maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[ARM] Use ADDCARRY / SUBCARRY 

This patch:

- makes nodes ISD::ADDCARRY and ISD::SUBCARRY legal for i32
- lowering is done by first converting the boolean value into the carry flag
  using (_, C) <- (ARMISD::ADDC R, -1) and converted back to an integer value
  using (R, _) <- (ARMISD::ADDE 0, 0, C). An ARMISD::ADDE between the two
  operations does the actual addition.
- for subtraction, given that ISD::SUBCARRY second result is actually a
  borrow, we need to invert the value of the second operand and result before
  and after using ARMISD::SUBE. We need to invert the carry result of
  ARMISD::SUBE to preserve the semantics.
- given that the generic combiner may lower ISD::ADDCARRY and
  ISD::SUBCARRY into ISD::UADDO and ISD::USUBO we need to update their lowering
  as well otherwise i64 operations now would require branches. This implies
  updating the corresponding test for unsigned.
- add new combiner to remove the redundant conversions from/to carry flags
  to/from boolean values (ARMISD::ADDC (ARMISD::ADDE 0, 0, C), -1) -> C

Differential Revision: https://reviews.llvm.org/D35192

llvm-svn: 309923
This commit is contained in:
Roger Ferrer Ibanez 2017-08-03 07:45:10 +00:00
parent 314ed201f3
commit 854980341b
3 changed files with 229 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

