Merge branch 'main' into drop-cmp0116-old

Author: boomanaiden154

clang-tools-extra/clang-tidy/readability/ImplicitBoolConversionCheck.cpp

@@ -10,6 +10,7 @@
 #include "../utils/FixItHintUtils.h"
 #include "clang/AST/ASTContext.h"
 #include "clang/ASTMatchers/ASTMatchFinder.h"
+#include "clang/ASTMatchers/ASTMatchers.h"
 #include "clang/Lex/Lexer.h"
 #include "clang/Tooling/FixIt.h"
 #include <queue>
@@ -26,6 +27,8 @@ AST_MATCHER(Stmt, isMacroExpansion) {
   return SM.isMacroBodyExpansion(Loc) || SM.isMacroArgExpansion(Loc);
 }
 
+AST_MATCHER(Stmt, isC23) { return Finder->getASTContext().getLangOpts().C23; }
+
 bool isNULLMacroExpansion(const Stmt *Statement, ASTContext &Context) {
   SourceManager &SM = Context.getSourceManager();
   const LangOptions &LO = Context.getLangOpts();
@@ -298,6 +301,11 @@ void ImplicitBoolConversionCheck::registerMatchers(MatchFinder *Finder) {
                          hasCastKind(CK_FloatingToBoolean),
                          hasCastKind(CK_PointerToBoolean),
                          hasCastKind(CK_MemberPointerToBoolean)),
+                   // Exclude cases of C23 comparison result.
+                   unless(allOf(isC23(),
+                                hasSourceExpression(ignoringParens(
+                                    binaryOperator(hasAnyOperatorName(
+                                        ">", ">=", "==", "!=", "<", "<=")))))),
                    // Exclude case of using if or while statements with variable
                    // declaration, e.g.:
                    //   if (int var = functionCall()) {}

clang-tools-extra/docs/ReleaseNotes.rst

@@ -249,7 +249,8 @@ Changes in existing checks
 - Improved :doc:`readability-implicit-bool-conversion
   <clang-tidy/checks/readability/implicit-bool-conversion>` check
   by adding the option `UseUpperCaseLiteralSuffix` to select the
-  case of the literal suffix in fixes.
+  case of the literal suffix in fixes and fixing false positive for implicit
+  conversion of comparison result in C23.
 
 - Improved :doc:`readability-redundant-smartptr-get
   <clang-tidy/checks/readability/redundant-smartptr-get>` check to

clang-tools-extra/test/clang-tidy/checkers/readability/implicit-bool-conversion.c

@@ -304,6 +304,15 @@ void implicitConversionToBoolFromUnaryMinusAndZeroLiterals() {
   // CHECK-FIXES: functionTakingBool((-0.0) != 0.0);
 }
 
+void ignoreImplicitCastToBoolForComparisonResult() {
+  bool boolFromComparison0 = 1 != 0;
+  bool boolFromComparison1 = 1 == 0;
+  bool boolFromComparison2 = 1 > 0;
+  bool boolFromComparison3 = 1 >= 0;
+  bool boolFromComparison4 = 1 < 0;
+  bool boolFromComparison5 = 1 <= 0;
+}
+
 void ignoreExplicitCastsToBool() {
   int integer = 10;
   bool boolComingFromInt = (bool)integer;

clang/docs/ReleaseNotes.rst

@@ -628,6 +628,10 @@ X86 Support
   * Supported MINMAX intrinsics of ``*_(mask(z)))_minmax(ne)_p[s|d|h|bh]`` and
   ``*_(mask(z)))_minmax_s[s|d|h]``.
 
+- Supported intrinsics for ``SM4 and AVX10.2``.
+  * Supported SM4 intrinsics of ``_mm512_sm4key4_epi32`` and
+  ``_mm512_sm4rnds4_epi32``.
+
 - All intrinsics in adcintrin.h can now be used in constant expressions.
 
 - All intrinsics in adxintrin.h can now be used in constant expressions.

clang/include/clang/Basic/BuiltinsX86.def

@@ -2179,6 +2179,10 @@ TARGET_BUILTIN(__builtin_ia32_vsm4key4256, "V8UiV8UiV8Ui", "nV:256:", "sm4")
 TARGET_BUILTIN(__builtin_ia32_vsm4rnds4128, "V4UiV4UiV4Ui", "nV:128:", "sm4")
 TARGET_BUILTIN(__builtin_ia32_vsm4rnds4256, "V8UiV8UiV8Ui", "nV:256:", "sm4")
 
