[llvm] 98562ff - [AArch64] Fix the type of NZCV operands/results (#150313)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Jul 24 01:48:31 PDT 2025
Author: Sergei Barannikov
Date: 2025-07-24T11:48:28+03:00
New Revision: 98562ffaaa74ebebfcfaf42f6604c736637e0d46
URL: https://github.com/llvm/llvm-project/commit/98562ffaaa74ebebfcfaf42f6604c736637e0d46
DIFF: https://github.com/llvm/llvm-project/commit/98562ffaaa74ebebfcfaf42f6604c736637e0d46.diff
LOG: [AArch64] Fix the type of NZCV operands/results (#150313)
Consistently use `FlagsVT` for operands/results of nodes that
consume/produce NZCV flags.
Previously, some of the operands/results had incorrect `MVT::Glue` type
while others had `MVT_CC` type, which is supposed to be used for
condition codes (`AArch64CC::CondCode` enum).
Found by #150125.
Added:
Modified:
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
llvm/lib/Target/AArch64/AArch64InstrInfo.td
llvm/lib/Target/AArch64/AArch64RegisterInfo.td
llvm/lib/Target/AArch64/AArch64SelectionDAGInfo.cpp
llvm/test/CodeGen/AArch64/abds-neg.ll
llvm/test/CodeGen/AArch64/abds.ll
llvm/test/CodeGen/AArch64/abdu-neg.ll
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 02ee517a0a9b8..d7baee4387561 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -164,6 +164,9 @@ static cl::opt<bool> UseFEATCPACodegen(
/// Value type used for condition codes.
static const MVT MVT_CC = MVT::i32;
+/// Value type used for NZCV flags.
+static constexpr MVT FlagsVT = MVT::i32;
+
static const MCPhysReg GPRArgRegs[] = {AArch64::X0, AArch64::X1, AArch64::X2,
AArch64::X3, AArch64::X4, AArch64::X5,
AArch64::X6, AArch64::X7};
@@ -3451,7 +3454,7 @@ static SDValue emitStrictFPComparison(SDValue LHS, SDValue RHS, const SDLoc &DL,
}
unsigned Opcode =
IsSignaling ? AArch64ISD::STRICT_FCMPE : AArch64ISD::STRICT_FCMP;
- return DAG.getNode(Opcode, DL, {MVT::i32, MVT::Other}, {Chain, LHS, RHS});
+ return DAG.getNode(Opcode, DL, {FlagsVT, MVT::Other}, {Chain, LHS, RHS});
}
static SDValue emitComparison(SDValue LHS, SDValue RHS, ISD::CondCode CC,
@@ -3465,7 +3468,7 @@ static SDValue emitComparison(SDValue LHS, SDValue RHS, ISD::CondCode CC,
LHS = DAG.getNode(ISD::FP_EXTEND, DL, MVT::f32, LHS);
RHS = DAG.getNode(ISD::FP_EXTEND, DL, MVT::f32, RHS);
}
- return DAG.getNode(AArch64ISD::FCMP, DL, MVT::i32, LHS, RHS);
+ return DAG.getNode(AArch64ISD::FCMP, DL, FlagsVT, LHS, RHS);
}
// The CMP instruction is just an alias for SUBS, and representing it as
@@ -3490,7 +3493,7 @@ static SDValue emitComparison(SDValue LHS, SDValue RHS, ISD::CondCode CC,
// (a.k.a. ANDS) except that the flags are only guaranteed to work for one
// of the signed comparisons.
