[DAG] Refactor X86 combineVSelectWithAllOnesOrZeros fold into a generic DAG Combine (#145298)
This PR resolves https://github.com/llvm/llvm-project/issues/144513 The modification include five pattern : 1.vselect Cond, 0, 0 → 0 2.vselect Cond, -1, 0 → bitcast Cond 3.vselect Cond, -1, x → or Cond, x 4.vselect Cond, x, 0 → and Cond, x 5.vselect Cond, 000..., X -> andn Cond, X 1-4 have been migrated to DAGCombine. 5 still in x86 code. The reason is that you cannot use the andn instruction directly in DAGCombine, you can only use and+xor, which will introduce optimization order issues. For example, in the x86 backend, select Cond, 0, x → (~Cond) & x, the backend will first check whether the cond node of (~Cond) is a setcc node. If so, it will modify the comparison operator of the condition.So the x86 backend cannot complete the optimization of andn.In short, I think it is a better choice to keep the pattern of vselect Cond, 000..., X instead of and+xor in combineDAG. For commit, the first is code changes and x86 test(note 1), the second is tests in other backend(node 2). --------- Co-authored-by: Simon Pilgrim <llvm-dev@redking.me.uk>
This commit is contained in:
woruyu
GitHub
parent
d78036f06e
commit
bbcebec3af
@ -13069,6 +13069,99 @@ SDValue DAGCombiner::visitVP_SELECT(SDNode *N) {
|
||||
return SDValue();
|
||||
}
|
||||
|
||||
static SDValue combineVSelectWithAllOnesOrZeros(SDValue Cond, SDValue TVal,
|
||||
SDValue FVal,
|
||||
const TargetLowering &TLI,
|
||||
SelectionDAG &DAG,
|
||||
const SDLoc &DL) {
|
||||
if (!TLI.isTypeLegal(TVal.getValueType()))
|
||||
return SDValue();
|
||||
|
||||
EVT VT = TVal.getValueType();
|
||||
EVT CondVT = Cond.getValueType();
|
||||
|
||||
assert(CondVT.isVector() && "Vector select expects a vector selector!");
|
||||
|
||||
bool IsTAllZero = ISD::isBuildVectorAllZeros(TVal.getNode());
|
||||
bool IsTAllOne = ISD::isBuildVectorAllOnes(TVal.getNode());
|
||||
bool IsFAllZero = ISD::isBuildVectorAllZeros(FVal.getNode());
|
||||
bool IsFAllOne = ISD::isBuildVectorAllOnes(FVal.getNode());
|
||||
|
||||
// no vselect(cond, 0/-1, X) or vselect(cond, X, 0/-1), return
|
||||
if (!IsTAllZero && !IsTAllOne && !IsFAllZero && !IsFAllOne)
|
||||
return SDValue();
|
||||
|
||||
// select Cond, 0, 0 → 0
|
||||
if (IsTAllZero && IsFAllZero) {
|
||||
return VT.isFloatingPoint() ? DAG.getConstantFP(0.0, DL, VT)
|
||||
: DAG.getConstant(0, DL, VT);
|
||||
}
|
||||
|
||||
// check select(setgt lhs, -1), 1, -1 --> or (sra lhs, bitwidth - 1), 1
|
||||
APInt TValAPInt;
|
||||
if (Cond.getOpcode() == ISD::SETCC &&
|
||||
Cond.getOperand(2) == DAG.getCondCode(ISD::SETGT) &&
|
||||
Cond.getOperand(0).getValueType() == VT && VT.isSimple() &&
|
||||
ISD::isConstantSplatVector(TVal.getNode(), TValAPInt) &&
|
||||
TValAPInt.isOne() &&
|
||||
ISD::isConstantSplatVectorAllOnes(Cond.getOperand(1).getNode()) &&
|
||||
ISD::isConstantSplatVectorAllOnes(FVal.getNode())) {
|
||||
return SDValue();
|
||||
}
|
||||
|
||||
// To use the condition operand as a bitwise mask, it must have elements that
|
||||
// are the same size as the select elements. Ie, the condition operand must
|
||||
// have already been promoted from the IR select condition type <N x i1>.
|
||||
// Don't check if the types themselves are equal because that excludes
|
||||
// vector floating-point selects.
|
||||
if (CondVT.getScalarSizeInBits() != VT.getScalarSizeInBits())
|
||||
return SDValue();
|
||||
|
||||
// Cond value must be 'sign splat' to be converted to a logical op.
|
||||
if (DAG.ComputeNumSignBits(Cond) != CondVT.getScalarSizeInBits())
|
||||
return SDValue();
|
||||
|
||||
// Try inverting Cond and swapping T/F if it gives all-ones/all-zeros form
|
||||
if (!IsTAllOne && !IsFAllZero && Cond.hasOneUse() &&
|
||||
Cond.getOpcode() == ISD::SETCC &&
|
||||
TLI.getSetCCResultType(DAG.getDataLayout(), *DAG.getContext(), VT) ==
|
||||
CondVT) {
|
||||
if (IsTAllZero || IsFAllOne) {
|
||||
SDValue CC = Cond.getOperand(2);
|
||||
ISD::CondCode InverseCC = ISD::getSetCCInverse(
|
||||
cast<CondCodeSDNode>(CC)->get(), Cond.getOperand(0).getValueType());
|
||||
Cond = DAG.getSetCC(DL, CondVT, Cond.getOperand(0), Cond.getOperand(1),
|
||||
InverseCC);
|
||||
std::swap(TVal, FVal);
|
||||
std::swap(IsTAllOne, IsFAllOne);
|
||||
std::swap(IsTAllZero, IsFAllZero);
|
||||
}
|
||||
}
|
||||
|
||||
assert(DAG.ComputeNumSignBits(Cond) == CondVT.getScalarSizeInBits() &&
|
||||
"Select condition no longer all-sign bits");
|
||||
|
||||
// select Cond, -1, 0 → bitcast Cond
|
||||
if (IsTAllOne && IsFAllZero)
|
||||
return DAG.getBitcast(VT, Cond);
|
||||
|
||||
// select Cond, -1, x → or Cond, x
|
||||
if (IsTAllOne) {
|
||||
SDValue X = DAG.getBitcast(CondVT, FVal);
|
||||
SDValue Or = DAG.getNode(ISD::OR, DL, CondVT, Cond, X);
|
||||
return DAG.getBitcast(VT, Or);
|
||||
}
|
||||
|
||||
// select Cond, x, 0 → and Cond, x
|
||||
if (IsFAllZero) {
|
||||
SDValue X = DAG.getBitcast(CondVT, TVal);
|
||||
SDValue And = DAG.getNode(ISD::AND, DL, CondVT, Cond, X);
|
||||
return DAG.getBitcast(VT, And);
|
||||
}
|
||||
|
||||
return SDValue();
|
||||
}
|
||||
|
||||
SDValue DAGCombiner::visitVSELECT(SDNode *N) {
|
||||
SDValue N0 = N->getOperand(0);
|
||||
SDValue N1 = N->getOperand(1);
|
||||
@ -13337,6 +13430,9 @@ SDValue DAGCombiner::visitVSELECT(SDNode *N) {
|
||||
if (SimplifyDemandedVectorElts(SDValue(N, 0)))
|
||||
return SDValue(N, 0);
|
||||
|
||||
if (SDValue V = combineVSelectWithAllOnesOrZeros(N0, N1, N2, TLI, DAG, DL))
|
||||
return V;
|
||||
|
||||
return SDValue();
|
||||
}
|
||||
|
||||
|
||||
@ -47254,11 +47254,12 @@ static SDValue combineToExtendBoolVectorInReg(
|
||||
DAG.getConstant(EltSizeInBits - 1, DL, VT));
|
||||
}
|
||||
|
||||
/// If a vector select has an operand that is -1 or 0, try to simplify the
|
||||
/// If a vector select has an left operand that is 0, try to simplify the
|
||||
/// select to a bitwise logic operation.
|
||||
/// TODO: Move to DAGCombiner, possibly using TargetLowering::hasAndNot()?
|
||||
static SDValue
|
||||
combineVSelectWithAllOnesOrZeros(SDNode *N, SelectionDAG &DAG, const SDLoc &DL,
|
||||
/// TODO: Move to DAGCombiner.combineVSelectWithAllOnesOrZeros, possibly using
|
||||
/// TargetLowering::hasAndNot()?
|
||||
static SDValue combineVSelectWithLastZeros(SDNode *N, SelectionDAG &DAG,
|
||||
const SDLoc &DL,
|
||||
TargetLowering::DAGCombinerInfo &DCI,
|
||||
const X86Subtarget &Subtarget) {
|
||||
SDValue Cond = N->getOperand(0);
|
||||
@ -47273,20 +47274,6 @@ combineVSelectWithAllOnesOrZeros(SDNode *N, SelectionDAG &DAG, const SDLoc &DL,
|
||||
|
||||
assert(CondVT.isVector() && "Vector select expects a vector selector!");
|
||||
|
||||
// TODO: Use isNullOrNullSplat() to distinguish constants with undefs?
