Optimize ZERO_EXTEND and SIGN_EXTEND in both SelectionDAG Builder and type

legalization stage. With those two optimizations, fewer signed/zero extension
instructions can be inserted, and then we can expose more opportunities to
Machine CSE pass in back-end.

llvm-svn: 216066

llvm/lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp

@@ -861,7 +861,28 @@ void DAGTypeLegalizer::PromoteSetCCOperands(SDValue &NewLHS,SDValue &NewRHS,
   switch (CCCode) {
   default: llvm_unreachable("Unknown integer comparison!");
   case ISD::SETEQ:
-  case ISD::SETNE:
+  case ISD::SETNE: {
+    SDValue OpL, OpR;
+
+    OpL = GetPromotedInteger(NewLHS);
+    OpR = GetPromotedInteger(NewRHS);
+
+    // We would prefer to promote the comparison operand with sign extension,
+    // if we find the operand is actually to truncate an AssertSext. With this
+    // optimization, we can avoid inserting real truncate instruction, which
+    // is redudant eventually.
+    if (OpL->getOpcode() == ISD::AssertSext &&
+        cast<VTSDNode>(OpL->getOperand(1))->getVT() == NewLHS.getValueType() &&
+        OpR->getOpcode() == ISD::AssertSext &&
+        cast<VTSDNode>(OpR->getOperand(1))->getVT() == NewRHS.getValueType()) {
+      NewLHS = OpL;
+      NewRHS = OpR;
+    } else {
+      NewLHS = ZExtPromotedInteger(NewLHS);
+      NewRHS = ZExtPromotedInteger(NewRHS);
+    }
+    break;
+  }
   case ISD::SETUGE:
   case ISD::SETUGT:
   case ISD::SETULE:

llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

@@ -757,6 +757,28 @@ SDValue RegsForValue::getCopyFromRegs(SelectionDAG &DAG,
   return DAG.getNode(ISD::MERGE_VALUES, dl, DAG.getVTList(ValueVTs), Values);
 }
 
+static ISD::NodeType getPreferredExtendForValue(const Value *V) {
+  // For the users of the source value being used for compare instruction, if
+  // the number of signed predicate is greater than unsigned predicate, we
+  // prefer to use SIGN_EXTEND.
+  //
+  // With this optimization, we would be able to reduce some redundant sign or
+  // zero extension instruction, and eventually more machine CSE opportunities
+  // can be exposed.
+  ISD::NodeType ExtendKind = ISD::ANY_EXTEND;
+  unsigned int NumOfSigned = 0, NumOfUnsigned = 0;
+  for (const User *U : V->users()) {
+    if (const CmpInst *CI = dyn_cast<CmpInst>(U)) {
+      NumOfSigned += CI->isSigned();
+      NumOfUnsigned += CI->isUnsigned();
+    }
+  }
+  if (NumOfSigned > NumOfUnsigned)
+    ExtendKind = ISD::SIGN_EXTEND;
+
+  return ExtendKind;
+}
+
 /// getCopyToRegs - Emit a series of CopyToReg nodes that copies the
 /// specified value into the registers specified by this object.  This uses
 /// Chain/Flag as the input and updates them for the output Chain/Flag.
@@ -765,6 +787,7 @@ void RegsForValue::getCopyToRegs(SDValue Val, SelectionDAG &DAG, SDLoc dl,
                                  SDValue &Chain, SDValue *Flag,
                                  const Value *V) const {
   const TargetLowering &TLI = DAG.getTargetLoweringInfo();
+  ISD::NodeType ExtendKind = getPreferredExtendForValue(V);
 
   // Get the list of the values's legal parts.
   unsigned NumRegs = Regs.size();
@@ -773,8 +796,9 @@ void RegsForValue::getCopyToRegs(SDValue Val, SelectionDAG &DAG, SDLoc dl,
     EVT ValueVT = ValueVTs[Value];
     unsigned NumParts = TLI.getNumRegisters(*DAG.getContext(), ValueVT);
     MVT RegisterVT = RegVTs[Value];
-    ISD::NodeType ExtendKind =
+
-      TLI.isZExtFree(Val, RegisterVT)? ISD::ZERO_EXTEND: ISD::ANY_EXTEND;
+    if (ExtendKind == ISD::ANY_EXTEND && TLI.isZExtFree(Val, RegisterVT))
+      ExtendKind = ISD::ZERO_EXTEND;
 