const SDValue ANDSNode =
- DAG.getNode(AArch64ISD::ANDS, DL, DAG.getVTList(VT, MVT_CC),
+ DAG.getNode(AArch64ISD::ANDS, DL, DAG.getVTList(VT, FlagsVT),
LHS.getOperand(0), LHS.getOperand(1));
// Replace all users of (and X, Y) with newly generated (ands X, Y)
DAG.ReplaceAllUsesWith(LHS, ANDSNode);
@@ -3501,7 +3504,7 @@ static SDValue emitComparison(SDValue LHS, SDValue RHS, ISD::CondCode CC,
}
}
- return DAG.getNode(Opcode, DL, DAG.getVTList(VT, MVT_CC), LHS, RHS)
+ return DAG.getNode(Opcode, DL, DAG.getVTList(VT, FlagsVT), LHS, RHS)
.getValue(1);
}
@@ -3597,7 +3600,7 @@ static SDValue emitConditionalComparison(SDValue LHS, SDValue RHS,
AArch64CC::CondCode InvOutCC = AArch64CC::getInvertedCondCode(OutCC);
unsigned NZCV = AArch64CC::getNZCVToSatisfyCondCode(InvOutCC);
SDValue NZCVOp = DAG.getConstant(NZCV, DL, MVT::i32);
- return DAG.getNode(Opcode, DL, MVT_CC, LHS, RHS, NZCVOp, Condition, CCOp);
+ return DAG.getNode(Opcode, DL, FlagsVT, LHS, RHS, NZCVOp, Condition, CCOp);
}
/// Returns true if @p Val is a tree of AND/OR/SETCC operations that can be
@@ -4036,7 +4039,7 @@ getAArch64XALUOOp(AArch64CC::CondCode &CC, SDValue Op, SelectionDAG &DAG) {
Value = DAG.getNode(ISD::TRUNCATE, DL, MVT::i32, Mul);
// Check that the result fits into a 32-bit integer.
- SDVTList VTs = DAG.getVTList(MVT::i64, MVT_CC);
+ SDVTList VTs = DAG.getVTList(MVT::i64, FlagsVT);
if (IsSigned) {
// cmp xreg, wreg, sxtw
SDValue SExtMul = DAG.getNode(ISD::SIGN_EXTEND, DL, MVT::i64, Value);
@@ -4059,12 +4062,12 @@ getAArch64XALUOOp(AArch64CC::CondCode &CC, SDValue Op, SelectionDAG &DAG) {
DAG.getConstant(63, DL, MVT::i64));
// It is important that LowerBits is last, otherwise the arithmetic
// shift will not be folded into the compare (SUBS).
- SDVTList VTs = DAG.getVTList(MVT::i64, MVT::i32);
+ SDVTList VTs = DAG.getVTList(MVT::i64, FlagsVT);
Overflow = DAG.getNode(AArch64ISD::SUBS, DL, VTs, UpperBits, LowerBits)
.getValue(1);
} else {
SDValue UpperBits = DAG.getNode(ISD::MULHU, DL, MVT::i64, LHS, RHS);
- SDVTList VTs = DAG.getVTList(MVT::i64, MVT::i32);
+ SDVTList VTs = DAG.getVTList(MVT::i64, FlagsVT);
Overflow =
DAG.getNode(AArch64ISD::SUBS, DL, VTs,
DAG.getConstant(0, DL, MVT::i64),
@@ -4075,7 +4078,7 @@ getAArch64XALUOOp(AArch64CC::CondCode &CC, SDValue Op, SelectionDAG &DAG) {
} // switch (...)
if (Opc) {
- SDVTList VTs = DAG.getVTList(Op->getValueType(0), MVT::i32);
+ SDVTList VTs = DAG.getVTList(Op->getValueType(0), FlagsVT);
// Emit the AArch64 operation with overflow check.
Value = DAG.getNode(Opc, DL, VTs, LHS, RHS);
@@ -4177,7 +4180,7 @@ static SDValue valueToCarryFlag(SDValue Value, SelectionDAG &DAG, bool Invert) {
SDValue Op0 = Invert ? DAG.getConstant(0, DL, VT) : Value;
SDValue Op1 = Invert ? Value : DAG.getConstant(1, DL, VT);
SDValue Cmp =
- DAG.getNode(AArch64ISD::SUBS, DL, DAG.getVTList(VT, MVT::Glue), Op0, Op1);
+ DAG.getNode(AArch64ISD::SUBS, DL, DAG.getVTList(VT, FlagsVT), Op0, Op1);
return Cmp.getValue(1);
}
@@ -4222,7 +4225,7 @@ static SDValue lowerADDSUBO_CARRY(SDValue Op, SelectionDAG &DAG,
SDLoc DL(Op);
SDVTList VTs = DAG.getVTList(VT0, VT1);
- SDValue Sum = DAG.getNode(Opcode, DL, DAG.getVTList(VT0, MVT::Glue), OpLHS,
+ SDValue Sum = DAG.getNode(Opcode, DL, DAG.getVTList(VT0, FlagsVT), OpLHS,
OpRHS, OpCarryIn);
SDValue OutFlag =
@@ -7037,9 +7040,8 @@ SDValue AArch64TargetLowering::LowerABS(SDValue Op, SelectionDAG &DAG) const {
SDValue Neg = DAG.getNode(ISD::SUB, DL, VT, DAG.getConstant(0, DL, VT),
Op.getOperand(0));
// Generate SUBS & CSEL.