|
||||
// TODO: Can we assert that both operands are not zeros (because that should
|
||||
// get simplified at node creation time)?
|
||||
bool TValIsAllZeros = ISD::isBuildVectorAllZeros(LHS.getNode());
|
||||
bool FValIsAllZeros = ISD::isBuildVectorAllZeros(RHS.getNode());
|
||||
|
||||
// If both inputs are 0/undef, create a complete zero vector.
|
||||
// FIXME: As noted above this should be handled by DAGCombiner/getNode.
|
||||
if (TValIsAllZeros && FValIsAllZeros) {
|
||||
if (VT.isFloatingPoint())
|
||||
return DAG.getConstantFP(0.0, DL, VT);
|
||||
return DAG.getConstant(0, DL, VT);
|
||||
}
|
||||
|
||||
// To use the condition operand as a bitwise mask, it must have elements that
|
||||
// are the same size as the select elements. Ie, the condition operand must
|
||||
// have already been promoted from the IR select condition type <N x i1>.
|
||||
@ -47295,56 +47282,15 @@ combineVSelectWithAllOnesOrZeros(SDNode *N, SelectionDAG &DAG, const SDLoc &DL,
|
||||
if (CondVT.getScalarSizeInBits() != VT.getScalarSizeInBits())
|
||||
return SDValue();
|
||||
|
||||
// Try to invert the condition if true value is not all 1s and false value is
|
||||
// not all 0s. Only do this if the condition has one use.
|
||||
bool TValIsAllOnes = ISD::isBuildVectorAllOnes(LHS.getNode());
|
||||
if (!TValIsAllOnes && !FValIsAllZeros && Cond.hasOneUse() &&
|
||||
// Check if the selector will be produced by CMPP*/PCMP*.
|
||||
Cond.getOpcode() == ISD::SETCC &&
|
||||
// Check if SETCC has already been promoted.
|
||||
TLI.getSetCCResultType(DAG.getDataLayout(), *DAG.getContext(), VT) ==
|
||||
CondVT) {
|
||||
bool FValIsAllOnes = ISD::isBuildVectorAllOnes(RHS.getNode());
|
||||
|
||||
if (TValIsAllZeros || FValIsAllOnes) {
|
||||
SDValue CC = Cond.getOperand(2);
|
||||
ISD::CondCode NewCC = ISD::getSetCCInverse(
|
||||
cast<CondCodeSDNode>(CC)->get(), Cond.getOperand(0).getValueType());
|
||||
Cond = DAG.getSetCC(DL, CondVT, Cond.getOperand(0), Cond.getOperand(1),
|
||||
NewCC);
|
||||
std::swap(LHS, RHS);
|
||||
TValIsAllOnes = FValIsAllOnes;
|
||||
FValIsAllZeros = TValIsAllZeros;
|
||||
}
|
||||
}
|
||||
|
||||
// Cond value must be 'sign splat' to be converted to a logical op.
|
||||
if (DAG.ComputeNumSignBits(Cond) != CondVT.getScalarSizeInBits())
|
||||
return SDValue();
|
||||
|
||||
// vselect Cond, 111..., 000... -> Cond
|
||||
if (TValIsAllOnes && FValIsAllZeros)
|
||||
return DAG.getBitcast(VT, Cond);
|
||||
|
||||
if (!TLI.isTypeLegal(CondVT))
|
||||
return SDValue();
|
||||
|
||||
// vselect Cond, 111..., X -> or Cond, X
|
||||
if (TValIsAllOnes) {
|
||||
SDValue CastRHS = DAG.getBitcast(CondVT, RHS);
|
||||
SDValue Or = DAG.getNode(ISD::OR, DL, CondVT, Cond, CastRHS);
|
||||
return DAG.getBitcast(VT, Or);
|
||||
}
|
||||
|
||||
// vselect Cond, X, 000... -> and Cond, X
|
||||
if (FValIsAllZeros) {
|
||||
SDValue CastLHS = DAG.getBitcast(CondVT, LHS);
|
||||
SDValue And = DAG.getNode(ISD::AND, DL, CondVT, Cond, CastLHS);
|
||||
return DAG.getBitcast(VT, And);
|
||||
}
|
||||
|
||||
// vselect Cond, 000..., X -> andn Cond, X
|
||||
if (TValIsAllZeros) {
|
||||
if (ISD::isBuildVectorAllZeros(LHS.getNode())) {
|
||||
SDValue CastRHS = DAG.getBitcast(CondVT, RHS);
|
||||
SDValue AndN;
|
||||
// The canonical form differs for i1 vectors - x86andnp is not used
|
||||
@ -48105,7 +48051,7 @@ static SDValue combineSelect(SDNode *N, SelectionDAG &DAG,
|
||||
if (!TLI.isTypeLegal(VT) || isSoftF16(VT, Subtarget))
|
||||
return SDValue();
|
||||
|
||||
if (SDValue V = combineVSelectWithAllOnesOrZeros(N, DAG, DL, DCI, Subtarget))
|
||||
if (SDValue V = combineVSelectWithLastZeros(N, DAG, DL, DCI, Subtarget))
|
||||
return V;
|
||||
|
||||
if (SDValue V = combineVSelectToBLENDV(N, DAG, DL, DCI, Subtarget))
|
||||
|
||||
@ -413,7 +413,7 @@ define <4 x float> @shuffle_zip1(<4 x float> %arg) {
|
||||
; CHECK-NEXT: fmov.4s v1, #1.00000000
|
||||
; CHECK-NEXT: zip1.4h v0, v0, v0
|
||||
; CHECK-NEXT: sshll.4s v0, v0, #0
|
||||
; CHECK-NEXT: and.16b v0, v1, v0
|
||||
; CHECK-NEXT: and.16b v0, v0, v1
|
||||
; CHECK-NEXT: ret
|
||||
bb:
|
||||
%inst = fcmp olt <4 x float> zeroinitializer, %arg
|
||||
|
||||
@ -197,11 +197,9 @@ define <4 x i32> @not_sign_4xi32(<4 x i32> %a) {
|
||||
; CHECK-LABEL: not_sign_4xi32:
|
||||
; CHECK: // %bb.0:
|
||||
; CHECK-NEXT: adrp x8, .LCPI16_0
|
||||
; CHECK-NEXT: movi v2.4s, #1
|
||||
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI16_0]
|
||||
; CHECK-NEXT: cmgt v0.4s, v0.4s, v1.4s
|
||||
; CHECK-NEXT: and v1.16b, v0.16b, v2.16b
|
||||
; CHECK-NEXT: orn v0.16b, v1.16b, v0.16b
|
||||
; CHECK-NEXT: cmge v0.4s, v1.4s, v0.4s
|
||||
; CHECK-NEXT: orr v0.4s, #1
|
||||
; CHECK-NEXT: ret
|
||||
%c = icmp sgt <4 x i32> %a, <i32 1, i32 -1, i32 -1, i32 -1>
|
||||
%res = select <4 x i1> %c, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
|
||||
|
||||
@ -179,7 +179,7 @@ define <16 x i8> @signOf_neon(ptr nocapture noundef readonly %a, ptr nocapture n
|
||||
; CHECK-NEXT: uzp1 v3.16b, v5.16b, v6.16b
|
||||
; CHECK-NEXT: uzp1 v1.16b, v1.16b, v2.16b
|
||||
; CHECK-NEXT: and v0.16b, v3.16b, v0.16b
|
||||
; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b
|
||||
; CHECK-NEXT: orr v0.16b, v1.16b, v0.16b
|
||||
; CHECK-NEXT: ret
|
||||
entry:
|
||||
%0 = load <8 x i16>, ptr %a, align 2
|
||||
|
||||
@ -530,7 +530,7 @@ define <16 x i8> @unsigned_sat_variable_v16i8_using_cmp_notval(<16 x i8> %x, <16
|
||||
; CHECK-NEXT: mvn v2.16b, v1.16b
|
||||
; CHECK-NEXT: add v1.16b, v0.16b, v1.16b
|
||||
; CHECK-NEXT: cmhi v0.16b, v0.16b, v2.16b
|
||||
; CHECK-NEXT: orr v0.16b, v1.16b, v0.16b
|
||||
; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b
|
||||
; CHECK-NEXT: ret
|
||||
%noty = xor <16 x i8> %y, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
|
||||
%a = add <16 x i8> %x, %y
|
||||
