Merge upstream LLVM into amd-gfx12

Author: SC llvm team

clang-tools-extra/clang-doc/Representation.cpp

@@ -502,13 +502,13 @@ ClangDocContext::ClangDocContext(tooling::ExecutionContext *ECtx,
 }
 
 void ScopeChildren::sort() {
-  llvm::sort(Namespaces.begin(), Namespaces.end());
-  llvm::sort(Records.begin(), Records.end());
-  llvm::sort(Functions.begin(), Functions.end());
-  llvm::sort(Enums.begin(), Enums.end());
-  llvm::sort(Typedefs.begin(), Typedefs.end());
-  llvm::sort(Concepts.begin(), Concepts.end());
-  llvm::sort(Variables.begin(), Variables.end());
+  llvm::sort(Namespaces);
+  llvm::sort(Records);
+  llvm::sort(Functions);
+  llvm::sort(Enums);
+  llvm::sort(Typedefs);
+  llvm::sort(Concepts);
+  llvm::sort(Variables);
 }
 } // namespace doc
 } // namespace clang

libc/src/wchar/wcspbrk.cpp

@@ -11,7 +11,7 @@
 #include "hdr/types/wchar_t.h"
 #include "src/__support/common.h"
 #include "src/__support/macros/null_check.h"
-#include "wchar_utils.h"
+#include "src/wchar/wchar_utils.h"
 
 namespace LIBC_NAMESPACE_DECL {
 

libclc/clc/include/clc/math/unary_def_via_fp32.inc

@@ -10,15 +10,8 @@
 #if (__CLC_VECSIZE_OR_1 == 1 || __CLC_VECSIZE_OR_1 == 2 ||                     \
      __CLC_VECSIZE_OR_1 == 3 || __CLC_VECSIZE_OR_1 == 4)
 
-// Until we have a native FP16 implementation, go via FP32
-#if __CLC_FPSIZE == 16
-
-_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE __clc_normalize(__CLC_GENTYPE p) {
-  return __CLC_CONVERT_GENTYPE(__clc_normalize(__CLC_CONVERT_FLOATN(p)));
-}
-
 // Scalar normalize
-#elif defined(__CLC_SCALAR)
+#if defined(__CLC_SCALAR)
 
 _CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE __clc_normalize(__CLC_GENTYPE p) {
   return __clc_sign(p);
@@ -27,7 +20,13 @@ _CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE __clc_normalize(__CLC_GENTYPE p) {
 // Vector normalize
 #else
 
-#if __CLC_FPSIZE == 32
+#if __CLC_FPSIZE == 16
+
+#define MIN_VAL HALF_MIN
+#define MAX_SQRT 0x1.0p+8h
+#define MIN_SQRT 0x1.0p-8h
+
+#elif __CLC_FPSIZE == 32
 
 #define MIN_VAL FLT_MIN
 #define MAX_SQRT 0x1.0p+86F

libclc/clc/lib/generic/geometric/clc_normalize.inc

@@ -6,7 +6,6 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include <clc/clcmacro.h>
 #include <clc/internal/clc.h>
 #include <clc/math/clc_exp.h>
 #include <clc/math/clc_fabs.h>
@@ -211,12 +210,6 @@ _CLC_OVERLOAD _CLC_DEF float __clc_erf(float x) {
   return ret;
 }
 
-#define __FLOAT_ONLY
-#define FUNCTION __clc_erf
-#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
-#include <clc/math/gentype.inc>
-#undef FUNCTION
-
 #ifdef cl_khr_fp64
 
 #pragma OPENCL EXTENSION cl_khr_fp64 : enable
@@ -500,24 +493,19 @@ _CLC_OVERLOAD _CLC_DEF double __clc_erf(double y) {
   return y < 0.0 ? -ret : ret;
 }
 
-#define __DOUBLE_ONLY
-#define FUNCTION __clc_erf
-#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
-#include <clc/math/gentype.inc>
-#undef FUNCTION
-
 #endif
 
 #ifdef cl_khr_fp16
 
-#include <clc/clc_convert.h>
-
 #pragma OPENCL EXTENSION cl_khr_fp16 : enable
 
 // Forward the half version of this builtin onto the float one
-#define __HALF_ONLY
-#define FUNCTION __clc_erf
-#define __CLC_BODY <clc/math/unary_def_via_fp32.inc>
-#include <clc/math/gentype.inc>
+_CLC_OVERLOAD _CLC_DEF half __clc_erf(half x) {
+  return (half)__clc_erf((float)x);
+}
 
 #endif
+
+#define FUNCTION __clc_erf
+#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
+#include <clc/math/gentype.inc>

libclc/clc/lib/generic/math/clc_erf.cl

@@ -6,7 +6,6 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include <clc/clcmacro.h>
 #include <clc/internal/clc.h>
 #include <clc/math/clc_exp.h>
 #include <clc/math/clc_fabs.h>
@@ -211,12 +210,6 @@ _CLC_OVERLOAD _CLC_DEF float __clc_erfc(float x) {
   return ret;
 }
 