166
llvm/lib/Target/ARM/ARMISelLowering.cpp
View File

@ -801,6 +801,9 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::SSUBO, MVT::i32, Custom);
setOperationAction(ISD::USUBO, MVT::i32, Custom);
setOperationAction(ISD::ADDCARRY, MVT::i32, Custom);
setOperationAction(ISD::SUBCARRY, MVT::i32, Custom);
// i64 operation support.
setOperationAction(ISD::MUL, MVT::i64, Expand);
setOperationAction(ISD::MULHU, MVT::i32, Expand);
@ -3952,7 +3955,7 @@ ARMTargetLowering::getARMXALUOOp(SDValue Op, SelectionDAG &DAG,
}
SDValue
ARMTargetLowering::LowerXALUO(SDValue Op, SelectionDAG &DAG) const {
ARMTargetLowering::LowerSignedALUO(SDValue Op, SelectionDAG &DAG) const {
// Let legalize expand this if it isn't a legal type yet.
if (!DAG.getTargetLoweringInfo().isTypeLegal(Op.getValueType()))
return SDValue();
@ -3974,6 +3977,66 @@ ARMTargetLowering::LowerXALUO(SDValue Op, SelectionDAG &DAG) const {
return DAG.getNode(ISD::MERGE_VALUES, dl, VTs, Value, Overflow);
}
static SDValue ConvertBooleanCarryToCarryFlag(SDValue BoolCarry,
SelectionDAG &DAG) {
SDLoc DL(BoolCarry);
EVT CarryVT = BoolCarry.getValueType();
APInt NegOne = APInt::getAllOnesValue(CarryVT.getScalarSizeInBits());
// This converts the boolean value carry into the carry flag by doing
// ARMISD::ADDC Carry, ~0
return DAG.getNode(ARMISD::ADDC, DL, DAG.getVTList(CarryVT, MVT::i32),
BoolCarry, DAG.getConstant(NegOne, DL, CarryVT));
}
static SDValue ConvertCarryFlagToBooleanCarry(SDValue Flags, EVT VT,
SelectionDAG &DAG) {
SDLoc DL(Flags);
// Now convert the carry flag into a boolean carry. We do this
// using ARMISD:ADDE 0, 0, Carry
return DAG.getNode(ARMISD::ADDE, DL, DAG.getVTList(VT, MVT::i32),
DAG.getConstant(0, DL, MVT::i32),
DAG.getConstant(0, DL, MVT::i32), Flags);
}
SDValue ARMTargetLowering::LowerUnsignedALUO(SDValue Op,
SelectionDAG &DAG) const {
// Let legalize expand this if it isn't a legal type yet.
if (!DAG.getTargetLoweringInfo().isTypeLegal(Op.getValueType()))
return SDValue();
SDValue LHS = Op.getOperand(0);
SDValue RHS = Op.getOperand(1);
SDLoc dl(Op);
EVT VT = Op.getValueType();
SDVTList VTs = DAG.getVTList(VT, MVT::i32);
SDValue Value;
SDValue Overflow;
switch (Op.getOpcode()) {
default:
llvm_unreachable("Unknown overflow instruction!");
case ISD::UADDO:
Value = DAG.getNode(ARMISD::ADDC, dl, VTs, LHS, RHS);
// Convert the carry flag into a boolean value.
Overflow = ConvertCarryFlagToBooleanCarry(Value.getValue(1), VT, DAG);
break;
case ISD::USUBO: {
Value = DAG.getNode(ARMISD::SUBC, dl, VTs, LHS, RHS);
// Convert the carry flag into a boolean value.
Overflow = ConvertCarryFlagToBooleanCarry(Value.getValue(1), VT, DAG);
// ARMISD::SUBC returns 0 when we have to borrow, so make it an overflow
// value. So compute 1 - C.
Overflow = DAG.getNode(ISD::SUB, dl, VTs,
DAG.getConstant(1, dl, MVT::i32), Overflow);
break;
}
}
return DAG.getNode(ISD::MERGE_VALUES, dl, VTs, Value, Overflow);
}
