summaryrefslogtreecommitdiff
path: root/lib/Target/SystemZ
diff options
context:
space:
mode:
Diffstat (limited to 'lib/Target/SystemZ')
-rw-r--r--lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp15
-rw-r--r--lib/Target/SystemZ/LLVMBuild.txt2
-rw-r--r--lib/Target/SystemZ/SystemZFeatures.td58
-rw-r--r--lib/Target/SystemZ/SystemZISelLowering.cpp104
-rw-r--r--lib/Target/SystemZ/SystemZISelLowering.h7
-rw-r--r--lib/Target/SystemZ/SystemZInstrFP.td88
-rw-r--r--lib/Target/SystemZ/SystemZInstrFormats.td330
-rw-r--r--lib/Target/SystemZ/SystemZInstrInfo.cpp32
-rw-r--r--lib/Target/SystemZ/SystemZInstrInfo.td68
-rw-r--r--lib/Target/SystemZ/SystemZInstrSystem.td4
-rw-r--r--lib/Target/SystemZ/SystemZInstrVector.td366
-rw-r--r--lib/Target/SystemZ/SystemZOperators.td20
-rw-r--r--lib/Target/SystemZ/SystemZPatterns.td7
-rw-r--r--lib/Target/SystemZ/SystemZProcessors.td3
-rw-r--r--lib/Target/SystemZ/SystemZRegisterInfo.td14
-rw-r--r--lib/Target/SystemZ/SystemZSchedule.td3
-rw-r--r--lib/Target/SystemZ/SystemZScheduleZ14.td1611
-rw-r--r--lib/Target/SystemZ/SystemZScheduleZ196.td163
-rw-r--r--lib/Target/SystemZ/SystemZScheduleZEC12.td161
-rw-r--r--lib/Target/SystemZ/SystemZShortenInst.cpp40
-rw-r--r--lib/Target/SystemZ/SystemZSubtarget.cpp4
-rw-r--r--lib/Target/SystemZ/SystemZSubtarget.h34
-rw-r--r--lib/Target/SystemZ/SystemZTargetMachine.cpp4
-rw-r--r--lib/Target/SystemZ/SystemZTargetTransformInfo.cpp3
-rw-r--r--lib/Target/SystemZ/SystemZTargetTransformInfo.h4
25 files changed, 2924 insertions, 221 deletions
diff --git a/lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp b/lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp
index ee23692ad1db2..33680789ee082 100644
--- a/lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp
+++ b/lib/Target/SystemZ/AsmParser/SystemZAsmParser.cpp
@@ -275,6 +275,10 @@ public:
SMLoc getEndLoc() const override { return EndLoc; }
void print(raw_ostream &OS) const override;
+ /// getLocRange - Get the range between the first and last token of this
+ /// operand.
+ SMRange getLocRange() const { return SMRange(StartLoc, EndLoc); }
+
// Used by the TableGen code to add particular types of operand
// to an instruction.
void addRegOperands(MCInst &Inst, unsigned N) const {
@@ -1164,6 +1168,8 @@ bool SystemZAsmParser::parseOperand(OperandVector &Operands,
return false;
}
+std::string SystemZMnemonicSpellCheck(StringRef S, uint64_t FBS);
+
bool SystemZAsmParser::MatchAndEmitInstruction(SMLoc IDLoc, unsigned &Opcode,
OperandVector &Operands,
MCStreamer &Out,
@@ -1209,8 +1215,13 @@ bool SystemZAsmParser::MatchAndEmitInstruction(SMLoc IDLoc, unsigned &Opcode,
return Error(ErrorLoc, "invalid operand for instruction");
}
- case Match_MnemonicFail:
- return Error(IDLoc, "invalid instruction");
+ case Match_MnemonicFail: {
+ uint64_t FBS = ComputeAvailableFeatures(getSTI().getFeatureBits());
+ std::string Suggestion = SystemZMnemonicSpellCheck(
+ ((SystemZOperand &)*Operands[0]).getToken(), FBS);
+ return Error(IDLoc, "invalid instruction" + Suggestion,
+ ((SystemZOperand &)*Operands[0]).getLocRange());
+ }
}
llvm_unreachable("Unexpected match type");
diff --git a/lib/Target/SystemZ/LLVMBuild.txt b/lib/Target/SystemZ/LLVMBuild.txt
index 6f8431db7b11c..9b8b141fd52ab 100644
--- a/lib/Target/SystemZ/LLVMBuild.txt
+++ b/lib/Target/SystemZ/LLVMBuild.txt
@@ -31,5 +31,5 @@ has_jit = 1
type = Library
name = SystemZCodeGen
parent = SystemZ
-required_libraries = Analysis AsmPrinter CodeGen Core MC SelectionDAG Support SystemZAsmPrinter SystemZDesc SystemZInfo Target
+required_libraries = Analysis AsmPrinter CodeGen Core MC Scalar SelectionDAG Support SystemZAsmPrinter SystemZDesc SystemZInfo Target
add_to_library_groups = SystemZ
diff --git a/lib/Target/SystemZ/SystemZFeatures.td b/lib/Target/SystemZ/SystemZFeatures.td
index c5faa0d62881d..fda9c30fe3fcc 100644
--- a/lib/Target/SystemZ/SystemZFeatures.td
+++ b/lib/Target/SystemZ/SystemZFeatures.td
@@ -189,6 +189,58 @@ def Arch11NewFeatures : SystemZFeatureList<[
//===----------------------------------------------------------------------===//
//
+// New features added in the Twelvth Edition of the z/Architecture
+//
+//===----------------------------------------------------------------------===//
+
+def FeatureMiscellaneousExtensions2 : SystemZFeature<
+ "miscellaneous-extensions-2", "MiscellaneousExtensions2",
+ "Assume that the miscellaneous-extensions facility 2 is installed"
+>;
+
+def FeatureGuardedStorage : SystemZFeature<
+ "guarded-storage", "GuardedStorage",
+ "Assume that the guarded-storage facility is installed"
+>;
+
+def FeatureMessageSecurityAssist7 : SystemZFeature<
+ "message-security-assist-extension7", "MessageSecurityAssist7",
+ "Assume that the message-security-assist extension facility 7 is installed"
+>;
+
+def FeatureMessageSecurityAssist8 : SystemZFeature<
+ "message-security-assist-extension8", "MessageSecurityAssist8",
+ "Assume that the message-security-assist extension facility 8 is installed"
+>;
+
+def FeatureVectorEnhancements1 : SystemZFeature<
+ "vector-enhancements-1", "VectorEnhancements1",
+ "Assume that the vector enhancements facility 1 is installed"
+>;
+def FeatureNoVectorEnhancements1 : SystemZMissingFeature<"VectorEnhancements1">;
+
+def FeatureVectorPackedDecimal : SystemZFeature<
+ "vector-packed-decimal", "VectorPackedDecimal",
+ "Assume that the vector packed decimal facility is installed"
+>;
+
+def FeatureInsertReferenceBitsMultiple : SystemZFeature<
+ "insert-reference-bits-multiple", "InsertReferenceBitsMultiple",
+ "Assume that the insert-reference-bits-multiple facility is installed"
+>;
+
+def Arch12NewFeatures : SystemZFeatureList<[
+ FeatureMiscellaneousExtensions2,
+ FeatureGuardedStorage,
+ FeatureMessageSecurityAssist7,
+ FeatureMessageSecurityAssist8,
+ FeatureVectorEnhancements1,
+ FeatureVectorPackedDecimal,
+ FeatureInsertReferenceBitsMultiple
+]>;
+
+//===----------------------------------------------------------------------===//
+//
// Cumulative supported and unsupported feature sets
//
//===----------------------------------------------------------------------===//
@@ -201,9 +253,13 @@ def Arch10SupportedFeatures
: SystemZFeatureAdd<Arch9SupportedFeatures.List, Arch10NewFeatures.List>;
def Arch11SupportedFeatures
: SystemZFeatureAdd<Arch10SupportedFeatures.List, Arch11NewFeatures.List>;
+def Arch12SupportedFeatures
+ : SystemZFeatureAdd<Arch11SupportedFeatures.List, Arch12NewFeatures.List>;
-def Arch11UnsupportedFeatures
+def Arch12UnsupportedFeatures
: SystemZFeatureList<[]>;
+def Arch11UnsupportedFeatures
+ : SystemZFeatureAdd<Arch12UnsupportedFeatures.List, Arch12NewFeatures.List>;
def Arch10UnsupportedFeatures
: SystemZFeatureAdd<Arch11UnsupportedFeatures.List, Arch11NewFeatures.List>;
def Arch9UnsupportedFeatures
diff --git a/lib/Target/SystemZ/SystemZISelLowering.cpp b/lib/Target/SystemZ/SystemZISelLowering.cpp
index 2801141cd951f..2d916d2e15214 100644
--- a/lib/Target/SystemZ/SystemZISelLowering.cpp
+++ b/lib/Target/SystemZ/SystemZISelLowering.cpp
@@ -101,7 +101,10 @@ SystemZTargetLowering::SystemZTargetLowering(const TargetMachine &TM,
addRegisterClass(MVT::f32, &SystemZ::FP32BitRegClass);
addRegisterClass(MVT::f64, &SystemZ::FP64BitRegClass);
}
- addRegisterClass(MVT::f128, &SystemZ::FP128BitRegClass);
+ if (Subtarget.hasVectorEnhancements1())
+ addRegisterClass(MVT::f128, &SystemZ::VR128BitRegClass);
+ else
+ addRegisterClass(MVT::f128, &SystemZ::FP128BitRegClass);
if (Subtarget.hasVector()) {
addRegisterClass(MVT::v16i8, &SystemZ::VR128BitRegClass);
@@ -316,7 +319,10 @@ SystemZTargetLowering::SystemZTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::AND, VT, Legal);
setOperationAction(ISD::OR, VT, Legal);
setOperationAction(ISD::XOR, VT, Legal);
- setOperationAction(ISD::CTPOP, VT, Custom);
+ if (Subtarget.hasVectorEnhancements1())
+ setOperationAction(ISD::CTPOP, VT, Legal);
+ else
+ setOperationAction(ISD::CTPOP, VT, Custom);
setOperationAction(ISD::CTTZ, VT, Legal);
setOperationAction(ISD::CTLZ, VT, Legal);
@@ -414,10 +420,60 @@ SystemZTargetLowering::SystemZTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::FROUND, MVT::v2f64, Legal);
}
+ // The vector enhancements facility 1 has instructions for these.
+ if (Subtarget.hasVectorEnhancements1()) {
+ setOperationAction(ISD::FADD, MVT::v4f32, Legal);
+ setOperationAction(ISD::FNEG, MVT::v4f32, Legal);
+ setOperationAction(ISD::FSUB, MVT::v4f32, Legal);
+ setOperationAction(ISD::FMUL, MVT::v4f32, Legal);
+ setOperationAction(ISD::FMA, MVT::v4f32, Legal);
+ setOperationAction(ISD::FDIV, MVT::v4f32, Legal);
+ setOperationAction(ISD::FABS, MVT::v4f32, Legal);
+ setOperationAction(ISD::FSQRT, MVT::v4f32, Legal);
+ setOperationAction(ISD::FRINT, MVT::v4f32, Legal);
+ setOperationAction(ISD::FNEARBYINT, MVT::v4f32, Legal);
+ setOperationAction(ISD::FFLOOR, MVT::v4f32, Legal);
+ setOperationAction(ISD::FCEIL, MVT::v4f32, Legal);
+ setOperationAction(ISD::FTRUNC, MVT::v4f32, Legal);
+ setOperationAction(ISD::FROUND, MVT::v4f32, Legal);
+
+ setOperationAction(ISD::FMAXNUM, MVT::f64, Legal);
+ setOperationAction(ISD::FMAXNAN, MVT::f64, Legal);
+ setOperationAction(ISD::FMINNUM, MVT::f64, Legal);
+ setOperationAction(ISD::FMINNAN, MVT::f64, Legal);
+
+ setOperationAction(ISD::FMAXNUM, MVT::v2f64, Legal);
+ setOperationAction(ISD::FMAXNAN, MVT::v2f64, Legal);
+ setOperationAction(ISD::FMINNUM, MVT::v2f64, Legal);
+ setOperationAction(ISD::FMINNAN, MVT::v2f64, Legal);
+
+ setOperationAction(ISD::FMAXNUM, MVT::f32, Legal);
+ setOperationAction(ISD::FMAXNAN, MVT::f32, Legal);
+ setOperationAction(ISD::FMINNUM, MVT::f32, Legal);
+ setOperationAction(ISD::FMINNAN, MVT::f32, Legal);
+
+ setOperationAction(ISD::FMAXNUM, MVT::v4f32, Legal);
+ setOperationAction(ISD::FMAXNAN, MVT::v4f32, Legal);
+ setOperationAction(ISD::FMINNUM, MVT::v4f32, Legal);
+ setOperationAction(ISD::FMINNAN, MVT::v4f32, Legal);
+
+ setOperationAction(ISD::FMAXNUM, MVT::f128, Legal);
+ setOperationAction(ISD::FMAXNAN, MVT::f128, Legal);
+ setOperationAction(ISD::FMINNUM, MVT::f128, Legal);
+ setOperationAction(ISD::FMINNAN, MVT::f128, Legal);
+ }
+
// We have fused multiply-addition for f32 and f64 but not f128.
setOperationAction(ISD::FMA, MVT::f32, Legal);
setOperationAction(ISD::FMA, MVT::f64, Legal);
- setOperationAction(ISD::FMA, MVT::f128, Expand);
+ if (Subtarget.hasVectorEnhancements1())
+ setOperationAction(ISD::FMA, MVT::f128, Legal);
+ else
+ setOperationAction(ISD::FMA, MVT::f128, Expand);
+
+ // We don't have a copysign instruction on vector registers.
+ if (Subtarget.hasVectorEnhancements1())
+ setOperationAction(ISD::FCOPYSIGN, MVT::f128, Expand);
// Needed so that we don't try to implement f128 constant loads using
// a load-and-extend of a f80 constant (in cases where the constant
@@ -425,6 +481,12 @@ SystemZTargetLowering::SystemZTargetLowering(const TargetMachine &TM,
for (MVT VT : MVT::fp_valuetypes())
setLoadExtAction(ISD::EXTLOAD, VT, MVT::f80, Expand);
+ // We don't have extending load instruction on vector registers.
+ if (Subtarget.hasVectorEnhancements1()) {
+ setLoadExtAction(ISD::EXTLOAD, MVT::f128, MVT::f32, Expand);
+ setLoadExtAction(ISD::EXTLOAD, MVT::f128, MVT::f64, Expand);
+ }
+
// Floating-point truncation and stores need to be done separately.
setTruncStoreAction(MVT::f64, MVT::f32, Expand);
setTruncStoreAction(MVT::f128, MVT::f32, Expand);
@@ -489,7 +551,7 @@ bool SystemZTargetLowering::isFMAFasterThanFMulAndFAdd(EVT VT) const {
case MVT::f64:
return true;
case MVT::f128:
- return false;
+ return Subtarget.hasVectorEnhancements1();
default:
break;
}
@@ -1462,21 +1524,25 @@ static bool isIntrinsicWithCC(SDValue Op, unsigned &Opcode, unsigned &CCValid) {
return true;
case Intrinsic::s390_vfcedbs:
+ case Intrinsic::s390_vfcesbs:
Opcode = SystemZISD::VFCMPES;
CCValid = SystemZ::CCMASK_VCMP;
return true;
case Intrinsic::s390_vfchdbs:
+ case Intrinsic::s390_vfchsbs:
Opcode = SystemZISD::VFCMPHS;
CCValid = SystemZ::CCMASK_VCMP;
return true;
case Intrinsic::s390_vfchedbs:
+ case Intrinsic::s390_vfchesbs:
Opcode = SystemZISD::VFCMPHES;
CCValid = SystemZ::CCMASK_VCMP;
return true;
case Intrinsic::s390_vftcidb:
+ case Intrinsic::s390_vftcisb:
Opcode = SystemZISD::VFTCI;
CCValid = SystemZ::CCMASK_VCMP;
return true;
@@ -2316,11 +2382,15 @@ static SDValue expandV4F32ToV2F64(SelectionDAG &DAG, int Start, const SDLoc &DL,
// Build a comparison of vectors CmpOp0 and CmpOp1 using opcode Opcode,
// producing a result of type VT.
-static SDValue getVectorCmp(SelectionDAG &DAG, unsigned Opcode, const SDLoc &DL,
- EVT VT, SDValue CmpOp0, SDValue CmpOp1) {
- // There is no hardware support for v4f32, so extend the vector into
- // two v2f64s and compare those.
- if (CmpOp0.getValueType() == MVT::v4f32) {
+SDValue SystemZTargetLowering::getVectorCmp(SelectionDAG &DAG, unsigned Opcode,
+ const SDLoc &DL, EVT VT,
+ SDValue CmpOp0,
+ SDValue CmpOp1) const {
+ // There is no hardware support for v4f32 (unless we have the vector
+ // enhancements facility 1), so extend the vector into two v2f64s
+ // and compare those.
+ if (CmpOp0.getValueType() == MVT::v4f32 &&
+ !Subtarget.hasVectorEnhancements1()) {
SDValue H0 = expandV4F32ToV2F64(DAG, 0, DL, CmpOp0);
SDValue L0 = expandV4F32ToV2F64(DAG, 2, DL, CmpOp0);
SDValue H1 = expandV4F32ToV2F64(DAG, 0, DL, CmpOp1);
@@ -2334,9 +2404,11 @@ static SDValue getVectorCmp(SelectionDAG &DAG, unsigned Opcode, const SDLoc &DL,
// Lower a vector comparison of type CC between CmpOp0 and CmpOp1, producing
// an integer mask of type VT.
-static SDValue lowerVectorSETCC(SelectionDAG &DAG, const SDLoc &DL, EVT VT,
- ISD::CondCode CC, SDValue CmpOp0,
- SDValue CmpOp1) {
+SDValue SystemZTargetLowering::lowerVectorSETCC(SelectionDAG &DAG,
+ const SDLoc &DL, EVT VT,
+ ISD::CondCode CC,
+ SDValue CmpOp0,
+ SDValue CmpOp1) const {
bool IsFP = CmpOp0.getValueType().isFloatingPoint();
bool Invert = false;
SDValue Cmp;
@@ -2960,6 +3032,12 @@ SDValue SystemZTargetLowering::lowerSMUL_LOHI(SDValue Op,
// We define this so that it can be used for constant division.
lowerMUL_LOHI32(DAG, DL, ISD::SIGN_EXTEND, Op.getOperand(0),
Op.getOperand(1), Ops[1], Ops[0]);
+ else if (Subtarget.hasMiscellaneousExtensions2())
+ // SystemZISD::SMUL_LOHI returns the low result in the odd register and
+ // the high result in the even register. ISD::SMUL_LOHI is defined to
+ // return the low half first, so the results are in reverse order.
+ lowerGR128Binary(DAG, DL, VT, SystemZISD::SMUL_LOHI,
+ Op.getOperand(0), Op.getOperand(1), Ops[1], Ops[0]);
else {
// Do a full 128-bit multiplication based on SystemZISD::UMUL_LOHI:
//
@@ -4658,6 +4736,7 @@ const char *SystemZTargetLowering::getTargetNodeName(unsigned Opcode) const {
OPCODE(SELECT_CCMASK);
OPCODE(ADJDYNALLOC);
OPCODE(POPCNT);
+ OPCODE(SMUL_LOHI);
OPCODE(UMUL_LOHI);
OPCODE(SDIVREM);
OPCODE(UDIVREM);
@@ -6118,6 +6197,7 @@ MachineBasicBlock *SystemZTargetLowering::EmitInstrWithCustomInserter(
case SystemZ::SelectF32:
case SystemZ::SelectF64:
case SystemZ::SelectF128:
+ case SystemZ::SelectVR128:
return emitSelect(MI, MBB, 0);
case SystemZ::CondStore8Mux:
diff --git a/lib/Target/SystemZ/SystemZISelLowering.h b/lib/Target/SystemZ/SystemZISelLowering.h
index 6c9c404816f09..abe8b7233e60c 100644
--- a/lib/Target/SystemZ/SystemZISelLowering.h
+++ b/lib/Target/SystemZ/SystemZISelLowering.h
@@ -88,6 +88,7 @@ enum NodeType : unsigned {
// Wrappers around the ISD opcodes of the same name. The output is GR128.
// Input operands may be GR64 or GR32, depending on the instruction.
+ SMUL_LOHI,
UMUL_LOHI,
SDIVREM,
UDIVREM,
@@ -479,6 +480,12 @@ private:
const SystemZSubtarget &Subtarget;
// Implement LowerOperation for individual opcodes.
+ SDValue getVectorCmp(SelectionDAG &DAG, unsigned Opcode,
+ const SDLoc &DL, EVT VT,
+ SDValue CmpOp0, SDValue CmpOp1) const;
+ SDValue lowerVectorSETCC(SelectionDAG &DAG, const SDLoc &DL,
+ EVT VT, ISD::CondCode CC,
+ SDValue CmpOp0, SDValue CmpOp1) const;
SDValue lowerSETCC(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerBR_CC(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
diff --git a/lib/Target/SystemZ/SystemZInstrFP.td b/lib/Target/SystemZ/SystemZInstrFP.td
index 10172bd452034..02aeaadad0d9a 100644
--- a/lib/Target/SystemZ/SystemZInstrFP.td
+++ b/lib/Target/SystemZ/SystemZInstrFP.td
@@ -12,9 +12,12 @@
//===----------------------------------------------------------------------===//
// C's ?: operator for floating-point operands.
-def SelectF32 : SelectWrapper<FP32>;
-def SelectF64 : SelectWrapper<FP64>;
-def SelectF128 : SelectWrapper<FP128>;
+def SelectF32 : SelectWrapper<f32, FP32>;
+def SelectF64 : SelectWrapper<f64, FP64>;
+let Predicates = [FeatureNoVectorEnhancements1] in
+ def SelectF128 : SelectWrapper<f128, FP128>;
+let Predicates = [FeatureVectorEnhancements1] in
+ def SelectVR128 : SelectWrapper<f128, VR128>;
defm CondStoreF32 : CondStores<FP32, nonvolatile_store,
nonvolatile_load, bdxaddr20only>;
@@ -69,8 +72,9 @@ let Defs = [CC], usesCustomInserter = 1 in {
let Predicates = [FeatureVector] in {
defm : CompareZeroFP<LTEBRCompare_VecPseudo, FP32>;
defm : CompareZeroFP<LTDBRCompare_VecPseudo, FP64>;
- defm : CompareZeroFP<LTXBRCompare_VecPseudo, FP128>;
}
+let Predicates = [FeatureVector, FeatureNoVectorEnhancements1] in
+ defm : CompareZeroFP<LTXBRCompare_VecPseudo, FP128>;
// Moves between 64-bit integer and floating-point registers.
def LGDR : UnaryRRE<"lgdr", 0xB3CD, bitconvert, GR64, FP64>;
@@ -83,8 +87,12 @@ let isCodeGenOnly = 1 in {
}
// The sign of an FP128 is in the high register.
-def : Pat<(fcopysign FP32:$src1, FP128:$src2),
- (CPSDRsd FP32:$src1, (EXTRACT_SUBREG FP128:$src2, subreg_h64))>;
+let Predicates = [FeatureNoVectorEnhancements1] in
+ def : Pat<(fcopysign FP32:$src1, (f32 (fpround (f128 FP128:$src2)))),
+ (CPSDRsd FP32:$src1, (EXTRACT_SUBREG FP128:$src2, subreg_h64))>;
+let Predicates = [FeatureVectorEnhancements1] in
+ def : Pat<(fcopysign FP32:$src1, (f32 (fpround (f128 VR128:$src2)))),
+ (CPSDRsd FP32:$src1, (EXTRACT_SUBREG VR128:$src2, subreg_r64))>;
// fcopysign with an FP64 result.
let isCodeGenOnly = 1 in
@@ -92,8 +100,12 @@ let isCodeGenOnly = 1 in
def CPSDRdd : BinaryRRFb<"cpsdr", 0xB372, fcopysign, FP64, FP64, FP64>;
// The sign of an FP128 is in the high register.
-def : Pat<(fcopysign FP64:$src1, FP128:$src2),
- (CPSDRdd FP64:$src1, (EXTRACT_SUBREG FP128:$src2, subreg_h64))>;
+let Predicates = [FeatureNoVectorEnhancements1] in
+ def : Pat<(fcopysign FP64:$src1, (f64 (fpround (f128 FP128:$src2)))),
+ (CPSDRdd FP64:$src1, (EXTRACT_SUBREG FP128:$src2, subreg_h64))>;
+let Predicates = [FeatureVectorEnhancements1] in
+ def : Pat<(fcopysign FP64:$src1, (f64 (fpround (f128 VR128:$src2)))),
+ (CPSDRdd FP64:$src1, (EXTRACT_SUBREG VR128:$src2, subreg_r64))>;
// fcopysign with an FP128 result. Use "upper" as the high half and leave
// the low half as-is.
@@ -101,12 +113,14 @@ class CopySign128<RegisterOperand cls, dag upper>
: Pat<(fcopysign FP128:$src1, cls:$src2),
(INSERT_SUBREG FP128:$src1, upper, subreg_h64)>;
-def : CopySign128<FP32, (CPSDRds (EXTRACT_SUBREG FP128:$src1, subreg_h64),
- FP32:$src2)>;
-def : CopySign128<FP64, (CPSDRdd (EXTRACT_SUBREG FP128:$src1, subreg_h64),
- FP64:$src2)>;
-def : CopySign128<FP128, (CPSDRdd (EXTRACT_SUBREG FP128:$src1, subreg_h64),
- (EXTRACT_SUBREG FP128:$src2, subreg_h64))>;
+let Predicates = [FeatureNoVectorEnhancements1] in {
+ def : CopySign128<FP32, (CPSDRds (EXTRACT_SUBREG FP128:$src1, subreg_h64),
+ FP32:$src2)>;
+ def : CopySign128<FP64, (CPSDRdd (EXTRACT_SUBREG FP128:$src1, subreg_h64),
+ FP64:$src2)>;
+ def : CopySign128<FP128, (CPSDRdd (EXTRACT_SUBREG FP128:$src1, subreg_h64),
+ (EXTRACT_SUBREG FP128:$src2, subreg_h64))>;
+}
defm LoadStoreF32 : MVCLoadStore<load, f32, MVCSequence, 4>;
defm LoadStoreF64 : MVCLoadStore<load, f64, MVCSequence, 8>;
@@ -166,20 +180,32 @@ def LEXBRA : TernaryRRFe<"lexbra", 0xB346, FP128, FP128>,
def LDXBRA : TernaryRRFe<"ldxbra", 0xB345, FP128, FP128>,
Requires<[FeatureFPExtension]>;
-def : Pat<(f32 (fpround FP128:$src)),
- (EXTRACT_SUBREG (LEXBR FP128:$src), subreg_hr32)>;
-def : Pat<(f64 (fpround FP128:$src)),
- (EXTRACT_SUBREG (LDXBR FP128:$src), subreg_h64)>;
+let Predicates = [FeatureNoVectorEnhancements1] in {
+ def : Pat<(f32 (fpround FP128:$src)),
+ (EXTRACT_SUBREG (LEXBR FP128:$src), subreg_hr32)>;
+ def : Pat<(f64 (fpround FP128:$src)),
+ (EXTRACT_SUBREG (LDXBR FP128:$src), subreg_h64)>;
+}
// Extend register floating-point values to wider representations.
-def LDEBR : UnaryRRE<"ldebr", 0xB304, fpextend, FP64, FP32>;
-def LXEBR : UnaryRRE<"lxebr", 0xB306, fpextend, FP128, FP32>;
-def LXDBR : UnaryRRE<"lxdbr", 0xB305, fpextend, FP128, FP64>;
+def LDEBR : UnaryRRE<"ldebr", 0xB304, fpextend, FP64, FP32>;
+def LXEBR : UnaryRRE<"lxebr", 0xB306, null_frag, FP128, FP32>;
+def LXDBR : UnaryRRE<"lxdbr", 0xB305, null_frag, FP128, FP64>;
+let Predicates = [FeatureNoVectorEnhancements1] in {
+ def : Pat<(f128 (fpextend (f32 FP32:$src))), (LXEBR FP32:$src)>;
+ def : Pat<(f128 (fpextend (f64 FP64:$src))), (LXDBR FP64:$src)>;
+}
// Extend memory floating-point values to wider representations.
def LDEB : UnaryRXE<"ldeb", 0xED04, extloadf32, FP64, 4>;
-def LXEB : UnaryRXE<"lxeb", 0xED06, extloadf32, FP128, 4>;
-def LXDB : UnaryRXE<"lxdb", 0xED05, extloadf64, FP128, 8>;
+def LXEB : UnaryRXE<"lxeb", 0xED06, null_frag, FP128, 4>;
+def LXDB : UnaryRXE<"lxdb", 0xED05, null_frag, FP128, 8>;
+let Predicates = [FeatureNoVectorEnhancements1] in {
+ def : Pat<(f128 (extloadf32 bdxaddr12only:$src)),
+ (LXEB bdxaddr12only:$src)>;
+ def : Pat<(f128 (extloadf64 bdxaddr12only:$src)),
+ (LXDB bdxaddr12only:$src)>;
+}
// Convert a signed integer register value to a floating-point one.
def CEFBR : UnaryRRE<"cefbr", 0xB394, sint_to_fp, FP32, GR32>;
@@ -426,16 +452,18 @@ def : Pat<(fmul (f64 (fpextend FP32:$src1)),
// f128 multiplication of two FP64 registers.
def MXDBR : BinaryRRE<"mxdbr", 0xB307, null_frag, FP128, FP64>;
-def : Pat<(fmul (f128 (fpextend FP64:$src1)), (f128 (fpextend FP64:$src2))),
- (MXDBR (INSERT_SUBREG (f128 (IMPLICIT_DEF)),
- FP64:$src1, subreg_h64), FP64:$src2)>;
+let Predicates = [FeatureNoVectorEnhancements1] in
+ def : Pat<(fmul (f128 (fpextend FP64:$src1)), (f128 (fpextend FP64:$src2))),
+ (MXDBR (INSERT_SUBREG (f128 (IMPLICIT_DEF)),
+ FP64:$src1, subreg_h64), FP64:$src2)>;
// f128 multiplication of an FP64 register and an f64 memory.
def MXDB : BinaryRXE<"mxdb", 0xED07, null_frag, FP128, load, 8>;
-def : Pat<(fmul (f128 (fpextend FP64:$src1)),
- (f128 (extloadf64 bdxaddr12only:$addr))),
- (MXDB (INSERT_SUBREG (f128 (IMPLICIT_DEF)), FP64:$src1, subreg_h64),
- bdxaddr12only:$addr)>;
+let Predicates = [FeatureNoVectorEnhancements1] in
+ def : Pat<(fmul (f128 (fpextend FP64:$src1)),
+ (f128 (extloadf64 bdxaddr12only:$addr))),
+ (MXDB (INSERT_SUBREG (f128 (IMPLICIT_DEF)), FP64:$src1, subreg_h64),
+ bdxaddr12only:$addr)>;
// Fused multiply-add.