     getCopyToParts(DAG, dl, Val.getValue(Val.getResNo() + Value),
                    &Parts[Part], NumParts, RegisterVT, V, ExtendKind);

llvm/test/CodeGen/AArch64/atomic-ops.ll

@@ -493,6 +493,7 @@ define i8 @test_atomic_load_min_i8(i8 %offset) nounwind {
 ; CHECK-LABEL: test_atomic_load_min_i8:
    %old = atomicrmw min i8* @var8, i8 %offset acquire
 ; CHECK-NOT: dmb
+; CHECK: sxtb w[[TMP:[0-9]+]], w0
 ; CHECK: adrp [[TMPADDR:x[0-9]+]], var8
 ; CHECK: add x[[ADDR:[0-9]+]], [[TMPADDR]], {{#?}}:lo12:var8
 
@@ -502,14 +503,13 @@ define i8 @test_atomic_load_min_i8(i8 %offset) nounwind {
   ;  function there.
 
 ; CHECK-NEXT: sxtb w[[OLD_EXT:[0-9]+]], w[[OLD]]
-; CHECK-NEXT: cmp w[[OLD_EXT]], w0, sxtb
+; CHECK-NEXT: cmp w[[OLD_EXT]], w[[TMP]]
-; CHECK-NEXT: csel [[NEW:w[0-9]+]], w[[OLD]], w0, le
+; CHECK-NEXT: csel [[NEW:w[0-9]+]], w[[OLD]], w[[TMP]], le
 
 ; CHECK-NEXT: stxrb [[STATUS:w[0-9]+]], [[NEW]], [x[[ADDR]]]
 ; CHECK-NEXT: cbnz [[STATUS]], .LBB{{[0-9]+}}_1
 ; CHECK-NOT: dmb
 
-; CHECK: mov {{[xw]}}0, {{[xw]}}[[OLD]]
    ret i8 %old
 }
 
@@ -517,6 +517,7 @@ define i16 @test_atomic_load_min_i16(i16 %offset) nounwind {
 ; CHECK-LABEL: test_atomic_load_min_i16:
    %old = atomicrmw min i16* @var16, i16 %offset release
 ; CHECK-NOT: dmb
+; CHECK: sxth w[[TMP:[0-9]+]], w0
 ; CHECK: adrp [[TMPADDR:x[0-9]+]], var16
 ; CHECK: add x[[ADDR:[0-9]+]], [[TMPADDR]], {{#?}}:lo12:var16
 
@@ -526,15 +527,14 @@ define i16 @test_atomic_load_min_i16(i16 %offset) nounwind {
   ;  function there.
 
 ; CHECK-NEXT: sxth w[[OLD_EXT:[0-9]+]], w[[OLD]]
-; CHECK-NEXT: cmp w[[OLD_EXT]], w0, sxth
+; CHECK-NEXT: cmp w[[OLD_EXT]], w[[TMP]]
-; CHECK-NEXT: csel [[NEW:w[0-9]+]], w[[OLD]], w0, le
+; CHECK-NEXT: csel [[NEW:w[0-9]+]], w[[OLD]], w[[TMP]], le
 
 
 ; CHECK-NEXT: stlxrh [[STATUS:w[0-9]+]], [[NEW]], [x[[ADDR]]]
 ; CHECK-NEXT: cbnz [[STATUS]], .LBB{{[0-9]+}}_1
 ; CHECK-NOT: dmb
 
-; CHECK: mov {{[xw]}}0, {{[xw]}}[[OLD]]
    ret i16 %old
 }
 
@@ -590,6 +590,7 @@ define i8 @test_atomic_load_max_i8(i8 %offset) nounwind {
 ; CHECK-LABEL: test_atomic_load_max_i8:
    %old = atomicrmw max i8* @var8, i8 %offset seq_cst
 ; CHECK-NOT: dmb
+; CHECK: sxtb w[[TMP:[0-9]+]], w0
 ; CHECK: adrp [[TMPADDR:x[0-9]+]], var8
 ; CHECK: add x[[ADDR:[0-9]+]], [[TMPADDR]], {{#?}}:lo12:var8
 
@@ -599,15 +600,14 @@ define i8 @test_atomic_load_max_i8(i8 %offset) nounwind {
   ;  function there.
 
