Vendor import of llvm-project branch release/18.x llvmorg-18.1.4-0-ge6c3289804a6.vendor/llvm-project/llvmorg-18.1.4-0-ge6c3289804a6

18 files changed, 219 insertions, 125 deletions

diff --git a/clang/include/clang/Basic/Attr.td b/clang/include/clang/Basic/Attr.td
index 58838b01b4fd..dbf2dd2120fb 100644
--- a/clang/include/clang/Basic/Attr.td
+++ b/clang/include/clang/Basic/Attr.td
@@ -1590,6 +1590,7 @@ def RegCall : DeclOrTypeAttr {
 }
 
 def Final : InheritableAttr {
+  let CanPrintOnLeft = 0;
   let Spellings = [CustomKeyword<"final">, CustomKeyword<"sealed">];
   let Accessors = [Accessor<"isSpelledAsSealed", [CustomKeyword<"sealed">]>];
   let SemaHandler = 0;
@@ -2472,6 +2473,7 @@ def Overloadable : Attr {
 }
 
 def Override : InheritableAttr {
+  let CanPrintOnLeft = 0;
   let Spellings = [CustomKeyword<"override">];
   let SemaHandler = 0;
   // Omitted from docs, since this is language syntax, not an attribute, as far
diff --git a/clang/lib/Format/TokenAnnotator.cpp b/clang/lib/Format/TokenAnnotator.cpp
index d0c4273cfc7e..4d482e6543d6 100644
--- a/clang/lib/Format/TokenAnnotator.cpp
+++ b/clang/lib/Format/TokenAnnotator.cpp
@@ -3450,10 +3450,11 @@ void TokenAnnotator::calculateFormattingInformation(AnnotatedLine &Line) const {
   for (AnnotatedLine *ChildLine : Line.Children)
     calculateFormattingInformation(*ChildLine);
 
-  Line.First->TotalLength =
-      Line.First->IsMultiline ? Style.ColumnLimit
-                              : Line.FirstStartColumn + Line.First->ColumnWidth;
-  FormatToken *Current = Line.First->Next;
+  auto *First = Line.First;
+  First->TotalLength = First->IsMultiline
+                           ? Style.ColumnLimit
+                           : Line.FirstStartColumn + First->ColumnWidth;
+  FormatToken *Current = First->Next;
   bool InFunctionDecl = Line.MightBeFunctionDecl;
   bool AlignArrayOfStructures =
       (Style.AlignArrayOfStructures != FormatStyle::AIAS_None &&
@@ -3475,16 +3476,15 @@ void TokenAnnotator::calculateFormattingInformation(AnnotatedLine &Line) const {
     if (const bool IsCtorOrDtor = Tok->is(TT_CtorDtorDeclName);
         IsCtorOrDtor ||
         isFunctionDeclarationName(Style.isCpp(), *Tok, Line, ClosingParen)) {
-      if (!IsCtorOrDtor) {
-        LineIsFunctionDeclaration = true;
+      if (!IsCtorOrDtor)
         Tok->setFinalizedType(TT_FunctionDeclarationName);
-      }
+      LineIsFunctionDeclaration = true;
       SeenName = true;
       break;
     }
   }
 
-  if (IsCpp && LineIsFunctionDeclaration &&
+  if (IsCpp && (LineIsFunctionDeclaration || First->is(TT_CtorDtorDeclName)) &&
       Line.endsWith(tok::semi, tok::r_brace)) {
     auto *Tok = Line.Last->Previous;
     while (Tok->isNot(tok::r_brace))
@@ -3507,7 +3507,7 @@ void TokenAnnotator::calculateFormattingInformation(AnnotatedLine &Line) const {
   if (IsCpp) {
     if (!LineIsFunctionDeclaration) {
       // Annotate */&/&& in `operator` function calls as binary operators.
-      for (const auto *Tok = Line.First; Tok; Tok = Tok->Next) {
+      for (const auto *Tok = First; Tok; Tok = Tok->Next) {
         if (Tok->isNot(tok::kw_operator))
           continue;
         do {
@@ -3644,7 +3644,7 @@ void TokenAnnotator::calculateFormattingInformation(AnnotatedLine &Line) const {
 
