Merge branch 'llvm:main' into cfi-show

Author: eugeneepshteyn

.ci/all_requirements.txt

@@ -194,9 +194,9 @@ ml-dtypes==0.5.1 ; python_version < "3.13" \
     --hash=sha256:d13755f8e8445b3870114e5b6240facaa7cb0c3361e54beba3e07fa912a6e12b \
     --hash=sha256:fd918d4e6a4e0c110e2e05be7a7814d10dc1b95872accbf6512b80a109b71ae1
     # via -r mlir/python/requirements.txt
-nanobind==2.9.2 \
-    --hash=sha256:c37957ffd5eac7eda349cff3622ecd32e5ee1244ecc912c99b5bc8188bafd16e \
-    --hash=sha256:e7608472de99d375759814cab3e2c94aba3f9ec80e62cfef8ced495ca5c27d6e
+nanobind==2.7.0 \
+    --hash=sha256:73b12d0e751d140d6c1bf4b215e18818a8debfdb374f08dc3776ad208d808e74 \
+    --hash=sha256:f9f1b160580c50dcf37b6495a0fd5ec61dc0d95dae5f8004f87dd9ad7eb46b34
     # via -r mlir/python/requirements.txt
 numpy==2.0.2 \
     --hash=sha256:0123ffdaa88fa4ab64835dcbde75dcdf89c453c922f18dced6e27c90d1d0ec5a \
@@ -383,10 +383,6 @@ swig==4.3.1 \
     --hash=sha256:efec16327029f682f649a26da726bb0305be8800bd0f1fa3e81bf0769cf5b476 \
     --hash=sha256:fc496c0d600cf1bb2d91e28d3d6eae9c4301e5ea7a0dec5a4281b5efed4245a8
     # via -r lldb/test/requirements.txt
-typing-extensions==4.15.0 \
-    --hash=sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466 \
-    --hash=sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548
-    # via -r mlir/python/requirements.txt
 urllib3==2.5.0 \
     --hash=sha256:3fc47733c7e419d4bc3f6b3dc2b4f890bb743906a30d56ba4a5bfa4bbff92760 \
     --hash=sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc

bolt/lib/Target/AArch64/AArch64MCPlusBuilder.cpp

@@ -2517,21 +2517,17 @@ class AArch64MCPlusBuilder : public MCPlusBuilder {
   createInstrIncMemory(const MCSymbol *Target, MCContext *Ctx, bool IsLeaf,
                        unsigned CodePointerSize) const override {
     unsigned int I = 0;
-    InstructionListType Instrs(10);
+    InstructionListType Instrs(6);
 
     createPushRegisters(Instrs[I++], AArch64::X0, AArch64::X1);
-    getSystemFlag(Instrs[I++], AArch64::X1);
     InstructionListType Addr = materializeAddress(Target, Ctx, AArch64::X0);
     assert(Addr.size() == 2 && "Invalid Addr size");
     std::copy(Addr.begin(), Addr.end(), Instrs.begin() + I);
     I += Addr.size();
-    storeReg(Instrs[I++], AArch64::X2, AArch64::SP);
-    InstructionListType Insts = createIncMemory(AArch64::X0, AArch64::X2);
+    InstructionListType Insts = createIncMemory(AArch64::X0, AArch64::X1);
     assert(Insts.size() == 2 && "Invalid Insts size");
     std::copy(Insts.begin(), Insts.end(), Instrs.begin() + I);
     I += Insts.size();
-    loadReg(Instrs[I++], AArch64::X2, AArch64::SP);
-    setSystemFlag(Instrs[I++], AArch64::X1);
     createPopRegisters(Instrs[I++], AArch64::X0, AArch64::X1);
     return Instrs;
   }