 ; CHECK-NEXT: sxtb w[[OLD_EXT:[0-9]+]], w[[OLD]]
-; CHECK-NEXT: cmp w[[OLD_EXT]], w0, sxtb
+; CHECK-NEXT: cmp w[[OLD_EXT]], w[[TMP]]
-; CHECK-NEXT: csel [[NEW:w[0-9]+]], w[[OLD]], w0, gt
+; CHECK-NEXT: csel [[NEW:w[0-9]+]], w[[OLD]], w[[TMP]], gt
 
 
 ; CHECK-NEXT: stlxrb [[STATUS:w[0-9]+]], [[NEW]], [x[[ADDR]]]
 ; CHECK-NEXT: cbnz [[STATUS]], .LBB{{[0-9]+}}_1
 ; CHECK-NOT: dmb
 
-; CHECK: mov {{[xw]}}0, {{[xw]}}[[OLD]]
    ret i8 %old
 }
 
@@ -615,6 +615,7 @@ define i16 @test_atomic_load_max_i16(i16 %offset) nounwind {
 ; CHECK-LABEL: test_atomic_load_max_i16:
    %old = atomicrmw max i16* @var16, i16 %offset acquire
 ; CHECK-NOT: dmb
+; CHECK: sxth w[[TMP:[0-9]+]], w0
 ; CHECK: adrp [[TMPADDR:x[0-9]+]], var16
 ; CHECK: add x[[ADDR:[0-9]+]], [[TMPADDR]], {{#?}}:lo12:var16
 
@@ -624,15 +625,14 @@ define i16 @test_atomic_load_max_i16(i16 %offset) nounwind {
   ;  function there.
 
 ; CHECK-NEXT: sxth w[[OLD_EXT:[0-9]+]], w[[OLD]]
-; CHECK-NEXT: cmp w[[OLD_EXT]], w0, sxth
+; CHECK-NEXT: cmp w[[OLD_EXT]], w[[TMP]]
-; CHECK-NEXT: csel [[NEW:w[0-9]+]], w[[OLD]], w0, gt
+; CHECK-NEXT: csel [[NEW:w[0-9]+]], w[[OLD]], w[[TMP]], gt
 
 
 ; CHECK-NEXT: stxrh [[STATUS:w[0-9]+]], [[NEW]], [x[[ADDR]]]
 ; CHECK-NEXT: cbnz [[STATUS]], .LBB{{[0-9]+}}_1
 ; CHECK-NOT: dmb
 