SDValue ARMTargetLowering::LowerSELECT(SDValue Op, SelectionDAG &DAG) const {
SDValue Cond = Op.getOperand(0);
SDValue SelectTrue = Op.getOperand(1);
@ -7378,6 +7441,53 @@ static SDValue LowerADDC_ADDE_SUBC_SUBE(SDValue Op, SelectionDAG &DAG) {
Op.getOperand(1), Op.getOperand(2));
}
static SDValue LowerADDSUBCARRY(SDValue Op, SelectionDAG &DAG) {
SDNode *N = Op.getNode();
EVT VT = N->getValueType(0);
SDVTList VTs = DAG.getVTList(VT, MVT::i32);
SDValue Carry = Op.getOperand(2);
EVT CarryVT = Carry.getValueType();
SDLoc DL(Op);
APInt NegOne = APInt::getAllOnesValue(CarryVT.getScalarSizeInBits());
SDValue Result;
if (Op.getOpcode() == ISD::ADDCARRY) {
// This converts the boolean value carry into the carry flag.
Carry = ConvertBooleanCarryToCarryFlag(Carry, DAG);
// Do the addition proper using the carry flag we wanted.
Result = DAG.getNode(ARMISD::ADDE, DL, VTs, Op.getOperand(0),
Op.getOperand(1), Carry.getValue(1));
// Now convert the carry flag into a boolean value.
Carry = ConvertCarryFlagToBooleanCarry(Result.getValue(1), VT, DAG);
} else {
// ARMISD::SUBE expects a carry not a borrow like ISD::SUBCARRY so we
// have to invert the carry first.
Carry =
DAG.getNode(ISD::SUB, DL, VTs, DAG.getConstant(1, DL, MVT::i32), Carry);
// This converts the boolean value carry into the carry flag.
Carry = ConvertBooleanCarryToCarryFlag(Carry, DAG);
// Do the subtraction proper using the carry flag we wanted.
Result = DAG.getNode(ARMISD::SUBE, DL, VTs, Op.getOperand(0),
Op.getOperand(1), Carry.getValue(1));
// Now convert the carry flag into a boolean value.
Carry = ConvertCarryFlagToBooleanCarry(Result.getValue(1), VT, DAG);
// But the carry returned by ARMISD::SUBE is not a borrow as expected
// by ISD::SUBCARRY, so compute 1 - C.
Carry =
DAG.getNode(ISD::SUB, DL, VTs, DAG.getConstant(1, DL, MVT::i32), Carry);
}
// Return both values.
return DAG.getNode(ISD::MERGE_VALUES, DL, N->getVTList(), Result, Carry);
}
SDValue ARMTargetLowering::LowerFSINCOS(SDValue Op, SelectionDAG &DAG) const {
assert(Subtarget->isTargetDarwin());
@ -7732,11 +7842,14 @@ SDValue ARMTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
case ISD::ADDE:
case ISD::SUBC:
case ISD::SUBE: return LowerADDC_ADDE_SUBC_SUBE(Op, DAG);
case ISD::ADDCARRY:
case ISD::SUBCARRY: return LowerADDSUBCARRY(Op, DAG);
case ISD::SADDO:
case ISD::UADDO:
case ISD::SSUBO:
return LowerSignedALUO(Op, DAG);
case ISD::UADDO:
case ISD::USUBO:
return LowerXALUO(Op, DAG);
return LowerUnsignedALUO(Op, DAG);
case ISD::ATOMIC_LOAD:
case ISD::ATOMIC_STORE: return LowerAtomicLoadStore(Op, DAG);
case ISD::FSINCOS: return LowerFSINCOS(Op, DAG);
@ -9871,8 +9984,22 @@ static SDValue PerformUMLALCombine(SDNode *N, SelectionDAG &DAG,
return SDValue();
}
static SDValue PerformAddcSubcCombine(SDNode *N, SelectionDAG &DAG,
static SDValue PerformAddcSubcCombine(SDNode *N,
TargetLowering::DAGCombinerInfo &DCI,
const ARMSubtarget *Subtarget) {
SelectionDAG &DAG(DCI.DAG);
if (N->getOpcode() == ARMISD::ADDC) {