@ -570,7 +570,7 @@ define <8 x i16> @unsigned_sat_variable_v8i16_using_cmp_notval(<8 x i16> %x, <8
|
||||
; CHECK-NEXT: mvn v2.16b, v1.16b
|
||||
; CHECK-NEXT: add v1.8h, v0.8h, v1.8h
|
||||
; CHECK-NEXT: cmhi v0.8h, v0.8h, v2.8h
|
||||
; CHECK-NEXT: orr v0.16b, v1.16b, v0.16b
|
||||
; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b
|
||||
; CHECK-NEXT: ret
|
||||
%noty = xor <8 x i16> %y, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
|
||||
%a = add <8 x i16> %x, %y
|
||||
@ -610,7 +610,7 @@ define <4 x i32> @unsigned_sat_variable_v4i32_using_cmp_notval(<4 x i32> %x, <4
|
||||
; CHECK-NEXT: mvn v2.16b, v1.16b
|
||||
; CHECK-NEXT: add v1.4s, v0.4s, v1.4s
|
||||
; CHECK-NEXT: cmhi v0.4s, v0.4s, v2.4s
|
||||
; CHECK-NEXT: orr v0.16b, v1.16b, v0.16b
|
||||
; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b
|
||||
; CHECK-NEXT: ret
|
||||
%noty = xor <4 x i32> %y, <i32 -1, i32 -1, i32 -1, i32 -1>
|
||||
%a = add <4 x i32> %x, %y
|
||||
@ -651,7 +651,7 @@ define <2 x i64> @unsigned_sat_variable_v2i64_using_cmp_notval(<2 x i64> %x, <2
|
||||
; CHECK-NEXT: mvn v2.16b, v1.16b
|
||||
; CHECK-NEXT: add v1.2d, v0.2d, v1.2d
|
||||
; CHECK-NEXT: cmhi v0.2d, v0.2d, v2.2d
|
||||
; CHECK-NEXT: orr v0.16b, v1.16b, v0.16b
|
||||
; CHECK-NEXT: orr v0.16b, v0.16b, v1.16b
|
||||
; CHECK-NEXT: ret
|
||||
%noty = xor <2 x i64> %y, <i64 -1, i64 -1>
|
||||
%a = add <2 x i64> %x, %y
|
||||
|
||||
@ -88,7 +88,7 @@ define <2 x double> @select_olt_load_cmp(<2 x double> %a, ptr %src) {
|
||||
; CHECK-SD-NEXT: ldr d1, [x0]
|
||||
; CHECK-SD-NEXT: fcmgt v1.2s, v1.2s, #0.0
|
||||
; CHECK-SD-NEXT: sshll v1.2d, v1.2s, #0
|
||||
; CHECK-SD-NEXT: and v0.16b, v0.16b, v1.16b
|
||||
; CHECK-SD-NEXT: and v0.16b, v1.16b, v0.16b
|
||||
; CHECK-SD-NEXT: ret
|
||||
;
|
||||
; CHECK-GI-LABEL: select_olt_load_cmp:
|
||||
|
||||
@ -249,9 +249,6 @@ define <16 x i8> @sel_shift_bool_v16i8(<16 x i1> %t) {
|
||||
; CHECK-SD-LABEL: sel_shift_bool_v16i8:
|
||||
; CHECK-SD: // %bb.0:
|
||||
; CHECK-SD-NEXT: shl v0.16b, v0.16b, #7
|
||||
; CHECK-SD-NEXT: movi v1.16b, #128
|
||||
; CHECK-SD-NEXT: cmlt v0.16b, v0.16b, #0
|
||||
; CHECK-SD-NEXT: and v0.16b, v0.16b, v1.16b
|
||||
; CHECK-SD-NEXT: ret
|
||||
;
|
||||
; CHECK-GI-LABEL: sel_shift_bool_v16i8:
|
||||
|
||||
@ -31,12 +31,12 @@ define void @loop1(ptr noalias nocapture noundef writeonly %dst, ptr nocapture n
|
||||
; CHECK-NEXT: add x13, x13, #32
|
||||
; CHECK-NEXT: fcmgt v3.4s, v1.4s, v0.4s
|
||||
; CHECK-NEXT: fcmgt v4.4s, v2.4s, v0.4s
|
||||
; CHECK-NEXT: fcmlt v5.4s, v1.4s, #0.0
|
||||
; CHECK-NEXT: fcmlt v6.4s, v2.4s, #0.0
|
||||
; CHECK-NEXT: bit v1.16b, v0.16b, v3.16b
|
||||
; CHECK-NEXT: bit v2.16b, v0.16b, v4.16b
|
||||
; CHECK-NEXT: bic v1.16b, v1.16b, v5.16b
|
||||
; CHECK-NEXT: bic v2.16b, v2.16b, v6.16b
|
||||
; CHECK-NEXT: bsl v3.16b, v0.16b, v1.16b
|
||||
; CHECK-NEXT: bsl v4.16b, v0.16b, v2.16b
|
||||
; CHECK-NEXT: fcmlt v1.4s, v1.4s, #0.0
|
||||
; CHECK-NEXT: fcmlt v2.4s, v2.4s, #0.0
|
||||
; CHECK-NEXT: bic v1.16b, v3.16b, v1.16b
|
||||
; CHECK-NEXT: bic v2.16b, v4.16b, v2.16b
|
||||
; CHECK-NEXT: fcvtzs v1.4s, v1.4s
|
||||
; CHECK-NEXT: fcvtzs v2.4s, v2.4s
|
||||
; CHECK-NEXT: xtn v1.4h, v1.4s
|
||||
|
||||
@ -146,10 +146,8 @@ define <4 x i32> @cmp_sel_0_or_minus1_vec(<4 x i32> %x, <4 x i32> %y) {
|
||||
define <4 x i32> @sel_1_or_0_vec(<4 x i1> %cond) {
|
||||
; CHECK-LABEL: sel_1_or_0_vec:
|
||||
; CHECK: // %bb.0:
|
||||
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
|
||||
; CHECK-NEXT: movi v1.4s, #1
|
||||
; CHECK-NEXT: shl v0.4s, v0.4s, #31
|
||||
; CHECK-NEXT: cmlt v0.4s, v0.4s, #0
|
||||
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
|
||||
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
|
||||
; CHECK-NEXT: ret
|
||||
%add = select <4 x i1> %cond, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
|
||||
|
||||
@ -12,10 +12,10 @@ define <16 x i32> @no_existing_zext(<16 x i8> %a, <16 x i32> %op) {
|
||||
; CHECK-NEXT: sshll.4s v6, v5, #0
|
||||
; CHECK-NEXT: sshll.4s v7, v0, #0
|
||||
; CHECK-NEXT: sshll2.4s v5, v5, #0
|
||||
; CHECK-NEXT: and.16b v4, v4, v16
|
||||
; CHECK-NEXT: and.16b v0, v1, v6
|
||||
; CHECK-NEXT: and.16b v1, v2, v5
|
||||
; CHECK-NEXT: and.16b v2, v3, v7
|
||||
; CHECK-NEXT: and.16b v4, v16, v4
|
||||
; CHECK-NEXT: and.16b v0, v6, v1
|
||||
; CHECK-NEXT: and.16b v1, v5, v2
|
||||
; CHECK-NEXT: and.16b v2, v7, v3
|
||||
; CHECK-NEXT: mov.16b v3, v4
|
||||
; CHECK-NEXT: ret
|
||||
entry:
|
||||
@ -40,10 +40,10 @@ define <16 x i32> @second_compare_operand_not_splat(<16 x i8> %a, <16 x i8> %b)
|
||||
; CHECK-NEXT: sshll.4s v7, v1, #0
|
||||
; CHECK-NEXT: sshll2.4s v16, v3, #0
|
||||
; CHECK-NEXT: sshll2.4s v1, v1, #0
|
||||
; CHECK-NEXT: and.16b v0, v4, v0
|
||||
; CHECK-NEXT: and.16b v3, v6, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v16
|
||||
; CHECK-NEXT: and.16b v2, v5, v7
|
||||
; CHECK-NEXT: and.16b v0, v0, v4
|
||||
; CHECK-NEXT: and.16b v3, v1, v6
|
||||
; CHECK-NEXT: and.16b v1, v16, v2
|
||||
; CHECK-NEXT: and.16b v2, v7, v5
|
||||
; CHECK-NEXT: ret
|
||||
entry:
|
||||
%ext = zext <16 x i8> %a to <16 x i32>
|
||||
@ -69,10 +69,10 @@ define <16 x i32> @same_zext_used_in_cmp_signed_pred_and_select(<16 x i8> %a) {
|
||||
; CHECK-NEXT: sshll.4s v7, v1, #0
|
||||
; CHECK-NEXT: sshll2.4s v16, v3, #0
|
||||
; CHECK-NEXT: sshll2.4s v1, v1, #0
|
||||
; CHECK-NEXT: and.16b v0, v4, v0
|
||||
; CHECK-NEXT: and.16b v3, v6, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v16
|
||||
; CHECK-NEXT: and.16b v2, v5, v7
|
||||
; CHECK-NEXT: and.16b v0, v0, v4
|
||||
; CHECK-NEXT: and.16b v3, v1, v6
|
||||
; CHECK-NEXT: and.16b v1, v16, v2
|
||||
; CHECK-NEXT: and.16b v2, v7, v5
|
||||
; CHECK-NEXT: ret
|
||||
entry:
|
||||
%ext = zext <16 x i8> %a to <16 x i32>
|
||||