def MAEBR : TernaryRRD<"maebr", 0xB30E, z_fma, FP32, FP32>;
diff --git a/lib/Target/SystemZ/SystemZInstrFormats.td b/lib/Target/SystemZ/SystemZInstrFormats.td
index 7620e06ccbc96..033a0a879d37d 100644
--- a/lib/Target/SystemZ/SystemZInstrFormats.td
+++ b/lib/Target/SystemZ/SystemZInstrFormats.td
@@ -1091,6 +1091,94 @@ class InstVRIe<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
let Inst{7-0} = op{7-0};
}
+class InstVRIf<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
+ : InstSystemZ<6, outs, ins, asmstr, pattern> {
+ field bits<48> Inst;
+ field bits<48> SoftFail = 0;
+
+ bits<5> V1;
+ bits<5> V2;
+ bits<5> V3;
+ bits<8> I4;
+ bits<4> M5;
+
+ let Inst{47-40} = op{15-8};
+ let Inst{39-36} = V1{3-0};
+ let Inst{35-32} = V2{3-0};
+ let Inst{31-28} = V3{3-0};
+ let Inst{27-24} = 0;
+ let Inst{23-20} = M5;
+ let Inst{19-12} = I4;
+ let Inst{11} = V1{4};
+ let Inst{10} = V2{4};
+ let Inst{9} = V3{4};
+ let Inst{8} = 0;
+ let Inst{7-0} = op{7-0};
+}
+
+class InstVRIg<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
+ : InstSystemZ<6, outs, ins, asmstr, pattern> {
+ field bits<48> Inst;
+ field bits<48> SoftFail = 0;
+
+ bits<5> V1;
+ bits<5> V2;
+ bits<8> I3;
+ bits<8> I4;
+ bits<4> M5;
+
+ let Inst{47-40} = op{15-8};
+ let Inst{39-36} = V1{3-0};
+ let Inst{35-32} = V2{3-0};
+ let Inst{31-24} = I4;
+ let Inst{23-20} = M5;
+ let Inst{19-12} = I3;
+ let Inst{11} = V1{4};
+ let Inst{10} = V2{4};
+ let Inst{9-8} = 0;
+ let Inst{7-0} = op{7-0};
+}
+
+class InstVRIh<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
+ : InstSystemZ<6, outs, ins, asmstr, pattern> {
+ field bits<48> Inst;
+ field bits<48> SoftFail = 0;
+
+ bits<5> V1;
+ bits<16> I2;
+ bits<4> I3;
+
+ let Inst{47-40} = op{15-8};
+ let Inst{39-36} = V1{3-0};
+ let Inst{35-32} = 0;
+ let Inst{31-16} = I2;
+ let Inst{15-12} = I3;
+ let Inst{11} = V1{4};
+ let Inst{10-8} = 0;
+ let Inst{7-0} = op{7-0};
+}
+
+class InstVRIi<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
+ : InstSystemZ<6, outs, ins, asmstr, pattern> {
+ field bits<48> Inst;
+ field bits<48> SoftFail = 0;
+
+ bits<5> V1;
+ bits<4> R2;
+ bits<8> I3;
+ bits<4> M4;
+
+ let Inst{47-40} = op{15-8};
+ let Inst{39-36} = V1{3-0};
+ let Inst{35-32} = R2;
+ let Inst{31-24} = 0;
+ let Inst{23-20} = M4;
+ let Inst{19-12} = I3;
+ let Inst{11} = V1{4};
+ let Inst{10-8} = 0;
+ let Inst{7-0} = op{7-0};
+}
+
// Depending on the instruction mnemonic, certain bits may be or-ed into
// the M4 value provided as explicit operand. These are passed as m4or.
class InstVRRa<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern,
@@ -1259,6 +1347,67 @@ class InstVRRf<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
let Inst{7-0} = op{7-0};
}
+class InstVRRg<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
+ : InstSystemZ<6, outs, ins, asmstr, pattern> {
+ field bits<48> Inst;
+ field bits<48> SoftFail = 0;
+
+ bits<5> V1;
+
+ let Inst{47-40} = op{15-8};
+ let Inst{39-36} = 0;
+ let Inst{35-32} = V1{3-0};
+ let Inst{31-12} = 0;
+ let Inst{11} = 0;
+ let Inst{10} = V1{4};
+ let Inst{9-8} = 0;
+ let Inst{7-0} = op{7-0};
+}
+
+class InstVRRh<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
+ : InstSystemZ<6, outs, ins, asmstr, pattern> {
+ field bits<48> Inst;
+ field bits<48> SoftFail = 0;
+
+ bits<5> V1;
+ bits<5> V2;
+ bits<4> M3;
+
+ let Inst{47-40} = op{15-8};
+ let Inst{39-36} = 0;
+ let Inst{35-32} = V1{3-0};
+ let Inst{31-28} = V2{3-0};
+ let Inst{27-24} = 0;
+ let Inst{23-20} = M3;
+ let Inst{19-12} = 0;
+ let Inst{11} = 0;
+ let Inst{10} = V1{4};
+ let Inst{9} = V2{4};
+ let Inst{8} = 0;
+ let Inst{7-0} = op{7-0};
+}
+
+class InstVRRi<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
+ : InstSystemZ<6, outs, ins, asmstr, pattern> {
+ field bits<48> Inst;
+ field bits<48> SoftFail = 0;
+
+ bits<4> R1;
+ bits<5> V2;
+ bits<4> M3;
+
+ let Inst{47-40} = op{15-8};
+ let Inst{39-36} = R1;
+ let Inst{35-32} = V2{3-0};
+ let Inst{31-24} = 0;
+ let Inst{23-20} = M3;
+ let Inst{19-12} = 0;
+ let Inst{11} = 0;
+ let Inst{10} = V2{4};
+ let Inst{9-8} = 0;
+ let Inst{7-0} = op{7-0};
+}
+
class InstVRSa<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
: InstSystemZ<6, outs, ins, asmstr, pattern> {
field bits<48> Inst;
@@ -1321,6 +1470,25 @@ class InstVRSc<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
let Inst{7-0} = op{7-0};
}
+class InstVRSd<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
+ : InstSystemZ<6, outs, ins, asmstr, pattern> {
+ field bits<48> Inst;
+ field bits<48> SoftFail = 0;
+
+ bits<5> V1;
+ bits<16> BD2;
+ bits<4> R3;
+
+ let Inst{47-40} = op{15-8};
+ let Inst{39-36} = 0;
+ let Inst{35-32} = R3;
+ let Inst{31-16} = BD2;
+ let Inst{15-12} = V1{3-0};
+ let Inst{11-9} = 0;
+ let Inst{8} = V1{4};
+ let Inst{7-0} = op{7-0};
+}
+
class InstVRV<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
: InstSystemZ<6, outs, ins, asmstr, pattern> {
field bits<48> Inst;
@@ -1358,6 +1526,24 @@ class InstVRX<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
let Inst{7-0} = op{7-0};
}
+class InstVSI<bits<16> op, dag outs, dag ins, string asmstr, list<dag> pattern>
+ : InstSystemZ<6, outs, ins, asmstr, pattern> {
+ field bits<48> Inst;
+ field bits<48> SoftFail = 0;
+
+ bits<5> V1;
+ bits<16> BD2;
+ bits<8> I3;
+
+ let Inst{47-40} = op{15-8};
+ let Inst{39-32} = I3;
+ let Inst{31-16} = BD2;
+ let Inst{15-12} = V1{3-0};
+ let Inst{11-9} = 0;
+ let Inst{8} = V1{4};
+ let Inst{7-0} = op{7-0};
+}
+
//===----------------------------------------------------------------------===//
// Instruction classes for .insn directives
//===----------------------------------------------------------------------===//
@@ -1910,6 +2096,25 @@ class FixedCondBranchRX<CondVariant V, string mnemonic, bits<8> opcode>
let M1 = V.ccmask;
}
+class CondBranchRXY<string mnemonic, bits<16> opcode>
+ : InstRXYb<opcode, (outs), (ins cond4:$valid, cond4:$M1, bdxaddr20only:$XBD2),
+ !subst("#", "${M1}", mnemonic)#"\t$XBD2", []> {
+ let CCMaskFirst = 1;
+}
+
+class AsmCondBranchRXY<string mnemonic, bits<16> opcode>
+ : InstRXYb<opcode, (outs), (ins imm32zx4:$M1, bdxaddr20only:$XBD2),
+ mnemonic#"\t$M1, $XBD2", []>;
+
+class FixedCondBranchRXY<CondVariant V, string mnemonic, bits<16> opcode,
+ SDPatternOperator operator = null_frag>
+ : InstRXYb<opcode, (outs), (ins bdxaddr20only:$XBD2),
+ !subst("#", V.suffix, mnemonic)#"\t$XBD2",
+ [(operator (load bdxaddr20only:$XBD2))]> {
+ let isAsmParserOnly = V.alternate;
+ let M1 = V.ccmask;
+}
+
class CmpBranchRIEa<string mnemonic, bits<16> opcode,
RegisterOperand cls, Immediate imm>
: InstRIEa<opcode, (outs), (ins cls:$R1, imm:$I2, cond4:$M3),
@@ -2272,6 +2477,24 @@ class StoreLengthVRSb<string mnemonic, bits<16> opcode,
let AccessBytes = bytes;
}
+class StoreLengthVRSd<string mnemonic, bits<16> opcode,
+ SDPatternOperator operator, bits<5> bytes>
+ : InstVRSd<opcode, (outs), (ins VR128:$V1, GR32:$R3, bdaddr12only:$BD2),
+ mnemonic#"\t$V1, $R3, $BD2",
+ [(operator VR128:$V1, GR32:$R3, bdaddr12only:$BD2)]> {
+ let mayStore = 1;
+ let AccessBytes = bytes;
+}
+
+class StoreLengthVSI<string mnemonic, bits<16> opcode,
+ SDPatternOperator operator, bits<5> bytes>
+ : InstVSI<opcode, (outs), (ins VR128:$V1, bdaddr12only:$BD2, imm32zx8:$I3),
+ mnemonic#"\t$V1, $BD2, $I3",
+ [(operator VR128:$V1, imm32zx8:$I3, bdaddr12only:$BD2)]> {
+ let mayStore = 1;
+ let AccessBytes = bytes;
+}
+
class StoreMultipleRS<string mnemonic, bits<8> opcode, RegisterOperand cls,
AddressingMode mode = bdaddr12only>
: InstRSa<opcode, (outs), (ins cls:$R1, cls:$R3, mode:$BD2),
@@ -2700,6 +2923,11 @@ class SideEffectBinaryRX<string mnemonic, bits<8> opcode,
: InstRXa<opcode, (outs), (ins cls:$R1, bdxaddr12only:$XBD2),
mnemonic##"\t$R1, $XBD2", []>;
+class SideEffectBinaryRXY<string mnemonic, bits<16> opcode,
+ RegisterOperand cls>
+ : InstRXYa<opcode, (outs), (ins cls:$R1, bdxaddr20only:$XBD2),
+ mnemonic##"\t$R1, $XBD2", []>;
+
class SideEffectBinaryRILPC<string mnemonic, bits<12> opcode,
RegisterOperand cls>
: InstRILb<opcode, (outs), (ins cls:$R1, pcrel32:$RI2),
@@ -3188,6 +3416,11 @@ class BinaryVRIeFloatGeneric<string mnemonic, bits<16> opcode>
(ins VR128:$V2, imm32zx12:$I3, imm32zx4:$M4, imm32zx4:$M5),
mnemonic#"\t$V1, $V2, $I3, $M4, $M5", []>;
+class BinaryVRIh<string mnemonic, bits<16> opcode>
+ : InstVRIh<opcode, (outs VR128:$V1),
+ (ins imm32zx16:$I2, imm32zx4:$I3),
+ mnemonic#"\t$V1, $I2, $I3", []>;
+
class BinaryVRRa<string mnemonic, bits<16> opcode, SDPatternOperator operator,
TypedReg tr1, TypedReg tr2, bits<4> type = 0, bits<4> m4 = 0>
: InstVRRa<opcode, (outs tr1.op:$V1), (ins tr2.op:$V2, imm32zx4:$M5),
@@ -3316,6 +3549,10 @@ class BinaryVRRf<string mnemonic, bits<16> opcode, SDPatternOperator operator,
mnemonic#"\t$V1, $R2, $R3",
[(set tr.op:$V1, (tr.vt (operator GR64:$R2, GR64:$R3)))]>;
+class BinaryVRRi<string mnemonic, bits<16> opcode, RegisterOperand cls>
+ : InstVRRi<opcode, (outs cls:$R1), (ins VR128:$V2, imm32zx4:$M3),
+ mnemonic#"\t$R1, $V2, $M3", []>;
+
class BinaryVRSa<string mnemonic, bits<16> opcode, SDPatternOperator operator,
TypedReg tr1, TypedReg tr2, bits<4> type>
: InstVRSa<opcode, (outs tr1.op:$V1), (ins tr2.op:$V3, shift12only:$BD2),
@@ -3353,6 +3590,15 @@ class BinaryVRScGeneric<string mnemonic, bits<16> opcode>
(ins VR128:$V3, shift12only:$BD2, imm32zx4: $M4),
mnemonic#"\t$R1, $V3, $BD2, $M4", []>;
+class BinaryVRSd<string mnemonic, bits<16> opcode, SDPatternOperator operator,
+ bits<5> bytes>
+ : InstVRSd<opcode, (outs VR128:$V1), (ins GR32:$R3, bdaddr12only:$BD2),
+ mnemonic#"\t$V1, $R3, $BD2",
+ [(set VR128:$V1, (operator GR32:$R3, bdaddr12only:$BD2))]> {
+ let mayLoad = 1;
+ let AccessBytes = bytes;
+}
+
class BinaryVRX<string mnemonic, bits<16> opcode, SDPatternOperator operator,
TypedReg tr, bits<5> bytes>
: InstVRX<opcode, (outs VR128:$V1), (ins bdxaddr12only:$XBD2, imm32zx4:$M3),
@@ -3398,6 +3644,15 @@ class StoreBinaryRSL<string mnemonic, bits<16> opcode, RegisterOperand cls>
let mayStore = 1;
}
+class BinaryVSI<string mnemonic, bits<16> opcode, SDPatternOperator operator,
+ bits<5> bytes>
+ : InstVSI<opcode, (outs VR128:$V1), (ins bdaddr12only:$BD2, imm32zx8:$I3),
+ mnemonic#"\t$V1, $BD2, $I3",
+ [(set VR128:$V1, (operator imm32zx8:$I3, bdaddr12only:$BD2))]> {
+ let mayLoad = 1;
+ let AccessBytes = bytes;
+}
+
class StoreBinaryVRV<string mnemonic, bits<16> opcode, bits<5> bytes,
Immediate index>
: InstVRV<opcode, (outs), (ins VR128:$V1, bdvaddr12only:$VBD2, index:$M3),
@@ -3625,6 +3880,12 @@ class CompareVRRaFloatGeneric<string mnemonic, bits<16> opcode>
let M5 = 0;
}
+class CompareVRRh<string mnemonic, bits<16> opcode>
+ : InstVRRh<opcode, (outs), (ins VR128:$V1, VR128:$V2, imm32zx4:$M3),
+ mnemonic#"\t$V1, $V2, $M3", []> {
+ let isCompare = 1;
+}
+
class TestRXE<string mnemonic, bits<16> opcode, SDPatternOperator operator,
RegisterOperand cls>
: InstRXE<opcode, (outs), (ins cls:$R1, bdxaddr12only:$XBD2),
@@ -3639,6 +3900,10 @@ class TestRSL<string mnemonic, bits<16> opcode>
let mayLoad = 1;
}
+class TestVRRg<string mnemonic, bits<16> opcode>
+ : InstVRRg<opcode, (outs), (ins VR128:$V1),
+ mnemonic#"\t$V1", []>;
+
class SideEffectTernarySSc<string mnemonic, bits<8> opcode>
: InstSSc<opcode, (outs), (ins bdladdr12onlylen4:$BDL1,
shift12only:$BD2, imm32zx4:$I3),
@@ -3842,6 +4107,11 @@ class TernaryVRId<string mnemonic, bits<16> opcode, SDPatternOperator operator,
let M5 = type;
}
+class TernaryVRIi<string mnemonic, bits<16> opcode, RegisterOperand cls>
+ : InstVRIi<opcode, (outs VR128:$V1),
+ (ins cls:$R2, imm32zx8:$I3, imm32zx4:$M4),
+ mnemonic#"\t$V1, $R2, $I3, $M4", []>;
+
class TernaryVRRa<string mnemonic, bits<16> opcode, SDPatternOperator operator,
TypedReg tr1, TypedReg tr2, bits<4> type, bits<4> m4or>
: InstVRRa<opcode, (outs tr1.op:$V1),
@@ -3914,6 +4184,25 @@ class TernaryVRRc<string mnemonic, bits<16> opcode, SDPatternOperator operator,
let M6 = 0;
}
+class TernaryVRRcFloat<string mnemonic, bits<16> opcode,
+ SDPatternOperator operator, TypedReg tr1, TypedReg tr2,
+ bits<4> type = 0, bits<4> m5 = 0>
+ : InstVRRc<opcode, (outs tr1.op:$V1),
+ (ins tr2.op:$V2, tr2.op:$V3, imm32zx4:$M6),
+ mnemonic#"\t$V1, $V2, $V3, $M6",
+ [(set tr1.op:$V1, (tr1.vt (operator (tr2.vt tr2.op:$V2),
+ (tr2.vt tr2.op:$V3),
+ imm32zx4:$M6)))]> {
+ let M4 = type;
+ let M5 = m5;
+}
+
+class TernaryVRRcFloatGeneric<string mnemonic, bits<16> opcode>
+ : InstVRRc<opcode, (outs VR128:$V1),
+ (ins VR128:$V2, VR128:$V3, imm32zx4:$M4, imm32zx4:$M5,
+ imm32zx4:$M6),
+ mnemonic#"\t$V1, $V2, $V3, $M4, $M5, $M6", []>;
+
class TernaryVRRd<string mnemonic, bits<16> opcode, SDPatternOperator operator,
TypedReg tr1, TypedReg tr2, bits<4> type = 0>
: InstVRRd<opcode, (outs tr1.op:$V1),
@@ -4019,20 +4308,38 @@ class QuaternaryVRIdGeneric<string mnemonic, bits<16> opcode>
let DisableEncoding = "$V1src";
}
+class QuaternaryVRIf<string mnemonic, bits<16> opcode>
+ : InstVRIf<opcode, (outs VR128:$V1),
+ (ins VR128:$V2, VR128:$V3,
+ imm32zx8:$I4, imm32zx4:$M5),
+ mnemonic#"\t$V1, $V2, $V3, $I4, $M5", []>;
+
+class QuaternaryVRIg<string mnemonic, bits<16> opcode>
+ : InstVRIg<opcode, (outs VR128:$V1),
+ (ins VR128:$V2, imm32zx8:$I3,
+ imm32zx8:$I4, imm32zx4:$M5),
+ mnemonic#"\t$V1, $V2, $I3, $I4, $M5", []>;
+
class QuaternaryVRRd<string mnemonic, bits<16> opcode,
SDPatternOperator operator, TypedReg tr1, TypedReg tr2,
- bits<4> type, SDPatternOperator m6mask, bits<4> m6or>
+ TypedReg tr3, TypedReg tr4, bits<4> type,
+ SDPatternOperator m6mask = imm32zx4, bits<4> m6or = 0>
: InstVRRd<opcode, (outs tr1.op:$V1),
- (ins tr2.op:$V2, tr2.op:$V3, tr2.op:$V4, m6mask:$M6),
+ (ins tr2.op:$V2, tr3.op:$V3, tr4.op:$V4, m6mask:$M6),
mnemonic#"\t$V1, $V2, $V3, $V4, $M6",
[(set tr1.op:$V1, (tr1.vt (operator (tr2.vt tr2.op:$V2),
- (tr2.vt tr2.op:$V3),
- (tr2.vt tr2.op:$V4),
+ (tr3.vt tr3.op:$V3),
+ (tr4.vt tr4.op:$V4),
m6mask:$M6)))],
m6or> {
let M5 = type;
}
+class QuaternaryVRRdGeneric<string mnemonic, bits<16> opcode>
+ : InstVRRd<opcode, (outs VR128:$V1),
+ (ins VR128:$V2, VR128:$V3, VR128:$V4, imm32zx4:$M5, imm32zx4:$M6),
+ mnemonic#"\t$V1, $V2, $V3, $V4, $M5, $M6", []>;
+
// Declare a pair of instructions, one which sets CC and one which doesn't.
// The CC-setting form ends with "S" and sets the low bit of M6.
// Also create aliases to make use of M6 operand optional in assembler.
@@ -4041,13 +4348,15 @@ multiclass QuaternaryOptVRRdSPair<string mnemonic, bits<16> opcode,
SDPatternOperator operator_cc,
TypedReg tr1, TypedReg tr2, bits<4> type,
bits<4> modifier = 0> {
- def "" : QuaternaryVRRd<mnemonic, opcode, operator, tr1, tr2, type,
+ def "" : QuaternaryVRRd<mnemonic, opcode, operator,
+ tr1, tr2, tr2, tr2, type,
imm32zx4even, !and (modifier, 14)>;
def : InstAlias<mnemonic#"\t$V1, $V2, $V3, $V4",
(!cast<Instruction>(NAME) tr1.op:$V1, tr2.op:$V2,
tr2.op:$V3, tr2.op:$V4, 0)>;
let Defs = [CC] in
- def S : QuaternaryVRRd<mnemonic##"s", opcode, operator_cc, tr1, tr2, type,
+ def S : QuaternaryVRRd<mnemonic##"s", opcode, operator_cc,
+ tr1, tr2, tr2, tr2, type,
imm32zx4even, !add (!and (modifier, 14), 1)>;
def : InstAlias<mnemonic#"s\t$V1, $V2, $V3, $V4",
(!cast<Instruction>(NAME#"S") tr1.op:$V1, tr2.op:$V2,
@@ -4055,10 +4364,7 @@ multiclass QuaternaryOptVRRdSPair<string mnemonic, bits<16> opcode,
}
multiclass QuaternaryOptVRRdSPairGeneric<string mnemonic, bits<16> opcode> {
- def "" : InstVRRd<opcode, (outs VR128:$V1),
- (ins VR128:$V2, VR128:$V3, VR128:$V4,
- imm32zx4:$M5, imm32zx4:$M6),
- mnemonic#"\t$V1, $V2, $V3, $V4, $M5, $M6", []>;
+ def "" : QuaternaryVRRdGeneric<mnemonic, opcode>;
def : InstAlias<mnemonic#"\t$V1, $V2, $V3, $V4, $M5",
(!cast<Instruction>(NAME) VR128:$V1, VR128:$V2, VR128:$V3,
VR128:$V4, imm32zx4:$M5, 0)>;
@@ -4366,10 +4672,10 @@ class RotateSelectRIEfPseudo<RegisterOperand cls1, RegisterOperand cls2>
// Implements "$dst = $cc & (8 >> CC) ? $src1 : $src2", where CC is
// the value of the PSW's 2-bit condition code field.
-class SelectWrapper<RegisterOperand cls>
+class SelectWrapper<ValueType vt, RegisterOperand cls>
: Pseudo<(outs cls:$dst),
(ins cls:$src1, cls:$src2, imm32zx4:$valid, imm32zx4:$cc),
- [(set cls:$dst, (z_select_ccmask cls:$src1, cls:$src2,
+ [(set (vt cls:$dst), (z_select_ccmask cls:$src1, cls:$src2,
imm32zx4:$valid, imm32zx4:$cc))]> {
let usesCustomInserter = 1;
// Although the instructions used by these nodes do not in themselves
diff --git a/lib/Target/SystemZ/SystemZInstrInfo.cpp b/lib/Target/SystemZ/SystemZInstrInfo.cpp
index 66a5ff12be464..4533f4fdf21ae 100644
--- a/lib/Target/SystemZ/SystemZInstrInfo.cpp
+++ b/lib/Target/SystemZ/SystemZInstrInfo.cpp
@@ -869,6 +869,37 @@ void SystemZInstrInfo::copyPhysReg(MachineBasicBlock &MBB,
return;
}
+ // Move 128-bit floating-point values between VR128 and FP128.
+ if (SystemZ::VR128BitRegClass.contains(DestReg) &&
+ SystemZ::FP128BitRegClass.contains(SrcReg)) {
+ unsigned SrcRegHi =
+ RI.getMatchingSuperReg(RI.getSubReg(SrcReg, SystemZ::subreg_h64),
+ SystemZ::subreg_r64, &SystemZ::VR128BitRegClass);
+ unsigned SrcRegLo =
+ RI.getMatchingSuperReg(RI.getSubReg(SrcReg, SystemZ::subreg_l64),
+ SystemZ::subreg_r64, &SystemZ::VR128BitRegClass);
+
+ BuildMI(MBB, MBBI, DL, get(SystemZ::VMRHG), DestReg)
+ .addReg(SrcRegHi, getKillRegState(KillSrc))
+ .addReg(SrcRegLo, getKillRegState(KillSrc));
+ return;
+ }
+ if (SystemZ::FP128BitRegClass.contains(DestReg) &&
+ SystemZ::VR128BitRegClass.contains(SrcReg)) {
+ unsigned DestRegHi =
+ RI.getMatchingSuperReg(RI.getSubReg(DestReg, SystemZ::subreg_h64),
+ SystemZ::subreg_r64, &SystemZ::VR128BitRegClass);
+ unsigned DestRegLo =
+ RI.getMatchingSuperReg(RI.getSubReg(DestReg, SystemZ::subreg_l64),
+ SystemZ::subreg_r64, &SystemZ::VR128BitRegClass);
+
+ if (DestRegHi != SrcReg)
+ copyPhysReg(MBB, MBBI, DL, DestRegHi, SrcReg, false);
+ BuildMI(MBB, MBBI, DL, get(SystemZ::VREPG), DestRegLo)
+ .addReg(SrcReg, getKillRegState(KillSrc)).addImm(1);
+ return;
+ }
+
// Everything else needs only one instruction.
unsigned Opcode;
if (SystemZ::GR64BitRegClass.contains(DestReg, SrcReg))
@@ -1434,6 +1465,7 @@ SystemZII::Branch
SystemZInstrInfo::getBranchInfo(const MachineInstr &MI) const {
switch (MI.getOpcode()) {
case SystemZ::BR:
+ case SystemZ::BI:
case SystemZ::J:
case SystemZ::JG:
return SystemZII::Branch(SystemZII::BranchNormal, SystemZ::CCMASK_ANY,
diff --git a/lib/Target/SystemZ/SystemZInstrInfo.td b/lib/Target/SystemZ/SystemZInstrInfo.td
index 4569be7602e45..f64c0d15ef83b 100644
--- a/lib/Target/SystemZ/SystemZInstrInfo.td
+++ b/lib/Target/SystemZ/SystemZInstrInfo.td
@@ -48,6 +48,8 @@ let isBranch = 1, isTerminator = 1, Uses = [CC] in {
let isIndirectBranch = 1 in {
def BC : CondBranchRX<"b#", 0x47>;
def BCR : CondBranchRR<"b#r", 0x07>;
+ def BIC : CondBranchRXY<"bi#", 0xe347>,
+ Requires<[FeatureMiscellaneousExtensions2]>;
}
}
@@ -58,6 +60,8 @@ let isBranch = 1, isTerminator = 1, Uses = [CC] in {
let isIndirectBranch = 1 in {
def BCAsm : AsmCondBranchRX<"bc", 0x47>;
def BCRAsm : AsmCondBranchRR<"bcr", 0x07>;
+ def BICAsm : AsmCondBranchRXY<"bic", 0xe347>,
+ Requires<[FeatureMiscellaneousExtensions2]>;
}
// Define AsmParser extended mnemonics for each general condition-code mask
@@ -69,6 +73,8 @@ let isBranch = 1, isTerminator = 1, Uses = [CC] in {
let isIndirectBranch = 1 in {
def BAsm#V : FixedCondBranchRX <CV<V>, "b#", 0x47>;
def BRAsm#V : FixedCondBranchRR <CV<V>, "b#r", 0x07>;
+ def BIAsm#V : FixedCondBranchRXY<CV<V>, "bi#", 0xe347>,
+ Requires<[FeatureMiscellaneousExtensions2]>;
}
}
}
@@ -81,6 +87,8 @@ let isBranch = 1, isTerminator = 1, isBarrier = 1 in {
let isIndirectBranch = 1 in {
def B : FixedCondBranchRX<CondAlways, "b", 0x47>;
def BR : FixedCondBranchRR<CondAlways, "br", 0x07, brind>;
+ def BI : FixedCondBranchRXY<CondAlways, "bi", 0xe347, brind>,
+ Requires<[FeatureMiscellaneousExtensions2]>;
}
}
@@ -316,9 +324,9 @@ let isReturn = 1, isTerminator = 1, hasCtrlDep = 1 in {
// Select instructions
//===----------------------------------------------------------------------===//
-def Select32Mux : SelectWrapper<GRX32>, Requires<[FeatureHighWord]>;
-def Select32 : SelectWrapper<GR32>;
-def Select64 : SelectWrapper<GR64>;
+def Select32Mux : SelectWrapper<i32, GRX32>, Requires<[FeatureHighWord]>;
+def Select32 : SelectWrapper<i32, GR32>;
+def Select64 : SelectWrapper<i64, GR64>;
// We don't define 32-bit Mux stores if we don't have STOCFH, because the
// low-only STOC should then always be used if possible.
@@ -921,6 +929,8 @@ let Defs = [CC], CCValues = 0xF, CompareZeroCCMask = 0x8 in {
// Addition of memory.
defm AH : BinaryRXPair<"ah", 0x4A, 0xE37A, add, GR32, asextloadi16, 2>;
defm A : BinaryRXPair<"a", 0x5A, 0xE35A, add, GR32, load, 4>;
+ def AGH : BinaryRXY<"agh", 0xE338, add, GR64, asextloadi16, 2>,
+ Requires<[FeatureMiscellaneousExtensions2]>;
def AGF : BinaryRXY<"agf", 0xE318, add, GR64, asextloadi32, 4>;
def AG : BinaryRXY<"ag", 0xE308, add, GR64, load, 8>;
@@ -1006,6 +1016,8 @@ let Defs = [CC], CCValues = 0xF, CompareZeroCCMask = 0x8 in {
// Subtraction of memory.
defm SH : BinaryRXPair<"sh", 0x4B, 0xE37B, sub, GR32, asextloadi16, 2>;
defm S : BinaryRXPair<"s", 0x5B, 0xE35B, sub, GR32, load, 4>;
+ def SGH : BinaryRXY<"sgh", 0xE339, sub, GR64, asextloadi16, 2>,
+ Requires<[FeatureMiscellaneousExtensions2]>;
def SGF : BinaryRXY<"sgf", 0xE319, sub, GR64, asextloadi32, 4>;
def SG : BinaryRXY<"sg", 0xE309, sub, GR64, load, 8>;
}
@@ -1207,6 +1219,15 @@ defm : RMWIByte<xor, bdaddr20pair, XIY>;
// Multiplication
//===----------------------------------------------------------------------===//
+// Multiplication of a register, setting the condition code. We prefer these
+// over MS(G)R if available, even though we cannot use the condition code,
+// since they are three-operand instructions.
+let Predicates = [FeatureMiscellaneousExtensions2],
+ Defs = [CC], isCommutable = 1 in {
+ def MSRKC : BinaryRRFa<"msrkc", 0xB9FD, mul, GR32, GR32, GR32>;
+ def MSGRKC : BinaryRRFa<"msgrkc", 0xB9ED, mul, GR64, GR64, GR64>;
+}
+
// Multiplication of a register.
let isCommutable = 1 in {
def MSR : BinaryRRE<"msr", 0xB252, mul, GR32, GR32>;
@@ -1226,21 +1247,37 @@ def MSGFI : BinaryRIL<"msgfi", 0xC20, mul, GR64, imm64sx32>;
// Multiplication of memory.
defm MH : BinaryRXPair<"mh", 0x4C, 0xE37C, mul, GR32, asextloadi16, 2>;
defm MS : BinaryRXPair<"ms", 0x71, 0xE351, mul, GR32, load, 4>;
+def MGH : BinaryRXY<"mgh", 0xE33C, mul, GR64, asextloadi16, 2>,
+ Requires<[FeatureMiscellaneousExtensions2]>;
def MSGF : BinaryRXY<"msgf", 0xE31C, mul, GR64, asextloadi32, 4>;
def MSG : BinaryRXY<"msg", 0xE30C, mul, GR64, load, 8>;
+// Multiplication of memory, setting the condition code.
+let Predicates = [FeatureMiscellaneousExtensions2], Defs = [CC] in {
+ def MSC : BinaryRXY<"msc", 0xE353, null_frag, GR32, load, 4>;
+ def MSGC : BinaryRXY<"msgc", 0xE383, null_frag, GR64, load, 8>;
+}
+
// Multiplication of a register, producing two results.
