Index: lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- lib/Target/AArch64/AArch64ISelLowering.cpp
+++ lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -2916,11 +2916,6 @@
             isPowerOf2_64(LHS.getConstantOperandVal(1))) {
           SDValue Test = LHS.getOperand(0);
           uint64_t Mask = LHS.getConstantOperandVal(1);
-
-          // TBZ only operates on i64's, but the ext should be free.
-          if (Test.getValueType() == MVT::i32)
-            Test = DAG.getAnyExtOrTrunc(Test, dl, MVT::i64);
-
           return DAG.getNode(AArch64ISD::TBZ, dl, MVT::Other, Chain, Test,
                              DAG.getConstant(Log2_64(Mask), MVT::i64), Dest);
         }
@@ -2936,18 +2931,29 @@
             isPowerOf2_64(LHS.getConstantOperandVal(1))) {
           SDValue Test = LHS.getOperand(0);
           uint64_t Mask = LHS.getConstantOperandVal(1);
-
-          // TBNZ only operates on i64's, but the ext should be free.
-          if (Test.getValueType() == MVT::i32)
-            Test = DAG.getAnyExtOrTrunc(Test, dl, MVT::i64);
-
           return DAG.getNode(AArch64ISD::TBNZ, dl, MVT::Other, Chain, Test,
                              DAG.getConstant(Log2_64(Mask), MVT::i64), Dest);
         }
 
         return DAG.getNode(AArch64ISD::CBNZ, dl, MVT::Other, Chain, LHS, Dest);
+      } else if (CC == ISD::SETLT && LHS.getOpcode() != ISD::AND) {
+        // Don't combine AND since emitComparison converts the AND to an ANDS
+        // (a.k.a. TST) and the test in the test bit and branch instruction
+        // becomes redundant.  This would also increase register pressure.
+        uint64_t Mask = LHS.getValueType().getSizeInBits() - 1;
+        return DAG.getNode(AArch64ISD::TBNZ, dl, MVT::Other, Chain, LHS,
+                           DAG.getConstant(Mask, MVT::i64), Dest);
       }
     }
+    if (RHSC && RHSC->getSExtValue() == -1 && CC == ISD::SETGT &&
+        LHS.getOpcode() != ISD::AND) {
+      // Don't combine AND since emitComparison converts the AND to an ANDS
+      // (a.k.a. TST) and the test in the test bit and branch instruction
+      // becomes redundant.  This would also increase register pressure.
+      uint64_t Mask = LHS.getValueType().getSizeInBits() - 1;
+      return DAG.getNode(AArch64ISD::TBZ, dl, MVT::Other, Chain, LHS,
+                         DAG.getConstant(Mask, MVT::i64), Dest);
+    }
 
     SDValue CCVal;
     SDValue Cmp = getAArch64Cmp(LHS, RHS, CC, CCVal, DAG, dl);
Index: test/CodeGen/AArch64/tbz-tbnz.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AArch64/tbz-tbnz.ll
@@ -0,0 +1,258 @@
+; RUN: llc -O1 -march=aarch64 < %s | FileCheck %s
+
+declare void @t()
+
+define void @test1(i32 %a) {
+; CHECK-LABEL: @test1
+entry:
+  %sub = add nsw i32 %a, -12
+  %cmp = icmp slt i32 %sub, 0
+  br i1 %cmp, label %if.then, label %if.end
+
+; CHECK: sub [[CMP:w[0-9]+]], w0, #12
+; CHECK: tbz [[CMP]], #31
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test2(i64 %a) {
+; CHECK-LABEL: @test2
+entry:
+  %sub = add nsw i64 %a, -12
+  %cmp = icmp slt i64 %sub, 0
+  br i1 %cmp, label %if.then, label %if.end
+
+; CHECK: sub [[CMP:x[0-9]+]], x0, #12
+; CHECK: tbz [[CMP]], #63
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test3(i32 %a) {
+; CHECK-LABEL: @test3
+entry:
+  %sub = add nsw i32 %a, -12
+  %cmp = icmp sgt i32 %sub, -1
+  br i1 %cmp, label %if.then, label %if.end
+
+; CHECK: sub [[CMP:w[0-9]+]], w0, #12