+// SM4_EVEX
+TARGET_BUILTIN(__builtin_ia32_vsm4key4512, "V16UiV16UiV16Ui", "nV:512:", "avx10.2-512,sm4")
+TARGET_BUILTIN(__builtin_ia32_vsm4rnds4512, "V16UiV16UiV16Ui", "nV:512:", "avx10.2-512,sm4")
+
 // AVX10 MINMAX
 TARGET_BUILTIN(__builtin_ia32_vminmaxnepbf16128, "V8yV8yV8yIi", "nV:128:", "avx10.2-256")
 TARGET_BUILTIN(__builtin_ia32_vminmaxnepbf16256, "V16yV16yV16yIi", "nV:256:", "avx10.2-256")

clang/include/clang/Sema/SemaInternal.h

@@ -58,7 +58,7 @@ inline InheritableAttr *getDLLAttr(Decl *D) {
 }
 
 /// Retrieve the depth and index of a template parameter.
-inline std::pair<unsigned, unsigned> getDepthAndIndex(NamedDecl *ND) {
+inline std::pair<unsigned, unsigned> getDepthAndIndex(const NamedDecl *ND) {
   if (const auto *TTP = dyn_cast<TemplateTypeParmDecl>(ND))
     return std::make_pair(TTP->getDepth(), TTP->getIndex());
 

clang/lib/CodeGen/CGBuiltin.cpp

@@ -20492,8 +20492,8 @@ static NVPTXMmaInfo getNVPTXMmaInfo(unsigned BuiltinID) {
 #undef MMA_VARIANTS_B1_XOR
 }
 
-static Value *MakeLdgLdu(unsigned IntrinsicID, CodeGenFunction &CGF,
-                         const CallExpr *E) {
+static Value *MakeLdu(unsigned IntrinsicID, CodeGenFunction &CGF,
+                      const CallExpr *E) {
   Value *Ptr = CGF.EmitScalarExpr(E->getArg(0));
   QualType ArgType = E->getArg(0)->getType();
   clang::CharUnits Align = CGF.CGM.getNaturalPointeeTypeAlignment(ArgType);
@@ -20503,6 +20503,21 @@ static Value *MakeLdgLdu(unsigned IntrinsicID, CodeGenFunction &CGF,
       {Ptr, ConstantInt::get(CGF.Builder.getInt32Ty(), Align.getQuantity())});
 }
 
+static Value *MakeLdg(CodeGenFunction &CGF, const CallExpr *E) {
+  Value *Ptr = CGF.EmitScalarExpr(E->getArg(0));
+  QualType ArgType = E->getArg(0)->getType();
+  clang::CharUnits AlignV = CGF.CGM.getNaturalPointeeTypeAlignment(ArgType);
+  llvm::Type *ElemTy = CGF.ConvertTypeForMem(ArgType->getPointeeType());
+
+  // Use addrspace(1) for NVPTX ADDRESS_SPACE_GLOBAL
+  auto *ASC = CGF.Builder.CreateAddrSpaceCast(Ptr, CGF.Builder.getPtrTy(1));
+  auto *LD = CGF.Builder.CreateAlignedLoad(ElemTy, ASC, AlignV.getAsAlign());
+  MDNode *MD = MDNode::get(CGF.Builder.getContext(), {});
+  LD->setMetadata(LLVMContext::MD_invariant_load, MD);
+
+  return LD;
+}
+
 static Value *MakeScopedAtomic(unsigned IntrinsicID, CodeGenFunction &CGF,
                                const CallExpr *E) {
   Value *Ptr = CGF.EmitScalarExpr(E->getArg(0));
@@ -20536,9 +20551,11 @@ static Value *MakeHalfType(unsigned IntrinsicID, unsigned BuiltinID,
     return nullptr;
   }
 
-  if (IntrinsicID == Intrinsic::nvvm_ldg_global_f ||
-      IntrinsicID == Intrinsic::nvvm_ldu_global_f)
-    return MakeLdgLdu(IntrinsicID, CGF, E);
+  if (BuiltinID == NVPTX::BI__nvvm_ldg_h || BuiltinID == NVPTX::BI__nvvm_ldg_h2)
+    return MakeLdg(CGF, E);
+
+  if (IntrinsicID == Intrinsic::nvvm_ldu_global_f)
+    return MakeLdu(IntrinsicID, CGF, E);
 
   SmallVector<Value *, 16> Args;
   auto *F = CGF.CGM.getIntrinsic(IntrinsicID);
@@ -20675,16 +20692,15 @@ Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
   case NVPTX::BI__nvvm_ldg_ul2:
   case NVPTX::BI__nvvm_ldg_ull:
   case NVPTX::BI__nvvm_ldg_ull2:
-    // PTX Interoperability section 2.2: "For a vector with an even number of
-    // elements, its alignment is set to number of elements times the alignment
-    // of its member: n*alignof(t)."
-    return MakeLdgLdu(Intrinsic::nvvm_ldg_global_i, *this, E);
   case NVPTX::BI__nvvm_ldg_f:
   case NVPTX::BI__nvvm_ldg_f2:
   case NVPTX::BI__nvvm_ldg_f4:
   case NVPTX::BI__nvvm_ldg_d:
   case NVPTX::BI__nvvm_ldg_d2:
-    return MakeLdgLdu(Intrinsic::nvvm_ldg_global_f, *this, E);
+    // PTX Interoperability section 2.2: "For a vector with an even number of
+    // elements, its alignment is set to number of elements times the alignment
+    // of its member: n*alignof(t)."
+    return MakeLdg(*this, E);
 