-def MR : BinaryRR <"mr", 0x1C, null_frag, GR128, GR32>;
+def MR : BinaryRR <"mr", 0x1C, null_frag, GR128, GR32>;
+def MGRK : BinaryRRFa<"mgrk", 0xB9EC, null_frag, GR128, GR64, GR64>,
+ Requires<[FeatureMiscellaneousExtensions2]>;
def MLR : BinaryRRE<"mlr", 0xB996, null_frag, GR128, GR32>;
def MLGR : BinaryRRE<"mlgr", 0xB986, null_frag, GR128, GR64>;
+def : Pat<(z_smul_lohi GR64:$src1, GR64:$src2),
+ (MGRK GR64:$src1, GR64:$src2)>;
def : Pat<(z_umul_lohi GR64:$src1, GR64:$src2),
(MLGR (AEXT128 GR64:$src1), GR64:$src2)>;
// Multiplication of memory, producing two results.
def M : BinaryRX <"m", 0x5C, null_frag, GR128, load, 4>;
def MFY : BinaryRXY<"mfy", 0xE35C, null_frag, GR128, load, 4>;
+def MG : BinaryRXY<"mg", 0xE384, null_frag, GR128, load, 8>,
+ Requires<[FeatureMiscellaneousExtensions2]>;
def ML : BinaryRXY<"ml", 0xE396, null_frag, GR128, load, 4>;
def MLG : BinaryRXY<"mlg", 0xE386, null_frag, GR128, load, 8>;
+def : Pat<(z_smul_lohi GR64:$src1, (i64 (load bdxaddr20only:$src2))),
+ (MG (AEXT128 GR64:$src1), bdxaddr20only:$src2)>;
def : Pat<(z_umul_lohi GR64:$src1, (i64 (load bdxaddr20only:$src2))),
(MLG (AEXT128 GR64:$src1), bdxaddr20only:$src2)>;
@@ -1765,8 +1802,29 @@ let mayLoad = 1, mayStore = 1, Uses = [R0L, R1D], Defs = [CC] in {
GR128, GR128, GR128>;
def PCC : SideEffectInherentRRE<"pcc", 0xB92C>;
}
+
let Predicates = [FeatureMessageSecurityAssist5] in
- def PPNO : SideEffectBinaryMemMemRRE<"ppno", 0xB93C, GR128, GR128>;
+ def PPNO : SideEffectBinaryMemMemRRE<"ppno", 0xB93C, GR128, GR128>;
+ let Predicates = [FeatureMessageSecurityAssist7], isAsmParserOnly = 1 in
+ def PRNO : SideEffectBinaryMemMemRRE<"prno", 0xB93C, GR128, GR128>;
+
+ let Predicates = [FeatureMessageSecurityAssist8] in
+ def KMA : SideEffectTernaryMemMemMemRRFb<"kma", 0xB929,
+ GR128, GR128, GR128>;
+}
+
+//===----------------------------------------------------------------------===//
+// Guarded storage
+//===----------------------------------------------------------------------===//
+
+let Predicates = [FeatureGuardedStorage] in {
+ def LGG : UnaryRXY<"lgg", 0xE34C, null_frag, GR64, 8>;
+ def LLGFSG : UnaryRXY<"llgfsg", 0xE348, null_frag, GR64, 4>;
+
+ let mayLoad = 1 in
+ def LGSC : SideEffectBinaryRXY<"lgsc", 0xE34D, GR64>;
+ let mayStore = 1 in
+ def STGSC : SideEffectBinaryRXY<"stgsc", 0xE349, GR64>;
}
//===----------------------------------------------------------------------===//
diff --git a/lib/Target/SystemZ/SystemZInstrSystem.td b/lib/Target/SystemZ/SystemZInstrSystem.td
index a9803c2d83e9f..0112ebf1eb10c 100644
--- a/lib/Target/SystemZ/SystemZInstrSystem.td
+++ b/lib/Target/SystemZ/SystemZInstrSystem.td
@@ -126,6 +126,10 @@ let hasSideEffects = 1, Defs = [CC] in
let Predicates = [FeatureResetReferenceBitsMultiple], hasSideEffects = 1 in
def RRBM : UnaryRRE<"rrbm", 0xB9AE, null_frag, GR64, GR64>;
+// Insert reference bits multiple.
+let Predicates = [FeatureInsertReferenceBitsMultiple], hasSideEffects = 1 in
+ def IRBM : UnaryRRE<"irbm", 0xB9AC, null_frag, GR64, GR64>;
+
// Perform frame management function.
let hasSideEffects = 1 in
def PFMF : SideEffectBinaryMemRRE<"pfmf", 0xB9AF, GR32, GR64>;
diff --git a/lib/Target/SystemZ/SystemZInstrVector.td b/lib/Target/SystemZ/SystemZInstrVector.td
index 0158fe6aec08d..c9a02d9c80821 100644
--- a/lib/Target/SystemZ/SystemZInstrVector.td
+++ b/lib/Target/SystemZ/SystemZInstrVector.td
@@ -14,7 +14,7 @@
let Predicates = [FeatureVector] in {
// Register move.
def VLR : UnaryVRRa<"vlr", 0xE756, null_frag, v128any, v128any>;
- def VLR32 : UnaryAliasVRR<null_frag, v32eb, v32eb>;
+ def VLR32 : UnaryAliasVRR<null_frag, v32sb, v32sb>;
def VLR64 : UnaryAliasVRR<null_frag, v64db, v64db>;
// Load GR from VR element.
@@ -141,7 +141,7 @@ let Predicates = [FeatureVector] in {
// LEY and LDY offer full 20-bit displacement fields. It's often better
// to use those instructions rather than force a 20-bit displacement
// into a GPR temporary.
- def VL32 : UnaryAliasVRX<load, v32eb, bdxaddr12pair>;
+ def VL32 : UnaryAliasVRX<load, v32sb, bdxaddr12pair>;
def VL64 : UnaryAliasVRX<load, v64db, bdxaddr12pair>;
// Load logical element and zero.
@@ -154,6 +154,11 @@ let Predicates = [FeatureVector] in {
(VLLEZF bdxaddr12only:$addr)>;
def : Pat<(v2f64 (z_vllezf64 bdxaddr12only:$addr)),
(VLLEZG bdxaddr12only:$addr)>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VLLEZLF : UnaryVRX<"vllezlf", 0xE704, z_vllezli32, v128f, 4, 6>;
+ def : Pat<(v4f32 (z_vllezlf32 bdxaddr12only:$addr)),
+ (VLLEZLF bdxaddr12only:$addr)>;
+ }
// Load element.
def VLEB : TernaryVRX<"vleb", 0xE700, z_vlei8, v128b, v128b, 1, imm32zx4>;
@@ -170,6 +175,13 @@ let Predicates = [FeatureVector] in {
def VGEG : TernaryVRV<"vgeg", 0xE712, 8, imm32zx1>;
}
+let Predicates = [FeatureVectorPackedDecimal] in {
+ // Load rightmost with length. The number of loaded bytes is only known
+ // at run time.
+ def VLRL : BinaryVSI<"vlrl", 0xE635, int_s390_vlrl, 0>;
+ def VLRLR : BinaryVRSd<"vlrlr", 0xE637, int_s390_vlrl, 0>;
+}
+
// Use replicating loads if we're inserting a single element into an
// undefined vector. This avoids a false dependency on the previous
// register contents.
@@ -219,7 +231,7 @@ let Predicates = [FeatureVector] in {
// STEY and STDY offer full 20-bit displacement fields. It's often better
// to use those instructions rather than force a 20-bit displacement
// into a GPR temporary.
- def VST32 : StoreAliasVRX<store, v32eb, bdxaddr12pair>;
+ def VST32 : StoreAliasVRX<store, v32sb, bdxaddr12pair>;
def VST64 : StoreAliasVRX<store, v64db, bdxaddr12pair>;
// Scatter element.
@@ -227,6 +239,13 @@ let Predicates = [FeatureVector] in {
def VSCEG : StoreBinaryVRV<"vsceg", 0xE71A, 8, imm32zx1>;
}
+let Predicates = [FeatureVectorPackedDecimal] in {
+ // Store rightmost with length. The number of stored bytes is only known
+ // at run time.
+ def VSTRL : StoreLengthVSI<"vstrl", 0xE63D, int_s390_vstrl, 0>;
+ def VSTRLR : StoreLengthVRSd<"vstrlr", 0xE63F, int_s390_vstrl, 0>;
+}
+
//===----------------------------------------------------------------------===//
// Selects and permutes
//===----------------------------------------------------------------------===//
@@ -256,6 +275,10 @@ let Predicates = [FeatureVector] in {
// Permute doubleword immediate.
def VPDI : TernaryVRRc<"vpdi", 0xE784, z_permute_dwords, v128g, v128g>;
+ // Bit Permute.
+ let Predicates = [FeatureVectorEnhancements1] in
+ def VBPERM : BinaryVRRc<"vbperm", 0xE785, int_s390_vbperm, v128g, v128b>;
+
// Replicate.
def VREP: BinaryVRIcGeneric<"vrep", 0xE74D>;
def VREPB : BinaryVRIc<"vrepb", 0xE74D, z_splat, v128b, v128b, 0>;
@@ -424,6 +447,10 @@ let Predicates = [FeatureVector] in {
def VCTZF : UnaryVRRa<"vctzf", 0xE752, cttz, v128f, v128f, 2>;
def VCTZG : UnaryVRRa<"vctzg", 0xE752, cttz, v128g, v128g, 3>;
+ // Not exclusive or.
+ let Predicates = [FeatureVectorEnhancements1] in
+ def VNX : BinaryVRRc<"vnx", 0xE76C, null_frag, v128any, v128any>;
+
// Exclusive or.
def VX : BinaryVRRc<"vx", 0xE76D, null_frag, v128any, v128any>;
@@ -567,6 +594,17 @@ let Predicates = [FeatureVector] in {
def VMLOH : BinaryVRRc<"vmloh", 0xE7A5, int_s390_vmloh, v128f, v128h, 1>;
def VMLOF : BinaryVRRc<"vmlof", 0xE7A5, int_s390_vmlof, v128g, v128f, 2>;
+ // Multiply sum logical.
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VMSL : QuaternaryVRRdGeneric<"vmsl", 0xE7B8>;
+ def VMSLG : QuaternaryVRRd<"vmslg", 0xE7B8, int_s390_vmslg,
+ v128q, v128g, v128g, v128q, 3>;
+ }
+
+ // Nand.
+ let Predicates = [FeatureVectorEnhancements1] in
+ def VNN : BinaryVRRc<"vnn", 0xE76E, null_frag, v128any, v128any>;
+
// Nor.
def VNO : BinaryVRRc<"vno", 0xE76B, null_frag, v128any, v128any>;
def : InstAlias<"vnot\t$V1, $V2", (VNO VR128:$V1, VR128:$V2, VR128:$V2), 0>;
@@ -574,9 +612,19 @@ let Predicates = [FeatureVector] in {
// Or.
def VO : BinaryVRRc<"vo", 0xE76A, null_frag, v128any, v128any>;
+ // Or with complement.
+ let Predicates = [FeatureVectorEnhancements1] in
+ def VOC : BinaryVRRc<"voc", 0xE76F, null_frag, v128any, v128any>;
+
// Population count.
def VPOPCT : UnaryVRRaGeneric<"vpopct", 0xE750>;
def : Pat<(v16i8 (z_popcnt VR128:$x)), (VPOPCT VR128:$x, 0)>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VPOPCTB : UnaryVRRa<"vpopctb", 0xE750, ctpop, v128b, v128b, 0>;
+ def VPOPCTH : UnaryVRRa<"vpopcth", 0xE750, ctpop, v128h, v128h, 1>;
+ def VPOPCTF : UnaryVRRa<"vpopctf", 0xE750, ctpop, v128f, v128f, 2>;
+ def VPOPCTG : UnaryVRRa<"vpopctg", 0xE750, ctpop, v128g, v128g, 3>;
+ }
// Element rotate left logical (with vector shift amount).
def VERLLV : BinaryVRRcGeneric<"verllv", 0xE773>;
@@ -724,6 +772,14 @@ multiclass BitwiseVectorOps<ValueType type> {
(VNO VR128:$x, VR128:$y)>;
def : Pat<(type (z_vnot VR128:$x)), (VNO VR128:$x, VR128:$x)>;
}
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def : Pat<(type (z_vnot (xor VR128:$x, VR128:$y))),
+ (VNX VR128:$x, VR128:$y)>;
+ def : Pat<(type (z_vnot (and VR128:$x, VR128:$y))),
+ (VNN VR128:$x, VR128:$y)>;
+ def : Pat<(type (or VR128:$x, (z_vnot VR128:$y))),
+ (VOC VR128:$x, VR128:$y)>;
+ }
}
defm : BitwiseVectorOps<v16i8>;
@@ -879,6 +935,11 @@ let Predicates = [FeatureVector] in {
def VFA : BinaryVRRcFloatGeneric<"vfa", 0xE7E3>;
def VFADB : BinaryVRRc<"vfadb", 0xE7E3, fadd, v128db, v128db, 3, 0>;
def WFADB : BinaryVRRc<"wfadb", 0xE7E3, fadd, v64db, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFASB : BinaryVRRc<"vfasb", 0xE7E3, fadd, v128sb, v128sb, 2, 0>;
+ def WFASB : BinaryVRRc<"wfasb", 0xE7E3, fadd, v32sb, v32sb, 2, 8>;
+ def WFAXB : BinaryVRRc<"wfaxb", 0xE7E3, fadd, v128xb, v128xb, 4, 8>;
+ }
// Convert from fixed 64-bit.
def VCDG : TernaryVRRaFloatGeneric<"vcdg", 0xE7C3>;
@@ -910,6 +971,11 @@ let Predicates = [FeatureVector] in {
def VFD : BinaryVRRcFloatGeneric<"vfd", 0xE7E5>;
def VFDDB : BinaryVRRc<"vfddb", 0xE7E5, fdiv, v128db, v128db, 3, 0>;
def WFDDB : BinaryVRRc<"wfddb", 0xE7E5, fdiv, v64db, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFDSB : BinaryVRRc<"vfdsb", 0xE7E5, fdiv, v128sb, v128sb, 2, 0>;
+ def WFDSB : BinaryVRRc<"wfdsb", 0xE7E5, fdiv, v32sb, v32sb, 2, 8>;
+ def WFDXB : BinaryVRRc<"wfdxb", 0xE7E5, fdiv, v128xb, v128xb, 4, 8>;
+ }
// Load FP integer.
def VFI : TernaryVRRaFloatGeneric<"vfi", 0xE7C7>;
@@ -917,66 +983,213 @@ let Predicates = [FeatureVector] in {
def WFIDB : TernaryVRRa<"wfidb", 0xE7C7, null_frag, v64db, v64db, 3, 8>;
defm : VectorRounding<VFIDB, v128db>;
defm : VectorRounding<WFIDB, v64db>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFISB : TernaryVRRa<"vfisb", 0xE7C7, int_s390_vfisb, v128sb, v128sb, 2, 0>;
+ def WFISB : TernaryVRRa<"wfisb", 0xE7C7, null_frag, v32sb, v32sb, 2, 8>;
+ def WFIXB : TernaryVRRa<"wfixb", 0xE7C7, null_frag, v128xb, v128xb, 4, 8>;
+ defm : VectorRounding<VFISB, v128sb>;
+ defm : VectorRounding<WFISB, v32sb>;
+ defm : VectorRounding<WFIXB, v128xb>;
+ }
// Load lengthened.
def VLDE : UnaryVRRaFloatGeneric<"vlde", 0xE7C4>;
- def VLDEB : UnaryVRRa<"vldeb", 0xE7C4, z_vextend, v128db, v128eb, 2, 0>;
- def WLDEB : UnaryVRRa<"wldeb", 0xE7C4, fpextend, v64db, v32eb, 2, 8>;
+ def VLDEB : UnaryVRRa<"vldeb", 0xE7C4, z_vextend, v128db, v128sb, 2, 0>;
+ def WLDEB : UnaryVRRa<"wldeb", 0xE7C4, fpextend, v64db, v32sb, 2, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ let isAsmParserOnly = 1 in {
+ def VFLL : UnaryVRRaFloatGeneric<"vfll", 0xE7C4>;
+ def VFLLS : UnaryVRRa<"vflls", 0xE7C4, null_frag, v128db, v128sb, 2, 0>;
+ def WFLLS : UnaryVRRa<"wflls", 0xE7C4, null_frag, v64db, v32sb, 2, 8>;
+ }
+ def WFLLD : UnaryVRRa<"wflld", 0xE7C4, fpextend, v128xb, v64db, 3, 8>;
+ def : Pat<(f128 (fpextend (f32 VR32:$src))),
+ (WFLLD (WLDEB VR32:$src))>;
+ }
- // Load rounded,
+ // Load rounded.
def VLED : TernaryVRRaFloatGeneric<"vled", 0xE7C5>;
- def VLEDB : TernaryVRRa<"vledb", 0xE7C5, null_frag, v128eb, v128db, 3, 0>;
- def WLEDB : TernaryVRRa<"wledb", 0xE7C5, null_frag, v32eb, v64db, 3, 8>;
+ def VLEDB : TernaryVRRa<"vledb", 0xE7C5, null_frag, v128sb, v128db, 3, 0>;
+ def WLEDB : TernaryVRRa<"wledb", 0xE7C5, null_frag, v32sb, v64db, 3, 8>;
def : Pat<(v4f32 (z_vround (v2f64 VR128:$src))), (VLEDB VR128:$src, 0, 0)>;
- def : FPConversion<WLEDB, fpround, v32eb, v64db, 0, 0>;
+ def : FPConversion<WLEDB, fpround, v32sb, v64db, 0, 0>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ let isAsmParserOnly = 1 in {
+ def VFLR : TernaryVRRaFloatGeneric<"vflr", 0xE7C5>;
+ def VFLRD : TernaryVRRa<"vflrd", 0xE7C5, null_frag, v128sb, v128db, 3, 0>;
+ def WFLRD : TernaryVRRa<"wflrd", 0xE7C5, null_frag, v32sb, v64db, 3, 8>;
+ }
+ def WFLRX : TernaryVRRa<"wflrx", 0xE7C5, null_frag, v64db, v128xb, 4, 8>;
+ def : FPConversion<WFLRX, fpround, v64db, v128xb, 0, 0>;
+ def : Pat<(f32 (fpround (f128 VR128:$src))),
+ (WLEDB (WFLRX VR128:$src, 0, 3), 0, 0)>;
+ }
+
+ // Maximum.
+ multiclass VectorMax<Instruction insn, TypedReg tr> {
+ def : FPMinMax<insn, fmaxnum, tr, 4>;
+ def : FPMinMax<insn, fmaxnan, tr, 1>;
+ }
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFMAX : TernaryVRRcFloatGeneric<"vfmax", 0xE7EF>;
+ def VFMAXDB : TernaryVRRcFloat<"vfmaxdb", 0xE7EF, int_s390_vfmaxdb,
+ v128db, v128db, 3, 0>;
+ def WFMAXDB : TernaryVRRcFloat<"wfmaxdb", 0xE7EF, null_frag,
+ v64db, v64db, 3, 8>;
+ def VFMAXSB : TernaryVRRcFloat<"vfmaxsb", 0xE7EF, int_s390_vfmaxsb,
+ v128sb, v128sb, 2, 0>;
+ def WFMAXSB : TernaryVRRcFloat<"wfmaxsb", 0xE7EF, null_frag,
+ v32sb, v32sb, 2, 8>;
+ def WFMAXXB : TernaryVRRcFloat<"wfmaxxb", 0xE7EF, null_frag,
+ v128xb, v128xb, 4, 8>;
+ defm : VectorMax<VFMAXDB, v128db>;
+ defm : VectorMax<WFMAXDB, v64db>;
+ defm : VectorMax<VFMAXSB, v128sb>;
+ defm : VectorMax<WFMAXSB, v32sb>;
+ defm : VectorMax<WFMAXXB, v128xb>;
+ }
+
+ // Minimum.
+ multiclass VectorMin<Instruction insn, TypedReg tr> {
+ def : FPMinMax<insn, fminnum, tr, 4>;
+ def : FPMinMax<insn, fminnan, tr, 1>;
+ }
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFMIN : TernaryVRRcFloatGeneric<"vfmin", 0xE7EE>;
+ def VFMINDB : TernaryVRRcFloat<"vfmindb", 0xE7EE, int_s390_vfmindb,
+ v128db, v128db, 3, 0>;
+ def WFMINDB : TernaryVRRcFloat<"wfmindb", 0xE7EE, null_frag,
+ v64db, v64db, 3, 8>;
+ def VFMINSB : TernaryVRRcFloat<"vfminsb", 0xE7EE, int_s390_vfminsb,
+ v128sb, v128sb, 2, 0>;
+ def WFMINSB : TernaryVRRcFloat<"wfminsb", 0xE7EE, null_frag,
+ v32sb, v32sb, 2, 8>;
+ def WFMINXB : TernaryVRRcFloat<"wfminxb", 0xE7EE, null_frag,
+ v128xb, v128xb, 4, 8>;
+ defm : VectorMin<VFMINDB, v128db>;
+ defm : VectorMin<WFMINDB, v64db>;
+ defm : VectorMin<VFMINSB, v128sb>;
+ defm : VectorMin<WFMINSB, v32sb>;
+ defm : VectorMin<WFMINXB, v128xb>;
+ }
// Multiply.
def VFM : BinaryVRRcFloatGeneric<"vfm", 0xE7E7>;
def VFMDB : BinaryVRRc<"vfmdb", 0xE7E7, fmul, v128db, v128db, 3, 0>;
def WFMDB : BinaryVRRc<"wfmdb", 0xE7E7, fmul, v64db, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFMSB : BinaryVRRc<"vfmsb", 0xE7E7, fmul, v128sb, v128sb, 2, 0>;
+ def WFMSB : BinaryVRRc<"wfmsb", 0xE7E7, fmul, v32sb, v32sb, 2, 8>;
+ def WFMXB : BinaryVRRc<"wfmxb", 0xE7E7, fmul, v128xb, v128xb, 4, 8>;
+ }
// Multiply and add.
def VFMA : TernaryVRReFloatGeneric<"vfma", 0xE78F>;
def VFMADB : TernaryVRRe<"vfmadb", 0xE78F, fma, v128db, v128db, 0, 3>;
def WFMADB : TernaryVRRe<"wfmadb", 0xE78F, fma, v64db, v64db, 8, 3>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFMASB : TernaryVRRe<"vfmasb", 0xE78F, fma, v128sb, v128sb, 0, 2>;
+ def WFMASB : TernaryVRRe<"wfmasb", 0xE78F, fma, v32sb, v32sb, 8, 2>;
+ def WFMAXB : TernaryVRRe<"wfmaxb", 0xE78F, fma, v128xb, v128xb, 8, 4>;
+ }
// Multiply and subtract.
def VFMS : TernaryVRReFloatGeneric<"vfms", 0xE78E>;
def VFMSDB : TernaryVRRe<"vfmsdb", 0xE78E, fms, v128db, v128db, 0, 3>;
def WFMSDB : TernaryVRRe<"wfmsdb", 0xE78E, fms, v64db, v64db, 8, 3>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFMSSB : TernaryVRRe<"vfmssb", 0xE78E, fms, v128sb, v128sb, 0, 2>;
+ def WFMSSB : TernaryVRRe<"wfmssb", 0xE78E, fms, v32sb, v32sb, 8, 2>;
+ def WFMSXB : TernaryVRRe<"wfmsxb", 0xE78E, fms, v128xb, v128xb, 8, 4>;
+ }
+
+ // Negative multiply and add.
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFNMA : TernaryVRReFloatGeneric<"vfnma", 0xE79F>;
+ def VFNMADB : TernaryVRRe<"vfnmadb", 0xE79F, fnma, v128db, v128db, 0, 3>;
+ def WFNMADB : TernaryVRRe<"wfnmadb", 0xE79F, fnma, v64db, v64db, 8, 3>;
+ def VFNMASB : TernaryVRRe<"vfnmasb", 0xE79F, fnma, v128sb, v128sb, 0, 2>;
+ def WFNMASB : TernaryVRRe<"wfnmasb", 0xE79F, fnma, v32sb, v32sb, 8, 2>;
+ def WFNMAXB : TernaryVRRe<"wfnmaxb", 0xE79F, fnma, v128xb, v128xb, 8, 4>;
+ }
+
+ // Negative multiply and subtract.
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFNMS : TernaryVRReFloatGeneric<"vfnms", 0xE79E>;
+ def VFNMSDB : TernaryVRRe<"vfnmsdb", 0xE79E, fnms, v128db, v128db, 0, 3>;
+ def WFNMSDB : TernaryVRRe<"wfnmsdb", 0xE79E, fnms, v64db, v64db, 8, 3>;
+ def VFNMSSB : TernaryVRRe<"vfnmssb", 0xE79E, fnms, v128sb, v128sb, 0, 2>;
+ def WFNMSSB : TernaryVRRe<"wfnmssb", 0xE79E, fnms, v32sb, v32sb, 8, 2>;
+ def WFNMSXB : TernaryVRRe<"wfnmsxb", 0xE79E, fnms, v128xb, v128xb, 8, 4>;
+ }
// Perform sign operation.
def VFPSO : BinaryVRRaFloatGeneric<"vfpso", 0xE7CC>;
def VFPSODB : BinaryVRRa<"vfpsodb", 0xE7CC, null_frag, v128db, v128db, 3, 0>;
def WFPSODB : BinaryVRRa<"wfpsodb", 0xE7CC, null_frag, v64db, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFPSOSB : BinaryVRRa<"vfpsosb", 0xE7CC, null_frag, v128sb, v128sb, 2, 0>;
+ def WFPSOSB : BinaryVRRa<"wfpsosb", 0xE7CC, null_frag, v32sb, v32sb, 2, 8>;
+ def WFPSOXB : BinaryVRRa<"wfpsoxb", 0xE7CC, null_frag, v128xb, v128xb, 4, 8>;
+ }
// Load complement.
def VFLCDB : UnaryVRRa<"vflcdb", 0xE7CC, fneg, v128db, v128db, 3, 0, 0>;
def WFLCDB : UnaryVRRa<"wflcdb", 0xE7CC, fneg, v64db, v64db, 3, 8, 0>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFLCSB : UnaryVRRa<"vflcsb", 0xE7CC, fneg, v128sb, v128sb, 2, 0, 0>;
+ def WFLCSB : UnaryVRRa<"wflcsb", 0xE7CC, fneg, v32sb, v32sb, 2, 8, 0>;
+ def WFLCXB : UnaryVRRa<"wflcxb", 0xE7CC, fneg, v128xb, v128xb, 4, 8, 0>;
+ }
// Load negative.
def VFLNDB : UnaryVRRa<"vflndb", 0xE7CC, fnabs, v128db, v128db, 3, 0, 1>;
def WFLNDB : UnaryVRRa<"wflndb", 0xE7CC, fnabs, v64db, v64db, 3, 8, 1>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFLNSB : UnaryVRRa<"vflnsb", 0xE7CC, fnabs, v128sb, v128sb, 2, 0, 1>;
+ def WFLNSB : UnaryVRRa<"wflnsb", 0xE7CC, fnabs, v32sb, v32sb, 2, 8, 1>;
+ def WFLNXB : UnaryVRRa<"wflnxb", 0xE7CC, fnabs, v128xb, v128xb, 4, 8, 1>;
+ }
// Load positive.
def VFLPDB : UnaryVRRa<"vflpdb", 0xE7CC, fabs, v128db, v128db, 3, 0, 2>;
def WFLPDB : UnaryVRRa<"wflpdb", 0xE7CC, fabs, v64db, v64db, 3, 8, 2>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFLPSB : UnaryVRRa<"vflpsb", 0xE7CC, fabs, v128sb, v128sb, 2, 0, 2>;
+ def WFLPSB : UnaryVRRa<"wflpsb", 0xE7CC, fabs, v32sb, v32sb, 2, 8, 2>;
+ def WFLPXB : UnaryVRRa<"wflpxb", 0xE7CC, fabs, v128xb, v128xb, 4, 8, 2>;
+ }
// Square root.
def VFSQ : UnaryVRRaFloatGeneric<"vfsq", 0xE7CE>;
def VFSQDB : UnaryVRRa<"vfsqdb", 0xE7CE, fsqrt, v128db, v128db, 3, 0>;
def WFSQDB : UnaryVRRa<"wfsqdb", 0xE7CE, fsqrt, v64db, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFSQSB : UnaryVRRa<"vfsqsb", 0xE7CE, fsqrt, v128sb, v128sb, 2, 0>;
+ def WFSQSB : UnaryVRRa<"wfsqsb", 0xE7CE, fsqrt, v32sb, v32sb, 2, 8>;
+ def WFSQXB : UnaryVRRa<"wfsqxb", 0xE7CE, fsqrt, v128xb, v128xb, 4, 8>;
+ }
// Subtract.
def VFS : BinaryVRRcFloatGeneric<"vfs", 0xE7E2>;
def VFSDB : BinaryVRRc<"vfsdb", 0xE7E2, fsub, v128db, v128db, 3, 0>;
def WFSDB : BinaryVRRc<"wfsdb", 0xE7E2, fsub, v64db, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFSSB : BinaryVRRc<"vfssb", 0xE7E2, fsub, v128sb, v128sb, 2, 0>;
+ def WFSSB : BinaryVRRc<"wfssb", 0xE7E2, fsub, v32sb, v32sb, 2, 8>;
+ def WFSXB : BinaryVRRc<"wfsxb", 0xE7E2, fsub, v128xb, v128xb, 4, 8>;
+ }
// Test data class immediate.
let Defs = [CC] in {
def VFTCI : BinaryVRIeFloatGeneric<"vftci", 0xE74A>;
def VFTCIDB : BinaryVRIe<"vftcidb", 0xE74A, z_vftci, v128g, v128db, 3, 0>;
def WFTCIDB : BinaryVRIe<"wftcidb", 0xE74A, null_frag, v64g, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def VFTCISB : BinaryVRIe<"vftcisb", 0xE74A, z_vftci, v128f, v128sb, 2, 0>;
+ def WFTCISB : BinaryVRIe<"wftcisb", 0xE74A, null_frag, v32f, v32sb, 2, 8>;
+ def WFTCIXB : BinaryVRIe<"wftcixb", 0xE74A, null_frag, v128q, v128xb, 4, 8>;
+ }
}
}
@@ -989,12 +1202,20 @@ let Predicates = [FeatureVector] in {
let Defs = [CC] in {
def WFC : CompareVRRaFloatGeneric<"wfc", 0xE7CB>;
def WFCDB : CompareVRRa<"wfcdb", 0xE7CB, z_fcmp, v64db, 3>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def WFCSB : CompareVRRa<"wfcsb", 0xE7CB, z_fcmp, v32sb, 2>;
+ def WFCXB : CompareVRRa<"wfcxb", 0xE7CB, z_fcmp, v128xb, 4>;
+ }
}
// Compare and signal scalar.
let Defs = [CC] in {
def WFK : CompareVRRaFloatGeneric<"wfk", 0xE7CA>;
def WFKDB : CompareVRRa<"wfkdb", 0xE7CA, null_frag, v64db, 3>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ def WFKSB : CompareVRRa<"wfksb", 0xE7CA, null_frag, v32sb, 2>;
+ def WFKXB : CompareVRRa<"wfkxb", 0xE7CA, null_frag, v128xb, 4>;
+ }
}
// Compare equal.
@@ -1003,6 +1224,28 @@ let Predicates = [FeatureVector] in {
v128g, v128db, 3, 0>;
defm WFCEDB : BinaryVRRcSPair<"wfcedb", 0xE7E8, null_frag, null_frag,
v64g, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ defm VFCESB : BinaryVRRcSPair<"vfcesb", 0xE7E8, z_vfcmpe, z_vfcmpes,
+ v128f, v128sb, 2, 0>;
+ defm WFCESB : BinaryVRRcSPair<"wfcesb", 0xE7E8, null_frag, null_frag,
+ v32f, v32sb, 2, 8>;
+ defm WFCEXB : BinaryVRRcSPair<"wfcexb", 0xE7E8, null_frag, null_frag,
+ v128q, v128xb, 4, 8>;
+ }
+
+ // Compare and signal equal.
+ let Predicates = [FeatureVectorEnhancements1] in {
+ defm VFKEDB : BinaryVRRcSPair<"vfkedb", 0xE7E8, null_frag, null_frag,
+ v128g, v128db, 3, 4>;
+ defm WFKEDB : BinaryVRRcSPair<"wfkedb", 0xE7E8, null_frag, null_frag,
+ v64g, v64db, 3, 12>;
+ defm VFKESB : BinaryVRRcSPair<"vfkesb", 0xE7E8, null_frag, null_frag,
+ v128f, v128sb, 2, 4>;
+ defm WFKESB : BinaryVRRcSPair<"wfkesb", 0xE7E8, null_frag, null_frag,
+ v32f, v32sb, 2, 12>;
+ defm WFKEXB : BinaryVRRcSPair<"wfkexb", 0xE7E8, null_frag, null_frag,
+ v128q, v128xb, 4, 12>;
+ }
// Compare high.
def VFCH : BinaryVRRcSPairFloatGeneric<"vfch", 0xE7EB>;
@@ -1010,6 +1253,28 @@ let Predicates = [FeatureVector] in {
v128g, v128db, 3, 0>;
defm WFCHDB : BinaryVRRcSPair<"wfchdb", 0xE7EB, null_frag, null_frag,
v64g, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ defm VFCHSB : BinaryVRRcSPair<"vfchsb", 0xE7EB, z_vfcmph, z_vfcmphs,
+ v128f, v128sb, 2, 0>;
+ defm WFCHSB : BinaryVRRcSPair<"wfchsb", 0xE7EB, null_frag, null_frag,
+ v32f, v32sb, 2, 8>;
+ defm WFCHXB : BinaryVRRcSPair<"wfchxb", 0xE7EB, null_frag, null_frag,
+ v128q, v128xb, 4, 8>;
+ }
+
+ // Compare and signal high.