   calculateUnbreakableTailLengths(Line);
   unsigned IndentLevel = Line.Level;
-  for (Current = Line.First; Current; Current = Current->Next) {
+  for (Current = First; Current; Current = Current->Next) {
     if (Current->Role)
       Current->Role->precomputeFormattingInfos(Current);
     if (Current->MatchingParen &&
diff --git a/clang/lib/Headers/__stddef_unreachable.h b/clang/lib/Headers/__stddef_unreachable.h
index 518580c92d3f..61df43e9732f 100644
--- a/clang/lib/Headers/__stddef_unreachable.h
+++ b/clang/lib/Headers/__stddef_unreachable.h
@@ -7,6 +7,8 @@
  *===-----------------------------------------------------------------------===
  */
 
+#ifndef __cplusplus
+
 /*
  * When -fbuiltin-headers-in-system-modules is set this is a non-modular header
  * and needs to behave as if it was textual.
@@ -15,3 +17,5 @@
     (__has_feature(modules) && !__building_module(_Builtin_stddef))
 #define unreachable() __builtin_unreachable()
 #endif
+
+#endif
diff --git a/compiler-rt/lib/builtins/riscv/restore.S b/compiler-rt/lib/builtins/riscv/restore.S
index 73f64a920d66..6f43842c8ca6 100644
--- a/compiler-rt/lib/builtins/riscv/restore.S
+++ b/compiler-rt/lib/builtins/riscv/restore.S
@@ -22,6 +22,8 @@
 
 #if __riscv_xlen == 32
 
+#ifndef __riscv_32e
+
   .globl  __riscv_restore_12
   .type   __riscv_restore_12,@function
 __riscv_restore_12:
@@ -86,8 +88,29 @@ __riscv_restore_0:
   addi    sp, sp, 16
   ret
 
+#else
+
+  .globl  __riscv_restore_2
+  .type   __riscv_restore_2,@function
+  .globl  __riscv_restore_1
+  .type   __riscv_restore_1,@function
+  .globl  __riscv_restore_0
+  .type   __riscv_restore_0,@function
+__riscv_restore_2:
+__riscv_restore_1:
+__riscv_restore_0:
+  lw      s1,  0(sp)
+  lw      s0,  4(sp)
+  lw      ra,  8(sp)
+  addi    sp, sp, 12
+  ret
+
+#endif
+
 #elif __riscv_xlen == 64
 
+#ifndef __riscv_64e
+
   .globl  __riscv_restore_12
   .type   __riscv_restore_12,@function
 __riscv_restore_12:
@@ -162,5 +185,24 @@ __riscv_restore_0:
   ret
 
 #else
+
+  .globl  __riscv_restore_2
+  .type   __riscv_restore_2,@function
+  .globl  __riscv_restore_1
+  .type   __riscv_restore_1,@function
+  .globl  __riscv_restore_0
+  .type   __riscv_restore_0,@function
+__riscv_restore_2:
+__riscv_restore_1:
+__riscv_restore_0:
+  ld      s1,  0(sp)
+  ld      s0,  8(sp)
+  ld      ra,  16(sp)
+  addi    sp, sp, 24
+  ret
+
+#endif
+
+#else
 # error "xlen must be 32 or 64 for save-restore implementation
 #endif
diff --git a/compiler-rt/lib/builtins/riscv/save.S b/compiler-rt/lib/builtins/riscv/save.S
index 85501aeb4c2e..3e044179ff7f 100644
--- a/compiler-rt/lib/builtins/riscv/save.S
+++ b/compiler-rt/lib/builtins/riscv/save.S
@@ -18,6 +18,8 @@
 
 #if __riscv_xlen == 32
 
+#ifndef __riscv_32e
+
   .globl  __riscv_save_12
   .type   __riscv_save_12,@function
 __riscv_save_12:
@@ -92,8 +94,29 @@ __riscv_save_0:
   sw      ra,  12(sp)
   jr      t0
 