@ -97,10 +97,10 @@ define <8 x i64> @same_zext_used_in_cmp_unsigned_pred_and_select_v8i64(<8 x i8>
|
||||
; CHECK-NEXT: cmhi.2d v7, v1, v2
|
||||
; CHECK-NEXT: cmhi.2d v6, v5, v2
|
||||
; CHECK-NEXT: cmhi.2d v2, v4, v2
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: and.16b v1, v1, v7
|
||||
; CHECK-NEXT: and.16b v3, v4, v2
|
||||
; CHECK-NEXT: and.16b v2, v5, v6
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v1, v7, v1
|
||||
; CHECK-NEXT: and.16b v3, v2, v4
|
||||
; CHECK-NEXT: and.16b v2, v6, v5
|
||||
; CHECK-NEXT: ret
|
||||
%ext = zext <8 x i8> %a to <8 x i64>
|
||||
%cmp = icmp ugt <8 x i8> %a, <i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10>
|
||||
@ -123,10 +123,10 @@ define <16 x i32> @same_zext_used_in_cmp_unsigned_pred_and_select_v16i32(<16 x i
|
||||
; CHECK-NEXT: cmhi.4s v7, v2, v1
|
||||
; CHECK-NEXT: cmhi.4s v6, v5, v1
|
||||
; CHECK-NEXT: cmhi.4s v1, v4, v1
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: and.16b v3, v4, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v7
|
||||
; CHECK-NEXT: and.16b v2, v5, v6
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v3, v1, v4
|
||||
; CHECK-NEXT: and.16b v1, v7, v2
|
||||
; CHECK-NEXT: and.16b v2, v6, v5
|
||||
; CHECK-NEXT: ret
|
||||
%ext = zext <16 x i8> %a to <16 x i32>
|
||||
%cmp = icmp ugt <16 x i8> %a, <i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10>
|
||||
@ -143,8 +143,8 @@ define <8 x i32> @same_zext_used_in_cmp_unsigned_pred_and_select_v8i32(<8 x i8>
|
||||
; CHECK-NEXT: ushll.4s v0, v0, #0
|
||||
; CHECK-NEXT: cmhi.4s v3, v0, v1
|
||||
; CHECK-NEXT: cmhi.4s v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v1, v1, v2
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: ret
|
||||
%ext = zext <8 x i8> %a to <8 x i32>
|
||||
%cmp = icmp ugt <8 x i8> %a, <i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10, i8 10>
|
||||
@ -160,8 +160,8 @@ define <8 x i32> @same_zext_used_in_cmp_unsigned_pred_and_select_v8i32_2(<8 x i1
|
||||
; CHECK-NEXT: ushll.4s v0, v0, #0
|
||||
; CHECK-NEXT: cmhi.4s v3, v0, v1
|
||||
; CHECK-NEXT: cmhi.4s v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v1, v1, v2
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: ret
|
||||
%ext = zext <8 x i16> %a to <8 x i32>
|
||||
%cmp = icmp ugt <8 x i16> %a, <i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10>
|
||||
@ -179,8 +179,8 @@ define <8 x i32> @same_zext_used_in_cmp_unsigned_pred_and_select_v8i32_from_v8i1
|
||||
; CHECK-NEXT: ushll.4s v0, v0, #0
|
||||
; CHECK-NEXT: cmhi.4s v3, v0, v1
|
||||
; CHECK-NEXT: cmhi.4s v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v1, v1, v2
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: ret
|
||||
%ext = zext <8 x i15> %a to <8 x i32>
|
||||
%cmp = icmp ugt <8 x i15> %a, <i15 10, i15 10, i15 10, i15 10, i15 10, i15 10, i15 10, i15 10>
|
||||
@ -197,8 +197,8 @@ define <7 x i32> @same_zext_used_in_cmp_unsigned_pred_and_select_v7i32(<7 x i16>
|
||||
; CHECK-NEXT: ushll2.4s v0, v0, #0
|
||||
; CHECK-NEXT: sshll.4s v3, v1, #0
|
||||
; CHECK-NEXT: sshll2.4s v1, v1, #0
|
||||
; CHECK-NEXT: and.16b v2, v2, v3
|
||||
; CHECK-NEXT: and.16b v0, v0, v1
|
||||
; CHECK-NEXT: and.16b v2, v3, v2
|
||||
; CHECK-NEXT: and.16b v0, v1, v0
|
||||
; CHECK-NEXT: mov.s w1, v2[1]
|
||||
; CHECK-NEXT: mov.s w2, v2[2]
|
||||
; CHECK-NEXT: mov.s w3, v2[3]
|
||||
@ -244,7 +244,7 @@ define <4 x i32> @same_zext_used_in_cmp_unsigned_pred_and_select_v4i32(<4 x i16>
|
||||
; CHECK-NEXT: movi.4s v1, #10
|
||||
; CHECK-NEXT: ushll.4s v0, v0, #0
|
||||
; CHECK-NEXT: cmhi.4s v1, v0, v1
|
||||
; CHECK-NEXT: and.16b v0, v0, v1
|
||||
; CHECK-NEXT: and.16b v0, v1, v0
|
||||
; CHECK-NEXT: ret
|
||||
%ext = zext <4 x i16> %a to <4 x i32>
|
||||
%cmp = icmp ugt <4 x i16> %a, <i16 10, i16 10, i16 10, i16 10>
|
||||
@ -259,7 +259,7 @@ define <2 x i32> @same_zext_used_in_cmp_unsigned_pred_and_select_v2i32(<2 x i16>
|
||||
; CHECK-NEXT: movi.2s v2, #10
|
||||
; CHECK-NEXT: and.8b v0, v0, v1
|
||||
; CHECK-NEXT: cmhi.2s v1, v0, v2
|
||||
; CHECK-NEXT: and.8b v0, v0, v1
|
||||
; CHECK-NEXT: and.8b v0, v1, v0
|
||||
; CHECK-NEXT: ret
|
||||
%ext = zext <2 x i16> %a to <2 x i32>
|
||||
%cmp = icmp ugt <2 x i16> %a, <i16 10, i16 10>
|
||||
@ -275,8 +275,8 @@ define <8 x i32> @same_zext_used_in_cmp_eq_and_select_v8i32(<8 x i16> %a) {
|
||||
; CHECK-NEXT: ushll.4s v0, v0, #0
|
||||
; CHECK-NEXT: cmeq.4s v3, v0, v1
|
||||
; CHECK-NEXT: cmeq.4s v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v1, v1, v2
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: ret
|
||||
%ext = zext <8 x i16> %a to <8 x i32>
|
||||
%cmp = icmp eq <8 x i16> %a, <i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10>
|
||||
@ -293,8 +293,8 @@ define <8 x i32> @same_zext_used_in_cmp_eq_and_select_v8i32_from_v8i13(<8 x i13>
|
||||
; CHECK-NEXT: ushll.4s v0, v0, #0
|
||||
; CHECK-NEXT: cmeq.4s v3, v0, v1
|
||||
; CHECK-NEXT: cmeq.4s v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v1, v1, v2
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: ret
|
||||
%ext = zext <8 x i13> %a to <8 x i32>
|
||||
%cmp = icmp eq <8 x i13> %a, <i13 10, i13 10, i13 10, i13 10, i13 10, i13 10, i13 10, i13 10>
|
||||
@ -358,16 +358,16 @@ define <16 x i32> @same_zext_used_in_cmp_unsigned_pred_and_select_other_use(<16
|
||||
; CHECK-NEXT: and.16b v6, v6, v26
|
||||
; CHECK-NEXT: sshll2.2d v26, v16, #0
|
||||
; CHECK-NEXT: and.16b v27, v4, v27
|
||||
; CHECK-NEXT: and.16b v4, v0, v18
|
||||
; CHECK-NEXT: and.16b v0, v24, v16
|
||||
; CHECK-NEXT: and.16b v4, v18, v0
|
||||
; CHECK-NEXT: and.16b v0, v16, v24
|
||||
; CHECK-NEXT: stp q7, q21, [x0, #96]
|
||||
; CHECK-NEXT: sshll.2d v21, v16, #0
|
||||
; CHECK-NEXT: and.16b v5, v5, v22
|
||||
; CHECK-NEXT: and.16b v7, v3, v23
|
||||
; CHECK-NEXT: and.16b v3, v19, v20
|
||||
; CHECK-NEXT: and.16b v3, v20, v19
|
||||