+ let Predicates = [FeatureVectorEnhancements1] in {
+ defm VFKHDB : BinaryVRRcSPair<"vfkhdb", 0xE7EB, null_frag, null_frag,
+ v128g, v128db, 3, 4>;
+ defm WFKHDB : BinaryVRRcSPair<"wfkhdb", 0xE7EB, null_frag, null_frag,
+ v64g, v64db, 3, 12>;
+ defm VFKHSB : BinaryVRRcSPair<"vfkhsb", 0xE7EB, null_frag, null_frag,
+ v128f, v128sb, 2, 4>;
+ defm WFKHSB : BinaryVRRcSPair<"wfkhsb", 0xE7EB, null_frag, null_frag,
+ v32f, v32sb, 2, 12>;
+ defm WFKHXB : BinaryVRRcSPair<"wfkhxb", 0xE7EB, null_frag, null_frag,
+ v128q, v128xb, 4, 12>;
+ }
// Compare high or equal.
def VFCHE : BinaryVRRcSPairFloatGeneric<"vfche", 0xE7EA>;
@@ -1017,6 +1282,28 @@ let Predicates = [FeatureVector] in {
v128g, v128db, 3, 0>;
defm WFCHEDB : BinaryVRRcSPair<"wfchedb", 0xE7EA, null_frag, null_frag,
v64g, v64db, 3, 8>;
+ let Predicates = [FeatureVectorEnhancements1] in {
+ defm VFCHESB : BinaryVRRcSPair<"vfchesb", 0xE7EA, z_vfcmphe, z_vfcmphes,
+ v128f, v128sb, 2, 0>;
+ defm WFCHESB : BinaryVRRcSPair<"wfchesb", 0xE7EA, null_frag, null_frag,
+ v32f, v32sb, 2, 8>;
+ defm WFCHEXB : BinaryVRRcSPair<"wfchexb", 0xE7EA, null_frag, null_frag,
+ v128q, v128xb, 4, 8>;
+ }
+
+ // Compare and signal high or equal.
+ let Predicates = [FeatureVectorEnhancements1] in {
+ defm VFKHEDB : BinaryVRRcSPair<"vfkhedb", 0xE7EA, null_frag, null_frag,
+ v128g, v128db, 3, 4>;
+ defm WFKHEDB : BinaryVRRcSPair<"wfkhedb", 0xE7EA, null_frag, null_frag,
+ v64g, v64db, 3, 12>;
+ defm VFKHESB : BinaryVRRcSPair<"vfkhesb", 0xE7EA, null_frag, null_frag,
+ v128f, v128sb, 2, 4>;
+ defm WFKHESB : BinaryVRRcSPair<"wfkhesb", 0xE7EA, null_frag, null_frag,
+ v32f, v32sb, 2, 12>;
+ defm WFKHEXB : BinaryVRRcSPair<"wfkhexb", 0xE7EA, null_frag, null_frag,
+ v128q, v128xb, 4, 12>;
+ }
}
//===----------------------------------------------------------------------===//
@@ -1028,36 +1315,49 @@ def : Pat<(v16i8 (bitconvert (v4i32 VR128:$src))), (v16i8 VR128:$src)>;
def : Pat<(v16i8 (bitconvert (v2i64 VR128:$src))), (v16i8 VR128:$src)>;
def : Pat<(v16i8 (bitconvert (v4f32 VR128:$src))), (v16i8 VR128:$src)>;
def : Pat<(v16i8 (bitconvert (v2f64 VR128:$src))), (v16i8 VR128:$src)>;
+def : Pat<(v16i8 (bitconvert (f128 VR128:$src))), (v16i8 VR128:$src)>;
def : Pat<(v8i16 (bitconvert (v16i8 VR128:$src))), (v8i16 VR128:$src)>;
def : Pat<(v8i16 (bitconvert (v4i32 VR128:$src))), (v8i16 VR128:$src)>;
def : Pat<(v8i16 (bitconvert (v2i64 VR128:$src))), (v8i16 VR128:$src)>;
def : Pat<(v8i16 (bitconvert (v4f32 VR128:$src))), (v8i16 VR128:$src)>;
def : Pat<(v8i16 (bitconvert (v2f64 VR128:$src))), (v8i16 VR128:$src)>;
+def : Pat<(v8i16 (bitconvert (f128 VR128:$src))), (v8i16 VR128:$src)>;
def : Pat<(v4i32 (bitconvert (v16i8 VR128:$src))), (v4i32 VR128:$src)>;
def : Pat<(v4i32 (bitconvert (v8i16 VR128:$src))), (v4i32 VR128:$src)>;
def : Pat<(v4i32 (bitconvert (v2i64 VR128:$src))), (v4i32 VR128:$src)>;
def : Pat<(v4i32 (bitconvert (v4f32 VR128:$src))), (v4i32 VR128:$src)>;
def : Pat<(v4i32 (bitconvert (v2f64 VR128:$src))), (v4i32 VR128:$src)>;
+def : Pat<(v4i32 (bitconvert (f128 VR128:$src))), (v4i32 VR128:$src)>;
def : Pat<(v2i64 (bitconvert (v16i8 VR128:$src))), (v2i64 VR128:$src)>;
def : Pat<(v2i64 (bitconvert (v8i16 VR128:$src))), (v2i64 VR128:$src)>;
def : Pat<(v2i64 (bitconvert (v4i32 VR128:$src))), (v2i64 VR128:$src)>;
def : Pat<(v2i64 (bitconvert (v4f32 VR128:$src))), (v2i64 VR128:$src)>;
def : Pat<(v2i64 (bitconvert (v2f64 VR128:$src))), (v2i64 VR128:$src)>;
+def : Pat<(v2i64 (bitconvert (f128 VR128:$src))), (v2i64 VR128:$src)>;
def : Pat<(v4f32 (bitconvert (v16i8 VR128:$src))), (v4f32 VR128:$src)>;
def : Pat<(v4f32 (bitconvert (v8i16 VR128:$src))), (v4f32 VR128:$src)>;
def : Pat<(v4f32 (bitconvert (v4i32 VR128:$src))), (v4f32 VR128:$src)>;
def : Pat<(v4f32 (bitconvert (v2i64 VR128:$src))), (v4f32 VR128:$src)>;
def : Pat<(v4f32 (bitconvert (v2f64 VR128:$src))), (v4f32 VR128:$src)>;
+def : Pat<(v4f32 (bitconvert (f128 VR128:$src))), (v4f32 VR128:$src)>;
def : Pat<(v2f64 (bitconvert (v16i8 VR128:$src))), (v2f64 VR128:$src)>;
def : Pat<(v2f64 (bitconvert (v8i16 VR128:$src))), (v2f64 VR128:$src)>;
def : Pat<(v2f64 (bitconvert (v4i32 VR128:$src))), (v2f64 VR128:$src)>;
def : Pat<(v2f64 (bitconvert (v2i64 VR128:$src))), (v2f64 VR128:$src)>;
def : Pat<(v2f64 (bitconvert (v4f32 VR128:$src))), (v2f64 VR128:$src)>;
+def : Pat<(v2f64 (bitconvert (f128 VR128:$src))), (v2f64 VR128:$src)>;
+
+def : Pat<(f128 (bitconvert (v16i8 VR128:$src))), (f128 VR128:$src)>;
+def : Pat<(f128 (bitconvert (v8i16 VR128:$src))), (f128 VR128:$src)>;
+def : Pat<(f128 (bitconvert (v4i32 VR128:$src))), (f128 VR128:$src)>;
+def : Pat<(f128 (bitconvert (v2i64 VR128:$src))), (f128 VR128:$src)>;
+def : Pat<(f128 (bitconvert (v4f32 VR128:$src))), (f128 VR128:$src)>;
+def : Pat<(f128 (bitconvert (v2f64 VR128:$src))), (f128 VR128:$src)>;
//===----------------------------------------------------------------------===//
// Replicating scalars
@@ -1134,6 +1434,20 @@ let AddedComplexity = 4 in {
}
//===----------------------------------------------------------------------===//
+// Support for 128-bit floating-point values in vector registers
+//===----------------------------------------------------------------------===//
+
+let Predicates = [FeatureVectorEnhancements1] in {
+ def : Pat<(f128 (load bdxaddr12only:$addr)),
+ (VL bdxaddr12only:$addr)>;
+ def : Pat<(store (f128 VR128:$src), bdxaddr12only:$addr),
+ (VST VR128:$src, bdxaddr12only:$addr)>;
+
+ def : Pat<(f128 fpimm0), (VZERO)>;
+ def : Pat<(f128 fpimmneg0), (WFLNXB (VZERO))>;
+}
+
+//===----------------------------------------------------------------------===//
// String instructions
//===----------------------------------------------------------------------===//
@@ -1202,3 +1516,37 @@ let Predicates = [FeatureVector] in {
defm VSTRCZF : QuaternaryOptVRRdSPair<"vstrczf", 0xE78A, int_s390_vstrczf,
z_vstrcz_cc, v128f, v128f, 2, 2>;
}
+
+//===----------------------------------------------------------------------===//
+// Packed-decimal instructions
+//===----------------------------------------------------------------------===//
+
+let Predicates = [FeatureVectorPackedDecimal] in {
+ def VLIP : BinaryVRIh<"vlip", 0xE649>;
+
+ def VPKZ : BinaryVSI<"vpkz", 0xE634, null_frag, 0>;
+ def VUPKZ : StoreLengthVSI<"vupkz", 0xE63C, null_frag, 0>;
+
+ let Defs = [CC] in {
+ def VCVB : BinaryVRRi<"vcvb", 0xE650, GR32>;
+ def VCVBG : BinaryVRRi<"vcvbg", 0xE652, GR64>;
+ def VCVD : TernaryVRIi<"vcvd", 0xE658, GR32>;
+ def VCVDG : TernaryVRIi<"vcvdg", 0xE65A, GR64>;
+
+ def VAP : QuaternaryVRIf<"vap", 0xE671>;
+ def VSP : QuaternaryVRIf<"vsp", 0xE673>;
+
+ def VMP : QuaternaryVRIf<"vmp", 0xE678>;
+ def VMSP : QuaternaryVRIf<"vmsp", 0xE679>;
+
+ def VDP : QuaternaryVRIf<"vdp", 0xE67A>;
+ def VRP : QuaternaryVRIf<"vrp", 0xE67B>;
+ def VSDP : QuaternaryVRIf<"vsdp", 0xE67E>;
+
+ def VSRP : QuaternaryVRIg<"vsrp", 0xE659>;
+ def VPSOP : QuaternaryVRIg<"vpsop", 0xE65B>;
+
+ def VTP : TestVRRg<"vtp", 0xE65F>;
+ def VCP : CompareVRRh<"vcp", 0xE677>;
+ }
+}
diff --git a/lib/Target/SystemZ/SystemZOperators.td b/lib/Target/SystemZ/SystemZOperators.td
index 9c6d5819f8a7e..759a8bb0ce14d 100644
--- a/lib/Target/SystemZ/SystemZOperators.td
+++ b/lib/Target/SystemZ/SystemZOperators.td
@@ -181,6 +181,7 @@ def z_select_ccmask : SDNode<"SystemZISD::SELECT_CCMASK", SDT_ZSelectCCMask,
[SDNPInGlue]>;
def z_adjdynalloc : SDNode<"SystemZISD::ADJDYNALLOC", SDT_ZAdjDynAlloc>;
def z_popcnt : SDNode<"SystemZISD::POPCNT", SDTIntUnaryOp>;
+def z_smul_lohi : SDNode<"SystemZISD::SMUL_LOHI", SDT_ZGR128Binary>;
def z_umul_lohi : SDNode<"SystemZISD::UMUL_LOHI", SDT_ZGR128Binary>;
def z_sdivrem : SDNode<"SystemZISD::SDIVREM", SDT_ZGR128Binary>;
def z_udivrem : SDNode<"SystemZISD::UDIVREM", SDT_ZGR128Binary>;
@@ -549,6 +550,12 @@ def z_fma : PatFrag<(ops node:$src1, node:$src2, node:$src3),
def z_fms : PatFrag<(ops node:$src1, node:$src2, node:$src3),
(fma node:$src2, node:$src3, (fneg node:$src1))>;
+// Negative fused multiply-add and multiply-subtract.
+def fnma : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+ (fneg (fma node:$src1, node:$src2, node:$src3))>;
+def fnms : PatFrag<(ops node:$src1, node:$src2, node:$src3),
+ (fneg (fms node:$src1, node:$src2, node:$src3))>;
+
// Floating-point negative absolute.
def fnabs : PatFrag<(ops node:$ptr), (fneg (fabs node:$ptr))>;
@@ -624,6 +631,19 @@ def z_vllezf64 : PatFrag<(ops node:$addr),
(scalar_to_vector (f64 (load node:$addr))),
(z_vzero))>;
+// Similarly for the high element of a zeroed vector.
+def z_vllezli32 : z_vllez<i32, load, 0>;
+def z_vllezlf32 : PatFrag<(ops node:$addr),
+ (bitconvert
+ (z_merge_high
+ (v2i64
+ (bitconvert
+ (z_merge_high
+ (v4f32 (scalar_to_vector
+ (f32 (load node:$addr)))),
+ (v4f32 (z_vzero))))),
+ (v2i64 (z_vzero))))>;
+
// Store one element of a vector.
class z_vste<ValueType scalartype, SDPatternOperator store>
: PatFrag<(ops node:$vec, node:$addr, node:$index),
diff --git a/lib/Target/SystemZ/SystemZPatterns.td b/lib/Target/SystemZ/SystemZPatterns.td
index 16a7ed784d709..152521fb66a8d 100644
--- a/lib/Target/SystemZ/SystemZPatterns.td
+++ b/lib/Target/SystemZ/SystemZPatterns.td
@@ -167,3 +167,10 @@ class FPConversion<Instruction insn, SDPatternOperator operator, TypedReg tr1,
TypedReg tr2, bits<3> suppress, bits<4> mode>
: Pat<(tr1.vt (operator (tr2.vt tr2.op:$vec))),
(insn tr2.op:$vec, suppress, mode)>;
+
+// Use INSN to perform mininum/maximum operation OPERATOR on type TR.
+// FUNCTION is the type of minimum/maximum function to perform.
+class FPMinMax<Instruction insn, SDPatternOperator operator, TypedReg tr,
+ bits<4> function>
+ : Pat<(tr.vt (operator (tr.vt tr.op:$vec1), (tr.vt tr.op:$vec2))),
+ (insn tr.op:$vec1, tr.op:$vec2, function)>;
diff --git a/lib/Target/SystemZ/SystemZProcessors.td b/lib/Target/SystemZ/SystemZProcessors.td
index 1cdc0949ff4ae..0dca4582dc0d6 100644
--- a/lib/Target/SystemZ/SystemZProcessors.td
+++ b/lib/Target/SystemZ/SystemZProcessors.td
@@ -33,3 +33,6 @@ def : ProcessorModel<"zEC12", ZEC12Model, Arch10SupportedFeatures.List>;
def : ProcessorModel<"arch11", Z13Model, Arch11SupportedFeatures.List>;
def : ProcessorModel<"z13", Z13Model, Arch11SupportedFeatures.List>;
+def : ProcessorModel<"arch12", Z14Model, Arch12SupportedFeatures.List>;
+def : ProcessorModel<"z14", Z14Model, Arch12SupportedFeatures.List>;
+
diff --git a/lib/Target/SystemZ/SystemZRegisterInfo.td b/lib/Target/SystemZ/SystemZRegisterInfo.td
index 36809ea81dc1c..52ba1a584017a 100644
--- a/lib/Target/SystemZ/SystemZRegisterInfo.td
+++ b/lib/Target/SystemZ/SystemZRegisterInfo.td
@@ -260,10 +260,10 @@ defm VF128 : SystemZRegClass<"VF128",
// All vector registers.
defm VR128 : SystemZRegClass<"VR128",
- [v16i8, v8i16, v4i32, v2i64, v4f32, v2f64], 128,
- (add (sequence "V%u", 0, 7),
- (sequence "V%u", 16, 31),
- (sequence "V%u", 8, 15))>;
+ [f128, v16i8, v8i16, v4i32, v2i64, v4f32, v2f64],
+ 128, (add (sequence "V%u", 0, 7),
+ (sequence "V%u", 16, 31),
+ (sequence "V%u", 8, 15))>;
// Attaches a ValueType to a register operand, to make the instruction
// definitions easier.
@@ -272,7 +272,8 @@ class TypedReg<ValueType vtin, RegisterOperand opin> {
RegisterOperand op = opin;
}
-def v32eb : TypedReg<f32, VR32>;
+def v32f : TypedReg<i32, VR32>;
+def v32sb : TypedReg<f32, VR32>;
def v64g : TypedReg<i64, VR64>;
def v64db : TypedReg<f64, VR64>;
def v128b : TypedReg<v16i8, VR128>;
@@ -280,8 +281,9 @@ def v128h : TypedReg<v8i16, VR128>;
def v128f : TypedReg<v4i32, VR128>;
def v128g : TypedReg<v2i64, VR128>;
def v128q : TypedReg<v16i8, VR128>;
-def v128eb : TypedReg<v4f32, VR128>;
+def v128sb : TypedReg<v4f32, VR128>;
def v128db : TypedReg<v2f64, VR128>;
+def v128xb : TypedReg<f128, VR128>;
def v128any : TypedReg<untyped, VR128>;
//===----------------------------------------------------------------------===//
diff --git a/lib/Target/SystemZ/SystemZSchedule.td b/lib/Target/SystemZ/SystemZSchedule.td
index 1ce0168f95e95..8dba89f70a422 100644
--- a/lib/Target/SystemZ/SystemZSchedule.td
+++ b/lib/Target/SystemZ/SystemZSchedule.td
@@ -59,7 +59,7 @@ def FPU2 : SchedWrite;
def DFU : SchedWrite;
def DFU2 : SchedWrite;
-// Vector sub units (z13)
+// Vector sub units (z13 and later)
def VecBF : SchedWrite;
def VecBF2 : SchedWrite;
def VecDF : SchedWrite;
@@ -75,6 +75,7 @@ def VecXsPm : SchedWrite;
def VBU : SchedWrite;
+include "SystemZScheduleZ14.td"
include "SystemZScheduleZ13.td"
include "SystemZScheduleZEC12.td"
include "SystemZScheduleZ196.td"
diff --git a/lib/Target/SystemZ/SystemZScheduleZ14.td b/lib/Target/SystemZ/SystemZScheduleZ14.td
new file mode 100644
index 0000000000000..f11177af91a53
--- /dev/null
+++ b/lib/Target/SystemZ/SystemZScheduleZ14.td
@@ -0,0 +1,1611 @@
+//-- SystemZScheduleZ14.td - SystemZ Scheduling Definitions ----*- tblgen -*-=//
+//
+// The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file defines the machine model for Z14 to support instruction
+// scheduling and other instruction cost heuristics.
+//
+//===----------------------------------------------------------------------===//
+
+def Z14Model : SchedMachineModel {
+
+ let UnsupportedFeatures = Arch12UnsupportedFeatures.List;
+
+ let IssueWidth = 8;
+ let MicroOpBufferSize = 60; // Issue queues
+ let LoadLatency = 1; // Optimistic load latency.
+
+ let PostRAScheduler = 1;
+
+ // Extra cycles for a mispredicted branch.
+ let MispredictPenalty = 20;
+}
+
+let SchedModel = Z14Model in {
+
+// These definitions could be put in a subtarget common include file,
+// but it seems the include system in Tablegen currently rejects
+// multiple includes of same file.
+def : WriteRes<GroupAlone, []> {
+ let NumMicroOps = 0;
+ let BeginGroup = 1;
+ let EndGroup = 1;
+}
+def : WriteRes<BeginGroup, []> {
+ let NumMicroOps = 0;
+ let BeginGroup = 1;
+}
+def : WriteRes<EndGroup, []> {
+ let NumMicroOps = 0;
+ let EndGroup = 1;
+}
+def : WriteRes<Lat2, []> { let Latency = 2; let NumMicroOps = 0;}
+def : WriteRes<Lat3, []> { let Latency = 3; let NumMicroOps = 0;}
+def : WriteRes<Lat4, []> { let Latency = 4; let NumMicroOps = 0;}
+def : WriteRes<Lat5, []> { let Latency = 5; let NumMicroOps = 0;}
+def : WriteRes<Lat6, []> { let Latency = 6; let NumMicroOps = 0;}
+def : WriteRes<Lat7, []> { let Latency = 7; let NumMicroOps = 0;}
+def : WriteRes<Lat8, []> { let Latency = 8; let NumMicroOps = 0;}
+def : WriteRes<Lat9, []> { let Latency = 9; let NumMicroOps = 0;}
+def : WriteRes<Lat10, []> { let Latency = 10; let NumMicroOps = 0;}
+def : WriteRes<Lat11, []> { let Latency = 11; let NumMicroOps = 0;}
+def : WriteRes<Lat12, []> { let Latency = 12; let NumMicroOps = 0;}
+def : WriteRes<Lat15, []> { let Latency = 15; let NumMicroOps = 0;}
+def : WriteRes<Lat20, []> { let Latency = 20; let NumMicroOps = 0;}
+def : WriteRes<Lat30, []> { let Latency = 30; let NumMicroOps = 0;}
+
+// Execution units.
+def Z14_FXaUnit : ProcResource<2>;
+def Z14_FXbUnit : ProcResource<2>;
+def Z14_LSUnit : ProcResource<2>;
+def Z14_VecUnit : ProcResource<2>;
+def Z14_VecFPdUnit : ProcResource<2> { let BufferSize = 1; /* blocking */ }
+def Z14_VBUnit : ProcResource<2>;
+
+// Subtarget specific definitions of scheduling resources.
+def : WriteRes<FXa, [Z14_FXaUnit]> { let Latency = 1; }
+def : WriteRes<FXa2, [Z14_FXaUnit, Z14_FXaUnit]> { let Latency = 2; }
+def : WriteRes<FXb, [Z14_FXbUnit]> { let Latency = 1; }
+def : WriteRes<LSU, [Z14_LSUnit]> { let Latency = 4; }
+def : WriteRes<VecBF, [Z14_VecUnit]> { let Latency = 8; }
+def : WriteRes<VecBF2, [Z14_VecUnit, Z14_VecUnit]> { let Latency = 9; }
+def : WriteRes<VecDF, [Z14_VecUnit]> { let Latency = 8; }
+def : WriteRes<VecDF2, [Z14_VecUnit, Z14_VecUnit]> { let Latency = 9; }
+def : WriteRes<VecDFX, [Z14_VecUnit]> { let Latency = 1; }
+def : WriteRes<VecDFX2, [Z14_VecUnit, Z14_VecUnit]> { let Latency = 2; }
+def : WriteRes<VecFPd, [Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit,
+ Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit,
+ Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit,
+ Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit,
+ Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit,
+ Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit,
+ Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit,
+ Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit,
+ Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit,
+ Z14_VecFPdUnit, Z14_VecFPdUnit, Z14_VecFPdUnit]>
+ { let Latency = 30; }
+def : WriteRes<VecMul, [Z14_VecUnit]> { let Latency = 5; }
+def : WriteRes<VecStr, [Z14_VecUnit]> { let Latency = 4; }
+def : WriteRes<VecXsPm, [Z14_VecUnit]> { let Latency = 3; }
+def : WriteRes<VBU, [Z14_VBUnit]>; // Virtual Branching Unit
+
+// -------------------------- INSTRUCTIONS ---------------------------------- //
+
+// InstRW constructs have been used in order to preserve the
+// readability of the InstrInfo files.
+
+// For each instruction, as matched by a regexp, provide a list of
+// resources that it needs. These will be combined into a SchedClass.
+
+//===----------------------------------------------------------------------===//
+// Stack allocation
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa], (instregex "ADJDYNALLOC$")>; // Pseudo -> LA / LAY
+
+//===----------------------------------------------------------------------===//
+// Branch instructions
+//===----------------------------------------------------------------------===//
+
+// Branch
+def : InstRW<[VBU], (instregex "(Call)?BRC(L)?(Asm.*)?$")>;
+def : InstRW<[VBU], (instregex "(Call)?J(G)?(Asm.*)?$")>;
+def : InstRW<[FXb], (instregex "(Call)?BC(R)?(Asm.*)?$")>;
+def : InstRW<[FXb], (instregex "(Call)?B(R)?(Asm.*)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "BI(C)?(Asm.*)?$")>;
+def : InstRW<[FXa, EndGroup], (instregex "BRCT(G)?$")>;
+def : InstRW<[FXb, FXa, Lat2, GroupAlone], (instregex "BRCTH$")>;
+def : InstRW<[FXb, FXa, Lat2, GroupAlone], (instregex "BCT(G)?(R)?$")>;
+def : InstRW<[FXa, FXa, FXb, FXb, Lat4, GroupAlone],
+ (instregex "B(R)?X(H|L).*$")>;
+
+// Compare and branch
+def : InstRW<[FXb], (instregex "C(L)?(G)?(I|R)J(Asm.*)?$")>;
+def : InstRW<[FXb, FXb, Lat2, GroupAlone],
+ (instregex "C(L)?(G)?(I|R)B(Call|Return|Asm.*)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Trap instructions
+//===----------------------------------------------------------------------===//
+
+// Trap
+def : InstRW<[VBU], (instregex "(Cond)?Trap$")>;
+
+// Compare and trap
+def : InstRW<[FXb], (instregex "C(G)?(I|R)T(Asm.*)?$")>;
+def : InstRW<[FXb], (instregex "CL(G)?RT(Asm.*)?$")>;
+def : InstRW<[FXb], (instregex "CL(F|G)IT(Asm.*)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CL(G)?T(Asm.*)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Call and return instructions
+//===----------------------------------------------------------------------===//
+
+// Call
+def : InstRW<[VBU, FXa, FXa, Lat3, GroupAlone], (instregex "(Call)?BRAS$")>;
+def : InstRW<[FXa, FXa, FXb, Lat3, GroupAlone], (instregex "(Call)?BRASL$")>;
+def : InstRW<[FXa, FXa, FXb, Lat3, GroupAlone], (instregex "(Call)?BAS(R)?$")>;
+def : InstRW<[FXa, FXa, FXb, Lat3, GroupAlone], (instregex "TLS_(G|L)DCALL$")>;
+
+// Return
+def : InstRW<[FXb, EndGroup], (instregex "Return$")>;
+def : InstRW<[FXb], (instregex "CondReturn$")>;
+
+//===----------------------------------------------------------------------===//
+// Select instructions
+//===----------------------------------------------------------------------===//
+
+// Select pseudo
+def : InstRW<[FXa], (instregex "Select(32|64|32Mux)$")>;
+
+// CondStore pseudos
+def : InstRW<[FXa], (instregex "CondStore16(Inv)?$")>;
+def : InstRW<[FXa], (instregex "CondStore16Mux(Inv)?$")>;
+def : InstRW<[FXa], (instregex "CondStore32(Inv)?$")>;
+def : InstRW<[FXa], (instregex "CondStore32Mux(Inv)?$")>;
+def : InstRW<[FXa], (instregex "CondStore64(Inv)?$")>;
+def : InstRW<[FXa], (instregex "CondStore8(Inv)?$")>;
+def : InstRW<[FXa], (instregex "CondStore8Mux(Inv)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Move instructions
+//===----------------------------------------------------------------------===//
+
+// Moves
+def : InstRW<[FXb, LSU, Lat5], (instregex "MV(G|H)?HI$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "MVI(Y)?$")>;
+
+// Move character
+def : InstRW<[FXb, LSU, LSU, LSU, Lat8, GroupAlone], (instregex "MVC$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MVCL(E|U)?$")>;
+
+// Pseudo -> reg move
+def : InstRW<[FXa], (instregex "COPY(_TO_REGCLASS)?$")>;
+def : InstRW<[FXa], (instregex "EXTRACT_SUBREG$")>;
+def : InstRW<[FXa], (instregex "INSERT_SUBREG$")>;
+def : InstRW<[FXa], (instregex "REG_SEQUENCE$")>;
+def : InstRW<[FXa], (instregex "SUBREG_TO_REG$")>;
+
+// Loads
+def : InstRW<[LSU], (instregex "L(Y|FH|RL|Mux|CBB)?$")>;
+def : InstRW<[LSU], (instregex "LG(RL)?$")>;
+def : InstRW<[LSU], (instregex "L128$")>;
+
+def : InstRW<[FXa], (instregex "LLIH(F|H|L)$")>;
+def : InstRW<[FXa], (instregex "LLIL(F|H|L)$")>;
+
+def : InstRW<[FXa], (instregex "LG(F|H)I$")>;
+def : InstRW<[FXa], (instregex "LHI(Mux)?$")>;
+def : InstRW<[FXa], (instregex "LR(Mux)?$")>;
+
+// Load and zero rightmost byte
+def : InstRW<[LSU], (instregex "LZR(F|G)$")>;
+
+// Load and trap
+def : InstRW<[FXb, LSU, Lat5], (instregex "L(FH|G)?AT$")>;
+
+// Load and test
+def : InstRW<[FXa, LSU, Lat5], (instregex "LT(G)?$")>;
+def : InstRW<[FXa], (instregex "LT(G)?R$")>;
+
+// Stores
+def : InstRW<[FXb, LSU, Lat5], (instregex "STG(RL)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "ST128$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "ST(Y|FH|RL|Mux)?$")>;
+
+// String moves.