// (ADDC (ADDE 0, 0, C), -1) -> C
SDValue LHS = N->getOperand(0);
SDValue RHS = N->getOperand(1);
if (LHS->getOpcode() == ARMISD::ADDE &&
isNullConstant(LHS->getOperand(0)) &&
isNullConstant(LHS->getOperand(1)) && isAllOnesConstant(RHS)) {
return DCI.CombineTo(N, SDValue(N, 0), LHS->getOperand(2));
}
}
if (Subtarget->isThumb1Only()) {
SDValue RHS = N->getOperand(1);
if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(RHS)) {
@ -11761,6 +11888,14 @@ static SDValue PerformExtendCombine(SDNode *N, SelectionDAG &DAG,
return SDValue();
}
static const APInt *isPowerOf2Constant(SDValue V) {
ConstantSDNode *C = dyn_cast<ConstantSDNode>(V);
if (!C)
return nullptr;
const APInt *CV = &C->getAPIntValue();
return CV->isPowerOf2() ? CV : nullptr;
}
SDValue ARMTargetLowering::PerformCMOVToBFICombine(SDNode *CMOV, SelectionDAG &DAG) const {
// If we have a CMOV, OR and AND combination such as:
// if (x & CN)
@ -11789,8 +11924,8 @@ SDValue ARMTargetLowering::PerformCMOVToBFICombine(SDNode *CMOV, SelectionDAG &D
SDValue And = CmpZ->getOperand(0);
if (And->getOpcode() != ISD::AND)
return SDValue();
ConstantSDNode *AndC = dyn_cast<ConstantSDNode>(And->getOperand(1));
if (!AndC || !AndC->getAPIntValue().isPowerOf2())
const APInt *AndC = isPowerOf2Constant(And->getOperand(1));
if (!AndC)
return SDValue();
SDValue X = And->getOperand(0);
@ -11830,7 +11965,7 @@ SDValue ARMTargetLowering::PerformCMOVToBFICombine(SDNode *CMOV, SelectionDAG &D
SDValue V = Y;
SDLoc dl(X);
EVT VT = X.getValueType();
unsigned BitInX = AndC->getAPIntValue().logBase2();
unsigned BitInX = AndC->logBase2();
if (BitInX != 0) {
// We must shift X first.
@ -11991,7 +12126,7 @@ SDValue ARMTargetLowering::PerformDAGCombine(SDNode *N,
case ISD::XOR: return PerformXORCombine(N, DCI, Subtarget);
case ISD::AND: return PerformANDCombine(N, DCI, Subtarget);
case ARMISD::ADDC:
case ARMISD::SUBC: return PerformAddcSubcCombine(N, DCI.DAG, Subtarget);
case ARMISD::SUBC: return PerformAddcSubcCombine(N, DCI, Subtarget);
case ARMISD::SUBE: return PerformAddeSubeCombine(N, DCI.DAG, Subtarget);
case ARMISD::BFI: return PerformBFICombine(N, DCI);
case ARMISD::VMOVRRD: return PerformVMOVRRDCombine(N, DCI, Subtarget);
@ -12665,10 +12800,17 @@ void ARMTargetLowering::computeKnownBitsForTargetNode(const SDValue Op,
case ARMISD::ADDE:
case ARMISD::SUBC:
case ARMISD::SUBE:
// These nodes' second result is a boolean
if (Op.getResNo() == 0)
break;
Known.Zero |= APInt::getHighBitsSet(BitWidth, BitWidth - 1);
// Special cases when we convert a carry to a boolean.
if (Op.getResNo() == 0) {
SDValue LHS = Op.getOperand(0);
SDValue RHS = Op.getOperand(1);
// (ADDE 0, 0, C) will give us a single bit.
if (Op->getOpcode() == ARMISD::ADDE && isNullConstant(LHS) &&
isNullConstant(RHS)) {
Known.Zero |= APInt::getHighBitsSet(BitWidth, BitWidth - 1);
return;
}
}
break;
case ARMISD::CMOV: {
// Bits are known zero/one if known on the LHS and RHS.