-; CHECK: mov {{[xw]}}0, {{[xw]}}[[OLD]]
    ret i16 %old
 }
 

llvm/test/CodeGen/AArch64/rm_redundant_cmp.ll

@@ -0,0 +1,254 @@
+; RUN: llc < %s -mtriple=aarch64-linux-gnuabi -O2 | FileCheck %s
+
+; The following cases are for i16
+
+%struct.s_signed_i16 = type { i16, i16, i16 }
+%struct.s_unsigned_i16 = type { i16, i16, i16 }
+
+@cost_s_i8_i16 = common global %struct.s_signed_i16 zeroinitializer, align 2
+@cost_u_i16 = common global %struct.s_unsigned_i16 zeroinitializer, align 2
+
+define void @test_i16_2cmp_signed_1() {
+; CHECK-LABEL: test_i16_2cmp_signed_1
+; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
+; CHECK-NEXT: b.gt
+; CHECK-NOT: cmp
+; CHECK: b.ne
+entry:
+  %0 = load i16* getelementptr inbounds (%struct.s_signed_i16* @cost_s_i8_i16, i64 0, i32 1), align 2
+  %1 = load i16* getelementptr inbounds (%struct.s_signed_i16* @cost_s_i8_i16, i64 0, i32 2), align 2
+  %cmp = icmp sgt i16 %0, %1
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  store i16 %0, i16* getelementptr inbounds (%struct.s_signed_i16* @cost_s_i8_i16, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.else:                                          ; preds = %entry
+  %cmp5 = icmp eq i16 %0, %1
+  br i1 %cmp5, label %if.then7, label %if.end8
+
+if.then7:                                         ; preds = %if.else
+  store i16 %0, i16* getelementptr inbounds (%struct.s_signed_i16* @cost_s_i8_i16, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.end8:                                          ; preds = %if.else, %if.then7, %if.then
+  ret void
+}
+
+define void @test_i16_2cmp_signed_2() {
+; CHECK-LABEL: test_i16_2cmp_signed_2
+; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
+; CHECK-NEXT: b.le
+; CHECK-NOT: cmp
+; CHECK: b.ge
+entry:
+  %0 = load i16* getelementptr inbounds (%struct.s_signed_i16* @cost_s_i8_i16, i64 0, i32 1), align 2
+  %1 = load i16* getelementptr inbounds (%struct.s_signed_i16* @cost_s_i8_i16, i64 0, i32 2), align 2
+  %cmp = icmp sgt i16 %0, %1
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  store i16 %0, i16* getelementptr inbounds (%struct.s_signed_i16* @cost_s_i8_i16, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.else:                                          ; preds = %entry
+  %cmp5 = icmp slt i16 %0, %1
+  br i1 %cmp5, label %if.then7, label %if.end8
+
+if.then7:                                         ; preds = %if.else
+  store i16 %1, i16* getelementptr inbounds (%struct.s_signed_i16* @cost_s_i8_i16, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.end8:                                          ; preds = %if.else, %if.then7, %if.then
+  ret void
+}
+
+define void @test_i16_2cmp_unsigned_1() {
+; CHECK-LABEL: test_i16_2cmp_unsigned_1
+; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
+; CHECK-NEXT: b.hi
+; CHECK-NOT: cmp
+; CHECK: b.ne
+entry:
+  %0 = load i16* getelementptr inbounds (%struct.s_unsigned_i16* @cost_u_i16, i64 0, i32 1), align 2
+  %1 = load i16* getelementptr inbounds (%struct.s_unsigned_i16* @cost_u_i16, i64 0, i32 2), align 2
+  %cmp = icmp ugt i16 %0, %1
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  store i16 %0, i16* getelementptr inbounds (%struct.s_unsigned_i16* @cost_u_i16, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.else:                                          ; preds = %entry
+  %cmp5 = icmp eq i16 %0, %1
+  br i1 %cmp5, label %if.then7, label %if.end8
+
+if.then7:                                         ; preds = %if.else
+  store i16 %0, i16* getelementptr inbounds (%struct.s_unsigned_i16* @cost_u_i16, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.end8:                                          ; preds = %if.else, %if.then7, %if.then
+  ret void
+}
+
+define void @test_i16_2cmp_unsigned_2() {
+; CHECK-LABEL: test_i16_2cmp_unsigned_2
+; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
+; CHECK-NEXT: b.ls
+; CHECK-NOT: cmp
+; CHECK: b.hs
+entry:
+  %0 = load i16* getelementptr inbounds (%struct.s_unsigned_i16* @cost_u_i16, i64 0, i32 1), align 2
+  %1 = load i16* getelementptr inbounds (%struct.s_unsigned_i16* @cost_u_i16, i64 0, i32 2), align 2
+  %cmp = icmp ugt i16 %0, %1
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  store i16 %0, i16* getelementptr inbounds (%struct.s_unsigned_i16* @cost_u_i16, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.else:                                          ; preds = %entry
+  %cmp5 = icmp ult i16 %0, %1
+  br i1 %cmp5, label %if.then7, label %if.end8
+
+if.then7:                                         ; preds = %if.else
+  store i16 %1, i16* getelementptr inbounds (%struct.s_unsigned_i16* @cost_u_i16, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.end8:                                          ; preds = %if.else, %if.then7, %if.then
+  ret void
+}
+
+; The following cases are for i8