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MVST$")>;
+
+//===----------------------------------------------------------------------===//
+// Conditional move instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, Lat2], (instregex "LOCRMux$")>;
+def : InstRW<[FXa, Lat2], (instregex "LOC(G|FH)?R(Asm.*)?$")>;
+def : InstRW<[FXa, Lat2], (instregex "LOC(G|H)?HI(Mux|(Asm.*))?$")>;
+def : InstRW<[FXa, LSU, Lat6], (instregex "LOC(G|FH|Mux)?(Asm.*)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "STOC(G|FH|Mux)?(Asm.*)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Sign extensions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa], (instregex "L(B|H|G)R$")>;
+def : InstRW<[FXa], (instregex "LG(B|H|F)R$")>;
+
+def : InstRW<[FXa, LSU, Lat5], (instregex "LTGF$")>;
+def : InstRW<[FXa], (instregex "LTGFR$")>;
+
+def : InstRW<[FXa, LSU, Lat5], (instregex "LB(H|Mux)?$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "LH(Y)?$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "LH(H|Mux|RL)$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "LG(B|H|F)$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "LG(H|F)RL$")>;
+
+//===----------------------------------------------------------------------===//
+// Zero extensions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa], (instregex "LLCR(Mux)?$")>;
+def : InstRW<[FXa], (instregex "LLHR(Mux)?$")>;
+def : InstRW<[FXa], (instregex "LLG(C|H|F|T)R$")>;
+def : InstRW<[LSU], (instregex "LLC(Mux)?$")>;
+def : InstRW<[LSU], (instregex "LLH(Mux)?$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "LL(C|H)H$")>;
+def : InstRW<[LSU], (instregex "LLHRL$")>;
+def : InstRW<[LSU], (instregex "LLG(C|H|F|T|HRL|FRL)$")>;
+
+// Load and zero rightmost byte
+def : InstRW<[LSU], (instregex "LLZRGF$")>;
+
+// Load and trap
+def : InstRW<[FXb, LSU, Lat5], (instregex "LLG(F|T)?AT$")>;
+
+//===----------------------------------------------------------------------===//
+// Truncations
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, LSU, Lat5], (instregex "STC(H|Y|Mux)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "STH(H|Y|RL|Mux)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "STCM(H|Y)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Multi-register moves
+//===----------------------------------------------------------------------===//
+
+// Load multiple (estimated average of 5 ops)
+def : InstRW<[LSU, LSU, LSU, LSU, LSU, Lat10, GroupAlone],
+ (instregex "LM(H|Y|G)?$")>;
+
+// Load multiple disjoint
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "LMD$")>;
+
+// Store multiple (estimated average of ceil(5/2) FXb ops)
+def : InstRW<[LSU, LSU, FXb, FXb, FXb, Lat10,
+ GroupAlone], (instregex "STM(G|H|Y)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Byte swaps
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa], (instregex "LRV(G)?R$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "LRV(G|H)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "STRV(G|H)?$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MVCIN$")>;
+
+//===----------------------------------------------------------------------===//
+// Load address instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa], (instregex "LA(Y|RL)?$")>;
+
+// Load the Global Offset Table address ( -> larl )
+def : InstRW<[FXa], (instregex "GOT$")>;
+
+//===----------------------------------------------------------------------===//
+// Absolute and Negation
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa], (instregex "LP(G)?R$")>;
+def : InstRW<[FXa, FXa, Lat2, BeginGroup], (instregex "L(N|P)GFR$")>;
+def : InstRW<[FXa], (instregex "LN(R|GR)$")>;
+def : InstRW<[FXa], (instregex "LC(R|GR)$")>;
+def : InstRW<[FXa, FXa, Lat2, BeginGroup], (instregex "LCGFR$")>;
+
+//===----------------------------------------------------------------------===//
+// Insertion
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, LSU, Lat5], (instregex "IC(Y)?$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "IC32(Y)?$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "ICM(H|Y)?$")>;
+def : InstRW<[FXa], (instregex "II(F|H|L)Mux$")>;
+def : InstRW<[FXa], (instregex "IIHF(64)?$")>;
+def : InstRW<[FXa], (instregex "IIHH(64)?$")>;
+def : InstRW<[FXa], (instregex "IIHL(64)?$")>;
+def : InstRW<[FXa], (instregex "IILF(64)?$")>;
+def : InstRW<[FXa], (instregex "IILH(64)?$")>;
+def : InstRW<[FXa], (instregex "IILL(64)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Addition
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, LSU, Lat5], (instregex "A(Y)?$")>;
+def : InstRW<[FXa, LSU, Lat6], (instregex "AH(Y)?$")>;
+def : InstRW<[FXa], (instregex "AIH$")>;
+def : InstRW<[FXa], (instregex "AFI(Mux)?$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "AG$")>;
+def : InstRW<[FXa], (instregex "AGFI$")>;
+def : InstRW<[FXa], (instregex "AGHI(K)?$")>;
+def : InstRW<[FXa], (instregex "AGR(K)?$")>;
+def : InstRW<[FXa], (instregex "AHI(K)?$")>;
+def : InstRW<[FXa], (instregex "AHIMux(K)?$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "AL(Y)?$")>;
+def : InstRW<[FXa], (instregex "AL(FI|HSIK)$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "ALG(F)?$")>;
+def : InstRW<[FXa], (instregex "ALGHSIK$")>;
+def : InstRW<[FXa], (instregex "ALGF(I|R)$")>;
+def : InstRW<[FXa], (instregex "ALGR(K)?$")>;
+def : InstRW<[FXa], (instregex "ALR(K)?$")>;
+def : InstRW<[FXa], (instregex "AR(K)?$")>;
+def : InstRW<[FXa], (instregex "A(L)?HHHR$")>;
+def : InstRW<[FXa, Lat2], (instregex "A(L)?HHLR$")>;
+def : InstRW<[FXa], (instregex "ALSIH(N)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "A(L)?(G)?SI$")>;
+
+// Logical addition with carry
+def : InstRW<[FXa, LSU, Lat6, GroupAlone], (instregex "ALC(G)?$")>;
+def : InstRW<[FXa, Lat2, GroupAlone], (instregex "ALC(G)?R$")>;
+
+// Add with sign extension (16/32 -> 64)
+def : InstRW<[FXa, LSU, Lat6], (instregex "AG(F|H)$")>;
+def : InstRW<[FXa, Lat2], (instregex "AGFR$")>;
+
+//===----------------------------------------------------------------------===//
+// Subtraction
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, LSU, Lat5], (instregex "S(G|Y)?$")>;
+def : InstRW<[FXa, LSU, Lat6], (instregex "SH(Y)?$")>;
+def : InstRW<[FXa], (instregex "SGR(K)?$")>;
+def : InstRW<[FXa], (instregex "SLFI$")>;
+def : InstRW<[FXa, LSU, Lat5], (instregex "SL(G|GF|Y)?$")>;
+def : InstRW<[FXa], (instregex "SLGF(I|R)$")>;
+def : InstRW<[FXa], (instregex "SLGR(K)?$")>;
+def : InstRW<[FXa], (instregex "SLR(K)?$")>;
+def : InstRW<[FXa], (instregex "SR(K)?$")>;
+def : InstRW<[FXa], (instregex "S(L)?HHHR$")>;
+def : InstRW<[FXa, Lat2], (instregex "S(L)?HHLR$")>;
+
+// Subtraction with borrow
+def : InstRW<[FXa, LSU, Lat6, GroupAlone], (instregex "SLB(G)?$")>;
+def : InstRW<[FXa, Lat2, GroupAlone], (instregex "SLB(G)?R$")>;
+
+// Subtraction with sign extension (16/32 -> 64)
+def : InstRW<[FXa, LSU, Lat6], (instregex "SG(F|H)$")>;
+def : InstRW<[FXa, Lat2], (instregex "SGFR$")>;
+
+//===----------------------------------------------------------------------===//
+// AND
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, LSU, Lat5], (instregex "N(G|Y)?$")>;
+def : InstRW<[FXa], (instregex "NGR(K)?$")>;
+def : InstRW<[FXa], (instregex "NI(FMux|HMux|LMux)$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "NI(Y)?$")>;
+def : InstRW<[FXa], (instregex "NIHF(64)?$")>;
+def : InstRW<[FXa], (instregex "NIHH(64)?$")>;
+def : InstRW<[FXa], (instregex "NIHL(64)?$")>;
+def : InstRW<[FXa], (instregex "NILF(64)?$")>;
+def : InstRW<[FXa], (instregex "NILH(64)?$")>;
+def : InstRW<[FXa], (instregex "NILL(64)?$")>;
+def : InstRW<[FXa], (instregex "NR(K)?$")>;
+def : InstRW<[LSU, LSU, FXb, Lat9, BeginGroup], (instregex "NC$")>;
+
+//===----------------------------------------------------------------------===//
+// OR
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, LSU, Lat5], (instregex "O(G|Y)?$")>;
+def : InstRW<[FXa], (instregex "OGR(K)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "OI(Y)?$")>;
+def : InstRW<[FXa], (instregex "OI(FMux|HMux|LMux)$")>;
+def : InstRW<[FXa], (instregex "OIHF(64)?$")>;
+def : InstRW<[FXa], (instregex "OIHH(64)?$")>;
+def : InstRW<[FXa], (instregex "OIHL(64)?$")>;
+def : InstRW<[FXa], (instregex "OILF(64)?$")>;
+def : InstRW<[FXa], (instregex "OILH(64)?$")>;
+def : InstRW<[FXa], (instregex "OILL(64)?$")>;
+def : InstRW<[FXa], (instregex "OR(K)?$")>;
+def : InstRW<[LSU, LSU, FXb, Lat9, BeginGroup], (instregex "OC$")>;
+
+//===----------------------------------------------------------------------===//
+// XOR
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, LSU, Lat5], (instregex "X(G|Y)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "XI(Y)?$")>;
+def : InstRW<[FXa], (instregex "XIFMux$")>;
+def : InstRW<[FXa], (instregex "XGR(K)?$")>;
+def : InstRW<[FXa], (instregex "XIHF(64)?$")>;
+def : InstRW<[FXa], (instregex "XILF(64)?$")>;
+def : InstRW<[FXa], (instregex "XR(K)?$")>;
+def : InstRW<[LSU, LSU, FXb, Lat9, BeginGroup], (instregex "XC$")>;
+
+//===----------------------------------------------------------------------===//
+// Multiplication
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, LSU, Lat9], (instregex "MS(GF|Y)?$")>;
+def : InstRW<[FXa, Lat5], (instregex "MS(R|FI)$")>;
+def : InstRW<[FXa, LSU, Lat11], (instregex "MSG$")>;
+def : InstRW<[FXa, Lat7], (instregex "MSGR$")>;
+def : InstRW<[FXa, Lat5], (instregex "MSGF(I|R)$")>;
+def : InstRW<[FXa2, LSU, Lat12, GroupAlone], (instregex "MLG$")>;
+def : InstRW<[FXa2, Lat8, GroupAlone], (instregex "MLGR$")>;
+def : InstRW<[FXa, Lat4], (instregex "MGHI$")>;
+def : InstRW<[FXa, Lat4], (instregex "MHI$")>;
+def : InstRW<[FXa, LSU, Lat8], (instregex "MH(Y)?$")>;
+def : InstRW<[FXa2, Lat6, GroupAlone], (instregex "M(L)?R$")>;
+def : InstRW<[FXa2, LSU, Lat10, GroupAlone], (instregex "M(FY|L)?$")>;
+def : InstRW<[FXa, LSU, Lat8], (instregex "MGH$")>;
+def : InstRW<[FXa, LSU, Lat12, GroupAlone], (instregex "MG$")>;
+def : InstRW<[FXa, Lat8, GroupAlone], (instregex "MGRK$")>;
+def : InstRW<[FXa, LSU, Lat9, GroupAlone], (instregex "MSC$")>;
+def : InstRW<[FXa, LSU, Lat11, GroupAlone], (instregex "MSGC$")>;
+def : InstRW<[FXa, Lat5], (instregex "MSRKC$")>;
+def : InstRW<[FXa, Lat7], (instregex "MSGRKC$")>;
+
+//===----------------------------------------------------------------------===//
+// Division and remainder
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa2, FXa2, Lat20, GroupAlone], (instregex "DR$")>;
+def : InstRW<[FXa2, FXa2, LSU, Lat30, GroupAlone], (instregex "D$")>;
+def : InstRW<[FXa2, Lat30, GroupAlone], (instregex "DSG(F)?R$")>;
+def : InstRW<[LSU, FXa2, Lat30, GroupAlone], (instregex "DSG(F)?$")>;
+def : InstRW<[FXa2, FXa2, Lat20, GroupAlone], (instregex "DLR$")>;
+def : InstRW<[FXa2, FXa2, Lat30, GroupAlone], (instregex "DLGR$")>;
+def : InstRW<[FXa2, FXa2, LSU, Lat30, GroupAlone], (instregex "DL(G)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Shifts
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa], (instregex "SLL(G|K)?$")>;
+def : InstRW<[FXa], (instregex "SRL(G|K)?$")>;
+def : InstRW<[FXa], (instregex "SRA(G|K)?$")>;
+def : InstRW<[FXa], (instregex "SLA(G|K)?$")>;
+def : InstRW<[FXa, FXa, FXa, FXa, LSU, Lat8, GroupAlone],
+ (instregex "S(L|R)D(A|L)$")>;
+
+// Rotate
+def : InstRW<[FXa, LSU, Lat6], (instregex "RLL(G)?$")>;
+
+// Rotate and insert
+def : InstRW<[FXa], (instregex "RISBG(N|32)?$")>;
+def : InstRW<[FXa], (instregex "RISBH(G|H|L)$")>;
+def : InstRW<[FXa], (instregex "RISBL(G|H|L)$")>;
+def : InstRW<[FXa], (instregex "RISBMux$")>;
+
+// Rotate and Select
+def : InstRW<[FXa, FXa, Lat2, BeginGroup], (instregex "R(N|O|X)SBG$")>;
+
+//===----------------------------------------------------------------------===//
+// Comparison
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, LSU, Lat5], (instregex "C(G|Y|Mux|RL)?$")>;
+def : InstRW<[FXb], (instregex "C(F|H)I(Mux)?$")>;
+def : InstRW<[FXb], (instregex "CG(F|H)I$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CG(HSI|RL)$")>;
+def : InstRW<[FXb], (instregex "C(G)?R$")>;
+def : InstRW<[FXb], (instregex "CIH$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CH(F|SI)$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CL(Y|Mux|FHSI)?$")>;
+def : InstRW<[FXb], (instregex "CLFI(Mux)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CLG(HRL|HSI)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CLGF(RL)?$")>;
+def : InstRW<[FXb], (instregex "CLGF(I|R)$")>;
+def : InstRW<[FXb], (instregex "CLGR$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CLGRL$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CLH(F|RL|HSI)$")>;
+def : InstRW<[FXb], (instregex "CLIH$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CLI(Y)?$")>;
+def : InstRW<[FXb], (instregex "CLR$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "CLRL$")>;
+def : InstRW<[FXb], (instregex "C(L)?HHR$")>;
+def : InstRW<[FXb, Lat2], (instregex "C(L)?HLR$")>;
+
+// Compare halfword
+def : InstRW<[FXb, LSU, Lat6], (instregex "CH(Y|RL)?$")>;
+def : InstRW<[FXb, LSU, Lat6], (instregex "CGH(RL)?$")>;
+def : InstRW<[FXa, FXb, LSU, Lat6, BeginGroup], (instregex "CHHSI$")>;
+
+// Compare with sign extension (32 -> 64)
+def : InstRW<[FXb, LSU, Lat6], (instregex "CGF(RL)?$")>;
+def : InstRW<[FXb, Lat2], (instregex "CGFR$")>;
+
+// Compare logical character
+def : InstRW<[FXb, LSU, LSU, Lat9, BeginGroup], (instregex "CLC$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CLCL(E|U)?$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CLST$")>;
+
+// Test under mask
+def : InstRW<[FXb, LSU, Lat5], (instregex "TM(Y)?$")>;
+def : InstRW<[FXb], (instregex "TM(H|L)Mux$")>;
+def : InstRW<[FXb], (instregex "TMHH(64)?$")>;
+def : InstRW<[FXb], (instregex "TMHL(64)?$")>;
+def : InstRW<[FXb], (instregex "TMLH(64)?$")>;
+def : InstRW<[FXb], (instregex "TMLL(64)?$")>;
+
+// Compare logical characters under mask
+def : InstRW<[FXb, LSU, Lat6], (instregex "CLM(H|Y)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Prefetch and execution hint
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[LSU], (instregex "PFD(RL)?$")>;
+def : InstRW<[FXb, Lat2], (instregex "BPP$")>;
+def : InstRW<[FXb, EndGroup], (instregex "BPRP$")>;
+def : InstRW<[FXb], (instregex "NIAI$")>;
+
+//===----------------------------------------------------------------------===//
+// Atomic operations
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, EndGroup], (instregex "Serialize$")>;
+
+def : InstRW<[FXb, LSU, Lat5], (instregex "LAA(G)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "LAAL(G)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "LAN(G)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "LAO(G)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "LAX(G)?$")>;
+
+// Test and set
+def : InstRW<[FXb, LSU, Lat5, EndGroup], (instregex "TS$")>;
+
+// Compare and swap
+def : InstRW<[FXa, FXb, LSU, Lat6, GroupAlone], (instregex "CS(G|Y)?$")>;
+
+// Compare double and swap
+def : InstRW<[FXa, FXa, FXb, FXb, FXa, LSU, Lat10, GroupAlone],
+ (instregex "CDS(Y)?$")>;
+def : InstRW<[FXa, FXa, FXb, FXb, LSU, FXb, FXb, LSU, LSU, Lat20, GroupAlone],
+ (instregex "CDSG$")>;
+
+// Compare and swap and store
+def : InstRW<[FXa, LSU, Lat30], (instregex "CSST$")>;
+
+// Perform locked operation
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "PLO$")>;
+
+// Load/store pair from/to quadword
+def : InstRW<[LSU, LSU, Lat5, GroupAlone], (instregex "LPQ$")>;
+def : InstRW<[FXb, FXb, LSU, Lat6, GroupAlone], (instregex "STPQ$")>;
+
+// Load pair disjoint
+def : InstRW<[LSU, LSU, Lat5, GroupAlone], (instregex "LPD(G)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Translate and convert
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "TR$")>;
+def : InstRW<[FXa, FXa, FXa, LSU, LSU, Lat30, GroupAlone], (instregex "TRT$")>;
+def : InstRW<[FXa, LSU, Lat30], (instregex "TRTR$")>;
+def : InstRW<[FXa, Lat30], (instregex "TR(TR)?(T)?(E|EOpt)?$")>;
+def : InstRW<[LSU, Lat30], (instregex "TR(T|O)(T|O)(Opt)?$")>;
+def : InstRW<[FXa, Lat30], (instregex "CU(12|14|21|24|41|42)(Opt)?$")>;
+def : InstRW<[FXa, Lat30], (instregex "(CUUTF|CUTFU)(Opt)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Message-security assist
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, Lat30], (instregex "KM(C|F|O|CTR|A)?$")>;
+def : InstRW<[FXa, Lat30], (instregex "(KIMD|KLMD|KMAC)$")>;
+def : InstRW<[FXa, Lat30], (instregex "(PCC|PPNO|PRNO)$")>;
+
+//===----------------------------------------------------------------------===//
+// Guarded storage
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[LSU], (instregex "LGG$")>;
+def : InstRW<[LSU, Lat5], (instregex "LLGFSG$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "(L|ST)GSC$")>;
+
+//===----------------------------------------------------------------------===//
+// Decimal arithmetic
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, VecDF, VecDF, LSU, LSU, Lat30, GroupAlone],
+ (instregex "CVBG$")>;
+def : InstRW<[FXb, VecDF, LSU, Lat30, GroupAlone], (instregex "CVB(Y)?$")>;
+def : InstRW<[FXb, FXb, FXb, VecDF2, VecDF2, LSU, Lat30, GroupAlone],
+ (instregex "CVDG$")>;
+def : InstRW<[FXb, VecDF, FXb, LSU, Lat30, GroupAlone], (instregex "CVD(Y)?$")>;
+def : InstRW<[LSU, Lat10, GroupAlone], (instregex "MVO$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MV(N|Z)$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "(PACK|PKA|PKU)$")>;
+def : InstRW<[LSU, Lat12, GroupAlone], (instregex "UNPK(A|U)$")>;
+def : InstRW<[FXb, LSU, LSU, Lat9, BeginGroup], (instregex "UNPK$")>;
+
+def : InstRW<[FXb, VecDFX, LSU, LSU, LSU, Lat9, GroupAlone],
+ (instregex "(A|S|ZA)P$")>;
+def : InstRW<[FXb, VecDFX2, VecDFX2, LSU, LSU, LSU, Lat30, GroupAlone],
+ (instregex "(M|D)P$")>;
+def : InstRW<[FXb, VecDFX, VecDFX, LSU, LSU, Lat15, GroupAlone],
+ (instregex "SRP$")>;
+def : InstRW<[VecDFX, LSU, LSU, Lat5, GroupAlone], (instregex "CP$")>;
+def : InstRW<[VecDFX, LSU, Lat4, BeginGroup], (instregex "TP$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "ED(MK)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Access registers
+//===----------------------------------------------------------------------===//
+
+// Extract/set/copy access register
+def : InstRW<[LSU], (instregex "(EAR|SAR|CPYA)$")>;
+
+// Load address extended
+def : InstRW<[LSU, FXa, Lat5, BeginGroup], (instregex "LAE(Y)?$")>;
+
+// Load/store access multiple (not modeled precisely)
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "(L|ST)AM(Y)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Program mask and addressing mode
+//===----------------------------------------------------------------------===//
+
+// Insert Program Mask
+def : InstRW<[FXa, Lat3, EndGroup], (instregex "IPM$")>;
+
+// Set Program Mask
+def : InstRW<[LSU, EndGroup], (instregex "SPM$")>;
+
+// Branch and link
+def : InstRW<[FXa, FXa, FXb, Lat5, GroupAlone], (instregex "BAL(R)?$")>;
+
+// Test addressing mode
+def : InstRW<[FXb], (instregex "TAM$")>;
+
+// Set addressing mode
+def : InstRW<[FXb, Lat2, EndGroup], (instregex "SAM(24|31|64)$")>;
+
+// Branch (and save) and set mode.
+def : InstRW<[FXa, FXb, Lat2, GroupAlone], (instregex "BSM$")>;
+def : InstRW<[FXa, FXa, FXb, Lat3, GroupAlone], (instregex "BASSM$")>;
+
+//===----------------------------------------------------------------------===//
+// Transactional execution
+//===----------------------------------------------------------------------===//
+
+// Transaction begin
+def : InstRW<[LSU, LSU, FXb, FXb, FXb, FXb, FXb, Lat15, GroupAlone],
+ (instregex "TBEGIN(C|_nofloat)?$")>;
+
+// Transaction end
+def : InstRW<[FXb, GroupAlone], (instregex "TEND$")>;
+
+// Transaction abort
+def : InstRW<[LSU, GroupAlone], (instregex "TABORT$")>;
+
+// Extract Transaction Nesting Depth
+def : InstRW<[FXa], (instregex "ETND$")>;
+
+// Nontransactional store
+def : InstRW<[FXb, LSU, Lat5], (instregex "NTSTG$")>;
+
+//===----------------------------------------------------------------------===//
+// Processor assist
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb], (instregex "PPA$")>;
+
+//===----------------------------------------------------------------------===//
+// Miscellaneous Instructions.
+//===----------------------------------------------------------------------===//
+
+// Find leftmost one
+def : InstRW<[FXa, FXa, Lat4, GroupAlone], (instregex "FLOGR$")>;
+
+// Population count
+def : InstRW<[FXa, Lat3], (instregex "POPCNT$")>;
+
+// Extend
+def : InstRW<[FXa], (instregex "AEXT128$")>;
+def : InstRW<[FXa], (instregex "ZEXT128$")>;
+
+// String instructions
+def : InstRW<[FXa, LSU, Lat30], (instregex "SRST$")>;
+def : InstRW<[FXa, Lat30], (instregex "SRSTU$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CUSE$")>;
+
+// Various complex instructions
+def : InstRW<[LSU, Lat30], (instregex "CFC$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "UPT$")>;
+def : InstRW<[LSU, Lat30], (instregex "CKSM$")>;
+def : InstRW<[FXa, Lat30], (instregex "CMPSC$")>;
+
+// Execute
+def : InstRW<[FXb, GroupAlone], (instregex "EX(RL)?$")>;
+
+//===----------------------------------------------------------------------===//
+// .insn directive instructions
+//===----------------------------------------------------------------------===//
+
+// An "empty" sched-class will be assigned instead of the "invalid sched-class".
+// getNumDecoderSlots() will then return 1 instead of 0.
+def : InstRW<[], (instregex "Insn.*")>;
+
+
+// ----------------------------- Floating point ----------------------------- //
+
+//===----------------------------------------------------------------------===//
+// FP: Select instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa], (instregex "Select(F32|F64|F128|VR128)$")>;
+def : InstRW<[FXa], (instregex "CondStoreF32(Inv)?$")>;
+def : InstRW<[FXa], (instregex "CondStoreF64(Inv)?$")>;
+
+//===----------------------------------------------------------------------===//
+// FP: Move instructions
+//===----------------------------------------------------------------------===//
+
+// Load zero
+def : InstRW<[FXb], (instregex "LZ(DR|ER)$")>;
+def : InstRW<[FXb, FXb, Lat2, BeginGroup], (instregex "LZXR$")>;
+
+// Load
+def : InstRW<[VecXsPm], (instregex "LER$")>;
+def : InstRW<[FXb], (instregex "LD(R|R32|GR)$")>;
+def : InstRW<[FXb, Lat3], (instregex "LGDR$")>;
+def : InstRW<[FXb, FXb, Lat2, GroupAlone], (instregex "LXR$")>;
+
+// Load and Test
+def : InstRW<[VecXsPm, Lat4], (instregex "LT(D|E)BR$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "LTEBRCompare(_VecPseudo)?$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "LTDBRCompare(_VecPseudo)?$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "LTXBR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone],
+ (instregex "LTXBRCompare(_VecPseudo)?$")>;
+
+// Copy sign
+def : InstRW<[VecXsPm], (instregex "CPSDRd(d|s)$")>;
+def : InstRW<[VecXsPm], (instregex "CPSDRs(d|s)$")>;
+
+//===----------------------------------------------------------------------===//
+// FP: Load instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[VecXsPm, LSU, Lat7], (instregex "LE(Y)?$")>;
+def : InstRW<[LSU], (instregex "LD(Y|E32)?$")>;
+def : InstRW<[LSU], (instregex "LX$")>;
+
+//===----------------------------------------------------------------------===//
+// FP: Store instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, LSU, Lat7], (instregex "STD(Y)?$")>;
+def : InstRW<[FXb, LSU, Lat7], (instregex "STE(Y)?$")>;
+def : InstRW<[FXb, LSU, Lat5], (instregex "STX$")>;
+
+//===----------------------------------------------------------------------===//
+// FP: Conversion instructions
+//===----------------------------------------------------------------------===//
+
+// Load rounded
+def : InstRW<[VecBF], (instregex "LEDBR(A)?$")>;
+def : InstRW<[VecDF, VecDF, Lat20], (instregex "LEXBR(A)?$")>;
+def : InstRW<[VecDF, VecDF, Lat20], (instregex "LDXBR(A)?$")>;
+
+// Load lengthened
+def : InstRW<[VecBF, LSU, Lat12], (instregex "LDEB$")>;
+def : InstRW<[VecBF], (instregex "LDEBR$")>;
+def : InstRW<[VecBF2, VecBF2, LSU, Lat12 , GroupAlone], (instregex "LX(D|E)B$")>;
+def : InstRW<[VecBF2, VecBF2, GroupAlone], (instregex "LX(D|E)BR$")>;
+
+// Convert from fixed / logical
+def : InstRW<[FXb, VecBF, Lat9, BeginGroup], (instregex "CE(F|G)BR(A)?$")>;
+def : InstRW<[FXb, VecBF, Lat9, BeginGroup], (instregex "CD(F|G)BR(A)?$")>;
+def : InstRW<[FXb, VecDF2, VecDF2, Lat12, GroupAlone], (instregex "CX(F|G)BR(A)?$")>;
+def : InstRW<[FXb, VecBF, Lat9, BeginGroup], (instregex "CEL(F|G)BR$")>;
+def : InstRW<[FXb, VecBF, Lat9, BeginGroup], (instregex "CDL(F|G)BR$")>;
+def : InstRW<[FXb, VecDF2, VecDF2, Lat12, GroupAlone], (instregex "CXL(F|G)BR$")>;
+
+// Convert to fixed / logical
+def : InstRW<[FXb, VecBF, Lat11, BeginGroup], (instregex "CF(E|D)BR(A)?$")>;
+def : InstRW<[FXb, VecBF, Lat11, BeginGroup], (instregex "CG(E|D)BR(A)?$")>;
+def : InstRW<[FXb, VecDF, VecDF, Lat20, BeginGroup], (instregex "C(F|G)XBR(A)?$")>;
+def : InstRW<[FXb, VecBF, Lat11, GroupAlone], (instregex "CLFEBR$")>;
+def : InstRW<[FXb, VecBF, Lat11, BeginGroup], (instregex "CLFDBR$")>;
+def : InstRW<[FXb, VecBF, Lat11, BeginGroup], (instregex "CLG(E|D)BR$")>;
+def : InstRW<[FXb, VecDF, VecDF, Lat20, BeginGroup], (instregex "CL(F|G)XBR$")>;
+
+//===----------------------------------------------------------------------===//
+// FP: Unary arithmetic
+//===----------------------------------------------------------------------===//
+
+// Load Complement / Negative / Positive
+def : InstRW<[VecXsPm, Lat4], (instregex "L(C|N|P)DBR$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "L(C|N|P)EBR$")>;
+def : InstRW<[FXb], (instregex "LCDFR(_32)?$")>;
+def : InstRW<[FXb], (instregex "LNDFR(_32)?$")>;
+def : InstRW<[FXb], (instregex "LPDFR(_32)?$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "L(C|N|P)XBR$")>;
+
+// Square root
+def : InstRW<[VecFPd, LSU], (instregex "SQ(E|D)B$")>;
+def : InstRW<[VecFPd], (instregex "SQ(E|D)BR$")>;
+def : InstRW<[VecFPd, VecFPd, GroupAlone], (instregex "SQXBR$")>;
+
+// Load FP integer
+def : InstRW<[VecBF], (instregex "FIEBR(A)?$")>;
+def : InstRW<[VecBF], (instregex "FIDBR(A)?$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "FIXBR(A)?$")>;
+
+//===----------------------------------------------------------------------===//
+// FP: Binary arithmetic
+//===----------------------------------------------------------------------===//
+
+// Addition
+def : InstRW<[VecBF, LSU, Lat12], (instregex "A(E|D)B$")>;
+def : InstRW<[VecBF], (instregex "A(E|D)BR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat10, GroupAlone], (instregex "AXBR$")>;
+
+// Subtraction
+def : InstRW<[VecBF, LSU, Lat12], (instregex "S(E|D)B$")>;
+def : InstRW<[VecBF], (instregex "S(E|D)BR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "SXBR$")>;
+
+// Multiply
+def : InstRW<[VecBF, LSU, Lat12], (instregex "M(D|DE|EE)B$")>;
+def : InstRW<[VecBF], (instregex "M(D|DE|EE)BR$")>;
+def : InstRW<[VecBF2, VecBF2, LSU, Lat12, GroupAlone], (instregex "MXDB$")>;
+def : InstRW<[VecBF2, VecBF2, GroupAlone], (instregex "MXDBR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat20, GroupAlone], (instregex "MXBR$")>;
+
+// Multiply and add / subtract
+def : InstRW<[VecBF2, LSU, Lat12, GroupAlone], (instregex "M(A|S)EB$")>;
+def : InstRW<[VecBF, GroupAlone], (instregex "M(A|S)EBR$")>;
+def : InstRW<[VecBF2, LSU, Lat12, GroupAlone], (instregex "M(A|S)DB$")>;
+def : InstRW<[VecBF], (instregex "M(A|S)DBR$")>;
+
+// Division
+def : InstRW<[VecFPd, LSU], (instregex "D(E|D)B$")>;
+def : InstRW<[VecFPd], (instregex "D(E|D)BR$")>;
+def : InstRW<[VecFPd, VecFPd, GroupAlone], (instregex "DXBR$")>;
+
+// Divide to integer
+def : InstRW<[VecFPd, Lat30], (instregex "DI(E|D)BR$")>;
+
+//===----------------------------------------------------------------------===//
+// FP: Comparisons
+//===----------------------------------------------------------------------===//
+
+// Compare
+def : InstRW<[VecXsPm, LSU, Lat8], (instregex "(K|C)(E|D)B$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "(K|C)(E|D)BR?$")>;
+def : InstRW<[VecDF, VecDF, Lat20, GroupAlone], (instregex "(K|C)XBR$")>;
+
+// Test Data Class
+def : InstRW<[LSU, VecXsPm, Lat9], (instregex "TC(E|D)B$")>;
+def : InstRW<[LSU, VecDF2, VecDF2, Lat15, GroupAlone], (instregex "TCXB$")>;
+
+//===----------------------------------------------------------------------===//
+// FP: Floating-point control register instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, LSU, Lat4, GroupAlone], (instregex "EFPC$")>;
+def : InstRW<[FXb, LSU, Lat5, GroupAlone], (instregex "STFPC$")>;
+def : InstRW<[LSU, Lat3, GroupAlone], (instregex "SFPC$")>;
+def : InstRW<[LSU, LSU, Lat6, GroupAlone], (instregex "LFPC$")>;
+def : InstRW<[FXa, Lat30], (instregex "SFASR$")>;
+def : InstRW<[FXa, LSU, Lat30], (instregex "LFAS$")>;
+def : InstRW<[FXb, Lat3, GroupAlone], (instregex "SRNM(B|T)?$")>;
+
+
+// --------------------- Hexadecimal floating point ------------------------- //
+
+//===----------------------------------------------------------------------===//
+// HFP: Move instructions
+//===----------------------------------------------------------------------===//
+
+// Load and Test
+def : InstRW<[VecXsPm, Lat4], (instregex "LT(D|E)R$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "LTXR$")>;
+
+//===----------------------------------------------------------------------===//
+// HFP: Conversion instructions
+//===----------------------------------------------------------------------===//
+
+// Load rounded
+def : InstRW<[VecBF], (instregex "(LEDR|LRER)$")>;
+def : InstRW<[VecBF], (instregex "LEXR$")>;
+def : InstRW<[VecDF2], (instregex "(LDXR|LRDR)$")>;
+
+// Load lengthened
+def : InstRW<[LSU], (instregex "LDE$")>;
+def : InstRW<[FXb], (instregex "LDER$")>;
+def : InstRW<[VecBF2, VecBF2, LSU, Lat12, GroupAlone], (instregex "LX(D|E)$")>;
+def : InstRW<[VecBF2, VecBF2, GroupAlone], (instregex "LX(D|E)R$")>;
+
+// Convert from fixed
+def : InstRW<[FXb, VecBF, Lat9, BeginGroup], (instregex "CE(F|G)R$")>;
+def : InstRW<[FXb, VecBF, Lat9, BeginGroup], (instregex "CD(F|G)R$")>;
+def : InstRW<[FXb, VecDF2, VecDF2, Lat12, GroupAlone], (instregex "CX(F|G)R$")>;
+
+// Convert to fixed
+def : InstRW<[FXb, VecBF, Lat11, BeginGroup], (instregex "CF(E|D)R$")>;
+def : InstRW<[FXb, VecBF, Lat11, BeginGroup], (instregex "CG(E|D)R$")>;
+def : InstRW<[FXb, VecDF, VecDF, Lat20, BeginGroup], (instregex "C(F|G)XR$")>;
+
+// Convert BFP to HFP / HFP to BFP.