+; CHECK: tbnz [[CMP]], #31
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test4(i64 %a) {
+; CHECK-LABEL: @test4
+entry:
+  %sub = add nsw i64 %a, -12
+  %cmp = icmp sgt i64 %sub, -1
+  br i1 %cmp, label %if.then, label %if.end
+
+; CHECK: sub [[CMP:x[0-9]+]], x0, #12
+; CHECK: tbnz [[CMP]], #63
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test5(i32 %a) {
+; CHECK-LABEL: @test5
+entry:
+  %sub = add nsw i32 %a, -12
+  %cmp = icmp sge i32 %sub, 0
+  br i1 %cmp, label %if.then, label %if.end
+
+; CHECK: sub [[CMP:w[0-9]+]], w0, #12
+; CHECK: tbnz [[CMP]], #31
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test6(i64 %a) {
+; CHECK-LABEL: @test6
+entry:
+  %sub = add nsw i64 %a, -12
+  %cmp = icmp sge i64 %sub, 0
+  br i1 %cmp, label %if.then, label %if.end
+
+; CHECK: sub [[CMP:x[0-9]+]], x0, #12
+; CHECK: tbnz [[CMP]], #63
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test7(i32 %a) {
+; CHECK-LABEL: @test7
+entry:
+  %sub = sub nsw i32 %a, 12
+  %cmp = icmp slt i32 %sub, 0
+  br i1 %cmp, label %if.then, label %if.end
+
+; CHECK: sub [[CMP:w[0-9]+]], w0, #12
+; CHECK: tbz [[CMP]], #31
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test8(i64 %val1, i64 %val2, i64 %val3) {
+; CHECK-LABEL: @test8
+  %and1 = and i64 %val1, %val2
+  %tst1 = icmp slt i64 %and1, 0
+  br i1 %tst1, label %if.then1, label %if.end
+
+; CHECK: tst x0, x1
+; CHECK-NEXT: b.ge .L
+
+if.then1:
+  %and2 = and i64 %val2, %val3
+  %tst2 = icmp sge i64 %and2, 0
+  br i1 %tst2, label %if.then2, label %if.end
+
+; CHECK: and [[CMP:x[0-9]+]], x1, x2
+; CHECK-NOT: cmp
+; CHECK: tbnz [[CMP]], #63, .LBB7_5
+
+if.then2:
+  %shifted_op1 = shl i64 %val2, 63
+  %shifted_and1 = and i64 %val1, %shifted_op1
+  %tst3 = icmp slt i64 %shifted_and1, 0
+  br i1 %tst3, label %if.then3, label %if.end
+
+; CHECK: tst x0, x1, lsl #63
+; CHECK: b.ge .L
+
+if.then3:
+  %shifted_op2 = shl i64 %val2, 62
+  %shifted_and2 = and i64 %val1, %shifted_op2
+  %tst4 = icmp sge i64 %shifted_and2, 0
+  br i1 %tst4, label %if.then4, label %if.end
+
+; CHECK: tst x0, x1, lsl #62
+; CHECK: b.lt .L
+
+if.then4:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test9(i64 %val1) {
+; CHECK-LABEL: @test9
+  %tst = icmp slt i64 %val1, 0
+  br i1 %tst, label %if.then, label %if.end
+
+; CHECK-NOT: cmp
+; CHECK: tbz x0, #63, .L
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test10(i64 %val1) {
+; CHECK-LABEL: @test10
+  %tst = icmp slt i64 %val1, 0
+  br i1 %tst, label %if.then, label %if.end
+
+; CHECK-NOT: cmp
+; CHECK: tbz x0, #63, .L
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test11(i64 %val1, i64* %ptr) {
+; CHECK-LABEL: @test11
+
+; CHECK: ldr [[CMP:x[0-9]+]], [x1]
+; CHECK-NOT: cmp
+; CHECK: tbz [[CMP]], #63, .L
+
+  %val = load i64* %ptr
+  %tst = icmp slt i64 %val, 0
+  br i1 %tst, label %if.then, label %if.end
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test12(i64 %val1) {
+; CHECK-LABEL: @test12
+  %tst = icmp slt i64 %val1, 0
+  br i1 %tst, label %if.then, label %if.end
+
+; CHECK-NOT: cmp
+; CHECK: tbz x0, #63, .L
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}
+
+define void @test13(i64 %val1, i64 %val2) {
+; CHECK-LABEL: @test13
+  %or = or i64 %val1, %val2
+  %tst = icmp slt i64 %or, 0
+  br i1 %tst, label %if.then, label %if.end
+
+; CHECK: orr [[CMP:x[0-9]+]], x0, x1
+; CHECK-NOT: cmp
+; CHECK: tbz [[CMP]], #63, .L
+
+if.then:
+  call void @t()
+  br label %if.end
+
+if.end:
+  ret void
+}