clang/docs/OpenMPSupport.rst

@@ -366,16 +366,25 @@ implementation.
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
 | threadset clause                                            | :part:`in progress`       | :none:`unclaimed`         |                                                                          |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Recording of task graphs                                    | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
+| Recording of task graphs                                    | :part:`in progress`       | :part:`in progress`       | clang: jtb20, flang: kparzysz                                            |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
 | Parallel inductions                                         | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
 | init_complete for scan directive                            | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Loop transformation constructs                              | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
+| loop interchange transformation                             | :good:`done`              | :none:`unclaimed`         | Clang (interchange): https://github.com/llvm/llvm-project/pull/93022     |
+|                                                             |                           |                           | Clang (permutation): https://github.com/llvm/llvm-project/pull/92030     |
++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
+| loop reverse transformation                                 | :good:`done`              | :none:`unclaimed`         | https://github.com/llvm/llvm-project/pull/92916                          |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
 | loop stripe transformation                                  | :good:`done`              | :none:`unclaimed`         | https://github.com/llvm/llvm-project/pull/119891                         |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
+| loop fusion transformation                                  | :part:`in progress`       | :none:`unclaimed`         | https://github.com/llvm/llvm-project/pull/139293                         |
++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
+| loop index set splitting transformation                     | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
+| loop transformation apply clause                            | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
 | workdistribute construct                                    |                           | :none:`in progress`       | @skc7, @mjklemm                                                          |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
 | task_iteration                                              | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
@@ -446,7 +455,7 @@ implementation.
 | Optionally omit array length expression                     | :good:`done`              | :none:`unclaimed`         | (Parse) https://github.com/llvm/llvm-project/pull/148048,                |
 |                                                             |                           |                           | (Sema) https://github.com/llvm/llvm-project/pull/152786                  |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
-| Canonical loop sequences                                    | :none:`unclaimed`         | :part:`In Progress`       |                                                                          |
+| Canonical loop sequences                                    | :part:`in progress`       | :part:`in progress`       | Clang: https://github.com/llvm/llvm-project/pull/139293                  |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
 | Clarifications to Fortran map semantics                     | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
@@ -507,6 +516,10 @@ implementation.
 |                                                             |                           |                           | https://github.com/llvm/llvm-project/pull/152830                         |
 |                                                             |                           |                           | https://github.com/llvm/llvm-project/pull/152831)                        |
 +-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
+| loop flatten transformation                                 | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
+| loop grid/tile modifiers for sizes clause                   | :none:`unclaimed`         | :none:`unclaimed`         |                                                                          |
++-------------------------------------------------------------+---------------------------+---------------------------+--------------------------------------------------------------------------+
 
 
 OpenMP Extensions

clang/docs/ReleaseNotes.rst

@@ -350,6 +350,9 @@ Bug Fixes to C++ Support
   authentication enabled. (#GH152601)
 - Fix the check for narrowing int-to-float conversions, so that they are detected in
   cases where converting the float back to an integer is undefined behaviour (#GH157067).
+- Fix a crash when applying binary or ternary operators to two same function types with different spellings,
+  where at least one of the function parameters has an attribute which affects
+  the function type.
 - Fix an assertion failure when a ``constexpr`` variable is only referenced through
   ``__builtin_addressof``, and related issues with builtin arguments. (#GH154034)
 

clang/include/clang/AST/Expr.h

@@ -1038,7 +1038,7 @@ class Expr : public ValueStmt {
 // PointerLikeTypeTraits is specialized so it can be used with a forward-decl of
 // Expr. Verify that we got it right.
 static_assert(llvm::PointerLikeTypeTraits<Expr *>::NumLowBitsAvailable <=
-                  llvm::detail::ConstantLog2<alignof(Expr)>::value,
+                  llvm::CTLog2<alignof(Expr)>(),
               "PointerLikeTypeTraits<Expr*> assumes too much alignment.");
 
 using ConstantExprKind = Expr::ConstantExprKind;

clang/include/clang/Basic/BuiltinsAMDGPU.def

@@ -34,6 +34,20 @@ BUILTIN(__builtin_amdgcn_workgroup_id_x, "Ui", "nc")
 BUILTIN(__builtin_amdgcn_workgroup_id_y, "Ui", "nc")
 BUILTIN(__builtin_amdgcn_workgroup_id_z, "Ui", "nc")
 