-#define __FLOAT_ONLY
-#define FUNCTION __clc_erfc
-#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
-#include <clc/math/gentype.inc>
-#undef FUNCTION
-
 #ifdef cl_khr_fp64
 
 #pragma OPENCL EXTENSION cl_khr_fp64 : enable
@@ -509,12 +502,6 @@ _CLC_OVERLOAD _CLC_DEF double __clc_erfc(double x) {
   return ret;
 }
 
-#define __DOUBLE_ONLY
-#define FUNCTION __clc_erfc
-#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
-#include <clc/math/gentype.inc>
-#undef FUNCTION
-
 #endif
 
 #ifdef cl_khr_fp16
@@ -524,9 +511,12 @@ _CLC_OVERLOAD _CLC_DEF double __clc_erfc(double x) {
 #pragma OPENCL EXTENSION cl_khr_fp16 : enable
 
 // Forward the half version of this builtin onto the float one
-#define __HALF_ONLY
-#define FUNCTION __clc_erfc
-#define __CLC_BODY <clc/math/unary_def_via_fp32.inc>
-#include <clc/math/gentype.inc>
+_CLC_OVERLOAD _CLC_DEF half __clc_erfc(half x) {
+  return (half)__clc_erfc((float)x);
+}
 
 #endif
+
+#define FUNCTION __clc_erfc
+#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
+#include <clc/math/gentype.inc>

libclc/clc/lib/generic/math/clc_erfc.cl

@@ -6,7 +6,6 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include <clc/clcmacro.h>
 #include <clc/float/definitions.h>
 #include <clc/internal/clc.h>
 #include <clc/math/clc_exp.h>
@@ -32,12 +31,6 @@ _CLC_OVERLOAD _CLC_DEF float __clc_tgamma(float x) {
   return g;
 }
 
-#define __FLOAT_ONLY
-#define FUNCTION __clc_tgamma
-#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
-#include <clc/math/gentype.inc>
-#undef FUNCTION
-
 #ifdef cl_khr_fp64
 
 #pragma OPENCL EXTENSION cl_khr_fp64 : enable
@@ -59,24 +52,19 @@ _CLC_OVERLOAD _CLC_DEF double __clc_tgamma(double x) {
   return g;
 }
 
-#define __DOUBLE_ONLY
-#define FUNCTION __clc_tgamma
-#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
-#include <clc/math/gentype.inc>
-#undef FUNCTION
-
 #endif
 
 #ifdef cl_khr_fp16
 
-#include <clc/clc_convert.h>
-
 #pragma OPENCL EXTENSION cl_khr_fp16 : enable
 
 // Forward the half version of this builtin onto the float one
-#define __HALF_ONLY
-#define FUNCTION __clc_tgamma
-#define __CLC_BODY <clc/math/unary_def_via_fp32.inc>
-#include <clc/math/gentype.inc>
+_CLC_OVERLOAD _CLC_DEF half __clc_tgamma(half x) {
+  return (half)__clc_tgamma((float)x);
+}
 
 #endif
+
+#define FUNCTION __clc_tgamma
+#define __CLC_BODY <clc/shared/unary_def_scalarize.inc>
+#include <clc/math/gentype.inc>

libclc/clc/lib/generic/math/clc_tgamma.cl

@@ -15,6 +15,9 @@
 #ifndef LLVM_DEMANGLE_DEMANGLECONFIG_H
 #define LLVM_DEMANGLE_DEMANGLECONFIG_H
 
+// llvm-config.h is required for LLVM_ENABLE_LLVM_EXPORT_ANNOTATIONS
+#include "llvm/Config/llvm-config.h"
+
 #ifndef __has_feature
 #define __has_feature(x) 0
 #endif

llvm/include/llvm/Demangle/DemangleConfig.h

@@ -759,18 +759,18 @@ class MDString : public Metadata {
 /// memory access used by the alias-analysis infrastructure.
 struct AAMDNodes {
   explicit AAMDNodes() = default;
-  explicit AAMDNodes(MDNode *T, MDNode *TS, MDNode *S, MDNode *N)
-      : TBAA(T), TBAAStruct(TS), Scope(S), NoAlias(N) {}
+  explicit AAMDNodes(MDNode *T, MDNode *TS, MDNode *S, MDNode *N, MDNode *NAS)
+      : TBAA(T), TBAAStruct(TS), Scope(S), NoAlias(N), NoAliasAddrSpace(NAS) {}
 
   bool operator==(const AAMDNodes &A) const {
     return TBAA == A.TBAA && TBAAStruct == A.TBAAStruct && Scope == A.Scope &&
-           NoAlias == A.NoAlias;
+           NoAlias == A.NoAlias && NoAliasAddrSpace == A.NoAliasAddrSpace;
   }
 
   bool operator!=(const AAMDNodes &A) const { return !(*this == A); }
 
   explicit operator bool() const {
-    return TBAA || TBAAStruct || Scope || NoAlias;
+    return TBAA || TBAAStruct || Scope || NoAlias || NoAliasAddrSpace;
   }
 