+
+%struct.s_signed_i8 = type { i8, i8, i8 }
+%struct.s_unsigned_i8 = type { i8, i8, i8 }
+
+@cost_s = common global %struct.s_signed_i8 zeroinitializer, align 2
+@cost_u_i8 = common global %struct.s_unsigned_i8 zeroinitializer, align 2
+
+
+define void @test_i8_2cmp_signed_1() {
+; CHECK-LABEL: test_i8_2cmp_signed_1
+; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
+; CHECK-NEXT: b.gt
+; CHECK-NOT: cmp
+; CHECK: b.ne
+entry:
+  %0 = load i8* getelementptr inbounds (%struct.s_signed_i8* @cost_s, i64 0, i32 1), align 2
+  %1 = load i8* getelementptr inbounds (%struct.s_signed_i8* @cost_s, i64 0, i32 2), align 2
+  %cmp = icmp sgt i8 %0, %1
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  store i8 %0, i8* getelementptr inbounds (%struct.s_signed_i8* @cost_s, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.else:                                          ; preds = %entry
+  %cmp5 = icmp eq i8 %0, %1
+  br i1 %cmp5, label %if.then7, label %if.end8
+
+if.then7:                                         ; preds = %if.else
+  store i8 %0, i8* getelementptr inbounds (%struct.s_signed_i8* @cost_s, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.end8:                                          ; preds = %if.else, %if.then7, %if.then
+  ret void
+}
+
+define void @test_i8_2cmp_signed_2() {
+; CHECK-LABEL: test_i8_2cmp_signed_2
+; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
+; CHECK-NEXT: b.le
+; CHECK-NOT: cmp
+; CHECK: b.ge
+entry:
+  %0 = load i8* getelementptr inbounds (%struct.s_signed_i8* @cost_s, i64 0, i32 1), align 2
+  %1 = load i8* getelementptr inbounds (%struct.s_signed_i8* @cost_s, i64 0, i32 2), align 2
+  %cmp = icmp sgt i8 %0, %1
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  store i8 %0, i8* getelementptr inbounds (%struct.s_signed_i8* @cost_s, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.else:                                          ; preds = %entry
+  %cmp5 = icmp slt i8 %0, %1
+  br i1 %cmp5, label %if.then7, label %if.end8
+
+if.then7:                                         ; preds = %if.else
+  store i8 %1, i8* getelementptr inbounds (%struct.s_signed_i8* @cost_s, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.end8:                                          ; preds = %if.else, %if.then7, %if.then
+  ret void
+}
+
+define void @test_i8_2cmp_unsigned_1() {
+; CHECK-LABEL: test_i8_2cmp_unsigned_1
+; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
+; CHECK-NEXT: b.hi
+; CHECK-NOT: cmp
+; CHECK: b.ne
+entry:
+  %0 = load i8* getelementptr inbounds (%struct.s_unsigned_i8* @cost_u_i8, i64 0, i32 1), align 2
+  %1 = load i8* getelementptr inbounds (%struct.s_unsigned_i8* @cost_u_i8, i64 0, i32 2), align 2
+  %cmp = icmp ugt i8 %0, %1
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  store i8 %0, i8* getelementptr inbounds (%struct.s_unsigned_i8* @cost_u_i8, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.else:                                          ; preds = %entry
+  %cmp5 = icmp eq i8 %0, %1
+  br i1 %cmp5, label %if.then7, label %if.end8
+
+if.then7:                                         ; preds = %if.else
+  store i8 %0, i8* getelementptr inbounds (%struct.s_unsigned_i8* @cost_u_i8, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.end8:                                          ; preds = %if.else, %if.then7, %if.then
+  ret void
+}
+
+define void @test_i8_2cmp_unsigned_2() {
+; CHECK-LABEL: test_i8_2cmp_unsigned_2
+; CHECK: cmp {{w[0-9]+}}, {{w[0-9]+}}
+; CHECK-NEXT: b.ls
+; CHECK-NOT: cmp
+; CHECK: b.hs
+entry:
+  %0 = load i8* getelementptr inbounds (%struct.s_unsigned_i8* @cost_u_i8, i64 0, i32 1), align 2
+  %1 = load i8* getelementptr inbounds (%struct.s_unsigned_i8* @cost_u_i8, i64 0, i32 2), align 2
+  %cmp = icmp ugt i8 %0, %1
+  br i1 %cmp, label %if.then, label %if.else
+
+if.then:                                          ; preds = %entry
+  store i8 %0, i8* getelementptr inbounds (%struct.s_unsigned_i8* @cost_u_i8, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.else:                                          ; preds = %entry
+  %cmp5 = icmp ult i8 %0, %1
+  br i1 %cmp5, label %if.then7, label %if.end8
+
+if.then7:                                         ; preds = %if.else
+  store i8 %1, i8* getelementptr inbounds (%struct.s_unsigned_i8* @cost_u_i8, i64 0, i32 0), align 2
+  br label %if.end8
+
+if.end8:                                          ; preds = %if.else, %if.then7, %if.then
+  ret void
+}
+
+; Make sure the case below won't crash.
+
+; The optimization of ZERO_EXTEND and SIGN_EXTEND in type legalization stage can't assert
+; the operand of a set_cc is always a TRUNCATE.
+
+define i1 @foo(float %inl, float %inr) {
+  %lval = fptosi float %inl to i8
+  %rval = fptosi float %inr to i8
+  %sum = icmp eq i8 %lval, %rval
+  ret i1 %sum
+}