+TARGET_BUILTIN(__builtin_amdgcn_cluster_id_x, "Ui", "nc", "gfx1250-insts")
+TARGET_BUILTIN(__builtin_amdgcn_cluster_id_y, "Ui", "nc", "gfx1250-insts")
+TARGET_BUILTIN(__builtin_amdgcn_cluster_id_z, "Ui", "nc", "gfx1250-insts")
+
+TARGET_BUILTIN(__builtin_amdgcn_cluster_workgroup_id_x, "Ui", "nc", "gfx1250-insts")
+TARGET_BUILTIN(__builtin_amdgcn_cluster_workgroup_id_y, "Ui", "nc", "gfx1250-insts")
+TARGET_BUILTIN(__builtin_amdgcn_cluster_workgroup_id_z, "Ui", "nc", "gfx1250-insts")
+TARGET_BUILTIN(__builtin_amdgcn_cluster_workgroup_flat_id, "Ui", "nc", "gfx1250-insts")
+
+TARGET_BUILTIN(__builtin_amdgcn_cluster_workgroup_max_id_x, "Ui", "nc", "gfx1250-insts")
+TARGET_BUILTIN(__builtin_amdgcn_cluster_workgroup_max_id_y, "Ui", "nc", "gfx1250-insts")
+TARGET_BUILTIN(__builtin_amdgcn_cluster_workgroup_max_id_z, "Ui", "nc", "gfx1250-insts")
+TARGET_BUILTIN(__builtin_amdgcn_cluster_workgroup_max_flat_id, "Ui", "nc", "gfx1250-insts")
+
 BUILTIN(__builtin_amdgcn_workitem_id_x, "Ui", "nc")
 BUILTIN(__builtin_amdgcn_workitem_id_y, "Ui", "nc")
 BUILTIN(__builtin_amdgcn_workitem_id_z, "Ui", "nc")
@@ -364,6 +378,31 @@ BUILTIN(__builtin_amdgcn_endpgm, "v", "nr")
 BUILTIN(__builtin_amdgcn_get_fpenv, "WUi", "n")
 BUILTIN(__builtin_amdgcn_set_fpenv, "vWUi", "n")
 
+//===----------------------------------------------------------------------===//
+
+// Wave Reduction builtins.
+
+//===----------------------------------------------------------------------===//
+
+BUILTIN(__builtin_amdgcn_wave_reduce_add_u32, "ZUiZUiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_sub_u32, "ZUiZUiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_min_i32, "ZiZiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_min_u32, "ZUiZUiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_max_i32, "ZiZiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_max_u32, "ZUiZUiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_and_b32, "ZiZiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_or_b32, "ZiZiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_xor_b32, "ZiZiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_add_u64, "WUiWUiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_sub_u64, "WUiWUiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_min_i64, "WiWiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_min_u64, "WUiWUiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_max_i64, "WiWiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_max_u64, "WUiWUiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_and_b64, "WiWiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_or_b64, "WiWiZi", "nc")
+BUILTIN(__builtin_amdgcn_wave_reduce_xor_b64, "WiWiZi", "nc")
+
 //===----------------------------------------------------------------------===//
 // R600-NI only builtins.
 //===----------------------------------------------------------------------===//

clang/include/clang/Basic/BuiltinsX86.td

@@ -1057,27 +1057,27 @@ let Features = "avx512f", Attributes = [NoThrow, Const, RequiredVectorWidth<512>
 }
 
 let Features = "avx512vl,avx512vnni|avxvnni", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
-  def vpdpbusd128 : X86Builtin<"_Vector<4, int>(_Vector<4, int>, _Vector<4, int>, _Vector<4, int>)">;
+  def vpdpbusd128 : X86Builtin<"_Vector<4, int>(_Vector<4, int>, _Vector<16, unsigned char>, _Vector<16, char>)">;
 }
 
 let Features = "avx512vl,avx512vnni|avxvnni", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
-  def vpdpbusd256 : X86Builtin<"_Vector<8, int>(_Vector<8, int>, _Vector<8, int>, _Vector<8, int>)">;
+  def vpdpbusd256 : X86Builtin<"_Vector<8, int>(_Vector<8, int>, _Vector<32, unsigned char>, _Vector<32, char>)">;
 }
 
 let Features = "avx512vnni", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
-  def vpdpbusd512 : X86Builtin<"_Vector<16, int>(_Vector<16, int>, _Vector<16, int>, _Vector<16, int>)">;
+  def vpdpbusd512 : X86Builtin<"_Vector<16, int>(_Vector<16, int>, _Vector<64, unsigned char>, _Vector<64, char>)">;
 }
 