   case NVPTX::BI__nvvm_ldu_c:
   case NVPTX::BI__nvvm_ldu_sc:
@@ -20715,13 +20731,13 @@ Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
   case NVPTX::BI__nvvm_ldu_ul2:
   case NVPTX::BI__nvvm_ldu_ull:
   case NVPTX::BI__nvvm_ldu_ull2:
-    return MakeLdgLdu(Intrinsic::nvvm_ldu_global_i, *this, E);
+    return MakeLdu(Intrinsic::nvvm_ldu_global_i, *this, E);
   case NVPTX::BI__nvvm_ldu_f:
   case NVPTX::BI__nvvm_ldu_f2:
   case NVPTX::BI__nvvm_ldu_f4:
   case NVPTX::BI__nvvm_ldu_d:
   case NVPTX::BI__nvvm_ldu_d2:
-    return MakeLdgLdu(Intrinsic::nvvm_ldu_global_f, *this, E);
+    return MakeLdu(Intrinsic::nvvm_ldu_global_f, *this, E);
 
   case NVPTX::BI__nvvm_atom_cta_add_gen_i:
   case NVPTX::BI__nvvm_atom_cta_add_gen_l:
@@ -21195,14 +21211,11 @@ Value *CodeGenFunction::EmitNVPTXBuiltinExpr(unsigned BuiltinID,
     return MakeHalfType(Intrinsic::nvvm_fmin_xorsign_abs_f16x2, BuiltinID, E,
                         *this);
   case NVPTX::BI__nvvm_ldg_h:
-    return MakeHalfType(Intrinsic::nvvm_ldg_global_f, BuiltinID, E, *this);
   case NVPTX::BI__nvvm_ldg_h2:
-    return MakeHalfType(Intrinsic::nvvm_ldg_global_f, BuiltinID, E, *this);
+    return MakeHalfType(Intrinsic::not_intrinsic, BuiltinID, E, *this);
   case NVPTX::BI__nvvm_ldu_h:
+  case NVPTX::BI__nvvm_ldu_h2:
     return MakeHalfType(Intrinsic::nvvm_ldu_global_f, BuiltinID, E, *this);
-  case NVPTX::BI__nvvm_ldu_h2: {
-    return MakeHalfType(Intrinsic::nvvm_ldu_global_f, BuiltinID, E, *this);
-  }
   case NVPTX::BI__nvvm_cp_async_ca_shared_global_4:
     return MakeCpAsync(Intrinsic::nvvm_cp_async_ca_shared_global_4,
                        Intrinsic::nvvm_cp_async_ca_shared_global_4_s, *this, E,

clang/lib/Headers/CMakeLists.txt

@@ -243,6 +243,7 @@ set(x86_files
   shaintrin.h
   sm3intrin.h
   sm4intrin.h
+  sm4evexintrin.h
   smmintrin.h
   tbmintrin.h
   tmmintrin.h

clang/lib/Headers/immintrin.h

@@ -677,6 +677,11 @@ _storebe_i64(void * __P, long long __D) {
 #include <avx10_2_512satcvtintrin.h>
 #endif
 
+#if !defined(__SCE__) || __has_feature(modules) ||                             \
+    (defined(__AVX10_2_512__) && defined(__SM4__))
+#include <sm4evexintrin.h>
+#endif
+
 #if !defined(__SCE__) || __has_feature(modules) || defined(__ENQCMD__)
 #include <enqcmdintrin.h>
 #endif

clang/lib/Headers/sm4evexintrin.h

@@ -0,0 +1,32 @@
+/*===--------------- sm4evexintrin.h - SM4 EVEX intrinsics -----------------===
+ *
+ * Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+ * See https://llvm.org/LICENSE.txt for license information.
+ * SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+ *
+ *===----------------------------------------------------------------------===
+ */
+#ifndef __IMMINTRIN_H
+#error "Never use <sm4evexintrin.h> directly; include <immintrin.h> instead."
+#endif // __IMMINTRIN_H
+
+#ifndef __SM4EVEXINTRIN_H
+#define __SM4EVEXINTRIN_H
+
+#define __DEFAULT_FN_ATTRS512                                                  \
+  __attribute__((__always_inline__, __nodebug__,                               \
+                 __target__("sm4,avx10.2-512"), __min_vector_width__(512)))
+
+static __inline__ __m512i __DEFAULT_FN_ATTRS512
+_mm512_sm4key4_epi32(__m512i __A, __m512i __B) {
+  return (__m512i)__builtin_ia32_vsm4key4512((__v16su)__A, (__v16su)__B);
+}
+
+static __inline__ __m512i __DEFAULT_FN_ATTRS512
+_mm512_sm4rnds4_epi32(__m512i __A, __m512i __B) {
+  return (__m512i)__builtin_ia32_vsm4rnds4512((__v16su)__A, (__v16su)__B);
+}
+
+#undef __DEFAULT_FN_ATTRS512
+
+#endif // __SM4EVEXINTRIN_H