+#else
+
+  .globl  __riscv_save_2
+  .type   __riscv_save_2,@function
+  .globl  __riscv_save_1
+  .type   __riscv_save_1,@function
+  .globl  __riscv_save_0
+  .type   __riscv_save_0,@function
+__riscv_save_2:
+__riscv_save_1:
+__riscv_save_0:
+  addi    sp, sp, -12
+  sw      s1,  0(sp)
+  sw      s0,  4(sp)
+  sw      ra,  8(sp)
+  jr      t0
+
+#endif
+
 #elif __riscv_xlen == 64
 
+#ifndef __riscv_64e
+
   .globl  __riscv_save_12
   .type   __riscv_save_12,@function
 __riscv_save_12:
@@ -182,5 +205,24 @@ __riscv_save_0:
   jr     t0
 
 #else
+
+  .globl  __riscv_save_2
+  .type   __riscv_save_2,@function
+  .globl  __riscv_save_1
+  .type   __riscv_save_1,@function
+  .globl  __riscv_save_0
+  .type   __riscv_save_0,@function
+__riscv_save_2:
+__riscv_save_1:
+__riscv_save_0:
+  addi   sp, sp, -24
+  sd     s1, 0(sp)
+  sd     s0, 8(sp)
+  sd     ra, 16(sp)
+  jr     t0
+
+#endif
+
+#else
 # error "xlen must be 32 or 64 for save-restore implementation
 #endif
diff --git a/libcxx/include/__format/formatter_floating_point.h b/libcxx/include/__format/formatter_floating_point.h
index 6802a8b7bd4c..46a090a787ae 100644
--- a/libcxx/include/__format/formatter_floating_point.h
+++ b/libcxx/include/__format/formatter_floating_point.h
@@ -689,7 +689,7 @@ __format_floating_point(_Tp __value, _FormatContext& __ctx, __format_spec::__par
       // Let P equal the precision if nonzero, 6 if the precision is not
       // specified, or 1 if the precision is 0. Then, if a conversion with
       // style E would have an exponent of X:
-      int __p = std::max(1, (__specs.__has_precision() ? __specs.__precision_ : 6));
+      int __p = std::max<int>(1, (__specs.__has_precision() ? __specs.__precision_ : 6));
       if (__result.__exponent == __result.__last)
         // if P > X >= -4, the conversion is with style f or F and precision P - 1 - X.
         // By including the radix point it calculates P - (1 + X)
diff --git a/libcxx/include/stddef.h b/libcxx/include/stddef.h
index 887776b150e4..1583e78e3739 100644
--- a/libcxx/include/stddef.h
+++ b/libcxx/include/stddef.h
@@ -7,18 +7,6 @@
 //
 //===----------------------------------------------------------------------===//
 
-#if defined(__need_ptrdiff_t) || defined(__need_size_t) || defined(__need_wchar_t) || defined(__need_NULL) ||          \
-    defined(__need_wint_t)
-
-#  if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
-#    pragma GCC system_header
-#  endif
-
-#  include_next <stddef.h>
-
-#elif !defined(_LIBCPP_STDDEF_H)
-#  define _LIBCPP_STDDEF_H
-
 /*
     stddef.h synopsis
 
@@ -36,15 +24,18 @@ Types:
 
 */
 
-#  include <__config>
+#include <__config>
 
-#  if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
-#    pragma GCC system_header
-#  endif
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+#  pragma GCC system_header
+#endif
 
-#  if __has_include_next(<stddef.h>)
-#    include_next <stddef.h>
-#  endif
+// Note: This include is outside of header guards because we sometimes get included multiple times
+//       with different defines and the underlying <stddef.h> will know how to deal with that.
+#include_next <stddef.h>
+
+#ifndef _LIBCPP_STDDEF_H
+#  define _LIBCPP_STDDEF_H
 