 let Features = "avx512vl,avx512vnni|avxvnni", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {
-  def vpdpbusds128 : X86Builtin<"_Vector<4, int>(_Vector<4, int>, _Vector<4, int>, _Vector<4, int>)">;
+  def vpdpbusds128 : X86Builtin<"_Vector<4, int>(_Vector<4, int>, _Vector<16, unsigned char>, _Vector<16, char>)">;
 }
 
 let Features = "avx512vl,avx512vnni|avxvnni", Attributes = [NoThrow, Const, RequiredVectorWidth<256>] in {
-  def vpdpbusds256 : X86Builtin<"_Vector<8, int>(_Vector<8, int>, _Vector<8, int>, _Vector<8, int>)">;
+  def vpdpbusds256 : X86Builtin<"_Vector<8, int>(_Vector<8, int>, _Vector<32, unsigned char>, _Vector<32, char>)">;
 }
 
 let Features = "avx512vnni", Attributes = [NoThrow, Const, RequiredVectorWidth<512>] in {
-  def vpdpbusds512 : X86Builtin<"_Vector<16, int>(_Vector<16, int>, _Vector<16, int>, _Vector<16, int>)">;
+  def vpdpbusds512 : X86Builtin<"_Vector<16, int>(_Vector<16, int>, _Vector<64, unsigned char>, _Vector<64, char>)">;
 }
 
 let Features = "avx512vl,avx512vnni|avxvnni", Attributes = [NoThrow, Const, RequiredVectorWidth<128>] in {

clang/include/clang/CIR/Dialect/IR/CIROps.td

@@ -3827,6 +3827,16 @@ def CIR_ACosOp : CIR_UnaryFPToFPBuiltinOp<"acos", "ACosOp"> {
   }];
 }
 
+def CIR_ASinOp : CIR_UnaryFPToFPBuiltinOp<"asin", "ASinOp"> {
+  let summary = "Computes the arcus sine of the specified value";
+  let description = [{
+    `cir.asin`computes the arcus sine of a given value and
+    returns a result of the same type.
+
+    Floating-point exceptions are ignored, and it does not set `errno`.
+  }];
+}
+
 def CIR_FAbsOp : CIR_UnaryFPToFPBuiltinOp<"fabs", "FAbsOp"> {
   let summary = "Computes the floating-point absolute value";
   let description = [{

clang/lib/AST/ASTContext.cpp

@@ -14195,7 +14195,11 @@ static QualType getCommonNonSugarTypeNode(const ASTContext &Ctx, const Type *X,
     FunctionProtoType::ExtProtoInfo EPIX = FX->getExtProtoInfo(),
                                     EPIY = FY->getExtProtoInfo();
     assert(EPIX.ExtInfo == EPIY.ExtInfo);
-    assert(EPIX.ExtParameterInfos == EPIY.ExtParameterInfos);
+    assert(!EPIX.ExtParameterInfos == !EPIY.ExtParameterInfos);
+    assert(!EPIX.ExtParameterInfos ||
+           llvm::equal(
+               llvm::ArrayRef(EPIX.ExtParameterInfos, FX->getNumParams()),
+               llvm::ArrayRef(EPIY.ExtParameterInfos, FY->getNumParams())));
     assert(EPIX.RefQualifier == EPIY.RefQualifier);
     assert(EPIX.TypeQuals == EPIY.TypeQuals);
     assert(EPIX.Variadic == EPIY.Variadic);

clang/lib/CIR/CodeGen/CIRGenBuiltin.cpp

@@ -411,6 +411,8 @@ RValue CIRGenFunction::emitBuiltinExpr(const GlobalDecl &gd, unsigned builtinID,
 
   case Builtin::BI__builtin_elementwise_acos:
     return emitUnaryFPBuiltin<cir::ACosOp>(*this, *e);
+  case Builtin::BI__builtin_elementwise_asin:
+    return emitUnaryFPBuiltin<cir::ASinOp>(*this, *e);
   }
 
   // If this is an alias for a lib function (e.g. __builtin_sin), emit