+def : InstRW<[VecBF], (instregex "THD(E)?R$")>;
+def : InstRW<[VecBF], (instregex "TB(E)?DR$")>;
+
+//===----------------------------------------------------------------------===//
+// HFP: Unary arithmetic
+//===----------------------------------------------------------------------===//
+
+// Load Complement / Negative / Positive
+def : InstRW<[VecXsPm, Lat4], (instregex "L(C|N|P)DR$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "L(C|N|P)ER$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "L(C|N|P)XR$")>;
+
+// Halve
+def : InstRW<[VecBF], (instregex "H(E|D)R$")>;
+
+// Square root
+def : InstRW<[VecFPd, LSU], (instregex "SQ(E|D)$")>;
+def : InstRW<[VecFPd], (instregex "SQ(E|D)R$")>;
+def : InstRW<[VecFPd, VecFPd, GroupAlone], (instregex "SQXR$")>;
+
+// Load FP integer
+def : InstRW<[VecBF], (instregex "FIER$")>;
+def : InstRW<[VecBF], (instregex "FIDR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "FIXR$")>;
+
+//===----------------------------------------------------------------------===//
+// HFP: Binary arithmetic
+//===----------------------------------------------------------------------===//
+
+// Addition
+def : InstRW<[VecBF, LSU, Lat12], (instregex "A(E|D|U|W)$")>;
+def : InstRW<[VecBF], (instregex "A(E|D|U|W)R$")>;
+def : InstRW<[VecDF2, VecDF2, Lat10, GroupAlone], (instregex "AXR$")>;
+
+// Subtraction
+def : InstRW<[VecBF, LSU, Lat12], (instregex "S(E|D|U|W)$")>;
+def : InstRW<[VecBF], (instregex "S(E|D|U|W)R$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "SXR$")>;
+
+// Multiply
+def : InstRW<[VecBF, LSU, Lat12], (instregex "M(D|DE|E|EE)$")>;
+def : InstRW<[VecBF], (instregex "M(D|DE|E|EE)R$")>;
+def : InstRW<[VecBF2, VecBF2, LSU, Lat12, GroupAlone], (instregex "MXD$")>;
+def : InstRW<[VecBF2, VecBF2, GroupAlone], (instregex "MXDR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat20, GroupAlone], (instregex "MXR$")>;
+def : InstRW<[VecBF2, VecBF2, LSU, Lat12, GroupAlone], (instregex "MY$")>;
+def : InstRW<[VecBF2, LSU, Lat12, GroupAlone], (instregex "MY(H|L)$")>;
+def : InstRW<[VecBF2, VecBF2, GroupAlone], (instregex "MYR$")>;
+def : InstRW<[VecBF, GroupAlone], (instregex "MY(H|L)R$")>;
+
+// Multiply and add / subtract
+def : InstRW<[VecBF2, LSU, Lat12, GroupAlone], (instregex "M(A|S)E$")>;
+def : InstRW<[VecBF, GroupAlone], (instregex "M(A|S)ER$")>;
+def : InstRW<[VecBF2, LSU, Lat12, GroupAlone], (instregex "M(A|S)D$")>;
+def : InstRW<[VecBF, GroupAlone], (instregex "M(A|S)DR$")>;
+def : InstRW<[VecBF2, LSU, Lat12, GroupAlone], (instregex "MAY(H|L)$")>;
+def : InstRW<[VecBF2, VecBF2, LSU, Lat12, GroupAlone], (instregex "MAY$")>;
+def : InstRW<[VecBF, GroupAlone], (instregex "MAY(H|L)R$")>;
+def : InstRW<[VecBF2, VecBF2, GroupAlone], (instregex "MAYR$")>;
+
+// Division
+def : InstRW<[VecFPd, LSU], (instregex "D(E|D)$")>;
+def : InstRW<[VecFPd], (instregex "D(E|D)R$")>;
+def : InstRW<[VecFPd, VecFPd, GroupAlone], (instregex "DXR$")>;
+
+//===----------------------------------------------------------------------===//
+// HFP: Comparisons
+//===----------------------------------------------------------------------===//
+
+// Compare
+def : InstRW<[VecBF, LSU, Lat12], (instregex "C(E|D)$")>;
+def : InstRW<[VecBF], (instregex "C(E|D)R$")>;
+def : InstRW<[VecDF, VecDF, Lat20, GroupAlone], (instregex "CXR$")>;
+
+
+// ------------------------ Decimal floating point -------------------------- //
+
+//===----------------------------------------------------------------------===//
+// DFP: Move instructions
+//===----------------------------------------------------------------------===//
+
+// Load and Test
+def : InstRW<[VecDF], (instregex "LTDTR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "LTXTR$")>;
+
+//===----------------------------------------------------------------------===//
+// DFP: Conversion instructions
+//===----------------------------------------------------------------------===//
+
+// Load rounded
+def : InstRW<[VecDF, Lat15], (instregex "LEDTR$")>;
+def : InstRW<[VecDF, VecDF, Lat20], (instregex "LDXTR$")>;
+
+// Load lengthened
+def : InstRW<[VecDF], (instregex "LDETR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "LXDTR$")>;
+
+// Convert from fixed / logical
+def : InstRW<[FXb, VecDF, Lat30, BeginGroup], (instregex "CD(F|G)TR(A)?$")>;
+def : InstRW<[FXb, VecDF2, VecDF2, Lat30, GroupAlone], (instregex "CX(F|G)TR(A)?$")>;
+def : InstRW<[FXb, VecDF, Lat30, BeginGroup], (instregex "CDL(F|G)TR$")>;
+def : InstRW<[FXb, VecDF2, VecDF2, Lat30, GroupAlone], (instregex "CXL(F|G)TR$")>;
+
+// Convert to fixed / logical
+def : InstRW<[FXb, VecDF, Lat30, BeginGroup], (instregex "C(F|G)DTR(A)?$")>;
+def : InstRW<[FXb, VecDF, VecDF, Lat30, BeginGroup], (instregex "C(F|G)XTR(A)?$")>;
+def : InstRW<[FXb, VecDF, Lat30, BeginGroup], (instregex "CL(F|G)DTR$")>;
+def : InstRW<[FXb, VecDF, VecDF, Lat30, BeginGroup], (instregex "CL(F|G)XTR$")>;
+
+// Convert from / to signed / unsigned packed
+def : InstRW<[FXb, VecDF, Lat9, BeginGroup], (instregex "CD(S|U)TR$")>;
+def : InstRW<[FXb, FXb, VecDF2, VecDF2, Lat15, GroupAlone], (instregex "CX(S|U)TR$")>;
+def : InstRW<[FXb, VecDF, Lat12, BeginGroup], (instregex "C(S|U)DTR$")>;
+def : InstRW<[FXb, FXb, VecDF2, VecDF2, Lat15, GroupAlone], (instregex "C(S|U)XTR$")>;
+
+// Convert from / to zoned
+def : InstRW<[LSU, VecDF, Lat11, BeginGroup], (instregex "CDZT$")>;
+def : InstRW<[LSU, LSU, VecDF2, VecDF2, Lat15, GroupAlone], (instregex "CXZT$")>;
+def : InstRW<[FXb, LSU, VecDF, Lat11, BeginGroup], (instregex "CZDT$")>;
+def : InstRW<[FXb, LSU, VecDF, VecDF, Lat15, GroupAlone], (instregex "CZXT$")>;
+
+// Convert from / to packed
+def : InstRW<[LSU, VecDF, Lat11, BeginGroup], (instregex "CDPT$")>;
+def : InstRW<[LSU, LSU, VecDF2, VecDF2, Lat15, GroupAlone], (instregex "CXPT$")>;
+def : InstRW<[FXb, LSU, VecDF, Lat11, BeginGroup], (instregex "CPDT$")>;
+def : InstRW<[FXb, LSU, VecDF, VecDF, Lat15, GroupAlone], (instregex "CPXT$")>;
+
+// Perform floating-point operation
+def : InstRW<[FXb, Lat30], (instregex "PFPO$")>;
+
+//===----------------------------------------------------------------------===//
+// DFP: Unary arithmetic
+//===----------------------------------------------------------------------===//
+
+// Load FP integer
+def : InstRW<[VecDF], (instregex "FIDTR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "FIXTR$")>;
+
+// Extract biased exponent
+def : InstRW<[FXb, VecDF, Lat12, BeginGroup], (instregex "EEDTR$")>;
+def : InstRW<[FXb, VecDF, Lat12, BeginGroup], (instregex "EEXTR$")>;
+
+// Extract significance
+def : InstRW<[FXb, VecDF, Lat12, BeginGroup], (instregex "ESDTR$")>;
+def : InstRW<[FXb, VecDF, VecDF, Lat15, BeginGroup], (instregex "ESXTR$")>;
+
+//===----------------------------------------------------------------------===//
+// DFP: Binary arithmetic
+//===----------------------------------------------------------------------===//
+
+// Addition
+def : InstRW<[VecDF], (instregex "ADTR(A)?$")>;
+def : InstRW<[VecDF2, VecDF2, Lat10, GroupAlone], (instregex "AXTR(A)?$")>;
+
+// Subtraction
+def : InstRW<[VecDF], (instregex "SDTR(A)?$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "SXTR(A)?$")>;
+
+// Multiply
+def : InstRW<[VecDF, Lat30], (instregex "MDTR(A)?$")>;
+def : InstRW<[VecDF2, VecDF2, Lat30, GroupAlone], (instregex "MXTR(A)?$")>;
+
+// Division
+def : InstRW<[VecDF, Lat30], (instregex "DDTR(A)?$")>;
+def : InstRW<[VecDF2, VecDF2, Lat30, GroupAlone], (instregex "DXTR(A)?$")>;
+
+// Quantize
+def : InstRW<[VecDF], (instregex "QADTR$")>;
+def : InstRW<[VecDF2, VecDF2, Lat11, GroupAlone], (instregex "QAXTR$")>;
+
+// Reround
+def : InstRW<[FXb, VecDF, Lat11, BeginGroup], (instregex "RRDTR$")>;
+def : InstRW<[FXb, VecDF2, VecDF2, Lat15, GroupAlone], (instregex "RRXTR$")>;
+
+// Shift significand left/right
+def : InstRW<[LSU, VecDF, Lat11, GroupAlone], (instregex "S(L|R)DT$")>;
+def : InstRW<[LSU, VecDF2, VecDF2, Lat15, GroupAlone], (instregex "S(L|R)XT$")>;
+
+// Insert biased exponent
+def : InstRW<[FXb, VecDF, Lat11, BeginGroup], (instregex "IEDTR$")>;
+def : InstRW<[FXb, VecDF2, VecDF2, Lat15, GroupAlone], (instregex "IEXTR$")>;
+
+//===----------------------------------------------------------------------===//
+// DFP: Comparisons
+//===----------------------------------------------------------------------===//
+
+// Compare
+def : InstRW<[VecDF], (instregex "(K|C)DTR$")>;
+def : InstRW<[VecDF, VecDF, Lat11, GroupAlone], (instregex "(K|C)XTR$")>;
+
+// Compare biased exponent
+def : InstRW<[VecDF], (instregex "CEDTR$")>;
+def : InstRW<[VecDF], (instregex "CEXTR$")>;
+
+// Test Data Class/Group
+def : InstRW<[LSU, VecDF, Lat11], (instregex "TD(C|G)(E|D)T$")>;
+def : InstRW<[LSU, VecDF, VecDF, Lat15, GroupAlone], (instregex "TD(C|G)XT$")>;
+
+
+// --------------------------------- Vector --------------------------------- //
+
+//===----------------------------------------------------------------------===//
+// Vector: Move instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb], (instregex "VLR(32|64)?$")>;
+def : InstRW<[FXb, Lat4], (instregex "VLGV(B|F|G|H)?$")>;
+def : InstRW<[FXb], (instregex "VLVG(B|F|G|H)?$")>;
+def : InstRW<[FXb, Lat2], (instregex "VLVGP(32)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Immediate instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[VecXsPm], (instregex "VZERO$")>;
+def : InstRW<[VecXsPm], (instregex "VONE$")>;
+def : InstRW<[VecXsPm], (instregex "VGBM$")>;
+def : InstRW<[VecXsPm], (instregex "VGM(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VREPI(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VLEI(B|F|G|H)$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Loads
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[LSU], (instregex "VL(L|BB)?$")>;
+def : InstRW<[LSU], (instregex "VL(32|64)$")>;
+def : InstRW<[LSU], (instregex "VLLEZ(B|F|G|H|LF)?$")>;
+def : InstRW<[LSU], (instregex "VLREP(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm, LSU, Lat7], (instregex "VLE(B|F|G|H)$")>;
+def : InstRW<[FXb, LSU, VecXsPm, Lat11, BeginGroup], (instregex "VGE(F|G)$")>;
+def : InstRW<[LSU, LSU, LSU, LSU, LSU, Lat10, GroupAlone],
+ (instregex "VLM$")>;
+def : InstRW<[LSU, Lat5], (instregex "VLRL(R)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Stores
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, LSU, Lat8], (instregex "VST(L|32|64)?$")>;
+def : InstRW<[FXb, LSU, Lat8], (instregex "VSTE(F|G)$")>;
+def : InstRW<[FXb, LSU, VecXsPm, Lat11, BeginGroup], (instregex "VSTE(B|H)$")>;
+def : InstRW<[LSU, LSU, FXb, FXb, FXb, FXb, FXb, Lat20, GroupAlone],
+ (instregex "VSTM$")>;
+def : InstRW<[FXb, FXb, LSU, Lat12, BeginGroup], (instregex "VSCE(F|G)$")>;
+def : InstRW<[FXb, LSU, Lat8], (instregex "VSTRL(R)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Selects and permutes
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[VecXsPm], (instregex "VMRH(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VMRL(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VPERM$")>;
+def : InstRW<[VecXsPm], (instregex "VPDI$")>;
+def : InstRW<[VecXsPm], (instregex "VBPERM$")>;
+def : InstRW<[VecXsPm], (instregex "VREP(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VSEL$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Widening and narrowing
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[VecXsPm], (instregex "VPK(F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VPKS(F|G|H)?$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "VPKS(F|G|H)S$")>;
+def : InstRW<[VecXsPm], (instregex "VPKLS(F|G|H)?$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "VPKLS(F|G|H)S$")>;
+def : InstRW<[VecXsPm], (instregex "VSEG(B|F|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VUPH(B|F|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VUPL(B|F)?$")>;
+def : InstRW<[VecXsPm], (instregex "VUPLH(B|F|H|W)?$")>;
+def : InstRW<[VecXsPm], (instregex "VUPLL(B|F|H)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Integer arithmetic
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[VecXsPm], (instregex "VA(B|F|G|H|Q|C|CQ)?$")>;
+def : InstRW<[VecXsPm], (instregex "VACC(B|F|G|H|Q|C|CQ)?$")>;
+def : InstRW<[VecXsPm], (instregex "VAVG(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VAVGL(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VN(C|O|N|X)?$")>;
+def : InstRW<[VecXsPm], (instregex "VO(C)?$")>;
+def : InstRW<[VecMul], (instregex "VCKSM$")>;
+def : InstRW<[VecXsPm], (instregex "VCLZ(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VCTZ(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VX$")>;
+def : InstRW<[VecMul], (instregex "VGFM?$")>;
+def : InstRW<[VecMul], (instregex "VGFMA(B|F|G|H)?$")>;
+def : InstRW<[VecMul], (instregex "VGFM(B|F|G|H)$")>;
+def : InstRW<[VecXsPm], (instregex "VLC(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VLP(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VMX(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VMXL(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VMN(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VMNL(B|F|G|H)?$")>;
+def : InstRW<[VecMul], (instregex "VMAL(B|F)?$")>;
+def : InstRW<[VecMul], (instregex "VMALE(B|F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VMALH(B|F|H|W)?$")>;
+def : InstRW<[VecMul], (instregex "VMALO(B|F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VMAO(B|F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VMAE(B|F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VMAH(B|F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VME(B|F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VMH(B|F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VML(B|F)?$")>;
+def : InstRW<[VecMul], (instregex "VMLE(B|F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VMLH(B|F|H|W)?$")>;
+def : InstRW<[VecMul], (instregex "VMLO(B|F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VMO(B|F|H)?$")>;
+def : InstRW<[VecBF2], (instregex "VMSL(G)?$")>;
+
+def : InstRW<[VecXsPm], (instregex "VPOPCT(B|F|G|H)?$")>;
+
+def : InstRW<[VecXsPm], (instregex "VERLL(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VERLLV(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VERIM(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VESL(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VESLV(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VESRA(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VESRAV(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VESRL(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VESRLV(B|F|G|H)?$")>;
+
+def : InstRW<[VecXsPm], (instregex "VSL(DB)?$")>;
+def : InstRW<[VecXsPm, VecXsPm, Lat8], (instregex "VSLB$")>;
+def : InstRW<[VecXsPm], (instregex "VSR(A|L)$")>;
+def : InstRW<[VecXsPm, VecXsPm, Lat8], (instregex "VSR(A|L)B$")>;
+
+def : InstRW<[VecXsPm], (instregex "VSB(I|IQ|CBI|CBIQ)?$")>;
+def : InstRW<[VecXsPm], (instregex "VSCBI(B|F|G|H|Q)?$")>;
+def : InstRW<[VecXsPm], (instregex "VS(F|G|H|Q)?$")>;
+
+def : InstRW<[VecMul], (instregex "VSUM(B|H)?$")>;
+def : InstRW<[VecMul], (instregex "VSUMG(F|H)?$")>;
+def : InstRW<[VecMul], (instregex "VSUMQ(F|G)?$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Integer comparison
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[VecXsPm, Lat4], (instregex "VEC(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "VECL(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm], (instregex "VCEQ(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "VCEQ(B|F|G|H)S$")>;
+def : InstRW<[VecXsPm], (instregex "VCH(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "VCH(B|F|G|H)S$")>;
+def : InstRW<[VecXsPm], (instregex "VCHL(B|F|G|H)?$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "VCHL(B|F|G|H)S$")>;
+def : InstRW<[VecStr, Lat5], (instregex "VTM$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Floating-point arithmetic
+//===----------------------------------------------------------------------===//
+
+// Conversion and rounding
+def : InstRW<[VecBF], (instregex "VCD(L)?G$")>;
+def : InstRW<[VecBF], (instregex "VCD(L)?GB$")>;
+def : InstRW<[VecBF], (instregex "WCD(L)?GB$")>;
+def : InstRW<[VecBF], (instregex "VC(L)?GD$")>;
+def : InstRW<[VecBF], (instregex "VC(L)?GDB$")>;
+def : InstRW<[VecBF], (instregex "WC(L)?GDB$")>;
+def : InstRW<[VecBF], (instregex "VL(DE|ED)$")>;
+def : InstRW<[VecBF], (instregex "VL(DE|ED)B$")>;
+def : InstRW<[VecBF], (instregex "WL(DE|ED)B$")>;
+def : InstRW<[VecBF], (instregex "VFL(L|R)$")>;
+def : InstRW<[VecBF], (instregex "VFL(LS|RD)$")>;
+def : InstRW<[VecBF], (instregex "WFL(LS|RD)$")>;
+def : InstRW<[VecBF2], (instregex "WFLLD$")>;
+def : InstRW<[VecDF2, Lat10], (instregex "WFLRX$")>;
+def : InstRW<[VecBF2], (instregex "VFI$")>;
+def : InstRW<[VecBF], (instregex "VFIDB$")>;
+def : InstRW<[VecBF], (instregex "WFIDB$")>;
+def : InstRW<[VecBF2], (instregex "VFISB$")>;
+def : InstRW<[VecBF], (instregex "WFISB$")>;
+def : InstRW<[VecDF2, Lat10], (instregex "WFIXB$")>;
+
+// Sign operations
+def : InstRW<[VecXsPm], (instregex "VFPSO$")>;
+def : InstRW<[VecXsPm], (instregex "(V|W)FPSODB$")>;
+def : InstRW<[VecXsPm], (instregex "(V|W)FPSOSB$")>;
+def : InstRW<[VecXsPm], (instregex "WFPSOXB$")>;
+def : InstRW<[VecXsPm], (instregex "(V|W)FL(C|N|P)DB$")>;
+def : InstRW<[VecXsPm], (instregex "(V|W)FL(C|N|P)SB$")>;
+def : InstRW<[VecXsPm], (instregex "WFL(C|N|P)XB$")>;
+
+// Minimum / maximum
+def : InstRW<[VecXsPm], (instregex "VF(MAX|MIN)$")>;
+def : InstRW<[VecXsPm], (instregex "VF(MAX|MIN)DB$")>;
+def : InstRW<[VecXsPm], (instregex "WF(MAX|MIN)DB$")>;
+def : InstRW<[VecXsPm], (instregex "VF(MAX|MIN)SB$")>;
+def : InstRW<[VecXsPm], (instregex "WF(MAX|MIN)SB$")>;
+def : InstRW<[VecDFX], (instregex "WF(MAX|MIN)XB$")>;
+
+// Test data class
+def : InstRW<[VecXsPm, Lat4], (instregex "VFTCI$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "(V|W)FTCIDB$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "(V|W)FTCISB$")>;
+def : InstRW<[VecDFX, Lat4], (instregex "WFTCIXB$")>;
+
+// Add / subtract
+def : InstRW<[VecBF2], (instregex "VF(A|S)$")>;
+def : InstRW<[VecBF], (instregex "VF(A|S)DB$")>;
+def : InstRW<[VecBF], (instregex "WF(A|S)DB$")>;
+def : InstRW<[VecBF2], (instregex "VF(A|S)SB$")>;
+def : InstRW<[VecBF], (instregex "WF(A|S)SB$")>;
+def : InstRW<[VecDF2, Lat10], (instregex "WF(A|S)XB$")>;
+
+// Multiply / multiply-and-add/subtract
+def : InstRW<[VecBF2], (instregex "VFM$")>;
+def : InstRW<[VecBF], (instregex "VFMDB$")>;
+def : InstRW<[VecBF], (instregex "WFMDB$")>;
+def : InstRW<[VecBF2], (instregex "VFMSB$")>;
+def : InstRW<[VecBF], (instregex "WFMSB$")>;
+def : InstRW<[VecDF2, Lat20], (instregex "WFMXB$")>;
+def : InstRW<[VecBF2], (instregex "VF(N)?M(A|S)$")>;
+def : InstRW<[VecBF], (instregex "VF(N)?M(A|S)DB$")>;
+def : InstRW<[VecBF], (instregex "WF(N)?M(A|S)DB$")>;
+def : InstRW<[VecBF2], (instregex "VF(N)?M(A|S)SB$")>;
+def : InstRW<[VecBF], (instregex "WF(N)?M(A|S)SB$")>;
+def : InstRW<[VecDF2, Lat20], (instregex "WF(N)?M(A|S)XB$")>;
+
+// Divide / square root
+def : InstRW<[VecFPd], (instregex "VFD$")>;
+def : InstRW<[VecFPd], (instregex "(V|W)FDDB$")>;
+def : InstRW<[VecFPd], (instregex "(V|W)FDSB$")>;
+def : InstRW<[VecFPd], (instregex "WFDXB$")>;
+def : InstRW<[VecFPd], (instregex "VFSQ$")>;
+def : InstRW<[VecFPd], (instregex "(V|W)FSQDB$")>;
+def : InstRW<[VecFPd], (instregex "(V|W)FSQSB$")>;
+def : InstRW<[VecFPd], (instregex "WFSQXB$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Floating-point comparison
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[VecXsPm], (instregex "VF(C|K)(E|H|HE)$")>;
+def : InstRW<[VecXsPm], (instregex "VF(C|K)(E|H|HE)DB$")>;
+def : InstRW<[VecXsPm], (instregex "WF(C|K)(E|H|HE)DB$")>;
+def : InstRW<[VecXsPm], (instregex "VF(C|K)(E|H|HE)SB$")>;
+def : InstRW<[VecXsPm], (instregex "WF(C|K)(E|H|HE)SB$")>;
+def : InstRW<[VecDFX], (instregex "WF(C|K)(E|H|HE)XB$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "VF(C|K)(E|H|HE)DBS$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "WF(C|K)(E|H|HE)DBS$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "VF(C|K)(E|H|HE)SBS$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "WF(C|K)(E|H|HE)SBS$")>;
+def : InstRW<[VecDFX, Lat4], (instregex "WF(C|K)(E|H|HE)XBS$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "WF(C|K)$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "WF(C|K)DB$")>;
+def : InstRW<[VecXsPm, Lat4], (instregex "WF(C|K)SB$")>;
+def : InstRW<[VecDFX, Lat4], (instregex "WF(C|K)XB$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Floating-point insertion and extraction
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb], (instregex "LEFR$")>;
+def : InstRW<[FXb, Lat4], (instregex "LFER$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: String instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[VecStr], (instregex "VFAE(B)?$")>;
+def : InstRW<[VecStr, Lat5], (instregex "VFAEBS$")>;
+def : InstRW<[VecStr], (instregex "VFAE(F|H)$")>;
+def : InstRW<[VecStr, Lat5], (instregex "VFAE(F|H)S$")>;
+def : InstRW<[VecStr], (instregex "VFAEZ(B|F|H)$")>;
+def : InstRW<[VecStr, Lat5], (instregex "VFAEZ(B|F|H)S$")>;
+def : InstRW<[VecStr], (instregex "VFEE(B|F|H|ZB|ZF|ZH)?$")>;
+def : InstRW<[VecStr, Lat5], (instregex "VFEE(B|F|H|ZB|ZF|ZH)S$")>;
+def : InstRW<[VecStr], (instregex "VFENE(B|F|H|ZB|ZF|ZH)?$")>;
+def : InstRW<[VecStr, Lat5], (instregex "VFENE(B|F|H|ZB|ZF|ZH)S$")>;
+def : InstRW<[VecStr], (instregex "VISTR(B|F|H)?$")>;
+def : InstRW<[VecStr, Lat5], (instregex "VISTR(B|F|H)S$")>;
+def : InstRW<[VecStr], (instregex "VSTRC(B|F|H)?$")>;
+def : InstRW<[VecStr, Lat5], (instregex "VSTRC(B|F|H)S$")>;
+def : InstRW<[VecStr], (instregex "VSTRCZ(B|F|H)$")>;
+def : InstRW<[VecStr, Lat5], (instregex "VSTRCZ(B|F|H)S$")>;
+
+//===----------------------------------------------------------------------===//
+// Vector: Packed-decimal instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[VecDF, VecDF, Lat10, GroupAlone], (instregex "VLIP$")>;
+def : InstRW<[VecDFX, LSU, Lat12, GroupAlone], (instregex "VPKZ$")>;
+def : InstRW<[VecDFX, FXb, LSU, Lat12, GroupAlone], (instregex "VUPKZ$")>;
+def : InstRW<[VecDF, VecDF, FXb, Lat20, GroupAlone], (instregex "VCVB(G)?$")>;
+def : InstRW<[VecDF, VecDF, FXb, Lat20, GroupAlone], (instregex "VCVD(G)?$")>;
+def : InstRW<[VecDFX], (instregex "V(A|S)P$")>;
+def : InstRW<[VecDF, VecDF, Lat30, GroupAlone], (instregex "VM(S)?P$")>;
+def : InstRW<[VecDF, VecDF, Lat30, GroupAlone], (instregex "V(D|R)P$")>;
+def : InstRW<[VecDFX, Lat30, GroupAlone], (instregex "VSDP$")>;
+def : InstRW<[VecDF, VecDF, Lat11], (instregex "VSRP$")>;
+def : InstRW<[VecDFX], (instregex "VPSOP$")>;
+def : InstRW<[VecDFX], (instregex "V(T|C)P$")>;
+
+
+// -------------------------------- System ---------------------------------- //
+
+//===----------------------------------------------------------------------===//
+// System: Program-Status Word Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, Lat30], (instregex "EPSW$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "LPSW(E)?$")>;
+def : InstRW<[FXa, Lat3, GroupAlone], (instregex "IPK$")>;
+def : InstRW<[LSU, EndGroup], (instregex "SPKA$")>;
+def : InstRW<[LSU, EndGroup], (instregex "SSM$")>;
+def : InstRW<[FXb, LSU, GroupAlone], (instregex "ST(N|O)SM$")>;
+def : InstRW<[FXa, Lat3], (instregex "IAC$")>;
+def : InstRW<[LSU, EndGroup], (instregex "SAC(F)?$")>;
+
+//===----------------------------------------------------------------------===//
+// System: Control Register Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, LSU, Lat30], (instregex "LCTL(G)?$")>;
+def : InstRW<[LSU, Lat30], (instregex "STCT(L|G)$")>;
+def : InstRW<[LSU], (instregex "E(P|S)A(I)?R$")>;
+def : InstRW<[FXb, Lat30], (instregex "SSA(I)?R$")>;
+def : InstRW<[FXb, Lat30], (instregex "ESEA$")>;
+
+//===----------------------------------------------------------------------===//
+// System: Prefix-Register Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, LSU, Lat30], (instregex "SPX$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "STPX$")>;
+
+//===----------------------------------------------------------------------===//
+// System: Storage-Key and Real Memory Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, Lat30], (instregex "ISKE$")>;
+def : InstRW<[FXb, Lat30], (instregex "IVSK$")>;
+def : InstRW<[FXb, Lat30], (instregex "SSKE(Opt)?$")>;
+def : InstRW<[FXb, Lat30], (instregex "RRB(E|M)$")>;
+def : InstRW<[FXb, Lat30], (instregex "IRBM$")>;
+def : InstRW<[FXb, Lat30], (instregex "PFMF$")>;
+def : InstRW<[FXb, Lat30], (instregex "TB$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "PGIN$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "PGOUT$")>;
+
+//===----------------------------------------------------------------------===//
+// System: Dynamic-Address-Translation Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, LSU, Lat30], (instregex "IPTE(Opt)?(Opt)?$")>;
+def : InstRW<[FXb, Lat30], (instregex "IDTE(Opt)?$")>;
+def : InstRW<[FXb, Lat30], (instregex "CRDTE(Opt)?$")>;
+def : InstRW<[FXb, Lat30], (instregex "PTLB$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "CSP(G)?$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "LPTEA$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "LRA(Y|G)?$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "STRAG$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "LURA(G)?$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "STUR(A|G)$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "TPROT$")>;