; CHECK-NEXT: stp q5, q6, [x0, #64]
|
||||
; CHECK-NEXT: and.16b v6, v2, v26
|
||||
; CHECK-NEXT: and.16b v2, v25, v17
|
||||
; CHECK-NEXT: and.16b v2, v17, v25
|
||||
; CHECK-NEXT: and.16b v5, v1, v21
|
||||
; CHECK-NEXT: mov.16b v1, v3
|
||||
; CHECK-NEXT: mov.16b v3, v4
|
||||
@ -397,10 +397,10 @@ define <16 x i32> @same_sext_used_in_cmp_signed_pred_and_select_v16i32(<16 x i8>
|
||||
; CHECK-NEXT: cmgt.4s v7, v2, v1
|
||||
; CHECK-NEXT: cmgt.4s v6, v5, v1
|
||||
; CHECK-NEXT: cmgt.4s v1, v4, v1
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: and.16b v3, v4, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v7
|
||||
; CHECK-NEXT: and.16b v2, v5, v6
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v3, v1, v4
|
||||
; CHECK-NEXT: and.16b v1, v7, v2
|
||||
; CHECK-NEXT: and.16b v2, v6, v5
|
||||
; CHECK-NEXT: ret
|
||||
entry:
|
||||
%ext = sext <16 x i8> %a to <16 x i32>
|
||||
@ -417,8 +417,8 @@ define <8 x i32> @same_sext_used_in_cmp_eq_and_select_v8i32(<8 x i16> %a) {
|
||||
; CHECK-NEXT: sshll.4s v0, v0, #0
|
||||
; CHECK-NEXT: cmeq.4s v3, v0, v1
|
||||
; CHECK-NEXT: cmeq.4s v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v1, v1, v2
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: ret
|
||||
%ext = sext <8 x i16> %a to <8 x i32>
|
||||
%cmp = icmp eq <8 x i16> %a, <i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10, i16 10>
|
||||
@ -438,8 +438,8 @@ define <8 x i32> @same_sext_used_in_cmp_eq_and_select_v8i32_from_v8i13(<8 x i13>
|
||||
; CHECK-NEXT: sshr.4s v2, v2, #19
|
||||
; CHECK-NEXT: cmeq.4s v3, v2, v1
|
||||
; CHECK-NEXT: cmeq.4s v1, v0, v1
|
||||
; CHECK-NEXT: and.16b v1, v0, v1
|
||||
; CHECK-NEXT: and.16b v0, v2, v3
|
||||
; CHECK-NEXT: and.16b v1, v1, v0
|
||||
; CHECK-NEXT: and.16b v0, v3, v2
|
||||
; CHECK-NEXT: ret
|
||||
%ext = sext <8 x i13> %a to <8 x i32>
|
||||
%cmp = icmp eq <8 x i13> %a, <i13 10, i13 10, i13 10, i13 10, i13 10, i13 10, i13 10, i13 10>
|
||||
@ -480,8 +480,8 @@ define <8 x i32> @same_sext_used_in_cmp_signed_pred_and_select_v8i32(<8 x i16> %
|
||||
; CHECK-NEXT: sshll.4s v0, v0, #0
|
||||
; CHECK-NEXT: cmgt.4s v3, v0, v1
|
||||
; CHECK-NEXT: cmgt.4s v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v1
|
||||
; CHECK-NEXT: and.16b v0, v0, v3
|
||||
; CHECK-NEXT: and.16b v1, v1, v2
|
||||
; CHECK-NEXT: and.16b v0, v3, v0
|
||||
; CHECK-NEXT: ret
|
||||
entry:
|
||||
%ext = sext <8 x i16> %a to <8 x i32>
|
||||
@ -502,8 +502,8 @@ define <8 x i32> @same_sext_used_in_cmp_unsigned_pred_and_select_v8i32_from_v8i1
|
||||
; CHECK-NEXT: sshr.4s v2, v2, #17
|
||||
; CHECK-NEXT: cmge.4s v3, v2, v1
|
||||
; CHECK-NEXT: cmge.4s v1, v0, v1
|
||||
; CHECK-NEXT: and.16b v1, v0, v1
|
||||
; CHECK-NEXT: and.16b v0, v2, v3
|
||||
; CHECK-NEXT: and.16b v1, v1, v0
|
||||
; CHECK-NEXT: and.16b v0, v3, v2
|
||||
; CHECK-NEXT: ret
|
||||
%ext = sext <8 x i15> %a to <8 x i32>
|
||||
%cmp = icmp sge <8 x i15> %a, <i15 10, i15 10, i15 10, i15 10, i15 10, i15 10, i15 10, i15 10>
|
||||
@ -524,11 +524,11 @@ define <16 x i32> @same_sext_used_in_cmp_unsigned_pred_and_select(<16 x i8> %a)
|
||||
; CHECK-NEXT: ext.16b v5, v0, v0, #8
|
||||
; CHECK-NEXT: ext.16b v6, v3, v3, #8
|
||||
; CHECK-NEXT: ext.16b v7, v1, v1, #8
|
||||
; CHECK-NEXT: and.8b v2, v2, v3
|
||||
; CHECK-NEXT: and.8b v1, v0, v1
|
||||
; CHECK-NEXT: and.8b v2, v3, v2
|
||||
; CHECK-NEXT: and.8b v1, v1, v0
|
||||
; CHECK-NEXT: sshll.4s v0, v2, #0
|
||||
; CHECK-NEXT: and.8b v3, v5, v7
|
||||
; CHECK-NEXT: and.8b v4, v4, v6
|
||||
; CHECK-NEXT: and.8b v3, v7, v5
|
||||
; CHECK-NEXT: and.8b v4, v6, v4
|
||||
; CHECK-NEXT: sshll.4s v2, v1, #0
|
||||
; CHECK-NEXT: sshll.4s v3, v3, #0
|
||||
; CHECK-NEXT: sshll.4s v1, v4, #0
|
||||
@ -556,10 +556,10 @@ define <16 x i32> @same_zext_used_in_cmp_signed_pred_and_select_can_convert_to_u
|
||||
; CHECK-NEXT: sshll.4s v7, v1, #0
|
||||
; CHECK-NEXT: sshll2.4s v16, v3, #0
|
||||
; CHECK-NEXT: sshll2.4s v1, v1, #0
|
||||
; CHECK-NEXT: and.16b v0, v4, v0
|
||||
; CHECK-NEXT: and.16b v3, v6, v1
|
||||
; CHECK-NEXT: and.16b v1, v2, v16
|
||||
; CHECK-NEXT: and.16b v2, v5, v7
|
||||
; CHECK-NEXT: and.16b v0, v0, v4
|
||||
; CHECK-NEXT: and.16b v3, v1, v6
|
||||
; CHECK-NEXT: and.16b v1, v16, v2
|
||||
; CHECK-NEXT: and.16b v2, v7, v5
|
||||
; CHECK-NEXT: ret
|
||||
entry:
|
||||
%ext = zext <16 x i8> %a to <16 x i32>
|
||||
@ -604,10 +604,10 @@ define void @extension_in_loop_v16i8_to_v16i32(ptr %src, ptr %dst) {
|
||||
; CHECK-NEXT: sshll.4s v6, v6, #0
|
||||
; CHECK-NEXT: sshll2.4s v19, v5, #0
|
||||
; CHECK-NEXT: sshll.4s v5, v5, #0
|
||||
; CHECK-NEXT: and.16b v7, v7, v17
|
||||
; CHECK-NEXT: and.16b v6, v16, v6
|
||||
; CHECK-NEXT: and.16b v16, v18, v19
|
||||
; CHECK-NEXT: and.16b v4, v4, v5
|
||||
; CHECK-NEXT: and.16b v7, v17, v7
|
||||
; CHECK-NEXT: and.16b v6, v6, v16
|
||||
; CHECK-NEXT: and.16b v16, v19, v18
|
||||
; CHECK-NEXT: and.16b v4, v5, v4
|
||||
; CHECK-NEXT: stp q6, q7, [x1, #32]
|
||||
; CHECK-NEXT: stp q4, q16, [x1], #64
|
||||
; CHECK-NEXT: b.ne LBB24_1
|
||||
@ -674,10 +674,10 @@ define void @extension_in_loop_as_shuffle_v16i8_to_v16i32(ptr %src, ptr %dst) {
|
||||
; CHECK-NEXT: sshll.4s v6, v6, #0
|
||||
; CHECK-NEXT: sshll2.4s v19, v5, #0
|
||||
; CHECK-NEXT: sshll.4s v5, v5, #0
|
||||
; CHECK-NEXT: and.16b v7, v7, v17
|
||||
; CHECK-NEXT: and.16b v6, v16, v6
|
||||
; CHECK-NEXT: and.16b v16, v18, v19
|
||||
; CHECK-NEXT: and.16b v4, v4, v5
|
||||
; CHECK-NEXT: and.16b v7, v17, v7
|
||||
; CHECK-NEXT: and.16b v6, v6, v16
|
||||
; CHECK-NEXT: and.16b v16, v19, v18
|
||||
; CHECK-NEXT: and.16b v4, v5, v4
|
||||
; CHECK-NEXT: stp q6, q7, [x1, #32]
|
||||
; CHECK-NEXT: stp q4, q16, [x1], #64
|
||||
; CHECK-NEXT: b.ne LBB25_1
|
||||
@ -745,10 +745,10 @@ define void @shuffle_in_loop_is_no_extend_v16i8_to_v16i32(ptr %src, ptr %dst) {
|
||||