3
llvm/lib/Target/ARM/ARMISelLowering.h
View File

@ -618,7 +618,8 @@ class InstrItineraryData;
SDValue LowerGlobalTLSAddressWindows(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerGLOBAL_OFFSET_TABLE(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBR_JT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerXALUO(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSignedALUO(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerUnsignedALUO(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSELECT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerBR_CC(SDValue Op, SelectionDAG &DAG) const;

88
llvm/test/CodeGen/ARM/intrinsics-overflow.ll
View File

@ -1,4 +1,6 @@
; RUN: llc < %s -mtriple=arm-linux -mcpu=generic | FileCheck %s
; RUN: llc < %s -mtriple=arm-linux -mcpu=generic -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=ARM
; RUN: llc < %s -mtriple=thumbv6m-eabi -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=THUMBV6
; RUN: llc < %s -mtriple=thumbv7-eabi -verify-machineinstrs | FileCheck %s --check-prefix=CHECK --check-prefix=THUMBV7
define i32 @uadd_overflow(i32 %a, i32 %b) #0 {
%sadd = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
@ -7,10 +9,19 @@ define i32 @uadd_overflow(i32 %a, i32 %b) #0 {
ret i32 %2
; CHECK-LABEL: uadd_overflow:
; CHECK: add r[[R2:[0-9]+]], r[[R0:[0-9]+]], r[[R1:[0-9]+]]
; CHECK: mov r[[R1]], #1
; CHECK: cmp r[[R2]], r[[R0]]
; CHECK: movhs r[[R1]], #0
; ARM: adds r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
; ARM: mov r[[R2:[0-9]+]], #0
; ARM: adc r[[R0]], r[[R2]], #0
; THUMBV6: movs r[[R2:[0-9]+]], #0
; THUMBV6: adds r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
; THUMBV6: adcs r[[R2]], r[[R2]]
; THUMBV6: mov r[[R0]], r[[R2]]
; THUMBV7: adds r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
; THUMBV7: mov.w r[[R2:[0-9]+]], #0
; THUMBV7: adc r[[R0]], r[[R2]], #0
}
@ -21,10 +32,26 @@ define i32 @sadd_overflow(i32 %a, i32 %b) #0 {
ret i32 %2
; CHECK-LABEL: sadd_overflow:
; CHECK: add r[[R2:[0-9]+]], r[[R0:[0-9]+]], r[[R1:[0-9]+]]
; CHECK: mov r[[R1]], #1
; CHECK: cmp r[[R2]], r[[R0]]
; CHECK: movvc r[[R1]], #0
; ARM: add r[[R2:[0-9]+]], r[[R0:[0-9]+]], r[[R1:[0-9]+]]
; ARM: mov r[[R1]], #1
; ARM: cmp r[[R2]], r[[R0]]
; ARM: movvc r[[R1]], #0
; THUMBV6: mov r[[R2:[0-9]+]], r[[R0:[0-9]+]]
; THUMBV6: adds r[[R3:[0-9]+]], r[[R2]], r[[R1:[0-9]+]]
; THUMBV6: movs r[[R0]], #0
; THUMBV6: movs r[[R1]], #1
; THUMBV6: cmp r[[R3]], r[[R2]]
; THUMBV6: bvc .L[[LABEL:.*]]
; THUMBV6: mov r[[R0]], r[[R1]]
; THUMBV6: .L[[LABEL]]:
; THUMBV7: movs r[[R1]], #1
; THUMBV7: cmp r[[R2]], r[[R0]]
; THUMBV7: it vc
; THUMBV7: movvc r[[R1]], #0
; THUMBV7: mov r[[R0]], r[[R1]]
}
define i32 @usub_overflow(i32 %a, i32 %b) #0 {
@ -34,9 +61,26 @@ define i32 @usub_overflow(i32 %a, i32 %b) #0 {
ret i32 %2
; CHECK-LABEL: usub_overflow:
; CHECK: mov r[[R2]], #1
; CHECK: cmp r[[R0]], r[[R1]]
; CHECK: movhs r[[R2]], #0
; ARM: subs r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
; ARM: mov r[[R2:[0-9]+]], #0
; ARM: adc r[[R0]], r[[R2]], #0
; ARM: rsb r[[R0]], r[[R0]], #1
; THUMBV6: movs r[[R2:[0-9]+]], #0
; THUMBV6: subs r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
; THUMBV6: adcs r[[R2]], r[[R2]]
; THUMBV6: movs r[[R0]], #1
; THUMBV6: subs r[[R0]], r[[R0]], r[[R2]]
; THUMBV7: subs r[[R0:[0-9]+]], r[[R0]], r[[R1:[0-9]+]]
; THUMBV7: mov.w r[[R2:[0-9]+]], #0
; THUMBV7: adc r[[R0]], r[[R2]], #0
; THUMBV7: rsb.w r[[R0]], r[[R0]], #1
; We should know that the overflow is just 1 bit,
; no need to clear any other bit
; CHECK-NOT: and
}
define i32 @ssub_overflow(i32 %a, i32 %b) #0 {
@ -46,9 +90,23 @@ define i32 @ssub_overflow(i32 %a, i32 %b) #0 {
ret i32 %2
; CHECK-LABEL: ssub_overflow:
; CHECK: mov r[[R2]], #1
; CHECK: cmp r[[R0]], r[[R1]]
; CHECK: movvc r[[R2]], #0
; ARM: mov r[[R2]], #1
; ARM: cmp r[[R0]], r[[R1]]
; ARM: movvc r[[R2]], #0
; THUMBV6: movs r[[R0]], #0
; THUMBV6: movs r[[R3:[0-9]+]], #1
; THUMBV6: cmp r[[R2]], r[[R1:[0-9]+]]
; THUMBV6: bvc .L[[LABEL:.*]]
; THUMBV6: mov r[[R0]], r[[R3]]
; THUMBV6: .L[[LABEL]]:
; THUMBV7: movs r[[R2:[0-9]+]], #1
; THUMBV7: cmp r[[R0:[0-9]+]], r[[R1:[0-9]+]]
; THUMBV7: it vc
; THUMBV7: movvc r[[R2]], #0
; THUMBV7: mov r[[R0]], r[[R2]]
}
declare { i32, i1 } @llvm.uadd.with.overflow.i32(i32, i32) #1