Index: lib/Target/ARM/ARM.td
===================================================================
--- lib/Target/ARM/ARM.td
+++ lib/Target/ARM/ARM.td
@@ -132,6 +132,27 @@
 def FeaturePrefISHSTBarrier : SubtargetFeature<"prefer-ishst", "PreferISHST",
                                            "true", "Prefer ISHST barriers">;
 
+// Some targets (e.g. Cortex-A9) have muxed AGU and NEON/FPU.
+def FeatureMuxedUnits : SubtargetFeature<"muxed-units", "HasMuxedUnits", "true",
+                                         "Has muxed AGU and NEON/FPU">;
+
+// On some targets, a VLDM/VSTM starting with an odd register number needs more
+// microops than single VLDRS.
+def FeatureSlowOddRegister : SubtargetFeature<"slow-odd-reg", "SlowOddRegister",
+                     "true", "VLDM/VSTM starting with an odd register is slow">;
+
+// Some targets have a renaming dependency when loading into D subregisters.
+def FeatureSlowLoadDSubreg : SubtargetFeature<"slow-load-D-subreg",
+                                              "SlowLoadDSubregister", "true",
+                                              "Loading into D subregs is slow">;
+
+// Some targets use a compact unwind format which assumes that VFPs are
+// allocated with stride 4. This can expand the prologue, so it won't be taken
+// into account when optimizing for size.
+def FeatureUseStride4VFPs : SubtargetFeature<"use-stride4-vfps",
+                                             "UseStride4VFPs", "true",
+                                             "Allocate VFPs with stride 4">;
+
 // Some targets (e.g. Cortex-A9) want to convert VMOVRS, VMOVSR and VMOVS from
 // VFP to NEON, as an execution domain optimization.
 def FeatureNEONForFPMovs : SubtargetFeature<"neon-fpmovs", "UseNEONForFPMovs",
@@ -578,6 +599,7 @@
                                                          FeatureFP16,
                                                          FeatureAvoidPartialCPSR,
                                                          FeaturePreferVMOVSR,
+                                                         FeatureMuxedUnits,
                                                          FeatureNEONForFPMovs,
                                                          FeatureCheckVLDnAlign,
                                                          FeatureMP]>;
@@ -598,6 +620,7 @@
 // FIXME: A15 has currently the same Schedule model as A9.
 def : ProcessorModel<"cortex-a15",  CortexA9Model,      [ARMv7a, ProcA15,
                                                          FeatureHasRetAddrStack,
+                                                         FeatureMuxedUnits,
                                                          FeatureTrustZone,
                                                          FeatureT2XtPk,
                                                          FeatureVFP4,
@@ -626,6 +649,7 @@
 //        division features.
 def : ProcessorModel<"krait",       CortexA9Model,      [ARMv7a, ProcKrait,
                                                          FeatureHasRetAddrStack,
+                                                         FeatureMuxedUnits,
                                                          FeatureCheckVLDnAlign,
                                                          FeatureVMLxForwarding,
                                                          FeatureT2XtPk,
@@ -639,6 +663,7 @@
                                                          FeatureHasRetAddrStack,
                                                          FeatureNEONForFP,
                                                          FeatureT2XtPk,
+                                                         FeatureUseStride4VFPs,
                                                          FeatureVFP4,
                                                          FeatureMP,
                                                          FeatureHWDiv,
@@ -648,6 +673,8 @@
                                                          FeatureHasSlowFPVMLx,
                                                          FeatureProfUnpredicate,
                                                          FeaturePrefISHSTBarrier,
+                                                         FeatureSlowOddRegister,
+                                                         FeatureSlowLoadDSubreg,
                                                          FeatureSlowVGETLNi32,
                                                          FeatureSlowVDUP32]>;
 
Index: lib/Target/ARM/ARMHazardRecognizer.cpp
===================================================================
--- lib/Target/ARM/ARMHazardRecognizer.cpp
+++ lib/Target/ARM/ARMHazardRecognizer.cpp
@@ -50,8 +50,7 @@
 
       // Skip over one non-VFP / NEON instruction.
       if (!LastMI->isBarrier() &&
-          // On A9, AGU and NEON/FPU are muxed.
-          !(TII.getSubtarget().isLikeA9() && LastMI->mayLoadOrStore()) &&
+          !(TII.getSubtarget().hasMuxedUnits() && LastMI->mayLoadOrStore()) &&
           (LastMCID.TSFlags & ARMII::DomainMask) == ARMII::DomainGeneral) {
         MachineBasicBlock::iterator I = LastMI;
         if (I != LastMI->getParent()->begin()) {
Index: lib/Target/ARM/ARMLoadStoreOptimizer.cpp
===================================================================
--- lib/Target/ARM/ARMLoadStoreOptimizer.cpp
+++ lib/Target/ARM/ARMLoadStoreOptimizer.cpp
@@ -982,7 +982,7 @@
     bool CanMergeToLSMulti = true;
     // On swift vldm/vstm starting with an odd register number as that needs
     // more uops than single vldrs.
-    if (STI->isSwift() && !isNotVFP && (PRegNum % 2) == 1)
+    if (STI->hasSlowOddRegister() && !isNotVFP && (PRegNum % 2) == 1)
       CanMergeToLSMulti = false;
 