- SDValue Cmp =
- DAG.getNode(AArch64ISD::SUBS, DL, DAG.getVTList(VT, MVT::i32),
- Op.getOperand(0), DAG.getConstant(0, DL, VT));
+ SDValue Cmp = DAG.getNode(AArch64ISD::SUBS, DL, DAG.getVTList(VT, FlagsVT),
+ Op.getOperand(0), DAG.getConstant(0, DL, VT));
return DAG.getNode(AArch64ISD::CSEL, DL, VT, Op.getOperand(0), Neg,
DAG.getConstant(AArch64CC::PL, DL, MVT::i32),
Cmp.getValue(1));
@@ -11108,7 +11110,7 @@ SDValue AArch64TargetLowering::LowerSETCCCARRY(SDValue Op,
SDValue Carry = Op.getOperand(2);
// SBCS uses a carry not a borrow so the carry flag should be inverted first.
SDValue InvCarry = valueToCarryFlag(Carry, DAG, true);
- SDValue Cmp = DAG.getNode(AArch64ISD::SBCS, DL, DAG.getVTList(VT, MVT::Glue),
+ SDValue Cmp = DAG.getNode(AArch64ISD::SBCS, DL, DAG.getVTList(VT, FlagsVT),
LHS, RHS, InvCarry);
EVT OpVT = Op.getValueType();
@@ -12441,10 +12443,10 @@ SDValue AArch64TargetLowering::LowerAsmOutputForConstraint(
// Get NZCV register. Only update chain when copyfrom is glued.
if (Glue.getNode()) {
- Glue = DAG.getCopyFromReg(Chain, DL, AArch64::NZCV, MVT::i32, Glue);
+ Glue = DAG.getCopyFromReg(Chain, DL, AArch64::NZCV, FlagsVT, Glue);
Chain = Glue.getValue(1);
} else
- Glue = DAG.getCopyFromReg(Chain, DL, AArch64::NZCV, MVT::i32);
+ Glue = DAG.getCopyFromReg(Chain, DL, AArch64::NZCV, FlagsVT);
// Extract CC code.
SDValue CC = getSETCC(Cond, Glue, DL, DAG);
@@ -18593,7 +18595,7 @@ AArch64TargetLowering::BuildSREMPow2(SDNode *N, const APInt &Divisor,
Created.push_back(And.getNode());
} else {
SDValue CCVal = DAG.getConstant(AArch64CC::MI, DL, MVT_CC);
- SDVTList VTs = DAG.getVTList(VT, MVT::i32);
+ SDVTList VTs = DAG.getVTList(VT, FlagsVT);
SDValue Negs = DAG.getNode(AArch64ISD::SUBS, DL, VTs, Zero, N0);
SDValue AndPos = DAG.getNode(ISD::AND, DL, VT, N0, Pow2MinusOne);
@@ -19482,10 +19484,10 @@ static SDValue performANDORCSELCombine(SDNode *N, SelectionDAG &DAG) {
// can select to CCMN to avoid the extra mov
SDValue AbsOp1 =
DAG.getConstant(Op1->getAPIntValue().abs(), DL, Op1->getValueType(0));
- CCmp = DAG.getNode(AArch64ISD::CCMN, DL, MVT_CC, Cmp1.getOperand(0), AbsOp1,
- NZCVOp, Condition, Cmp0);
+ CCmp = DAG.getNode(AArch64ISD::CCMN, DL, FlagsVT, Cmp1.getOperand(0),
+ AbsOp1, NZCVOp, Condition, Cmp0);
} else {
- CCmp = DAG.getNode(AArch64ISD::CCMP, DL, MVT_CC, Cmp1.getOperand(0),