; CHECK-NEXT: sshll.4s v6, v6, #0
|
||||
; CHECK-NEXT: sshll2.4s v19, v5, #0
|
||||
; CHECK-NEXT: sshll.4s v5, v5, #0
|
||||
; CHECK-NEXT: and.16b v7, v7, v17
|
||||
; CHECK-NEXT: and.16b v6, v16, v6
|
||||
; CHECK-NEXT: and.16b v16, v18, v19
|
||||
; CHECK-NEXT: and.16b v4, v4, v5
|
||||
; CHECK-NEXT: and.16b v7, v17, v7
|
||||
; CHECK-NEXT: and.16b v6, v6, v16
|
||||
; CHECK-NEXT: and.16b v16, v19, v18
|
||||
; CHECK-NEXT: and.16b v4, v5, v4
|
||||
; CHECK-NEXT: stp q6, q7, [x1, #32]
|
||||
; CHECK-NEXT: stp q4, q16, [x1], #64
|
||||
; CHECK-NEXT: b.ne LBB26_1
|
||||
|
||||
@ -174,7 +174,7 @@ define <2 x i32> @ustest_f64i32(<2 x double> %x) {
|
||||
; CHECK-NEXT: cmp r2, #0
|
||||
; CHECK-NEXT: mvnne r2, #0
|
||||
; CHECK-NEXT: vmov.32 d18[0], r2
|
||||
; CHECK-NEXT: vand q8, q8, q9
|
||||
; CHECK-NEXT: vand q8, q9, q8
|
||||
; CHECK-NEXT: vmovn.i64 d0, q8
|
||||
; CHECK-NEXT: vpop {d8, d9}
|
||||
; CHECK-NEXT: pop {r4, r5, r11, pc}
|
||||
@ -483,8 +483,8 @@ define <4 x i32> @ustest_f32i32(<4 x float> %x) {
|
||||
; CHECK-NEXT: vmov.32 d20[0], r7
|
||||
; CHECK-NEXT: mvnne r4, #0
|
||||
; CHECK-NEXT: vmov.32 d18[0], r4
|
||||
; CHECK-NEXT: vand q10, q4, q10
|
||||
; CHECK-NEXT: vand q8, q8, q9
|
||||
; CHECK-NEXT: vand q10, q10, q4
|
||||
; CHECK-NEXT: vand q8, q9, q8
|
||||
; CHECK-NEXT: vmovn.i64 d1, q10
|
||||
; CHECK-NEXT: vmovn.i64 d0, q8
|
||||
; CHECK-NEXT: vpop {d8, d9, d10, d11, d12, d13}
|
||||
@ -995,8 +995,8 @@ define <4 x i32> @ustest_f16i32(<4 x half> %x) {
|
||||
; CHECK-NEON-NEXT: vmov.32 d20[0], r6
|
||||
; CHECK-NEON-NEXT: mvnne r7, #0
|
||||
; CHECK-NEON-NEXT: vmov.32 d18[0], r7
|
||||
; CHECK-NEON-NEXT: vand q10, q4, q10
|
||||
; CHECK-NEON-NEXT: vand q8, q8, q9
|
||||
; CHECK-NEON-NEXT: vand q10, q10, q4
|
||||
; CHECK-NEON-NEXT: vand q8, q9, q8
|
||||
; CHECK-NEON-NEXT: vmovn.i64 d1, q10
|
||||
; CHECK-NEON-NEXT: vmovn.i64 d0, q8
|
||||
; CHECK-NEON-NEXT: vpop {d8, d9, d10, d11, d12, d13}
|
||||
@ -1097,8 +1097,8 @@ define <4 x i32> @ustest_f16i32(<4 x half> %x) {
|
||||
; CHECK-FP16-NEXT: vmov.32 d20[0], r7
|
||||
; CHECK-FP16-NEXT: mvnne r6, #0
|
||||
; CHECK-FP16-NEXT: vmov.32 d18[0], r6
|
||||
; CHECK-FP16-NEXT: vand q10, q4, q10
|
||||
; CHECK-FP16-NEXT: vand q8, q8, q9
|
||||
; CHECK-FP16-NEXT: vand q10, q10, q4
|
||||
; CHECK-FP16-NEXT: vand q8, q9, q8
|
||||
; CHECK-FP16-NEXT: vmovn.i64 d1, q10
|
||||
; CHECK-FP16-NEXT: vmovn.i64 d0, q8
|
||||
; CHECK-FP16-NEXT: vpop {d8, d9, d10, d11, d12, d13}
|
||||
|
||||
@ -1362,7 +1362,7 @@ define void @pr65820(ptr %y, <4 x float> %splat) {
|
||||
; ARMV7-NEXT: vmov d16, r2, r3
|
||||
; ARMV7-NEXT: vdup.32 q8, d16[0]
|
||||
; ARMV7-NEXT: vcgt.f32 q9, q8, #0
|
||||
; ARMV7-NEXT: vand q8, q8, q9
|
||||
; ARMV7-NEXT: vand q8, q9, q8
|
||||
; ARMV7-NEXT: vst1.32 {d16, d17}, [r0]
|
||||
; ARMV7-NEXT: bx lr
|
||||
;
|
||||
|
||||
@ -383,8 +383,7 @@ define i8 @xvmsk_eq_vsel_slt_v8i32(<8 x i32> %a0, <8 x i32> %a1, <8 x i32> %a2)
|
||||
; CHECK-LABEL: xvmsk_eq_vsel_slt_v8i32:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: xvseq.w $xr0, $xr0, $xr1
|
||||
; CHECK-NEXT: xvrepli.b $xr1, -1
|
||||
; CHECK-NEXT: xvbitsel.v $xr0, $xr2, $xr1, $xr0
|
||||
; CHECK-NEXT: xvor.v $xr0, $xr0, $xr2
|
||||
; CHECK-NEXT: xvmskltz.w $xr0, $xr0
|
||||
; CHECK-NEXT: xvpickve2gr.wu $a0, $xr0, 0
|
||||
; CHECK-NEXT: xvpickve2gr.wu $a1, $xr0, 4
|
||||
|
||||
@ -6,8 +6,8 @@ define void @select_v16i8_imm(ptr %res, ptr %a0) nounwind {
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vld $vr0, $a1, 0
|
||||
; CHECK-NEXT: vrepli.h $vr1, -256
|
||||
; CHECK-NEXT: vbitseli.b $vr1, $vr0, 255
|
||||
; CHECK-NEXT: vst $vr1, $a0, 0
|
||||
; CHECK-NEXT: vor.v $vr0, $vr0, $vr1
|
||||
; CHECK-NEXT: vst $vr0, $a0, 0
|
||||
; CHECK-NEXT: ret
|
||||
%v0 = load <16 x i8>, ptr %a0
|
||||
%sel = select <16 x i1> <i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true, i1 false, i1 true>, <16 x i8> <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>, <16 x i8> %v0
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
||||
; RUN: llc -mtriple=mips-elf -mattr=+msa,+fp64,+mips32r2 < %s | FileCheck %s --check-prefixes=CHECK,MIPS
|
||||
; RUN: llc -mtriple=mipsel-elf -mattr=+msa,+fp64,+mips32r2 < %s | FileCheck %s --check-prefixes=CHECK,MIPSEL
|
||||
; RUN: llc -mtriple=mips-elf -mattr=+msa,+fp64,+mips32r2 < %s | FileCheck %s
|
||||
; RUN: llc -mtriple=mipsel-elf -mattr=+msa,+fp64,+mips32r2 < %s | FileCheck %s
|
||||
|
||||
declare <4 x float> @llvm.mips.fmax.w(<4 x float>, <4 x float>) nounwind
|
||||
declare <2 x double> @llvm.mips.fmax.d(<2 x double>, <2 x double>) nounwind
|
||||
@ -525,26 +525,14 @@ define void @bsel_v2f64(ptr %d, ptr %a, ptr %b, ptr %c) nounwind {
|
||||
|
||||
; Note that IfSet and IfClr are swapped since the condition is inverted
|
||||
define void @bseli_v4f32(ptr %d, ptr %a, ptr %b, ptr %c) nounwind {
|
||||
; MIPS-LABEL: bseli_v4f32:
|
||||
; MIPS: # %bb.0:
|
||||
; MIPS-NEXT: ld.w $w0, 0($5)
|
||||
; MIPS-NEXT: ld.w $w1, 0($6)
|
||||
; MIPS-NEXT: fclt.w $w1, $w1, $w0
|
||||
; MIPS-NEXT: ldi.b $w2, 0
|
||||
; MIPS-NEXT: shf.b $w2, $w2, 27
|
||||
; MIPS-NEXT: bsel.v $w1, $w2, $w0
|
||||
; MIPS-NEXT: jr $ra
|
||||
; MIPS-NEXT: st.w $w1, 0($4)
|
||||
;
|
||||
; MIPSEL-LABEL: bseli_v4f32:
|
||||
; MIPSEL: # %bb.0:
|
||||
; MIPSEL-NEXT: ld.w $w0, 0($5)
|
||||
; MIPSEL-NEXT: ld.w $w1, 0($6)
|
||||
; MIPSEL-NEXT: fclt.w $w1, $w1, $w0
|
||||
; MIPSEL-NEXT: ldi.b $w2, 0
|
||||
; MIPSEL-NEXT: bsel.v $w1, $w2, $w0
|
||||
; MIPSEL-NEXT: jr $ra
|
||||
; MIPSEL-NEXT: st.w $w1, 0($4)
|
||||
; CHECK-LABEL: bseli_v4f32:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: ld.w $w0, 0($5)
|
||||
; CHECK-NEXT: ld.w $w1, 0($6)
|
||||
; CHECK-NEXT: fclt.w $w1, $w1, $w0
|
||||
; CHECK-NEXT: and.v $w0, $w1, $w0
|
||||
; CHECK-NEXT: jr $ra
|
||||
; CHECK-NEXT: st.w $w0, 0($4)