 #  ifdef __cplusplus
 typedef decltype(nullptr) nullptr_t;
diff --git a/lld/COFF/Chunks.cpp b/lld/COFF/Chunks.cpp
index 39f4575031be..e2074932bc46 100644
--- a/lld/COFF/Chunks.cpp
+++ b/lld/COFF/Chunks.cpp
@@ -652,6 +652,13 @@ void SectionChunk::getRuntimePseudoRelocs(
         dyn_cast_or_null<Defined>(file->getSymbol(rel.SymbolTableIndex));
     if (!target || !target->isRuntimePseudoReloc)
       continue;
+    // If the target doesn't have a chunk allocated, it may be a
+    // DefinedImportData symbol which ended up unnecessary after GC.
+    // Normally we wouldn't eliminate section chunks that are referenced, but
+    // references within DWARF sections don't count for keeping section chunks
+    // alive. Thus such dangling references in DWARF sections are expected.
+    if (!target->getChunk())
+      continue;
     int sizeInBits =
         getRuntimePseudoRelocSize(rel.Type, file->ctx.config.machine);
     if (sizeInBits == 0) {
diff --git a/llvm/lib/Analysis/InstructionSimplify.cpp b/llvm/lib/Analysis/InstructionSimplify.cpp
index d0c27cae0dff..72b6dfa181e8 100644
--- a/llvm/lib/Analysis/InstructionSimplify.cpp
+++ b/llvm/lib/Analysis/InstructionSimplify.cpp
@@ -439,7 +439,8 @@ static Value *threadBinOpOverSelect(Instruction::BinaryOps Opcode, Value *LHS,
     // Check that the simplified value has the form "X op Y" where "op" is the
     // same as the original operation.
     Instruction *Simplified = dyn_cast<Instruction>(FV ? FV : TV);
-    if (Simplified && Simplified->getOpcode() == unsigned(Opcode)) {
+    if (Simplified && Simplified->getOpcode() == unsigned(Opcode) &&
+        !Simplified->hasPoisonGeneratingFlags()) {
       // The value that didn't simplify is "UnsimplifiedLHS op UnsimplifiedRHS".
       // We already know that "op" is the same as for the simplified value.  See
       // if the operands match too.  If so, return the simplified value.
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 3135ec73a99e..e806e0f0731f 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -3575,6 +3575,11 @@ static SDValue combineCarryDiamond(SelectionDAG &DAG, const TargetLowering &TLI,
     return SDValue();
   if (Opcode != ISD::UADDO && Opcode != ISD::USUBO)
     return SDValue();
+  // Guarantee identical type of CarryOut
+  EVT CarryOutType = N->getValueType(0);
+  if (CarryOutType != Carry0.getValue(1).getValueType() ||
+      CarryOutType != Carry1.getValue(1).getValueType())
+    return SDValue();
 
   // Canonicalize the add/sub of A and B (the top node in the above ASCII art)
   // as Carry0 and the add/sub of the carry in as Carry1 (the middle node).
@@ -3622,7 +3627,7 @@ static SDValue combineCarryDiamond(SelectionDAG &DAG, const TargetLowering &TLI,
   // TODO: match other operations that can merge flags (ADD, etc)
   DAG.ReplaceAllUsesOfValueWith(Carry1.getValue(0), Merged.getValue(0));
   if (N->getOpcode() == ISD::AND)
-    return DAG.getConstant(0, DL, MVT::i1);
+    return DAG.getConstant(0, DL, CarryOutType);
   return Merged.getValue(1);
 }
 
diff --git a/llvm/lib/IR/ConstantRange.cpp b/llvm/lib/IR/ConstantRange.cpp
index cbb64b299e64..f105bdb4816a 100644
--- a/llvm/lib/IR/ConstantRange.cpp
+++ b/llvm/lib/IR/ConstantRange.cpp
@@ -746,7 +746,7 @@ ConstantRange ConstantRange::castOp(Instruction::CastOps CastOp,
       Min = Min.zext(ResultBitWidth);
       Max = Max.zext(ResultBitWidth);
     }
-    return ConstantRange(std::move(Min), std::move(Max));
+    return getNonEmpty(std::move(Min), std::move(Max) + 1);
   }
   case Instruction::SIToFP: {
     // TODO: use input range if available
@@ -757,7 +757,7 @@ ConstantRange ConstantRange::castOp(Instruction::CastOps CastOp,
       SMin = SMin.sext(ResultBitWidth);
       SMax = SMax.sext(ResultBitWidth);
     }
-    return ConstantRange(std::move(SMin), std::move(SMax));
+    return getNonEmpty(std::move(SMin), std::move(SMax) + 1);
   }
   case Instruction::FPTrunc:
   case Instruction::FPExt:
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 196aa50cf406..95d8ab95b2c0 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -1658,40 +1658,14 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
   setMaxAtomicSizeInBitsSupported(128);
 