+ CCmp = DAG.getNode(AArch64ISD::CCMP, DL, FlagsVT, Cmp1.getOperand(0),
Cmp1.getOperand(1), NZCVOp, Condition, Cmp0);
}
return DAG.getNode(AArch64ISD::CSEL, DL, VT, CSel0.getOperand(0),
@@ -25134,8 +25136,9 @@ static SDValue reassociateCSELOperandsForCSE(SDNode *N, SelectionDAG &DAG) {
if (!TReassocOp && !FReassocOp)
return SDValue();
- SDValue NewCmp = DAG.getNode(AArch64ISD::SUBS, SDLoc(SubsNode),
- DAG.getVTList(VT, MVT_CC), CmpOpOther, SubsOp);
+ SDValue NewCmp =
+ DAG.getNode(AArch64ISD::SUBS, SDLoc(SubsNode),
+ DAG.getVTList(VT, FlagsVT), CmpOpOther, SubsOp);
auto Reassociate = [&](SDValue ReassocOp, unsigned OpNum) {
if (!ReassocOp)
@@ -27161,7 +27164,7 @@ SDValue AArch64TargetLowering::PerformDAGCombine(SDNode *N,
: AArch64SysReg::RNDRRS);
SDLoc DL(N);
SDValue A = DAG.getNode(
- AArch64ISD::MRS, DL, DAG.getVTList(MVT::i64, MVT::i32, MVT::Other),
+ AArch64ISD::MRS, DL, DAG.getVTList(MVT::i64, FlagsVT, MVT::Other),
N->getOperand(0), DAG.getConstant(Register, DL, MVT::i32));
SDValue B = DAG.getNode(
AArch64ISD::CSINC, DL, MVT::i32, DAG.getConstant(0, DL, MVT::i32),
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index 6ef28f052e836..9ebdf2e72cefd 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -430,26 +430,27 @@ def UseWzrToVecMove : Predicate<"Subtarget->useWzrToVecMove()">;
def SDTBinaryArithWithFlagsOut : SDTypeProfile<2, 2,
[SDTCisSameAs<0, 2>,
SDTCisSameAs<0, 3>,
- SDTCisInt<0>, SDTCisVT<1, i32>]>;
+ SDTCisInt<0>,
+ SDTCisVT<1, FlagsVT>]>;
// SDTBinaryArithWithFlagsIn - RES1, FLAGS = op LHS, RHS, FLAGS
def SDTBinaryArithWithFlagsIn : SDTypeProfile<1, 3,
[SDTCisSameAs<0, 1>,
SDTCisSameAs<0, 2>,
SDTCisInt<0>,
- SDTCisVT<3, i32>]>;
+ SDTCisVT<3, FlagsVT>]>;
// SDTBinaryArithWithFlagsInOut - RES1, FLAGS = op LHS, RHS, FLAGS
def SDTBinaryArithWithFlagsInOut : SDTypeProfile<2, 3,
[SDTCisSameAs<0, 2>,
SDTCisSameAs<0, 3>,
SDTCisInt<0>,
- SDTCisVT<1, i32>,
- SDTCisVT<4, i32>]>;
+ SDTCisVT<1, FlagsVT>,
+ SDTCisVT<4, FlagsVT>]>;
def SDT_AArch64Brcond : SDTypeProfile<0, 3,
[SDTCisVT<0, OtherVT>, SDTCisVT<1, i32>,
- SDTCisVT<2, i32>]>;
+ SDTCisVT<2, FlagsVT>]>;
def SDT_AArch64cbz : SDTypeProfile<0, 2, [SDTCisInt<0>, SDTCisVT<1, OtherVT>]>;
def SDT_AArch64tbz : SDTypeProfile<0, 3, [SDTCisInt<0>, SDTCisInt<1>,
SDTCisVT<2, OtherVT>]>;
@@ -458,22 +459,22 @@ def SDT_AArch64CSel : SDTypeProfile<1, 4,