   /// The tag for type-based alias analysis.
@@ -785,6 +785,9 @@ struct AAMDNodes {
   /// The tag specifying the noalias scope.
   MDNode *NoAlias = nullptr;
 
+  /// The tag specifying the noalias address spaces.
+  MDNode *NoAliasAddrSpace = nullptr;
+
   // Shift tbaa Metadata node to start off bytes later
   LLVM_ABI static MDNode *shiftTBAA(MDNode *M, size_t off);
 
@@ -806,6 +809,8 @@ struct AAMDNodes {
     Result.TBAAStruct = Other.TBAAStruct == TBAAStruct ? TBAAStruct : nullptr;
     Result.Scope = Other.Scope == Scope ? Scope : nullptr;
     Result.NoAlias = Other.NoAlias == NoAlias ? NoAlias : nullptr;
+    Result.NoAliasAddrSpace =
+        Other.NoAliasAddrSpace == NoAliasAddrSpace ? NoAliasAddrSpace : nullptr;
     return Result;
   }
 
@@ -818,6 +823,7 @@ struct AAMDNodes {
         TBAAStruct ? shiftTBAAStruct(TBAAStruct, Offset) : nullptr;
     Result.Scope = Scope;
     Result.NoAlias = NoAlias;
+    Result.NoAliasAddrSpace = NoAliasAddrSpace;
     return Result;
   }
 
@@ -833,6 +839,7 @@ struct AAMDNodes {
     Result.TBAAStruct = TBAAStruct;
     Result.Scope = Scope;
     Result.NoAlias = NoAlias;
+    Result.NoAliasAddrSpace = NoAliasAddrSpace;
     return Result;
   }
 
@@ -860,20 +867,21 @@ struct AAMDNodes {
 template<>
 struct DenseMapInfo<AAMDNodes> {
   static inline AAMDNodes getEmptyKey() {
-    return AAMDNodes(DenseMapInfo<MDNode *>::getEmptyKey(),
-                     nullptr, nullptr, nullptr);
+    return AAMDNodes(DenseMapInfo<MDNode *>::getEmptyKey(), nullptr, nullptr,
+                     nullptr, nullptr);
   }
 
   static inline AAMDNodes getTombstoneKey() {
-    return AAMDNodes(DenseMapInfo<MDNode *>::getTombstoneKey(),
+    return AAMDNodes(DenseMapInfo<MDNode *>::getTombstoneKey(), nullptr,
                      nullptr, nullptr, nullptr);
   }
 
   static unsigned getHashValue(const AAMDNodes &Val) {
     return DenseMapInfo<MDNode *>::getHashValue(Val.TBAA) ^
            DenseMapInfo<MDNode *>::getHashValue(Val.TBAAStruct) ^
            DenseMapInfo<MDNode *>::getHashValue(Val.Scope) ^
-           DenseMapInfo<MDNode *>::getHashValue(Val.NoAlias);
+           DenseMapInfo<MDNode *>::getHashValue(Val.NoAlias) ^
+           DenseMapInfo<MDNode *>::getHashValue(Val.NoAliasAddrSpace);
   }
 
   static bool isEqual(const AAMDNodes &LHS, const AAMDNodes &RHS) {

llvm/include/llvm/IR/Metadata.h

@@ -525,6 +525,8 @@ AAMDNodes AAMDNodes::merge(const AAMDNodes &Other) const {
   Result.TBAAStruct = nullptr;
   Result.Scope = MDNode::getMostGenericAliasScope(Scope, Other.Scope);
   Result.NoAlias = MDNode::intersect(NoAlias, Other.NoAlias);
+  Result.NoAliasAddrSpace = MDNode::getMostGenericNoaliasAddrspace(
+      NoAliasAddrSpace, Other.NoAliasAddrSpace);
   return Result;
 }
 
@@ -533,6 +535,8 @@ AAMDNodes AAMDNodes::concat(const AAMDNodes &Other) const {
   Result.TBAA = Result.TBAAStruct = nullptr;
   Result.Scope = MDNode::getMostGenericAliasScope(Scope, Other.Scope);
   Result.NoAlias = MDNode::intersect(NoAlias, Other.NoAlias);
+  Result.NoAliasAddrSpace = MDNode::getMostGenericNoaliasAddrspace(
+      NoAliasAddrSpace, Other.NoAliasAddrSpace);
   return Result;
 }