     // LDRD/STRD do not allow SP/PC. LDM/STM do not support it or have it
Index: lib/Target/ARM/ARMSubtarget.h
===================================================================
--- lib/Target/ARM/ARMSubtarget.h
+++ lib/Target/ARM/ARMSubtarget.h
@@ -249,6 +249,19 @@
   /// If true, ISHST barriers will be used for Release semantics.
   bool PreferISHST = false;
 
+  /// If true, a VLDM/VSTM starting with an odd register number is considered to
+  /// take more microops than single VLDRS/VSTRS.
+  bool SlowOddRegister = false;
+
+  /// If true, loading into a D subregister will be penalized.
+  bool SlowLoadDSubregister = false;
+
+  /// If true, prefer to allocate VFPs with stride 4.
+  bool UseStride4VFPs = false;
+
+  /// If true, the AGU and NEON/FPU units are multiplexed.
+  bool HasMuxedUnits = false;
+
   /// If true, VMOVRS, VMOVSR and VMOVS will be converted from VFP to NEON.
   bool UseNEONForFPMovs = false;
 
@@ -382,6 +395,9 @@
   bool hasV8MBaselineOps() const { return HasV8MBaselineOps; }
   bool hasV8MMainlineOps() const { return HasV8MMainlineOps; }
 
+  /// @{
+  /// These functions are obsolete, please consider adding subtarget features
+  /// or properties instead of calling them.
   bool isCortexA5() const { return ARMProcFamily == CortexA5; }
   bool isCortexA7() const { return ARMProcFamily == CortexA7; }
   bool isCortexA8() const { return ARMProcFamily == CortexA8; }
@@ -392,6 +408,7 @@
   bool isLikeA9() const { return isCortexA9() || isCortexA15() || isKrait(); }
   bool isCortexR5() const { return ARMProcFamily == CortexR5; }
   bool isKrait() const { return ARMProcFamily == Krait; }
+  /// @}
 
   bool hasARMOps() const { return !NoARM; }
 
@@ -431,6 +448,9 @@
   bool hasSlowVDUP32() const { return HasSlowVDUP32; }
   bool preferVMOVSR() const { return PreferVMOVSR; }
   bool preferISHSTBarriers() const { return PreferISHST; }
+  bool hasSlowOddRegister() const { return SlowOddRegister; }
+  bool hasSlowLoadDSubregister() const { return SlowLoadDSubregister; }
+  bool hasMuxedUnits() const { return HasMuxedUnits; }
   bool useNEONForFPMovs() const { return UseNEONForFPMovs; }
   bool checkVLDnAccessAlignment() const { return CheckVLDnAlign; }
   bool nonpipelinedVFP() const { return NonpipelinedVFP; }
Index: lib/Target/ARM/ARMSubtarget.cpp
===================================================================
--- lib/Target/ARM/ARMSubtarget.cpp
+++ lib/Target/ARM/ARMSubtarget.cpp
@@ -310,7 +310,8 @@
   // For general targets, the prologue can grow when VFPs are allocated with
   // stride 4 (more vpush instructions). But WatchOS uses a compact unwind
   // format which it's more important to get right.
-  return isTargetWatchABI() || (isSwift() && !MF.getFunction()->optForMinSize());
+  return isTargetWatchABI() ||
+         (UseStride4VFPs && !MF.getFunction()->optForMinSize());
 }
 
 bool ARMSubtarget::useMovt(const MachineFunction &MF) const {
Index: lib/Target/ARM/ARMTargetTransformInfo.cpp
===================================================================
--- lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -259,10 +259,8 @@
                                    unsigned Index) {
   // Penalize inserting into an D-subregister. We end up with a three times
   // lower estimated throughput on swift.
-  if (ST->isSwift() &&
-      Opcode == Instruction::InsertElement &&
-      ValTy->isVectorTy() &&
-      ValTy->getScalarSizeInBits() <= 32)
+  if (ST->hasSlowLoadDSubregister() && Opcode == Instruction::InsertElement &&
+      ValTy->isVectorTy() && ValTy->getScalarSizeInBits() <= 32)
     return 3;
 
   if ((Opcode == Instruction::InsertElement ||