[SDTCisSameAs<0, 1>,
SDTCisSameAs<0, 2>,
SDTCisInt<3>,
- SDTCisVT<4, i32>]>;
+ SDTCisVT<4, FlagsVT>]>;
def SDT_AArch64CCMP : SDTypeProfile<1, 5,
- [SDTCisVT<0, i32>,
+ [SDTCisVT<0, FlagsVT>,
SDTCisInt<1>,
SDTCisSameAs<1, 2>,
SDTCisInt<3>,
SDTCisInt<4>,
SDTCisVT<5, i32>]>;
def SDT_AArch64FCCMP : SDTypeProfile<1, 5,
- [SDTCisVT<0, i32>,
+ [SDTCisVT<0, FlagsVT>,
SDTCisFP<1>,
SDTCisSameAs<1, 2>,
SDTCisInt<3>,
SDTCisInt<4>,
SDTCisVT<5, i32>]>;
-def SDT_AArch64FCmp : SDTypeProfile<1, 2, [SDTCisVT<0, i32>,
+def SDT_AArch64FCmp : SDTypeProfile<1, 2, [SDTCisVT<0, FlagsVT>,
SDTCisFP<1>,
SDTCisSameAs<2, 1>]>;
def SDT_AArch64Rev : SDTypeProfile<1, 1, [SDTCisSameAs<0, 1>]>;
@@ -1124,10 +1125,10 @@ def AArch64probedalloca
SDTypeProfile<0, 1, [SDTCisPtrTy<0>]>,
[SDNPHasChain, SDNPMayStore]>;
-// MRS, also sets the flags via a glue.
+// MRS, also sets the flags.
def AArch64mrs : SDNode<"AArch64ISD::MRS",
SDTypeProfile<2, 1, [SDTCisVT<0, i64>,
- SDTCisVT<1, i32>,
+ SDTCisVT<1, FlagsVT>,
SDTCisVT<2, i32>]>,
[SDNPHasChain]>;
diff --git a/llvm/lib/Target/AArch64/AArch64RegisterInfo.td b/llvm/lib/Target/AArch64/AArch64RegisterInfo.td
index 61bf87fe71441..1a7609bfee8a1 100644
--- a/llvm/lib/Target/AArch64/AArch64RegisterInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64RegisterInfo.td
@@ -305,7 +305,8 @@ def GPR64pi48 : RegisterOperand<GPR64, "printPostIncOperand<48>">;
def GPR64pi64 : RegisterOperand<GPR64, "printPostIncOperand<64>">;
// Condition code regclass.
-def CCR : RegisterClass<"AArch64", [i32], 32, (add NZCV)> {
+defvar FlagsVT = i32;
+def CCR : RegisterClass<"AArch64", [FlagsVT], 32, (add NZCV)> {
let CopyCost = -1; // Don't allow copying of status registers.
// CCR is not allocatable.
diff --git a/llvm/lib/Target/AArch64/AArch64SelectionDAGInfo.cpp b/llvm/lib/Target/AArch64/AArch64SelectionDAGInfo.cpp
index bafb8d0773232..8a5b5ba09f3aa 100644
--- a/llvm/lib/Target/AArch64/AArch64SelectionDAGInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64SelectionDAGInfo.cpp
@@ -32,10 +32,29 @@ AArch64SelectionDAGInfo::AArch64SelectionDAGInfo()
void AArch64SelectionDAGInfo::verifyTargetNode(const SelectionDAG &DAG,
const SDNode *N) const {
+ SelectionDAGGenTargetInfo::verifyTargetNode(DAG, N);
+
#ifndef NDEBUG
+ // Some additional checks not yet implemented by verifyTargetNode.