+
+//===----------------------------------------------------------------------===//
+// System: Memory-move Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXa, FXa, FXb, LSU, Lat8, GroupAlone], (instregex "MVC(K|P|S)$")>;
+def : InstRW<[FXa, LSU, Lat6, GroupAlone], (instregex "MVC(S|D)K$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "MVCOS$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MVPG$")>;
+
+//===----------------------------------------------------------------------===//
+// System: Address-Space Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, LSU, Lat30], (instregex "LASP$")>;
+def : InstRW<[LSU, GroupAlone], (instregex "PALB$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "PC$")>;
+def : InstRW<[FXb, Lat30], (instregex "PR$")>;
+def : InstRW<[FXb, Lat30], (instregex "PT(I)?$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "RP$")>;
+def : InstRW<[FXb, Lat30], (instregex "BS(G|A)$")>;
+def : InstRW<[FXb, Lat20], (instregex "TAR$")>;
+
+//===----------------------------------------------------------------------===//
+// System: Linkage-Stack Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, Lat30, EndGroup], (instregex "BAKR$")>;
+def : InstRW<[FXb, Lat30], (instregex "EREG(G)?$")>;
+def : InstRW<[FXb, Lat30], (instregex "(E|M)STA$")>;
+
+//===----------------------------------------------------------------------===//
+// System: Time-Related Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, Lat30], (instregex "PTFF$")>;
+def : InstRW<[FXb, LSU, Lat20], (instregex "SCK$")>;
+def : InstRW<[FXb, Lat30], (instregex "SCKPF$")>;
+def : InstRW<[FXb, LSU, Lat20], (instregex "SCKC$")>;
+def : InstRW<[LSU, LSU, GroupAlone], (instregex "SPT$")>;
+def : InstRW<[LSU, LSU, LSU, FXa, FXa, FXb, Lat9, GroupAlone],
+ (instregex "STCK(F)?$")>;
+def : InstRW<[LSU, LSU, LSU, LSU, FXa, FXa, FXb, FXb, Lat11, GroupAlone],
+ (instregex "STCKE$")>;
+def : InstRW<[FXb, LSU, Lat9], (instregex "STCKC$")>;
+def : InstRW<[LSU, LSU, FXb, Lat5, BeginGroup], (instregex "STPT$")>;
+
+//===----------------------------------------------------------------------===//
+// System: CPU-Related Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, LSU, Lat30], (instregex "STAP$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "STIDP$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "STSI$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "STFL(E)?$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "ECAG$")>;
+def : InstRW<[FXa, LSU, Lat30], (instregex "ECTG$")>;
+def : InstRW<[FXb, Lat30], (instregex "PTF$")>;
+def : InstRW<[FXb, Lat30], (instregex "PCKMO$")>;
+
+//===----------------------------------------------------------------------===//
+// System: Miscellaneous Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, Lat30], (instregex "SVC$")>;
+def : InstRW<[FXb, GroupAlone], (instregex "MC$")>;
+def : InstRW<[FXb, Lat30], (instregex "DIAG$")>;
+def : InstRW<[FXb], (instregex "TRAC(E|G)$")>;
+def : InstRW<[FXb, Lat30], (instregex "TRAP(2|4)$")>;
+def : InstRW<[FXb, Lat30], (instregex "SIGP$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "SIGA$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "SIE$")>;
+
+//===----------------------------------------------------------------------===//
+// System: CPU-Measurement Facility Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb], (instregex "LPP$")>;
+def : InstRW<[FXb, Lat30], (instregex "ECPGA$")>;
+def : InstRW<[FXb, Lat30], (instregex "E(C|P)CTR$")>;
+def : InstRW<[FXb, Lat30], (instregex "LCCTL$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "L(P|S)CTL$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "Q(S|CTR)I$")>;
+def : InstRW<[FXb, Lat30], (instregex "S(C|P)CTR$")>;
+
+//===----------------------------------------------------------------------===//
+// System: I/O Instructions
+//===----------------------------------------------------------------------===//
+
+def : InstRW<[FXb, Lat30], (instregex "(C|H|R|X)SCH$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "(M|S|ST|T)SCH$")>;
+def : InstRW<[FXb, Lat30], (instregex "RCHP$")>;
+def : InstRW<[FXb, Lat30], (instregex "SCHM$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "STC(PS|RW)$")>;
+def : InstRW<[FXb, LSU, Lat30], (instregex "TPI$")>;
+def : InstRW<[FXb, Lat30], (instregex "SAL$")>;
+
+}
+
diff --git a/lib/Target/SystemZ/SystemZScheduleZ196.td b/lib/Target/SystemZ/SystemZScheduleZ196.td
index e3e1999d8ad8d..4d986e8391cf5 100644
--- a/lib/Target/SystemZ/SystemZScheduleZ196.td
+++ b/lib/Target/SystemZ/SystemZScheduleZ196.td
@@ -311,7 +311,7 @@ def : InstRW<[FXU], (instregex "ALGR(K)?$")>;
def : InstRW<[FXU], (instregex "ALR(K)?$")>;
def : InstRW<[FXU], (instregex "AR(K)?$")>;
def : InstRW<[FXU], (instregex "A(L)?HHHR$")>;
-def : InstRW<[FXU, FXU, Lat3], (instregex "A(L)?HHLR$")>;
+def : InstRW<[FXU, FXU, Lat3, GroupAlone], (instregex "A(L)?HHLR$")>;
def : InstRW<[FXU], (instregex "ALSIH(N)?$")>;
def : InstRW<[FXU, LSU, Lat5], (instregex "A(L)?G(SI)?$")>;
@@ -337,7 +337,7 @@ def : InstRW<[FXU], (instregex "SLGR(K)?$")>;
def : InstRW<[FXU], (instregex "SLR(K)?$")>;
def : InstRW<[FXU], (instregex "SR(K)?$")>;
def : InstRW<[FXU], (instregex "S(L)?HHHR$")>;
-def : InstRW<[FXU, FXU, Lat3], (instregex "S(L)?HHLR$")>;
+def : InstRW<[FXU, FXU, Lat3, GroupAlone], (instregex "S(L)?HHLR$")>;
// Subtraction with borrow
def : InstRW<[FXU, LSU, Lat7, GroupAlone], (instregex "SLB(G)?$")>;
@@ -403,13 +403,13 @@ def : InstRW<[FXU, Lat6], (instregex "MS(R|FI)$")>;
def : InstRW<[FXU, LSU, Lat12], (instregex "MSG$")>;
def : InstRW<[FXU, Lat8], (instregex "MSGR$")>;
def : InstRW<[FXU, Lat6], (instregex "MSGF(I|R)$")>;
-def : InstRW<[FXU, LSU, Lat15, GroupAlone], (instregex "MLG$")>;
-def : InstRW<[FXU, Lat9, GroupAlone], (instregex "MLGR$")>;
+def : InstRW<[FXU, FXU, LSU, Lat15, GroupAlone], (instregex "MLG$")>;
+def : InstRW<[FXU, FXU, Lat9, GroupAlone], (instregex "MLGR$")>;
def : InstRW<[FXU, Lat5], (instregex "MGHI$")>;
def : InstRW<[FXU, Lat5], (instregex "MHI$")>;
def : InstRW<[FXU, LSU, Lat9], (instregex "MH(Y)?$")>;
-def : InstRW<[FXU, Lat7, GroupAlone], (instregex "M(L)?R$")>;
-def : InstRW<[FXU, LSU, Lat7, GroupAlone], (instregex "M(FY|L)?$")>;
+def : InstRW<[FXU, FXU, Lat7, GroupAlone], (instregex "M(L)?R$")>;
+def : InstRW<[FXU, FXU, LSU, Lat7, GroupAlone], (instregex "M(FY|L)?$")>;
//===----------------------------------------------------------------------===//
// Division and remainder
@@ -436,7 +436,8 @@ def : InstRW<[FXU], (instregex "SLL(G|K)?$")>;
def : InstRW<[FXU], (instregex "SRL(G|K)?$")>;
def : InstRW<[FXU], (instregex "SRA(G|K)?$")>;
def : InstRW<[FXU, Lat2], (instregex "SLA(G|K)?$")>;
-def : InstRW<[FXU, FXU, FXU, FXU, Lat8], (instregex "S(L|R)D(A|L)$")>;
+def : InstRW<[FXU, FXU, FXU, FXU, LSU, Lat8, GroupAlone],
+ (instregex "S(L|R)D(A|L)$")>;
// Rotate
def : InstRW<[FXU, LSU, Lat6], (instregex "RLL(G)?$")>;
@@ -474,7 +475,7 @@ def : InstRW<[FXU, LSU, Lat5], (instregex "CLI(Y)?$")>;
def : InstRW<[FXU], (instregex "CLR$")>;
def : InstRW<[FXU, LSU, Lat5], (instregex "CLRL$")>;
def : InstRW<[FXU], (instregex "C(L)?HHR$")>;
-def : InstRW<[FXU, FXU, Lat3], (instregex "C(L)?HLR$")>;
+def : InstRW<[FXU, FXU, Lat3, GroupAlone], (instregex "C(L)?HLR$")>;
// Compare halfword
def : InstRW<[FXU, LSU, FXU, Lat6, GroupAlone], (instregex "CH(Y|RL)?$")>;
@@ -499,7 +500,7 @@ def : InstRW<[FXU], (instregex "TMLH(64)?$")>;
def : InstRW<[FXU], (instregex "TMLL(64)?$")>;
// Compare logical characters under mask
-def : InstRW<[FXU, LSU, Lat5], (instregex "CLM(H|Y)?$")>;
+def : InstRW<[FXU, FXU, LSU, Lat5, GroupAlone], (instregex "CLM(H|Y)?$")>;
//===----------------------------------------------------------------------===//
// Prefetch
@@ -532,7 +533,7 @@ def : InstRW<[FXU, FXU, FXU, FXU, FXU, FXU, LSU, LSU, Lat12, GroupAlone],
(instregex "CDSG$")>;
// Compare and swap and store
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "CSST$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "CSST$")>;
// Perform locked operation
def : InstRW<[LSU, Lat30, GroupAlone], (instregex "PLO$")>;
@@ -548,36 +549,44 @@ def : InstRW<[LSU, LSU, Lat5, GroupAlone], (instregex "LPD(G)?$")>;
// Translate and convert
//===----------------------------------------------------------------------===//
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "TR(T|TR)?(E|EOpt)?$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "TR(T|O)(T|O)(Opt)?$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "CU(12|14|21|24|41|42)(Opt)?$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "(CUUTF|CUTFU)(Opt)?$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "TR$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "TRT$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "TRTR$")>;
+def : InstRW<[FXU, Lat30], (instregex "TR(TR)?(T)?(E|EOpt)?$")>;
+def : InstRW<[LSU, Lat30], (instregex "TR(T|O)(T|O)(Opt)?$")>;
+def : InstRW<[FXU, Lat30], (instregex "CU(12|14|21|24|41|42)(Opt)?$")>;
+def : InstRW<[FXU, Lat30], (instregex "(CUUTF|CUTFU)(Opt)?$")>;
//===----------------------------------------------------------------------===//
// Message-security assist
//===----------------------------------------------------------------------===//
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "KM(C|F|O|CTR)?$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "(KIMD|KLMD|KMAC|PCC)$")>;
+def : InstRW<[FXU, Lat30], (instregex "KM(C|F|O|CTR)?$")>;
+def : InstRW<[FXU, Lat30], (instregex "(KIMD|KLMD|KMAC|PCC)$")>;
//===----------------------------------------------------------------------===//
// Decimal arithmetic
//===----------------------------------------------------------------------===//
-def : InstRW<[FXU, DFU, LSU, Lat30, GroupAlone], (instregex "CVB(Y|G)?$")>;
-def : InstRW<[FXU, DFU, FXU, Lat30, GroupAlone], (instregex "CVD(Y|G)?$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MV(N|Z|O)$")>;
+def : InstRW<[FXU, DFU2, LSU, LSU, Lat30, GroupAlone], (instregex "CVBG$")>;
+def : InstRW<[FXU, DFU, LSU, Lat30, GroupAlone], (instregex "CVB(Y)?$")>;
+def : InstRW<[FXU, FXU, FXU, DFU2, DFU2, LSU, Lat30, GroupAlone],
+ (instregex "CVDG$")>;
+def : InstRW<[FXU, FXU, DFU, LSU, Lat30, GroupAlone], (instregex "CVD(Y)?$")>;
+def : InstRW<[LSU, Lat10, GroupAlone], (instregex "MVO$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MV(N|Z)$")>;
def : InstRW<[LSU, Lat30, GroupAlone], (instregex "(PACK|PKA|PKU)$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "UNPK(A|U)?$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "UNPK$")>;
+def : InstRW<[LSU, Lat12, GroupAlone], (instregex "UNPK(A|U)$")>;
-def : InstRW<[FXU, FXU, DFU2, LSU, LSU, LSU, LSU, Lat15, GroupAlone],
+def : InstRW<[FXU, DFU2, DFU2, LSU, LSU, Lat15, GroupAlone],
(instregex "(A|S|ZA)P$")>;
-def : InstRW<[FXU, FXU, DFU2, LSU, LSU, LSU, LSU, Lat30, GroupAlone],
+def : InstRW<[FXU, DFU2, DFU2, LSU, LSU, Lat30, GroupAlone],
(instregex "(M|D)P$")>;
-def : InstRW<[FXU, FXU, DFU2, LSU, LSU, Lat15, GroupAlone],
+def : InstRW<[FXU, FXU, DFU2, DFU2, LSU, LSU, LSU, Lat15, GroupAlone],
(instregex "SRP$")>;
-def : InstRW<[DFU2, LSU, LSU, LSU, LSU, Lat11, GroupAlone], (instregex "CP$")>;
-def : InstRW<[DFU2, LSU, LSU, Lat3, GroupAlone], (instregex "TP$")>;
+def : InstRW<[DFU2, DFU2, LSU, LSU, Lat11, GroupAlone], (instregex "CP$")>;
+def : InstRW<[DFU2, LSU, LSU, GroupAlone], (instregex "TP$")>;
def : InstRW<[LSU, Lat30, GroupAlone], (instregex "ED(MK)?$")>;
//===----------------------------------------------------------------------===//
@@ -621,7 +630,7 @@ def : InstRW<[FXU, FXU, LSU, Lat6, GroupAlone], (instregex "BASSM$")>;
//===----------------------------------------------------------------------===//
// Find leftmost one
-def : InstRW<[FXU, Lat7, GroupAlone], (instregex "FLOGR$")>;
+def : InstRW<[FXU, FXU, Lat7, GroupAlone], (instregex "FLOGR$")>;
// Population count
def : InstRW<[FXU, Lat3], (instregex "POPCNT$")>;
@@ -632,14 +641,14 @@ def : InstRW<[FXU], (instregex "ZEXT128$")>;
// String instructions
def : InstRW<[FXU, LSU, Lat30], (instregex "SRST$")>;
-def : InstRW<[LSU, Lat30], (instregex "SRSTU$")>;
+def : InstRW<[FXU, Lat30], (instregex "SRSTU$")>;
def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CUSE$")>;
// Various complex instructions
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CFC$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "UPT$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CKSM$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CMPSC$")>;
+def : InstRW<[LSU, Lat30], (instregex "CFC$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "UPT$")>;
+def : InstRW<[LSU, Lat30], (instregex "CKSM$")>;
+def : InstRW<[FXU, Lat30], (instregex "CMPSC$")>;
// Execute
def : InstRW<[LSU, GroupAlone], (instregex "EX(RL)?$")>;
@@ -780,9 +789,9 @@ def : InstRW<[FPU2, FPU2, Lat10, GroupAlone], (instregex "MXDBR$")>;
def : InstRW<[FPU2, FPU2, Lat30, GroupAlone], (instregex "MXBR$")>;
// Multiply and add / subtract
-def : InstRW<[FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)EB$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)EB$")>;
def : InstRW<[FPU, GroupAlone], (instregex "M(A|S)EBR$")>;
-def : InstRW<[FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)DB$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)DB$")>;
def : InstRW<[FPU, GroupAlone], (instregex "M(A|S)DBR$")>;
// Division
@@ -791,7 +800,7 @@ def : InstRW<[FPU, Lat30], (instregex "D(E|D)BR$")>;
def : InstRW<[FPU2, FPU2, Lat30, GroupAlone], (instregex "DXBR$")>;
// Divide to integer
-def : InstRW<[FPU, Lat30, GroupAlone], (instregex "DI(E|D)BR$")>;
+def : InstRW<[FPU, Lat30], (instregex "DI(E|D)BR$")>;
//===----------------------------------------------------------------------===//
// FP: Comparisons
@@ -813,9 +822,9 @@ def : InstRW<[FPU2, FPU2, LSU, Lat15, GroupAlone], (instregex "TCXB$")>;
def : InstRW<[FXU, LSU, Lat4, GroupAlone], (instregex "EFPC$")>;
def : InstRW<[LSU, Lat3, GroupAlone], (instregex "SFPC$")>;
def : InstRW<[LSU, LSU, Lat6, GroupAlone], (instregex "LFPC$")>;
-def : InstRW<[LSU, Lat3, GroupAlone], (instregex "STFPC$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "SFASR$")>;
-def : InstRW<[FXU, LSU, Lat30, GroupAlone], (instregex "LFAS$")>;
+def : InstRW<[FXU, LSU, Lat3, GroupAlone], (instregex "STFPC$")>;
+def : InstRW<[FXU, Lat30], (instregex "SFASR$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "LFAS$")>;
def : InstRW<[FXU, Lat2, GroupAlone], (instregex "SRNM(B|T)?$")>;
@@ -900,16 +909,20 @@ def : InstRW<[FPU], (instregex "M(D|DE|E|EE)R$")>;
def : InstRW<[FPU2, FPU2, LSU, Lat15, GroupAlone], (instregex "MXD$")>;
def : InstRW<[FPU2, FPU2, Lat10, GroupAlone], (instregex "MXDR$")>;
def : InstRW<[FPU2, FPU2, Lat30, GroupAlone], (instregex "MXR$")>;
-def : InstRW<[FPU2, FPU2, LSU, Lat15, GroupAlone], (instregex "MY(H|L)?$")>;
-def : InstRW<[FPU2, FPU2, Lat10, GroupAlone], (instregex "MY(H|L)?R$")>;
+def : InstRW<[FPU2, FPU2, LSU, Lat15, GroupAlone], (instregex "MY$")>;
+def : InstRW<[FPU, FPU, LSU, Lat15, GroupAlone], (instregex "MY(H|L)$")>;
+def : InstRW<[FPU2, FPU2, Lat10, GroupAlone], (instregex "MYR$")>;
+def : InstRW<[FPU, Lat10, GroupAlone], (instregex "MY(H|L)R$")>;
// Multiply and add / subtract
-def : InstRW<[FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)E$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)E$")>;
def : InstRW<[FPU, GroupAlone], (instregex "M(A|S)ER$")>;
-def : InstRW<[FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)D$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)D$")>;
def : InstRW<[FPU, GroupAlone], (instregex "M(A|S)DR$")>;
-def : InstRW<[FPU2, FPU2, LSU, Lat12, GroupAlone], (instregex "MAY(H|L)?$")>;
-def : InstRW<[FPU2, FPU2, GroupAlone], (instregex "MAY(H|L)?R$")>;
+def : InstRW<[FPU2, FPU2, LSU, GroupAlone], (instregex "MAY$")>;
+def : InstRW<[FPU2, FPU2, GroupAlone], (instregex "MAYR$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "MAY(H|L)$")>;
+def : InstRW<[FPU, GroupAlone], (instregex "MAY(H|L)R$")>;
// Division
def : InstRW<[FPU, LSU, Lat30], (instregex "D(E|D)$")>;
@@ -949,16 +962,21 @@ def : InstRW<[DFU, Lat20], (instregex "LDETR$")>;
def : InstRW<[DFU2, DFU2, Lat20, GroupAlone], (instregex "LXDTR$")>;
// Convert from fixed / logical
-def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "CD(F|G)TR(A)?$")>;
-def : InstRW<[FXU, DFU2, DFU2, Lat30, GroupAlone], (instregex "CX(F|G)TR(A)?$")>;
+def : InstRW<[FXU, DFU, Lat9, GroupAlone], (instregex "CDFTR$")>;
+def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "CDGTR(A)?$")>;
+def : InstRW<[FXU, DFU2, DFU2, GroupAlone], (instregex "CXFTR$")>;
+def : InstRW<[FXU, DFU2, DFU2, Lat30, GroupAlone], (instregex "CXGTR(A)?$")>;
def : InstRW<[FXU, DFU, Lat11, GroupAlone], (instregex "CDL(F|G)TR$")>;
-def : InstRW<[FXU, DFU2, DFU2, Lat11, GroupAlone], (instregex "CXL(F|G)TR$")>;
+def : InstRW<[FXU, DFU2, DFU2, Lat11, GroupAlone], (instregex "CXLFTR$")>;
+def : InstRW<[FXU, DFU2, DFU2, Lat6, GroupAlone], (instregex "CXLGTR$")>;
// Convert to fixed / logical
-def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "C(F|G)DTR(A)?$")>;
-def : InstRW<[FXU, DFU, DFU, Lat30, GroupAlone], (instregex "C(F|G)XTR(A)?$")>;
-def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "CL(F|G)DTR$")>;
-def : InstRW<[FXU, DFU, DFU, Lat30, GroupAlone], (instregex "CL(F|G)XTR$")>;
+def : InstRW<[FXU, DFU, Lat11, GroupAlone], (instregex "CFDTR(A)?$")>;
+def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "CGDTR(A)?$")>;
+def : InstRW<[FXU, DFU, DFU, Lat11, GroupAlone], (instregex "CFXTR$")>;
+def : InstRW<[FXU, DFU, DFU, Lat30, GroupAlone], (instregex "CGXTR(A)?$")>;
+def : InstRW<[FXU, DFU, Lat11, GroupAlone], (instregex "CL(F|G)DTR$")>;
+def : InstRW<[FXU, DFU, DFU, Lat11, GroupAlone], (instregex "CL(F|G)XTR$")>;
// Convert from / to signed / unsigned packed
def : InstRW<[FXU, DFU, Lat12, GroupAlone], (instregex "CD(S|U)TR$")>;
@@ -967,7 +985,7 @@ def : InstRW<[FXU, DFU, Lat12, GroupAlone], (instregex "C(S|U)DTR$")>;
def : InstRW<[FXU, FXU, DFU2, DFU2, Lat20, GroupAlone], (instregex "C(S|U)XTR$")>;
// Perform floating-point operation
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "PFPO$")>;
+def : InstRW<[FXU, Lat30], (instregex "PFPO$")>;
//===----------------------------------------------------------------------===//
// DFP: Unary arithmetic
@@ -979,7 +997,7 @@ def : InstRW<[DFU2, DFU2, Lat20, GroupAlone], (instregex "FIXTR$")>;
// Extract biased exponent
def : InstRW<[FXU, DFU, Lat15, GroupAlone], (instregex "EEDTR$")>;
-def : InstRW<[FXU, DFU, Lat15, GroupAlone], (instregex "EEXTR$")>;
+def : InstRW<[FXU, DFU2, Lat15, GroupAlone], (instregex "EEXTR$")>;
// Extract significance
def : InstRW<[FXU, DFU, Lat15, GroupAlone], (instregex "ESDTR$")>;
@@ -1010,15 +1028,15 @@ def : InstRW<[DFU, Lat30], (instregex "QADTR$")>;
def : InstRW<[DFU2, DFU2, Lat30, GroupAlone], (instregex "QAXTR$")>;
// Reround
-def : InstRW<[FXU, DFU, Lat30], (instregex "RRDTR$")>;
+def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "RRDTR$")>;
def : InstRW<[FXU, DFU2, DFU2, Lat30, GroupAlone], (instregex "RRXTR$")>;
// Shift significand left/right
-def : InstRW<[LSU, DFU, Lat11], (instregex "S(L|R)DT$")>;
+def : InstRW<[LSU, DFU, Lat11, GroupAlone], (instregex "S(L|R)DT$")>;
def : InstRW<[LSU, DFU2, DFU2, Lat15, GroupAlone], (instregex "S(L|R)XT$")>;
// Insert biased exponent
-def : InstRW<[FXU, DFU, Lat11], (instregex "IEDTR$")>;
+def : InstRW<[FXU, DFU, Lat11, GroupAlone], (instregex "IEDTR$")>;
def : InstRW<[FXU, DFU2, DFU2, Lat15, GroupAlone], (instregex "IEXTR$")>;
//===----------------------------------------------------------------------===//
@@ -1027,15 +1045,15 @@ def : InstRW<[FXU, DFU2, DFU2, Lat15, GroupAlone], (instregex "IEXTR$")>;
// Compare
def : InstRW<[DFU, Lat11], (instregex "(K|C)DTR$")>;
-def : InstRW<[DFU, DFU, Lat15, GroupAlone], (instregex "(K|C)XTR$")>;
+def : InstRW<[DFU, DFU, Lat15], (instregex "(K|C)XTR$")>;
// Compare biased exponent
def : InstRW<[DFU, Lat8], (instregex "CEDTR$")>;
-def : InstRW<[DFU, Lat9], (instregex "CEXTR$")>;
+def : InstRW<[DFU2, Lat9], (instregex "CEXTR$")>;
// Test Data Class/Group
def : InstRW<[LSU, DFU, Lat15], (instregex "TD(C|G)(E|D)T$")>;
-def : InstRW<[LSU, DFU2, DFU2, Lat15, GroupAlone], (instregex "TD(C|G)XT$")>;
+def : InstRW<[LSU, DFU2, Lat15], (instregex "TD(C|G)XT$")>;
// -------------------------------- System ---------------------------------- //
@@ -1046,19 +1064,20 @@ def : InstRW<[LSU, DFU2, DFU2, Lat15, GroupAlone], (instregex "TD(C|G)XT$")>;
def : InstRW<[FXU, Lat30], (instregex "EPSW$")>;
def : InstRW<[FXU, LSU, Lat30], (instregex "LPSW(E)?$")>;
-def : InstRW<[FXU, Lat3], (instregex "IPK$")>;
-def : InstRW<[LSU], (instregex "SPKA$")>;
-def : InstRW<[LSU], (instregex "SSM$")>;
-def : InstRW<[FXU], (instregex "ST(N|O)SM$")>;
+def : InstRW<[FXU, Lat3, GroupAlone], (instregex "IPK$")>;
+def : InstRW<[LSU, EndGroup], (instregex "SPKA$")>;
+def : InstRW<[LSU, EndGroup], (instregex "SSM$")>;
+def : InstRW<[FXU, LSU, GroupAlone], (instregex "ST(N|O)SM$")>;
def : InstRW<[FXU, Lat3], (instregex "IAC$")>;
-def : InstRW<[LSU], (instregex "SAC(F)?$")>;
+def : InstRW<[LSU, EndGroup], (instregex "SAC(F)?$")>;
//===----------------------------------------------------------------------===//
// System: Control Register Instructions
//===----------------------------------------------------------------------===//
def : InstRW<[FXU, LSU, Lat30], (instregex "LCTL(G)?$")>;
-def : InstRW<[LSU, Lat30], (instregex "STCT(L|G)$")>;
+def : InstRW<[FXU, LSU, LSU, LSU, LSU, Lat10, GroupAlone],
+ (instregex "STCT(L|G)$")>;
def : InstRW<[LSU], (instregex "E(P|S)A(I)?R$")>;
def : InstRW<[FXU, Lat30], (instregex "SSA(I)?R$")>;
def : InstRW<[FXU, Lat30], (instregex "ESEA$")>;
@@ -1103,16 +1122,17 @@ def : InstRW<[FXU, LSU, Lat30], (instregex "TPROT$")>;
//===----------------------------------------------------------------------===//
def : InstRW<[LSU, Lat8, GroupAlone], (instregex "MVC(K|P|S)$")>;
-def : InstRW<[LSU, Lat6, GroupAlone], (instregex "MVC(S|D)K$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MVCSK$")>;
+def : InstRW<[LSU, Lat6, GroupAlone], (instregex "MVCDK$")>;
def : InstRW<[FXU, LSU, Lat30], (instregex "MVCOS$")>;
-def : InstRW<[LSU, Lat30], (instregex "MVPG$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MVPG$")>;
//===----------------------------------------------------------------------===//
// System: Address-Space Instructions
//===----------------------------------------------------------------------===//
def : InstRW<[FXU, LSU, Lat30], (instregex "LASP$")>;
-def : InstRW<[LSU], (instregex "PALB$")>;
+def : InstRW<[LSU, GroupAlone], (instregex "PALB$")>;
def : InstRW<[FXU, LSU, Lat30], (instregex "PC$")>;
def : InstRW<[FXU, Lat30], (instregex "PR$")>;
def : InstRW<[FXU, Lat30], (instregex "PT(I)?$")>;
@@ -1124,7 +1144,7 @@ def : InstRW<[FXU, Lat20], (instregex "TAR$")>;
// System: Linkage-Stack Instructions
//===----------------------------------------------------------------------===//
-def : InstRW<[FXU, LSU, Lat30], (instregex "BAKR$")>;
+def : InstRW<[FXU, LSU, Lat30, EndGroup], (instregex "BAKR$")>;
def : InstRW<[FXU, Lat30], (instregex "EREG(G)?$")>;
def : InstRW<[FXU, Lat30], (instregex "(E|M)STA$")>;
@@ -1161,9 +1181,9 @@ def : InstRW<[FXU, Lat30], (instregex "PCKMO$")>;
//===----------------------------------------------------------------------===//
def : InstRW<[FXU, Lat30], (instregex "SVC$")>;
-def : InstRW<[FXU], (instregex "MC$")>;
+def : InstRW<[FXU, GroupAlone], (instregex "MC$")>;
def : InstRW<[FXU, Lat30], (instregex "DIAG$")>;
-def : InstRW<[FXU], (instregex "TRAC(E|G)$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "TRAC(E|G)$")>;
def : InstRW<[FXU, Lat30], (instregex "TRAP(2|4)$")>;
def : InstRW<[FXU, Lat30], (instregex "SIGP$")>;
def : InstRW<[FXU, LSU, Lat30], (instregex "SIGA$")>;
@@ -1176,7 +1196,8 @@ def : InstRW<[FXU, LSU, Lat30], (instregex "SIE$")>;
def : InstRW<[FXU], (instregex "LPP$")>;
def : InstRW<[FXU, Lat30], (instregex "ECPGA$")>;
def : InstRW<[FXU, Lat30], (instregex "E(C|P)CTR$")>;
-def : InstRW<[FXU, LSU, Lat30], (instregex "L(C|P|S)CTL$")>;
+def : InstRW<[FXU, Lat30], (instregex "LCCTL$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "L(P|S)CTL$")>;
def : InstRW<[FXU, LSU, Lat30], (instregex "Q(S|CTR)I$")>;
def : InstRW<[FXU, Lat30], (instregex "S(C|P)CTR$")>;
diff --git a/lib/Target/SystemZ/SystemZScheduleZEC12.td b/lib/Target/SystemZ/SystemZScheduleZEC12.td
index 59f37205f4127..a0f2115eb9d72 100644
--- a/lib/Target/SystemZ/SystemZScheduleZEC12.td
+++ b/lib/Target/SystemZ/SystemZScheduleZEC12.td
@@ -69,7 +69,7 @@ def : WriteRes<LSU_lat1, [ZEC12_LSUnit]> { let Latency = 1; }
def : WriteRes<FPU, [ZEC12_FPUnit]> { let Latency = 8; }
def : WriteRes<FPU2, [ZEC12_FPUnit, ZEC12_FPUnit]> { let Latency = 9; }
def : WriteRes<DFU, [ZEC12_DFUnit]> { let Latency = 2; }
-def : WriteRes<DFU2, [ZEC12_DFUnit, ZEC12_FPUnit]> { let Latency = 3; }
+def : WriteRes<DFU2, [ZEC12_DFUnit, ZEC12_DFUnit]> { let Latency = 3; }
def : WriteRes<VBU, [ZEC12_VBUnit]>; // Virtual Branching Unit
// -------------------------- INSTRUCTIONS ---------------------------------- //
@@ -251,7 +251,7 @@ def : InstRW<[LSU, LSU, LSU, LSU, LSU, Lat10, GroupAlone],
(instregex "LM(H|Y|G)?$")>;
// Load multiple disjoint
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "LMD$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "LMD$")>;
// Store multiple (estimated average of 3 ops)