   if (Subtarget->isWindowsArm64EC()) {
-    // FIXME: are there other intrinsics we need to add here?
-    setLibcallName(RTLIB::MEMCPY, "#memcpy");
-    setLibcallName(RTLIB::MEMSET, "#memset");
-    setLibcallName(RTLIB::MEMMOVE, "#memmove");
-    setLibcallName(RTLIB::REM_F32, "#fmodf");
-    setLibcallName(RTLIB::REM_F64, "#fmod");
-    setLibcallName(RTLIB::FMA_F32, "#fmaf");
-    setLibcallName(RTLIB::FMA_F64, "#fma");
-    setLibcallName(RTLIB::SQRT_F32, "#sqrtf");
-    setLibcallName(RTLIB::SQRT_F64, "#sqrt");
-    setLibcallName(RTLIB::CBRT_F32, "#cbrtf");
-    setLibcallName(RTLIB::CBRT_F64, "#cbrt");
-    setLibcallName(RTLIB::LOG_F32, "#logf");
-    setLibcallName(RTLIB::LOG_F64, "#log");
-    setLibcallName(RTLIB::LOG2_F32, "#log2f");
-    setLibcallName(RTLIB::LOG2_F64, "#log2");
-    setLibcallName(RTLIB::LOG10_F32, "#log10f");
-    setLibcallName(RTLIB::LOG10_F64, "#log10");
-    setLibcallName(RTLIB::EXP_F32, "#expf");
-    setLibcallName(RTLIB::EXP_F64, "#exp");
-    setLibcallName(RTLIB::EXP2_F32, "#exp2f");
-    setLibcallName(RTLIB::EXP2_F64, "#exp2");
-    setLibcallName(RTLIB::EXP10_F32, "#exp10f");
-    setLibcallName(RTLIB::EXP10_F64, "#exp10");
-    setLibcallName(RTLIB::SIN_F32, "#sinf");
-    setLibcallName(RTLIB::SIN_F64, "#sin");
-    setLibcallName(RTLIB::COS_F32, "#cosf");
-    setLibcallName(RTLIB::COS_F64, "#cos");
-    setLibcallName(RTLIB::POW_F32, "#powf");
-    setLibcallName(RTLIB::POW_F64, "#pow");
-    setLibcallName(RTLIB::LDEXP_F32, "#ldexpf");
-    setLibcallName(RTLIB::LDEXP_F64, "#ldexp");
-    setLibcallName(RTLIB::FREXP_F32, "#frexpf");
-    setLibcallName(RTLIB::FREXP_F64, "#frexp");
+    // FIXME: are there intrinsics we need to exclude from this?
+    for (int i = 0; i < RTLIB::UNKNOWN_LIBCALL; ++i) {
+      auto code = static_cast<RTLIB::Libcall>(i);
+      auto libcallName = getLibcallName(code);
+      if ((libcallName != nullptr) && (libcallName[0] != '#')) {
+        setLibcallName(code, Saver.save(Twine("#") + libcallName).data());
+      }
+    }
   }
 }
 
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.h b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
index 541a810fb5cb..74d0c4bde8dd 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -1001,6 +1001,9 @@ private:
   /// make the right decision when generating code for different targets.
   const AArch64Subtarget *Subtarget;
 