+ constexpr MVT FlagsVT = MVT::i32;
switch (N->getOpcode()) {
- default:
- return SelectionDAGGenTargetInfo::verifyTargetNode(DAG, N);
+ case AArch64ISD::SUBS:
+ assert(N->getValueType(1) == FlagsVT);
+ break;
+ case AArch64ISD::ADC:
+ case AArch64ISD::SBC:
+ assert(N->getOperand(2).getValueType() == FlagsVT);
+ break;
+ case AArch64ISD::ADCS:
+ case AArch64ISD::SBCS:
+ assert(N->getValueType(1) == FlagsVT);
+ assert(N->getOperand(2).getValueType() == FlagsVT);
+ break;
+ case AArch64ISD::CSEL:
+ case AArch64ISD::CSINC:
+ case AArch64ISD::BRCOND:
+ assert(N->getOperand(3).getValueType() == FlagsVT);
+ break;
case AArch64ISD::SADDWT:
case AArch64ISD::SADDWB:
case AArch64ISD::UADDWT:
diff --git a/llvm/test/CodeGen/AArch64/abds-neg.ll b/llvm/test/CodeGen/AArch64/abds-neg.ll
index ac7cb1f619557..432ffc30eec5e 100644
--- a/llvm/test/CodeGen/AArch64/abds-neg.ll
+++ b/llvm/test/CodeGen/AArch64/abds-neg.ll
@@ -200,8 +200,7 @@ define i128 @abd_ext_i128(i128 %a, i128 %b) nounwind {
; CHECK-NEXT: subs x8, x0, x2
; CHECK-NEXT: sbc x9, x1, x3
; CHECK-NEXT: subs x10, x2, x0
-; CHECK-NEXT: sbc x11, x3, x1
-; CHECK-NEXT: sbcs xzr, x3, x1
+; CHECK-NEXT: sbcs x11, x3, x1
; CHECK-NEXT: csel x8, x8, x10, lt
; CHECK-NEXT: csel x9, x9, x11, lt
; CHECK-NEXT: negs x0, x8
@@ -222,8 +221,7 @@ define i128 @abd_ext_i128_undef(i128 %a, i128 %b) nounwind {
; CHECK-NEXT: subs x8, x0, x2
; CHECK-NEXT: sbc x9, x1, x3
; CHECK-NEXT: subs x10, x2, x0
-; CHECK-NEXT: sbc x11, x3, x1
-; CHECK-NEXT: sbcs xzr, x3, x1
+; CHECK-NEXT: sbcs x11, x3, x1
; CHECK-NEXT: csel x8, x8, x10, lt
; CHECK-NEXT: csel x9, x9, x11, lt
; CHECK-NEXT: negs x0, x8
@@ -389,14 +387,12 @@ define i64 @abd_cmp_i64(i64 %a, i64 %b) nounwind {
define i128 @abd_cmp_i128(i128 %a, i128 %b) nounwind {
; CHECK-LABEL: abd_cmp_i128:
; CHECK: // %bb.0:
-; CHECK-NEXT: cmp x0, x2
-; CHECK-NEXT: sbc x8, x1, x3
-; CHECK-NEXT: subs x9, x2, x0
-; CHECK-NEXT: sbc x10, x3, x1
-; CHECK-NEXT: subs x11, x0, x2
-; CHECK-NEXT: sbcs xzr, x1, x3
-; CHECK-NEXT: csel x0, x11, x9, lt
-; CHECK-NEXT: csel x1, x8, x10, lt
+; CHECK-NEXT: subs x8, x2, x0
+; CHECK-NEXT: sbc x9, x3, x1
+; CHECK-NEXT: subs x10, x0, x2
+; CHECK-NEXT: sbcs x11, x1, x3
+; CHECK-NEXT: csel x0, x10, x8, lt
+; CHECK-NEXT: csel x1, x11, x9, lt
; CHECK-NEXT: ret
%cmp = icmp slt i128 %a, %b
%ab = sub i128 %a, %b
diff --git a/llvm/test/CodeGen/AArch64/abds.ll b/llvm/test/CodeGen/AArch64/abds.ll
index 62db30f17747c..ed1e6077948ee 100644
--- a/llvm/test/CodeGen/AArch64/abds.ll
+++ b/llvm/test/CodeGen/AArch64/abds.ll
@@ -183,8 +183,7 @@ define i128 @abd_ext_i128(i128 %a, i128 %b) nounwind {
; CHECK-NEXT: subs x8, x0, x2
