res) nounwind uwtable readnone ssp {
+define i32 @test10(i64 %res) nounwind {
 entry:
 ; CHECK: test10:
 ; CHECK-NOT: movabsq
@@ -138,3 +138,16 @@ entry:
   ret i32 %lnot.ext
 }
 
+; rdar://9758774
+define i32 @test11(i64 %l) nounwind {
+entry:
+; CHECK: test11:
+; CHECK-NOT: movabsq
+; CHECK-NOT: andq
+; CHECK: shrq $47, %rdi
+; CHECK: cmpq $1, %rdi
+  %shr.mask = and i64 %l, -140737488355328
+  %cmp = icmp eq i64 %shr.mask, 140737488355328
+  %conv = zext i1 %cmp to i32
+  ret i32 %conv
+}