+  llvm::BumpPtrAllocator BumpAlloc;
+  llvm::StringSaver Saver{BumpAlloc};
+
   bool isExtFreeImpl(const Instruction *Ext) const override;
 
   void addTypeForNEON(MVT VT);
diff --git a/llvm/lib/Target/Mips/Mips32r6InstrInfo.td b/llvm/lib/Target/Mips/Mips32r6InstrInfo.td
index 854563ab32bd..3ef04e488f01 100644
--- a/llvm/lib/Target/Mips/Mips32r6InstrInfo.td
+++ b/llvm/lib/Target/Mips/Mips32r6InstrInfo.td
@@ -152,15 +152,15 @@ class SELNEZ_ENC : SPECIAL_3R_FM<0b00000, 0b110111>;
 
 class LWPC_ENC   : PCREL19_FM<OPCODE2_LWPC>;
 
-class MAX_S_ENC : COP1_3R_FM<0b011101, FIELD_FMT_S>;
-class MAX_D_ENC : COP1_3R_FM<0b011101, FIELD_FMT_D>;
+class MAX_S_ENC : COP1_3R_FM<0b011110, FIELD_FMT_S>;
+class MAX_D_ENC : COP1_3R_FM<0b011110, FIELD_FMT_D>;
 class MIN_S_ENC : COP1_3R_FM<0b011100, FIELD_FMT_S>;
 class MIN_D_ENC : COP1_3R_FM<0b011100, FIELD_FMT_D>;
 
 class MAXA_S_ENC : COP1_3R_FM<0b011111, FIELD_FMT_S>;
 class MAXA_D_ENC : COP1_3R_FM<0b011111, FIELD_FMT_D>;
-class MINA_S_ENC : COP1_3R_FM<0b011110, FIELD_FMT_S>;
-class MINA_D_ENC : COP1_3R_FM<0b011110, FIELD_FMT_D>;
+class MINA_S_ENC : COP1_3R_FM<0b011101, FIELD_FMT_S>;
+class MINA_D_ENC : COP1_3R_FM<0b011101, FIELD_FMT_D>;
 
 class SELEQZ_S_ENC : COP1_3R_FM<0b010100, FIELD_FMT_S>;
 class SELEQZ_D_ENC : COP1_3R_FM<0b010100, FIELD_FMT_D>;
diff --git a/llvm/lib/Target/Mips/MipsExpandPseudo.cpp b/llvm/lib/Target/Mips/MipsExpandPseudo.cpp
index c30129743a96..2c2554b5b4bc 100644
--- a/llvm/lib/Target/Mips/MipsExpandPseudo.cpp
+++ b/llvm/lib/Target/Mips/MipsExpandPseudo.cpp
@@ -388,32 +388,18 @@ bool MipsExpandPseudo::expandAtomicBinOpSubword(
     Opcode = Mips::XOR;
     break;
   case Mips::ATOMIC_LOAD_UMIN_I8_POSTRA:
-    IsUnsigned = true;
-    IsMin = true;
-    break;
   case Mips::ATOMIC_LOAD_UMIN_I16_POSTRA:
     IsUnsigned = true;
-    IsMin = true;
-    break;
+    [[fallthrough]];
   case Mips::ATOMIC_LOAD_MIN_I8_POSTRA:
-    SEOp = Mips::SEB;
-    IsMin = true;
-    break;
   case Mips::ATOMIC_LOAD_MIN_I16_POSTRA:
     IsMin = true;
     break;
   case Mips::ATOMIC_LOAD_UMAX_I8_POSTRA:
-    IsUnsigned = true;
-    IsMax = true;
-    break;
   case Mips::ATOMIC_LOAD_UMAX_I16_POSTRA:
     IsUnsigned = true;
-    IsMax = true;
-    break;
+    [[fallthrough]];
   case Mips::ATOMIC_LOAD_MAX_I8_POSTRA:
-    SEOp = Mips::SEB;
-    IsMax = true;
-    break;
   case Mips::ATOMIC_LOAD_MAX_I16_POSTRA:
     IsMax = true;
     break;
@@ -475,42 +461,14 @@ bool MipsExpandPseudo::expandAtomicBinOpSubword(
 