def : InstRW<[LSU, LSU, FXU, FXU, FXU, Lat10, GroupAlone],
@@ -413,13 +413,13 @@ def : InstRW<[FXU, Lat6], (instregex "MS(R|FI)$")>;
def : InstRW<[FXU, LSU, Lat12], (instregex "MSG$")>;
def : InstRW<[FXU, Lat8], (instregex "MSGR$")>;
def : InstRW<[FXU, Lat6], (instregex "MSGF(I|R)$")>;
-def : InstRW<[FXU, LSU, Lat15, GroupAlone], (instregex "MLG$")>;
-def : InstRW<[FXU, Lat9, GroupAlone], (instregex "MLGR$")>;
+def : InstRW<[FXU, FXU, LSU, Lat15, GroupAlone], (instregex "MLG$")>;
+def : InstRW<[FXU, FXU, Lat9, GroupAlone], (instregex "MLGR$")>;
def : InstRW<[FXU, Lat5], (instregex "MGHI$")>;
def : InstRW<[FXU, Lat5], (instregex "MHI$")>;
def : InstRW<[FXU, LSU, Lat9], (instregex "MH(Y)?$")>;
-def : InstRW<[FXU, Lat7, GroupAlone], (instregex "M(L)?R$")>;
-def : InstRW<[FXU, LSU, Lat7, GroupAlone], (instregex "M(FY|L)?$")>;
+def : InstRW<[FXU, FXU, Lat7, GroupAlone], (instregex "M(L)?R$")>;
+def : InstRW<[FXU, FXU, LSU, Lat7, GroupAlone], (instregex "M(FY|L)?$")>;
//===----------------------------------------------------------------------===//
// Division and remainder
@@ -446,7 +446,8 @@ def : InstRW<[FXU], (instregex "SLL(G|K)?$")>;
def : InstRW<[FXU], (instregex "SRL(G|K)?$")>;
def : InstRW<[FXU], (instregex "SRA(G|K)?$")>;
def : InstRW<[FXU], (instregex "SLA(G|K)?$")>;
-def : InstRW<[FXU, FXU, FXU, FXU, Lat8], (instregex "S(L|R)D(A|L)$")>;
+def : InstRW<[FXU, FXU, FXU, FXU, LSU, Lat8, GroupAlone],
+ (instregex "S(L|R)D(A|L)$")>;
// Rotate
def : InstRW<[FXU, LSU, Lat6], (instregex "RLL(G)?$")>;
@@ -544,7 +545,7 @@ def : InstRW<[FXU, FXU, FXU, FXU, FXU, FXU, LSU, LSU, Lat12, GroupAlone],
(instregex "CDSG$")>;
// Compare and swap and store
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "CSST$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "CSST$")>;
// Perform locked operation
def : InstRW<[LSU, Lat30, GroupAlone], (instregex "PLO$")>;
@@ -560,36 +561,44 @@ def : InstRW<[LSU, LSU, Lat5, GroupAlone], (instregex "LPD(G)?$")>;
// Translate and convert
//===----------------------------------------------------------------------===//
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "TR(T|TR)?(E|EOpt)?$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "TR(T|O)(T|O)(Opt)?$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "CU(12|14|21|24|41|42)(Opt)?$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "(CUUTF|CUTFU)(Opt)?$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "TR$")>;
+def : InstRW<[FXU, FXU, FXU, LSU, LSU, Lat30, GroupAlone], (instregex "TRT$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "TRTR$")>;
+def : InstRW<[FXU, Lat30], (instregex "TR(TR)?(T)?(E|EOpt)?$")>;
+def : InstRW<[LSU, Lat30], (instregex "TR(T|O)(T|O)(Opt)?$")>;
+def : InstRW<[FXU, Lat30], (instregex "CU(12|14|21|24|41|42)(Opt)?$")>;
+def : InstRW<[FXU, Lat30], (instregex "(CUUTF|CUTFU)(Opt)?$")>;
//===----------------------------------------------------------------------===//
// Message-security assist
//===----------------------------------------------------------------------===//
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "KM(C|F|O|CTR)?$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "(KIMD|KLMD|KMAC|PCC)$")>;
+def : InstRW<[FXU, Lat30], (instregex "KM(C|F|O|CTR)?$")>;
+def : InstRW<[FXU, Lat30], (instregex "(KIMD|KLMD|KMAC|PCC)$")>;
//===----------------------------------------------------------------------===//
// Decimal arithmetic
//===----------------------------------------------------------------------===//
-def : InstRW<[FXU, DFU, LSU, Lat30, GroupAlone], (instregex "CVB(Y|G)?$")>;
-def : InstRW<[FXU, DFU, FXU, Lat30, GroupAlone], (instregex "CVD(Y|G)?$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MV(N|Z|O)$")>;
+def : InstRW<[FXU, DFU2, LSU, LSU, Lat30, GroupAlone], (instregex "CVBG$")>;
+def : InstRW<[FXU, DFU, LSU, Lat30, GroupAlone], (instregex "CVB(Y)?$")>;
+def : InstRW<[FXU, FXU, FXU, DFU2, DFU2, LSU, Lat30, GroupAlone],
+ (instregex "CVDG$")>;
+def : InstRW<[FXU, FXU, DFU, LSU, Lat30, GroupAlone], (instregex "CVD(Y)?$")>;
+def : InstRW<[LSU, Lat10, GroupAlone], (instregex "MVO$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MV(N|Z)$")>;
def : InstRW<[LSU, Lat30, GroupAlone], (instregex "(PACK|PKA|PKU)$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "UNPK(A|U)?$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "UNPK$")>;
+def : InstRW<[LSU, Lat12, GroupAlone], (instregex "UNPK(A|U)$")>;
-def : InstRW<[FXU, FXU, DFU2, LSU, LSU, LSU, LSU, Lat15, GroupAlone],
+def : InstRW<[FXU, DFU2, DFU2, LSU, LSU, Lat15, GroupAlone],
(instregex "(A|S|ZA)P$")>;
-def : InstRW<[FXU, FXU, DFU2, LSU, LSU, LSU, LSU, Lat30, GroupAlone],
+def : InstRW<[FXU, DFU2, DFU2, LSU, LSU, Lat30, GroupAlone],
(instregex "(M|D)P$")>;
-def : InstRW<[FXU, FXU, DFU2, LSU, LSU, Lat15, GroupAlone],
+def : InstRW<[FXU, FXU, DFU2, DFU2, LSU, LSU, LSU, Lat15, GroupAlone],
(instregex "SRP$")>;
-def : InstRW<[DFU2, LSU, LSU, LSU, LSU, Lat11, GroupAlone], (instregex "CP$")>;
-def : InstRW<[DFU2, LSU, LSU, Lat3, GroupAlone], (instregex "TP$")>;
+def : InstRW<[DFU2, DFU2, LSU, LSU, Lat11, GroupAlone], (instregex "CP$")>;
+def : InstRW<[DFU2, LSU, LSU, Lat5, GroupAlone], (instregex "TP$")>;
def : InstRW<[LSU, Lat30, GroupAlone], (instregex "ED(MK)?$")>;
//===----------------------------------------------------------------------===//
@@ -659,7 +668,7 @@ def : InstRW<[FXU], (instregex "PPA$")>;
//===----------------------------------------------------------------------===//
// Find leftmost one
-def : InstRW<[FXU, Lat7, GroupAlone], (instregex "FLOGR$")>;
+def : InstRW<[FXU, FXU, Lat7, GroupAlone], (instregex "FLOGR$")>;
// Population count
def : InstRW<[FXU, Lat3], (instregex "POPCNT$")>;
@@ -670,14 +679,14 @@ def : InstRW<[FXU], (instregex "ZEXT128$")>;
// String instructions
def : InstRW<[FXU, LSU, Lat30], (instregex "SRST$")>;
-def : InstRW<[LSU, Lat30], (instregex "SRSTU$")>;
+def : InstRW<[FXU, Lat30], (instregex "SRSTU$")>;
def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CUSE$")>;
// Various complex instructions
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CFC$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "UPT$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CKSM$")>;
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "CMPSC$")>;
+def : InstRW<[LSU, Lat30], (instregex "CFC$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "UPT$")>;
+def : InstRW<[LSU, Lat30], (instregex "CKSM$")>;
+def : InstRW<[FXU, Lat30], (instregex "CMPSC$")>;
// Execute
def : InstRW<[LSU, GroupAlone], (instregex "EX(RL)?$")>;
@@ -818,9 +827,9 @@ def : InstRW<[FPU2, FPU2, Lat10, GroupAlone], (instregex "MXDBR$")>;
def : InstRW<[FPU2, FPU2, Lat30, GroupAlone], (instregex "MXBR$")>;
// Multiply and add / subtract
-def : InstRW<[FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)EB$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)EB$")>;
def : InstRW<[FPU, GroupAlone], (instregex "M(A|S)EBR$")>;
-def : InstRW<[FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)DB$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)DB$")>;
def : InstRW<[FPU, GroupAlone], (instregex "M(A|S)DBR$")>;
// Division
@@ -829,7 +838,7 @@ def : InstRW<[FPU, Lat30], (instregex "D(E|D)BR$")>;
def : InstRW<[FPU2, FPU2, Lat30, GroupAlone], (instregex "DXBR$")>;
// Divide to integer
-def : InstRW<[FPU, Lat30, GroupAlone], (instregex "DI(E|D)BR$")>;
+def : InstRW<[FPU, Lat30], (instregex "DI(E|D)BR$")>;
//===----------------------------------------------------------------------===//
// FP: Comparisons
@@ -851,10 +860,10 @@ def : InstRW<[FPU2, FPU2, LSU, Lat15, GroupAlone], (instregex "TCXB$")>;
def : InstRW<[FXU, LSU, Lat4, GroupAlone], (instregex "EFPC$")>;
def : InstRW<[LSU, Lat3, GroupAlone], (instregex "SFPC$")>;
def : InstRW<[LSU, LSU, Lat6, GroupAlone], (instregex "LFPC$")>;
-def : InstRW<[LSU, Lat3, GroupAlone], (instregex "STFPC$")>;
-def : InstRW<[FXU, Lat30, GroupAlone], (instregex "SFASR$")>;
-def : InstRW<[FXU, LSU, Lat30, GroupAlone], (instregex "LFAS$")>;
-def : InstRW<[FXU, Lat2, GroupAlone], (instregex "SRNM(B|T)?$")>;
+def : InstRW<[FXU, LSU, Lat3, GroupAlone], (instregex "STFPC$")>;
+def : InstRW<[FXU, Lat30], (instregex "SFASR$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "LFAS$")>;
+def : InstRW<[FXU, GroupAlone], (instregex "SRNM(B|T)?$")>;
// --------------------- Hexadecimal floating point ------------------------- //
@@ -938,16 +947,20 @@ def : InstRW<[FPU], (instregex "M(D|DE|E|EE)R$")>;
def : InstRW<[FPU2, FPU2, LSU, Lat15, GroupAlone], (instregex "MXD$")>;
def : InstRW<[FPU2, FPU2, Lat10, GroupAlone], (instregex "MXDR$")>;
def : InstRW<[FPU2, FPU2, Lat30, GroupAlone], (instregex "MXR$")>;
-def : InstRW<[FPU2, FPU2, LSU, Lat15, GroupAlone], (instregex "MY(H|L)?$")>;
-def : InstRW<[FPU2, FPU2, Lat10, GroupAlone], (instregex "MY(H|L)?R$")>;
+def : InstRW<[FPU2, FPU2, LSU, Lat15, GroupAlone], (instregex "MY$")>;
+def : InstRW<[FPU, FPU, LSU, Lat15, GroupAlone], (instregex "MY(H|L)$")>;
+def : InstRW<[FPU2, FPU2, Lat10, GroupAlone], (instregex "MYR$")>;
+def : InstRW<[FPU, Lat10, GroupAlone], (instregex "MY(H|L)R$")>;
// Multiply and add / subtract
-def : InstRW<[FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)E$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)E$")>;
def : InstRW<[FPU, GroupAlone], (instregex "M(A|S)ER$")>;
-def : InstRW<[FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)D$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "M(A|S)D$")>;
def : InstRW<[FPU, GroupAlone], (instregex "M(A|S)DR$")>;
-def : InstRW<[FPU2, FPU2, LSU, Lat12, GroupAlone], (instregex "MAY(H|L)?$")>;
-def : InstRW<[FPU2, FPU2, GroupAlone], (instregex "MAY(H|L)?R$")>;
+def : InstRW<[FPU2, FPU2, LSU, GroupAlone], (instregex "MAY$")>;
+def : InstRW<[FPU2, FPU2, GroupAlone], (instregex "MAYR$")>;
+def : InstRW<[FPU, FPU, LSU, Lat12, GroupAlone], (instregex "MAY(H|L)$")>;
+def : InstRW<[FPU, GroupAlone], (instregex "MAY(H|L)R$")>;
// Division
def : InstRW<[FPU, LSU, Lat30], (instregex "D(E|D)$")>;
@@ -987,16 +1000,21 @@ def : InstRW<[DFU, Lat20], (instregex "LDETR$")>;
def : InstRW<[DFU2, DFU2, Lat20, GroupAlone], (instregex "LXDTR$")>;
// Convert from fixed / logical
-def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "CD(F|G)TR(A)?$")>;
-def : InstRW<[FXU, DFU2, DFU2, Lat30, GroupAlone], (instregex "CX(F|G)TR(A)?$")>;
+def : InstRW<[FXU, DFU, Lat9, GroupAlone], (instregex "CDFTR$")>;
+def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "CDGTR(A)?$")>;
+def : InstRW<[FXU, DFU2, DFU2, GroupAlone], (instregex "CXFTR$")>;
+def : InstRW<[FXU, DFU2, DFU2, Lat30, GroupAlone], (instregex "CXGTR(A)?$")>;
def : InstRW<[FXU, DFU, Lat11, GroupAlone], (instregex "CDL(F|G)TR$")>;
-def : InstRW<[FXU, DFU2, DFU2, Lat11, GroupAlone], (instregex "CXL(F|G)TR$")>;
+def : InstRW<[FXU, DFU2, DFU2, Lat11, GroupAlone], (instregex "CXLFTR$")>;
+def : InstRW<[FXU, DFU2, DFU2, Lat6, GroupAlone], (instregex "CXLGTR$")>;
// Convert to fixed / logical
-def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "C(F|G)DTR(A)?$")>;
-def : InstRW<[FXU, DFU, DFU, Lat30, GroupAlone], (instregex "C(F|G)XTR(A)?$")>;
-def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "CL(F|G)DTR$")>;
-def : InstRW<[FXU, DFU, DFU, Lat30, GroupAlone], (instregex "CL(F|G)XTR$")>;
+def : InstRW<[FXU, DFU, Lat11, GroupAlone], (instregex "CFDTR(A)?$")>;
+def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "CGDTR(A)?$")>;
+def : InstRW<[FXU, DFU, DFU, Lat11, GroupAlone], (instregex "CFXTR$")>;
+def : InstRW<[FXU, DFU, DFU, Lat30, GroupAlone], (instregex "CGXTR(A)?$")>;
+def : InstRW<[FXU, DFU, Lat11, GroupAlone], (instregex "CL(F|G)DTR$")>;
+def : InstRW<[FXU, DFU, DFU, Lat11, GroupAlone], (instregex "CL(F|G)XTR$")>;
// Convert from / to signed / unsigned packed
def : InstRW<[FXU, DFU, Lat12, GroupAlone], (instregex "CD(S|U)TR$")>;
@@ -1007,11 +1025,11 @@ def : InstRW<[FXU, FXU, DFU2, DFU2, Lat20, GroupAlone], (instregex "C(S|U)XTR$")
// Convert from / to zoned
def : InstRW<[LSU, DFU2, Lat7, GroupAlone], (instregex "CDZT$")>;
def : InstRW<[LSU, LSU, DFU2, DFU2, Lat10, GroupAlone], (instregex "CXZT$")>;
-def : InstRW<[FXU, LSU, DFU, Lat11, GroupAlone], (instregex "CZDT$")>;
+def : InstRW<[FXU, LSU, DFU, DFU, Lat11, GroupAlone], (instregex "CZDT$")>;
def : InstRW<[FXU, LSU, DFU, DFU, Lat15, GroupAlone], (instregex "CZXT$")>;
// Perform floating-point operation
-def : InstRW<[LSU, Lat30, GroupAlone], (instregex "PFPO$")>;
+def : InstRW<[FXU, Lat30], (instregex "PFPO$")>;
//===----------------------------------------------------------------------===//
// DFP: Unary arithmetic
@@ -1023,7 +1041,7 @@ def : InstRW<[DFU2, DFU2, Lat20, GroupAlone], (instregex "FIXTR$")>;
// Extract biased exponent
def : InstRW<[FXU, DFU, Lat15, GroupAlone], (instregex "EEDTR$")>;
-def : InstRW<[FXU, DFU, Lat15, GroupAlone], (instregex "EEXTR$")>;
+def : InstRW<[FXU, DFU2, Lat15, GroupAlone], (instregex "EEXTR$")>;
// Extract significance
def : InstRW<[FXU, DFU, Lat15, GroupAlone], (instregex "ESDTR$")>;
@@ -1054,15 +1072,15 @@ def : InstRW<[DFU, Lat30], (instregex "QADTR$")>;
def : InstRW<[DFU2, DFU2, Lat30, GroupAlone], (instregex "QAXTR$")>;
// Reround
-def : InstRW<[FXU, DFU, Lat30], (instregex "RRDTR$")>;
+def : InstRW<[FXU, DFU, Lat30, GroupAlone], (instregex "RRDTR$")>;
def : InstRW<[FXU, DFU2, DFU2, Lat30, GroupAlone], (instregex "RRXTR$")>;
// Shift significand left/right
-def : InstRW<[LSU, DFU, Lat11], (instregex "S(L|R)DT$")>;
+def : InstRW<[LSU, DFU, Lat11, GroupAlone], (instregex "S(L|R)DT$")>;
def : InstRW<[LSU, DFU2, DFU2, Lat15, GroupAlone], (instregex "S(L|R)XT$")>;
// Insert biased exponent
-def : InstRW<[FXU, DFU, Lat11], (instregex "IEDTR$")>;
+def : InstRW<[FXU, DFU, Lat11, GroupAlone], (instregex "IEDTR$")>;
def : InstRW<[FXU, DFU2, DFU2, Lat15, GroupAlone], (instregex "IEXTR$")>;
//===----------------------------------------------------------------------===//
@@ -1071,15 +1089,15 @@ def : InstRW<[FXU, DFU2, DFU2, Lat15, GroupAlone], (instregex "IEXTR$")>;
// Compare
def : InstRW<[DFU, Lat11], (instregex "(K|C)DTR$")>;
-def : InstRW<[DFU, DFU, Lat15, GroupAlone], (instregex "(K|C)XTR$")>;
+def : InstRW<[DFU, DFU, Lat15], (instregex "(K|C)XTR$")>;
// Compare biased exponent
def : InstRW<[DFU, Lat8], (instregex "CEDTR$")>;
-def : InstRW<[DFU, Lat9], (instregex "CEXTR$")>;
+def : InstRW<[DFU, DFU, Lat9], (instregex "CEXTR$")>;
// Test Data Class/Group
def : InstRW<[LSU, DFU, Lat15], (instregex "TD(C|G)(E|D)T$")>;
-def : InstRW<[LSU, DFU2, DFU2, Lat15, GroupAlone], (instregex "TD(C|G)XT$")>;
+def : InstRW<[LSU, DFU2, Lat15], (instregex "TD(C|G)XT$")>;
// -------------------------------- System ---------------------------------- //
@@ -1090,19 +1108,20 @@ def : InstRW<[LSU, DFU2, DFU2, Lat15, GroupAlone], (instregex "TD(C|G)XT$")>;
def : InstRW<[FXU, Lat30], (instregex "EPSW$")>;
def : InstRW<[FXU, LSU, Lat30], (instregex "LPSW(E)?$")>;
-def : InstRW<[FXU, Lat3], (instregex "IPK$")>;
-def : InstRW<[LSU], (instregex "SPKA$")>;
-def : InstRW<[LSU], (instregex "SSM$")>;
-def : InstRW<[FXU], (instregex "ST(N|O)SM$")>;
+def : InstRW<[FXU, Lat3, GroupAlone], (instregex "IPK$")>;
+def : InstRW<[LSU, EndGroup], (instregex "SPKA$")>;
+def : InstRW<[LSU, EndGroup], (instregex "SSM$")>;
+def : InstRW<[FXU, LSU, GroupAlone], (instregex "ST(N|O)SM$")>;
def : InstRW<[FXU, Lat3], (instregex "IAC$")>;
-def : InstRW<[LSU], (instregex "SAC(F)?$")>;
+def : InstRW<[LSU, EndGroup], (instregex "SAC(F)?$")>;
//===----------------------------------------------------------------------===//
// System: Control Register Instructions
//===----------------------------------------------------------------------===//
def : InstRW<[FXU, LSU, Lat30], (instregex "LCTL(G)?$")>;
-def : InstRW<[LSU, Lat30], (instregex "STCT(L|G)$")>;
+def : InstRW<[FXU, LSU, LSU, LSU, LSU, Lat30, GroupAlone],
+ (instregex "STCT(L|G)$")>;
def : InstRW<[LSU], (instregex "E(P|S)A(I)?R$")>;
def : InstRW<[FXU, Lat30], (instregex "SSA(I)?R$")>;
def : InstRW<[FXU, Lat30], (instregex "ESEA$")>;
@@ -1148,16 +1167,17 @@ def : InstRW<[FXU, LSU, Lat30], (instregex "TPROT$")>;
//===----------------------------------------------------------------------===//
def : InstRW<[LSU, Lat8, GroupAlone], (instregex "MVC(K|P|S)$")>;
-def : InstRW<[LSU, Lat6, GroupAlone], (instregex "MVC(S|D)K$")>;
+def : InstRW<[LSU, Lat6, Lat30, GroupAlone], (instregex "MVCSK$")>;
+def : InstRW<[LSU, Lat6, GroupAlone], (instregex "MVCDK$")>;
def : InstRW<[FXU, LSU, Lat30], (instregex "MVCOS$")>;
-def : InstRW<[LSU, Lat30], (instregex "MVPG$")>;
+def : InstRW<[LSU, Lat30, GroupAlone], (instregex "MVPG$")>;
//===----------------------------------------------------------------------===//
// System: Address-Space Instructions
//===----------------------------------------------------------------------===//
def : InstRW<[FXU, LSU, Lat30], (instregex "LASP$")>;
-def : InstRW<[LSU], (instregex "PALB$")>;
+def : InstRW<[LSU, GroupAlone], (instregex "PALB$")>;
def : InstRW<[FXU, LSU, Lat30], (instregex "PC$")>;
def : InstRW<[FXU, Lat30], (instregex "PR$")>;
def : InstRW<[FXU, Lat30], (instregex "PT(I)?$")>;
@@ -1169,7 +1189,7 @@ def : InstRW<[FXU, Lat20], (instregex "TAR$")>;
// System: Linkage-Stack Instructions
//===----------------------------------------------------------------------===//
-def : InstRW<[FXU, LSU, Lat30], (instregex "BAKR$")>;
+def : InstRW<[FXU, LSU, Lat30, EndGroup], (instregex "BAKR$")>;
def : InstRW<[FXU, Lat30], (instregex "EREG(G)?$")>;
def : InstRW<[FXU, Lat30], (instregex "(E|M)STA$")>;
@@ -1206,7 +1226,7 @@ def : InstRW<[FXU, Lat30], (instregex "PCKMO$")>;
//===----------------------------------------------------------------------===//
def : InstRW<[FXU, Lat30], (instregex "SVC$")>;
-def : InstRW<[FXU], (instregex "MC$")>;
+def : InstRW<[FXU, GroupAlone], (instregex "MC$")>;
def : InstRW<[FXU, Lat30], (instregex "DIAG$")>;
def : InstRW<[FXU], (instregex "TRAC(E|G)$")>;
def : InstRW<[FXU, Lat30], (instregex "TRAP(2|4)$")>;
@@ -1221,7 +1241,8 @@ def : InstRW<[FXU, LSU, Lat30], (instregex "SIE$")>;
def : InstRW<[FXU], (instregex "LPP$")>;
def : InstRW<[FXU, Lat30], (instregex "ECPGA$")>;
def : InstRW<[FXU, Lat30], (instregex "E(C|P)CTR$")>;
-def : InstRW<[FXU, LSU, Lat30], (instregex "L(C|P|S)CTL$")>;
+def : InstRW<[FXU, Lat30], (instregex "LCCTL$")>;
+def : InstRW<[FXU, LSU, Lat30], (instregex "L(P|S)CTL$")>;
def : InstRW<[FXU, LSU, Lat30], (instregex "Q(S|CTR)I$")>;
def : InstRW<[FXU, Lat30], (instregex "S(C|P)CTR$")>;
diff --git a/lib/Target/SystemZ/SystemZShortenInst.cpp b/lib/Target/SystemZ/SystemZShortenInst.cpp
index 7391df8342efd..13ceb371a425e 100644
--- a/lib/Target/SystemZ/SystemZShortenInst.cpp
+++ b/lib/Target/SystemZ/SystemZShortenInst.cpp
@@ -200,14 +200,26 @@ bool SystemZShortenInst::processBlock(MachineBasicBlock &MBB) {
Changed |= shortenOn001AddCC(MI, SystemZ::ADBR);
break;
+ case SystemZ::WFASB:
+ Changed |= shortenOn001AddCC(MI, SystemZ::AEBR);
+ break;
+
case SystemZ::WFDDB:
Changed |= shortenOn001(MI, SystemZ::DDBR);
break;
+ case SystemZ::WFDSB:
+ Changed |= shortenOn001(MI, SystemZ::DEBR);
+ break;
+
case SystemZ::WFIDB:
Changed |= shortenFPConv(MI, SystemZ::FIDBRA);
break;
+ case SystemZ::WFISB:
+ Changed |= shortenFPConv(MI, SystemZ::FIEBRA);
+ break;
+
case SystemZ::WLDEB:
Changed |= shortenOn01(MI, SystemZ::LDEBR);
break;
@@ -220,30 +232,58 @@ bool SystemZShortenInst::processBlock(MachineBasicBlock &MBB) {
Changed |= shortenOn001(MI, SystemZ::MDBR);
break;
+ case SystemZ::WFMSB:
+ Changed |= shortenOn001(MI, SystemZ::MEEBR);
+ break;
+
case SystemZ::WFLCDB:
Changed |= shortenOn01(MI, SystemZ::LCDFR);
break;
+ case SystemZ::WFLCSB:
+ Changed |= shortenOn01(MI, SystemZ::LCDFR_32);
+ break;
+
case SystemZ::WFLNDB:
Changed |= shortenOn01(MI, SystemZ::LNDFR);
break;
+ case SystemZ::WFLNSB:
+ Changed |= shortenOn01(MI, SystemZ::LNDFR_32);
+ break;
+
case SystemZ::WFLPDB:
Changed |= shortenOn01(MI, SystemZ::LPDFR);
break;
+ case SystemZ::WFLPSB:
+ Changed |= shortenOn01(MI, SystemZ::LPDFR_32);
+ break;
+
case SystemZ::WFSQDB:
Changed |= shortenOn01(MI, SystemZ::SQDBR);
break;
+ case SystemZ::WFSQSB:
+ Changed |= shortenOn01(MI, SystemZ::SQEBR);
+ break;
+
case SystemZ::WFSDB:
Changed |= shortenOn001AddCC(MI, SystemZ::SDBR);
break;
+ case SystemZ::WFSSB:
+ Changed |= shortenOn001AddCC(MI, SystemZ::SEBR);
+ break;
+
case SystemZ::WFCDB:
Changed |= shortenOn01(MI, SystemZ::CDBR);
break;
+ case SystemZ::WFCSB:
+ Changed |= shortenOn01(MI, SystemZ::CEBR);
+ break;
+
case SystemZ::VL32:
// For z13 we prefer LDE over LE to avoid partial register dependencies.
Changed |= shortenOn0(MI, SystemZ::LDE32);
diff --git a/lib/Target/SystemZ/SystemZSubtarget.cpp b/lib/Target/SystemZ/SystemZSubtarget.cpp
index eb4a0962f7eb2..9cd09b0f911e0 100644
--- a/lib/Target/SystemZ/SystemZSubtarget.cpp
+++ b/lib/Target/SystemZ/SystemZSubtarget.cpp
@@ -47,6 +47,10 @@ SystemZSubtarget::SystemZSubtarget(const Triple &TT, const std::string &CPU,
HasVector(false), HasLoadStoreOnCond2(false),
HasLoadAndZeroRightmostByte(false), HasMessageSecurityAssist5(false),
HasDFPPackedConversion(false),
+ HasMiscellaneousExtensions2(false), HasGuardedStorage(false),
+ HasMessageSecurityAssist7(false), HasMessageSecurityAssist8(false),
+ HasVectorEnhancements1(false), HasVectorPackedDecimal(false),
+ HasInsertReferenceBitsMultiple(false),
TargetTriple(TT), InstrInfo(initializeSubtargetDependencies(CPU, FS)),
TLInfo(TM, *this), TSInfo(), FrameLowering() {}
diff --git a/lib/Target/SystemZ/SystemZSubtarget.h b/lib/Target/SystemZ/SystemZSubtarget.h
index b05a1bb6cafd0..4829f73e080e2 100644
--- a/lib/Target/SystemZ/SystemZSubtarget.h
+++ b/lib/Target/SystemZ/SystemZSubtarget.h
@@ -56,6 +56,13 @@ protected:
bool HasLoadAndZeroRightmostByte;
bool HasMessageSecurityAssist5;
bool HasDFPPackedConversion;
+ bool HasMiscellaneousExtensions2;
+ bool HasGuardedStorage;
+ bool HasMessageSecurityAssist7;
+ bool HasMessageSecurityAssist8;
+ bool HasVectorEnhancements1;
+ bool HasVectorPackedDecimal;
+ bool HasInsertReferenceBitsMultiple;
private:
Triple TargetTriple;
@@ -168,6 +175,33 @@ public:
// Return true if the target has the vector facility.
bool hasVector() const { return HasVector; }
+ // Return true if the target has the miscellaneous-extensions facility 2.
+ bool hasMiscellaneousExtensions2() const {
+ return HasMiscellaneousExtensions2;
+ }
+
+ // Return true if the target has the guarded-storage facility.
+ bool hasGuardedStorage() const { return HasGuardedStorage; }
+
+ // Return true if the target has the message-security-assist
+ // extension facility 7.
+ bool hasMessageSecurityAssist7() const { return HasMessageSecurityAssist7; }
+
+ // Return true if the target has the message-security-assist
+ // extension facility 8.
+ bool hasMessageSecurityAssist8() const { return HasMessageSecurityAssist8; }
+
+ // Return true if the target has the vector-enhancements facility 1.
+ bool hasVectorEnhancements1() const { return HasVectorEnhancements1; }
+
+ // Return true if the target has the vector-packed-decimal facility.
+ bool hasVectorPackedDecimal() const { return HasVectorPackedDecimal; }
+
+ // Return true if the target has the insert-reference-bits-multiple facility.
+ bool hasInsertReferenceBitsMultiple() const {
+ return HasInsertReferenceBitsMultiple;
+ }
+
// Return true if GV can be accessed using LARL for reloc model RM
// and code model CM.
bool isPC32DBLSymbol(const GlobalValue *GV, CodeModel::Model CM) const;
diff --git a/lib/Target/SystemZ/SystemZTargetMachine.cpp b/lib/Target/SystemZ/SystemZTargetMachine.cpp
index cb81c0e5276e7..025bf73d2df0d 100644
--- a/lib/Target/SystemZ/SystemZTargetMachine.cpp
+++ b/lib/Target/SystemZ/SystemZTargetMachine.cpp
@@ -143,8 +143,10 @@ public:
} // end anonymous namespace
void SystemZPassConfig::addIRPasses() {
- if (getOptLevel() != CodeGenOpt::None)
+ if (getOptLevel() != CodeGenOpt::None) {
addPass(createSystemZTDCPass());
+ addPass(createLoopDataPrefetchPass());
+ }
TargetPassConfig::addIRPasses();
}
diff --git a/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp b/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
index 9ac768b2189d7..506dc74279932 100644
--- a/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
+++ b/lib/Target/SystemZ/SystemZTargetTransformInfo.cpp
@@ -372,6 +372,9 @@ int SystemZTTIImpl::getArithmeticInstrCost(
Opcode == Instruction::FMul || Opcode == Instruction::FDiv) {
switch (ScalarBits) {
case 32: {
+ // The vector enhancements facility 1 provides v4f32 instructions.
+ if (ST->hasVectorEnhancements1())
+ return NumVectors;
// Return the cost of multiple scalar invocation plus the cost of
// inserting and extracting the values.
unsigned ScalarCost = getArithmeticInstrCost(Opcode, Ty->getScalarType());
diff --git a/lib/Target/SystemZ/SystemZTargetTransformInfo.h b/lib/Target/SystemZ/SystemZTargetTransformInfo.h
index 6923fc6fc9104..a0c6fa94f8c1e 100644
--- a/lib/Target/SystemZ/SystemZTargetTransformInfo.h
+++ b/lib/Target/SystemZ/SystemZTargetTransformInfo.h
@@ -56,6 +56,10 @@ public:
unsigned getNumberOfRegisters(bool Vector);
unsigned getRegisterBitWidth(bool Vector) const;
+ unsigned getCacheLineSize() { return 256; }
+ unsigned getPrefetchDistance() { return 2000; }
+ unsigned getMinPrefetchStride() { return 2048; }
+
bool prefersVectorizedAddressing() { return false; }
bool supportsEfficientVectorElementLoadStore() { return true; }
bool enableInterleavedAccessVectorization() { return true; }