|
||||
%1 = load <4 x float>, ptr %a
|
||||
%2 = load <4 x float>, ptr %b
|
||||
%3 = fcmp ogt <4 x float> %1, %2
|
||||
@ -555,27 +543,14 @@ define void @bseli_v4f32(ptr %d, ptr %a, ptr %b, ptr %c) nounwind {
|
||||
|
||||
; Note that IfSet and IfClr are swapped since the condition is inverted
|
||||
define void @bseli_v2f64(ptr %d, ptr %a, ptr %b, ptr %c) nounwind {
|
||||
; MIPS-LABEL: bseli_v2f64:
|
||||
; MIPS: # %bb.0:
|
||||
; MIPS-NEXT: ld.d $w0, 0($5)
|
||||
; MIPS-NEXT: ld.d $w1, 0($6)
|
||||
; MIPS-NEXT: fclt.d $w1, $w1, $w0
|
||||
; MIPS-NEXT: ldi.b $w2, 0
|
||||
; MIPS-NEXT: shf.b $w2, $w2, 27
|
||||
; MIPS-NEXT: shf.w $w2, $w2, 177
|
||||
; MIPS-NEXT: bsel.v $w1, $w2, $w0
|
||||
; MIPS-NEXT: jr $ra
|
||||
; MIPS-NEXT: st.d $w1, 0($4)
|
||||
;
|
||||
; MIPSEL-LABEL: bseli_v2f64:
|
||||
; MIPSEL: # %bb.0:
|
||||
; MIPSEL-NEXT: ld.d $w0, 0($5)
|
||||
; MIPSEL-NEXT: ld.d $w1, 0($6)
|
||||
; MIPSEL-NEXT: fclt.d $w1, $w1, $w0
|
||||
; MIPSEL-NEXT: ldi.b $w2, 0
|
||||
; MIPSEL-NEXT: bsel.v $w1, $w2, $w0
|
||||
; MIPSEL-NEXT: jr $ra
|
||||
; MIPSEL-NEXT: st.d $w1, 0($4)
|
||||
; CHECK-LABEL: bseli_v2f64:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: ld.d $w0, 0($5)
|
||||
; CHECK-NEXT: ld.d $w1, 0($6)
|
||||
; CHECK-NEXT: fclt.d $w1, $w1, $w0
|
||||
; CHECK-NEXT: and.v $w0, $w1, $w0
|
||||
; CHECK-NEXT: jr $ra
|
||||
; CHECK-NEXT: st.d $w0, 0($4)
|
||||
%1 = load <2 x double>, ptr %a
|
||||
%2 = load <2 x double>, ptr %b
|
||||
%3 = fcmp ogt <2 x double> %1, %2
|
||||
|
||||
@ -1024,15 +1024,16 @@ define <4 x float> @hoo3_fmf(<4 x float> %a) #1 {
|
||||
; CHECK-P7-NEXT: vslw 3, 3, 3
|
||||
; CHECK-P7-NEXT: lvx 0, 0, 3
|
||||
; CHECK-P7-NEXT: addis 3, 2, .LCPI25_1@toc@ha
|
||||
; CHECK-P7-NEXT: addi 3, 3, .LCPI25_1@toc@l
|
||||
; CHECK-P7-NEXT: vmaddfp 5, 2, 4, 3
|
||||
; CHECK-P7-NEXT: lvx 1, 0, 3
|
||||
; CHECK-P7-NEXT: addi 3, 3, .LCPI25_1@toc@l
|
||||
; CHECK-P7-NEXT: vmaddfp 4, 5, 4, 0
|
||||
; CHECK-P7-NEXT: vmaddfp 5, 5, 1, 3
|
||||
; CHECK-P7-NEXT: lvx 0, 0, 3
|
||||
; CHECK-P7-NEXT: vmaddfp 5, 5, 0, 3
|
||||
; CHECK-P7-NEXT: vmaddfp 3, 5, 4, 3
|
||||
; CHECK-P7-NEXT: vxor 4, 4, 4
|
||||
; CHECK-P7-NEXT: vcmpeqfp 2, 2, 4
|
||||
; CHECK-P7-NEXT: vsel 2, 3, 4, 2
|
||||
; CHECK-P7-NEXT: vnot 2, 2
|
||||
; CHECK-P7-NEXT: vand 2, 2, 3
|
||||
; CHECK-P7-NEXT: blr
|
||||
;
|
||||
; CHECK-P8-LABEL: hoo3_fmf:
|
||||
|
||||
@ -536,12 +536,11 @@ define <2 x i64> @unsigned_sat_constant_v2i64_using_cmp_sum(<2 x i64> %x) {
|
||||
; CHECK-LABEL: unsigned_sat_constant_v2i64_using_cmp_sum:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: addis 3, 2, .LCPI34_0@toc@ha
|
||||
; CHECK-NEXT: xxleqv 0, 0, 0
|
||||
; CHECK-NEXT: addi 3, 3, .LCPI34_0@toc@l
|
||||
; CHECK-NEXT: lxvd2x 35, 0, 3
|
||||
; CHECK-NEXT: vaddudm 3, 2, 3
|
||||
; CHECK-NEXT: vcmpgtud 2, 2, 3
|
||||
; CHECK-NEXT: xxsel 34, 35, 0, 34
|
||||
; CHECK-NEXT: xxlor 34, 34, 35
|
||||
; CHECK-NEXT: blr
|
||||
%a = add <2 x i64> %x, <i64 42, i64 42>
|
||||
%c = icmp ugt <2 x i64> %x, %a
|
||||
@ -553,7 +552,6 @@ define <2 x i64> @unsigned_sat_constant_v2i64_using_cmp_notval(<2 x i64> %x) {
|
||||
; CHECK-LABEL: unsigned_sat_constant_v2i64_using_cmp_notval:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: addis 3, 2, .LCPI35_0@toc@ha
|
||||
; CHECK-NEXT: xxleqv 0, 0, 0
|
||||
; CHECK-NEXT: addi 3, 3, .LCPI35_0@toc@l
|
||||
; CHECK-NEXT: lxvd2x 35, 0, 3
|
||||
; CHECK-NEXT: addis 3, 2, .LCPI35_1@toc@ha
|
||||
@ -561,7 +559,7 @@ define <2 x i64> @unsigned_sat_constant_v2i64_using_cmp_notval(<2 x i64> %x) {
|
||||
; CHECK-NEXT: lxvd2x 36, 0, 3
|
||||
; CHECK-NEXT: vaddudm 3, 2, 3
|
||||
; CHECK-NEXT: vcmpgtud 2, 2, 4
|
||||
; CHECK-NEXT: xxsel 34, 35, 0, 34
|
||||
; CHECK-NEXT: xxlor 34, 34, 35
|
||||
; CHECK-NEXT: blr
|
||||
%a = add <2 x i64> %x, <i64 42, i64 42>
|
||||
%c = icmp ugt <2 x i64> %x, <i64 -43, i64 -43>
|
||||
@ -599,9 +597,8 @@ define <16 x i8> @unsigned_sat_variable_v16i8_using_cmp_notval(<16 x i8> %x, <16
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: xxlnor 36, 35, 35
|
||||
; CHECK-NEXT: vaddubm 3, 2, 3
|
||||
; CHECK-NEXT: xxleqv 0, 0, 0
|
||||
; CHECK-NEXT: vcmpgtub 2, 2, 4
|
||||
; CHECK-NEXT: xxsel 34, 35, 0, 34
|
||||
; CHECK-NEXT: xxlor 34, 34, 35
|
||||
; CHECK-NEXT: blr
|
||||
%noty = xor <16 x i8> %y, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
|
||||
%a = add <16 x i8> %x, %y
|
||||
@ -640,9 +637,8 @@ define <8 x i16> @unsigned_sat_variable_v8i16_using_cmp_notval(<8 x i16> %x, <8
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: xxlnor 36, 35, 35
|
||||
; CHECK-NEXT: vadduhm 3, 2, 3
|
||||
; CHECK-NEXT: xxleqv 0, 0, 0
|
||||
; CHECK-NEXT: vcmpgtuh 2, 2, 4
|
||||
; CHECK-NEXT: xxsel 34, 35, 0, 34
|
||||
; CHECK-NEXT: xxlor 34, 34, 35
|
||||
; CHECK-NEXT: blr
|
||||
%noty = xor <8 x i16> %y, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
|
||||
%a = add <8 x i16> %x, %y
|
||||
@ -681,9 +677,8 @@ define <4 x i32> @unsigned_sat_variable_v4i32_using_cmp_notval(<4 x i32> %x, <4
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: xxlnor 36, 35, 35
|
||||
; CHECK-NEXT: vadduwm 3, 2, 3
|
||||
; CHECK-NEXT: xxleqv 0, 0, 0
|
||||
; CHECK-NEXT: vcmpgtuw 2, 2, 4
|
||||
; CHECK-NEXT: xxsel 34, 35, 0, 34
|
||||
; CHECK-NEXT: xxlor 34, 34, 35
|
||||
; CHECK-NEXT: blr
|
||||
%noty = xor <4 x i32> %y, <i32 -1, i32 -1, i32 -1, i32 -1>
|
||||
%a = add <4 x i32> %x, %y
|
||||
@ -710,9 +705,8 @@ define <2 x i64> @unsigned_sat_variable_v2i64_using_cmp_sum(<2 x i64> %x, <2 x i
|
||||
; CHECK-LABEL: unsigned_sat_variable_v2i64_using_cmp_sum:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vaddudm 3, 2, 3
|
||||
; CHECK-NEXT: xxleqv 0, 0, 0
|
||||
; CHECK-NEXT: vcmpgtud 2, 2, 3
|
||||
; CHECK-NEXT: xxsel 34, 35, 0, 34
|
||||
; CHECK-NEXT: xxlor 34, 34, 35
|
||||
; CHECK-NEXT: blr
|