     // For little endian we need to clear uninterested bits.
     if (STI->isLittle()) {
-      if (!IsUnsigned) {
-        BuildMI(loopMBB, DL, TII->get(Mips::SRAV), OldVal)
-            .addReg(OldVal)
-            .addReg(ShiftAmnt);
-        BuildMI(loopMBB, DL, TII->get(Mips::SRAV), Incr)
-            .addReg(Incr)
-            .addReg(ShiftAmnt);
-        if (STI->hasMips32r2()) {
-          BuildMI(loopMBB, DL, TII->get(SEOp), OldVal).addReg(OldVal);
-          BuildMI(loopMBB, DL, TII->get(SEOp), Incr).addReg(Incr);
-        } else {
-          const unsigned ShiftImm = SEOp == Mips::SEH ? 16 : 24;
-          BuildMI(loopMBB, DL, TII->get(Mips::SLL), OldVal)
-              .addReg(OldVal, RegState::Kill)
-              .addImm(ShiftImm);
-          BuildMI(loopMBB, DL, TII->get(Mips::SRA), OldVal)
-              .addReg(OldVal, RegState::Kill)
-              .addImm(ShiftImm);
-          BuildMI(loopMBB, DL, TII->get(Mips::SLL), Incr)
-              .addReg(Incr, RegState::Kill)
-              .addImm(ShiftImm);
-          BuildMI(loopMBB, DL, TII->get(Mips::SRA), Incr)
-              .addReg(Incr, RegState::Kill)
-              .addImm(ShiftImm);
-        }
-      } else {
-        // and OldVal, OldVal, Mask
-        // and Incr, Incr, Mask
-        BuildMI(loopMBB, DL, TII->get(Mips::AND), OldVal)
-            .addReg(OldVal)
-            .addReg(Mask);
-        BuildMI(loopMBB, DL, TII->get(Mips::AND), Incr)
-            .addReg(Incr)
-            .addReg(Mask);
-      }
+      // and OldVal, OldVal, Mask
+      // and Incr, Incr, Mask
+      BuildMI(loopMBB, DL, TII->get(Mips::AND), OldVal)
+          .addReg(OldVal)
+          .addReg(Mask);
+      BuildMI(loopMBB, DL, TII->get(Mips::AND), Incr).addReg(Incr).addReg(Mask);
     }
+
     // unsigned: sltu Scratch4, oldVal, Incr
     // signed:   slt Scratch4, oldVal, Incr
     BuildMI(loopMBB, DL, TII->get(SLTScratch4), Scratch4)
diff --git a/llvm/lib/Target/Sparc/SparcAsmPrinter.cpp b/llvm/lib/Target/Sparc/SparcAsmPrinter.cpp
index 215a8ea83190..6855471840e9 100644
--- a/llvm/lib/Target/Sparc/SparcAsmPrinter.cpp
+++ b/llvm/lib/Target/Sparc/SparcAsmPrinter.cpp
@@ -434,6 +434,50 @@ bool SparcAsmPrinter::PrintAsmOperand(const MachineInstr *MI, unsigned OpNo,
     default:
       // See if this is a generic print operand
       return AsmPrinter::PrintAsmOperand(MI, OpNo, ExtraCode, O);
+    case 'L': // Low order register of a twin word register operand
+    case 'H': // High order register of a twin word register operand
+    {
+      const SparcSubtarget &Subtarget = MF->getSubtarget<SparcSubtarget>();
+      const MachineOperand &MO = MI->getOperand(OpNo);
+      const SparcRegisterInfo *RegisterInfo = Subtarget.getRegisterInfo();
+      Register MOReg = MO.getReg();
+
+      Register HiReg, LoReg;
+      if (!SP::IntPairRegClass.contains(MOReg)) {
+        // If we aren't given a register pair already, find out which pair it
+        // belongs to. Note that here, the specified register operand, which
+        // refers to the high part of the twinword, needs to be an even-numbered
+        // register.
+        MOReg = RegisterInfo->getMatchingSuperReg(MOReg, SP::sub_even,
+                                                  &SP::IntPairRegClass);
+        if (!MOReg) {
+          SMLoc Loc;
+          OutContext.reportError(
+              Loc, "Hi part of pair should point to an even-numbered register");
+          OutContext.reportError(
+              Loc, "(note that in some cases it might be necessary to manually "
+                   "bind the input/output registers instead of relying on "
+                   "automatic allocation)");
+          return true;
+        }
+      }
+
+      HiReg = RegisterInfo->getSubReg(MOReg, SP::sub_even);
+      LoReg = RegisterInfo->getSubReg(MOReg, SP::sub_odd);
+
+      Register Reg;
+      switch (ExtraCode[0]) {
+      case 'L':
+        Reg = LoReg;
+        break;
+      case 'H':
+        Reg = HiReg;
+        break;
+      }
+
+      O << '%' << SparcInstPrinter::getRegisterName(Reg);
+      return false;
+    }
     case 'f':
     case 'r':
      break;
diff --git a/llvm/lib/Target/X86/X86MCInstLower.cpp b/llvm/lib/Target/X86/X86MCInstLower.cpp
index 58ebe023cd61..7ce0aa22b997 100644
--- a/llvm/lib/Target/X86/X86MCInstLower.cpp
+++ b/llvm/lib/Target/X86/X86MCInstLower.cpp
@@ -959,8 +959,10 @@ void X86AsmPrinter::LowerPATCHABLE_OP(const MachineInstr &MI,
   SmallString<256> Code;
   unsigned MinSize = MI.getOperand(0).getImm();
 