; CHECK-NEXT: sbc x9, x1, x3
; CHECK-NEXT: subs x10, x2, x0
-; CHECK-NEXT: sbc x11, x3, x1
-; CHECK-NEXT: sbcs xzr, x3, x1
+; CHECK-NEXT: sbcs x11, x3, x1
; CHECK-NEXT: csel x0, x8, x10, lt
; CHECK-NEXT: csel x1, x9, x11, lt
; CHECK-NEXT: ret
@@ -202,8 +201,7 @@ define i128 @abd_ext_i128_undef(i128 %a, i128 %b) nounwind {
; CHECK-NEXT: subs x8, x0, x2
; CHECK-NEXT: sbc x9, x1, x3
; CHECK-NEXT: subs x10, x2, x0
-; CHECK-NEXT: sbc x11, x3, x1
-; CHECK-NEXT: sbcs xzr, x3, x1
+; CHECK-NEXT: sbcs x11, x3, x1
; CHECK-NEXT: csel x0, x8, x10, lt
; CHECK-NEXT: csel x1, x9, x11, lt
; CHECK-NEXT: ret
@@ -279,8 +277,7 @@ define i128 @abd_minmax_i128(i128 %a, i128 %b) nounwind {
; CHECK-NEXT: subs x8, x0, x2
; CHECK-NEXT: sbc x9, x1, x3
; CHECK-NEXT: subs x10, x2, x0
-; CHECK-NEXT: sbc x11, x3, x1
-; CHECK-NEXT: sbcs xzr, x3, x1
+; CHECK-NEXT: sbcs x11, x3, x1
; CHECK-NEXT: csel x0, x8, x10, lt
; CHECK-NEXT: csel x1, x9, x11, lt
; CHECK-NEXT: ret
@@ -358,8 +355,7 @@ define i128 @abd_cmp_i128(i128 %a, i128 %b) nounwind {
; CHECK-NEXT: subs x8, x0, x2
; CHECK-NEXT: sbc x9, x1, x3
; CHECK-NEXT: subs x10, x2, x0
-; CHECK-NEXT: sbc x11, x3, x1
-; CHECK-NEXT: sbcs xzr, x3, x1
+; CHECK-NEXT: sbcs x11, x3, x1
; CHECK-NEXT: csel x0, x8, x10, lt
; CHECK-NEXT: csel x1, x9, x11, lt
; CHECK-NEXT: ret
@@ -607,8 +603,7 @@ define i128 @abd_select_i128(i128 %a, i128 %b) nounwind {
; CHECK-NEXT: subs x8, x0, x2
; CHECK-NEXT: sbc x9, x1, x3
; CHECK-NEXT: subs x10, x2, x0
-; CHECK-NEXT: sbc x11, x3, x1
-; CHECK-NEXT: sbcs xzr, x3, x1
+; CHECK-NEXT: sbcs x11, x3, x1
; CHECK-NEXT: csel x0, x8, x10, lt
; CHECK-NEXT: csel x1, x9, x11, lt
; CHECK-NEXT: ret
diff --git a/llvm/test/CodeGen/AArch64/abdu-neg.ll b/llvm/test/CodeGen/AArch64/abdu-neg.ll
index 2118816ca7c58..8fb106e92866e 100644
--- a/llvm/test/CodeGen/AArch64/abdu-neg.ll
+++ b/llvm/test/CodeGen/AArch64/abdu-neg.ll
@@ -391,14 +391,12 @@ define i64 @abd_cmp_i64(i64 %a, i64 %b) nounwind {
define i128 @abd_cmp_i128(i128 %a, i128 %b) nounwind {
; CHECK-LABEL: abd_cmp_i128:
; CHECK: // %bb.0:
-; CHECK-NEXT: cmp x0, x2
-; CHECK-NEXT: sbc x8, x1, x3
-; CHECK-NEXT: subs x9, x2, x0
-; CHECK-NEXT: sbc x10, x3, x1
-; CHECK-NEXT: subs x11, x0, x2
-; CHECK-NEXT: sbcs xzr, x1, x3
-; CHECK-NEXT: csel x0, x11, x9, lo
-; CHECK-NEXT: csel x1, x8, x10, lo
+; CHECK-NEXT: subs x8, x2, x0
+; CHECK-NEXT: sbc x9, x3, x1
+; CHECK-NEXT: subs x10, x0, x2
+; CHECK-NEXT: sbcs x11, x1, x3
+; CHECK-NEXT: csel x0, x10, x8, lo
+; CHECK-NEXT: csel x1, x11, x9, lo
; CHECK-NEXT: ret
%cmp = icmp ult i128 %a, %b
%ab = sub i128 %a, %b
More information about the llvm-commits
mailing list