||||
%a = add <2 x i64> %x, %y
|
||||
%c = icmp ugt <2 x i64> %x, %a
|
||||
@ -725,9 +719,8 @@ define <2 x i64> @unsigned_sat_variable_v2i64_using_cmp_notval(<2 x i64> %x, <2
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: xxlnor 36, 35, 35
|
||||
; CHECK-NEXT: vaddudm 3, 2, 3
|
||||
; CHECK-NEXT: xxleqv 0, 0, 0
|
||||
; CHECK-NEXT: vcmpgtud 2, 2, 4
|
||||
; CHECK-NEXT: xxsel 34, 35, 0, 34
|
||||
; CHECK-NEXT: xxlor 34, 34, 35
|
||||
; CHECK-NEXT: blr
|
||||
%noty = xor <2 x i64> %y, <i64 -1, i64 -1>
|
||||
%a = add <2 x i64> %x, %y
|
||||
|
||||
@ -52,8 +52,8 @@ define <2 x double> @f5(<2 x double> %val) {
|
||||
; CHECK-LABEL: f5:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vgbm %v0, 0
|
||||
; CHECK-NEXT: vfchedb %v1, %v0, %v24
|
||||
; CHECK-NEXT: vsel %v24, %v0, %v24, %v1
|
||||
; CHECK-NEXT: vfchedb %v0, %v0, %v24
|
||||
; CHECK-NEXT: vnc %v24, %v24, %v0
|
||||
; CHECK-NEXT: br %r14
|
||||
%cmp = fcmp ugt <2 x double> %val, zeroinitializer
|
||||
%ret = select <2 x i1> %cmp, <2 x double> %val, <2 x double> zeroinitializer
|
||||
@ -64,8 +64,8 @@ define <2 x double> @f6(<2 x double> %val) {
|
||||
; CHECK-LABEL: f6:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vgbm %v0, 0
|
||||
; CHECK-NEXT: vfchedb %v1, %v24, %v0
|
||||
; CHECK-NEXT: vsel %v24, %v0, %v24, %v1
|
||||
; CHECK-NEXT: vfchedb %v0, %v24, %v0
|
||||
; CHECK-NEXT: vnc %v24, %v24, %v0
|
||||
; CHECK-NEXT: br %r14
|
||||
%cmp = fcmp ult <2 x double> %val, zeroinitializer
|
||||
%ret = select <2 x i1> %cmp, <2 x double> %val, <2 x double> zeroinitializer
|
||||
@ -76,8 +76,8 @@ define <4 x float> @f7(<4 x float> %val) {
|
||||
; CHECK-LABEL: f7:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vgbm %v0, 0
|
||||
; CHECK-NEXT: vfchesb %v1, %v0, %v24
|
||||
; CHECK-NEXT: vsel %v24, %v0, %v24, %v1
|
||||
; CHECK-NEXT: vfchesb %v0, %v0, %v24
|
||||
; CHECK-NEXT: vnc %v24, %v24, %v0
|
||||
; CHECK-NEXT: br %r14
|
||||
%cmp = fcmp ugt <4 x float> %val, zeroinitializer
|
||||
%ret = select <4 x i1> %cmp, <4 x float> %val, <4 x float> zeroinitializer
|
||||
@ -88,8 +88,8 @@ define <4 x float> @f8(<4 x float> %val) {
|
||||
; CHECK-LABEL: f8:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vgbm %v0, 0
|
||||
; CHECK-NEXT: vfchesb %v1, %v24, %v0
|
||||
; CHECK-NEXT: vsel %v24, %v0, %v24, %v1
|
||||
; CHECK-NEXT: vfchesb %v0, %v24, %v0
|
||||
; CHECK-NEXT: vnc %v24, %v24, %v0
|
||||
; CHECK-NEXT: br %r14
|
||||
%cmp = fcmp ult <4 x float> %val, zeroinitializer
|
||||
%ret = select <4 x i1> %cmp, <4 x float> %val, <4 x float> zeroinitializer
|
||||
|
||||
@ -77,11 +77,9 @@ define <4 x i1> @t1_all_odd_ne(<4 x i32> %X) nounwind {
|
||||
; CHECK-SSE2-LABEL: t1_all_odd_ne:
|
||||
; CHECK-SSE2: # %bb.0:
|
||||
; CHECK-SSE2-NEXT: pmuludq {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
|
||||
; CHECK-SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
|
||||
; CHECK-SSE2-NEXT: pxor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
|
||||
; CHECK-SSE2-NEXT: pcmpgtd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
|
||||
; CHECK-SSE2-NEXT: pcmpeqd %xmm1, %xmm1
|
||||
; CHECK-SSE2-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
|
||||
; CHECK-SSE2-NEXT: por {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
|
||||
; CHECK-SSE2-NEXT: retq
|
||||
;
|
||||
; CHECK-SSE41-LABEL: t1_all_odd_ne:
|
||||
@ -92,7 +90,7 @@ define <4 x i1> @t1_all_odd_ne(<4 x i32> %X) nounwind {
|
||||
; CHECK-SSE41-NEXT: pcmpeqd %xmm1, %xmm0
|
||||
; CHECK-SSE41-NEXT: pcmpeqd %xmm1, %xmm1
|
||||
; CHECK-SSE41-NEXT: pxor %xmm1, %xmm0
|
||||
; CHECK-SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
|
||||
; CHECK-SSE41-NEXT: por {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
|
||||
; CHECK-SSE41-NEXT: retq
|
||||
;
|
||||
; CHECK-AVX1-LABEL: t1_all_odd_ne:
|
||||
@ -102,7 +100,7 @@ define <4 x i1> @t1_all_odd_ne(<4 x i32> %X) nounwind {
|
||||
; CHECK-AVX1-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
|
||||
; CHECK-AVX1-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
|
||||
; CHECK-AVX1-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; CHECK-AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
|
||||
; CHECK-AVX1-NEXT: vpor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
|
||||
; CHECK-AVX1-NEXT: retq
|
||||
;
|
||||
; CHECK-AVX2-LABEL: t1_all_odd_ne:
|
||||
@ -113,17 +111,16 @@ define <4 x i1> @t1_all_odd_ne(<4 x i32> %X) nounwind {
|
||||
; CHECK-AVX2-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
|
||||
; CHECK-AVX2-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
|
||||
; CHECK-AVX2-NEXT: vpxor %xmm1, %xmm0, %xmm0
|
||||
; CHECK-AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
|
||||
; CHECK-AVX2-NEXT: vpor {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm0
|
||||
; CHECK-AVX2-NEXT: retq
|
||||
;
|
||||
; CHECK-AVX512VL-LABEL: t1_all_odd_ne:
|
||||
; CHECK-AVX512VL: # %bb.0:
|
||||
; CHECK-AVX512VL-NEXT: vpmulld {{\.?LCPI[0-9]+_[0-9]+}}(%rip){1to4}, %xmm0, %xmm0
|
||||
; CHECK-AVX512VL-NEXT: vpminud {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm1
|
||||
; CHECK-AVX512VL-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm0
|
||||
; CHECK-AVX512VL-NEXT: vpternlogq {{.*#+}} xmm0 = ~xmm0
|
||||
; CHECK-AVX512VL-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
|
||||
; CHECK-AVX512VL-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3]
|
||||
; CHECK-AVX512VL-NEXT: vpcmpeqd %xmm1, %xmm0, %xmm1
|
||||
; CHECK-AVX512VL-NEXT: vpcmpeqd %xmm0, %xmm0, %xmm0
|
||||
; CHECK-AVX512VL-NEXT: vpternlogq {{.*#+}} xmm0 = m64bcst | (xmm0 ^ xmm1)
|
||||
; CHECK-AVX512VL-NEXT: retq
|
||||
%urem = urem <4 x i32> %X, <i32 3, i32 1, i32 1, i32 9>
|
||||
%cmp = icmp ne <4 x i32> %urem, <i32 0, i32 42, i32 0, i32 42>
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user