-  if (NextMI != MI.getParent()->end()) {
+  if (NextMI != MI.getParent()->end() && !NextMI->isInlineAsm()) {
     // Lower the next MachineInstr to find its byte size.
+    // If the next instruction is inline assembly, we skip lowering it for now,
+    // and assume we should always generate NOPs.
     MCInst MCI;
     MCIL.Lower(&*NextMI, MCI);
 
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 0a9e2c7f49f5..1fbd69e38eae 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -11653,12 +11653,12 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E, bool PostponedPHIs) {
       if (UseIntrinsic && isVectorIntrinsicWithOverloadTypeAtArg(ID, -1))
         TysForDecl.push_back(
             FixedVectorType::get(CI->getType(), E->Scalars.size()));
+      auto *CEI = cast<CallInst>(VL0);
       for (unsigned I : seq<unsigned>(0, CI->arg_size())) {
         ValueList OpVL;
         // Some intrinsics have scalar arguments. This argument should not be
         // vectorized.
         if (UseIntrinsic && isVectorIntrinsicWithScalarOpAtArg(ID, I)) {
-          CallInst *CEI = cast<CallInst>(VL0);
           ScalarArg = CEI->getArgOperand(I);
           OpVecs.push_back(CEI->getArgOperand(I));
           if (isVectorIntrinsicWithOverloadTypeAtArg(ID, I))
@@ -11671,6 +11671,25 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E, bool PostponedPHIs) {
           LLVM_DEBUG(dbgs() << "SLP: Diamond merged for " << *VL0 << ".\n");
           return E->VectorizedValue;
         }
+        auto GetOperandSignedness = [&](unsigned Idx) {
+          const TreeEntry *OpE = getOperandEntry(E, Idx);
+          bool IsSigned = false;
+          auto It = MinBWs.find(OpE);
+          if (It != MinBWs.end())
+            IsSigned = It->second.second;
+          else
+            IsSigned = any_of(OpE->Scalars, [&](Value *R) {
+              return !isKnownNonNegative(R, SimplifyQuery(*DL));
+            });
+          return IsSigned;
+        };
+        ScalarArg = CEI->getArgOperand(I);
+        if (cast<VectorType>(OpVec->getType())->getElementType() !=
+            ScalarArg->getType()) {
+          auto *CastTy = FixedVectorType::get(ScalarArg->getType(),
+                                              VecTy->getNumElements());
+          OpVec = Builder.CreateIntCast(OpVec, CastTy, GetOperandSignedness(I));
+        }
         LLVM_DEBUG(dbgs() << "SLP: OpVec[" << I << "]: " << *OpVec << "\n");
         OpVecs.push_back(OpVec);
         if (UseIntrinsic && isVectorIntrinsicWithOverloadTypeAtArg(ID, I))