[X86] Add support for more than 32 features for __builtin_cpu_is

[craig.topper]

Summary

libgcc now supports more than 32 features by adding a new 32-bit variable __cpu_features2.

This adds the clang support for checking these feature bits.

Patches for compiler-rt and llvm to support this are coming as well.

Probably still need an additional patch for target multiversioning in clang.

[echristo]

Feel free to make any follow on changes you need here.

[craig.topper]

Rebase on top of D53460

lib/CodeGen/CGBuiltin.cpp

 }
 
 Value *CodeGenFunction::EmitX86CpuSupports(const CallExpr *E) {
   const Expr *FeatureExpr = E->getArg(0)->IgnoreParenCasts();
   StringRef FeatureStr = cast<StringLiteral>(FeatureExpr)->getString();
   return EmitX86CpuSupports(FeatureStr);
 }
 
-uint32_t
+uint64_t
 CodeGenFunction::GetX86CpuSupportsMask(ArrayRef<StringRef> FeatureStrs) {
   // Processor features and mapping to processor feature value.
-  uint32_t FeaturesMask = 0;
+  uint64_t FeaturesMask = 0;
   for (const StringRef &FeatureStr : FeatureStrs) {
     unsigned Feature =
         StringSwitch<unsigned>(FeatureStr)
 #define X86_FEATURE_COMPAT(VAL, ENUM, STR) .Case(STR, VAL)
 #include "llvm/Support/X86TargetParser.def"
         ;
-    FeaturesMask |= (1U << Feature);
+    FeaturesMask |= (1ULL << Feature);
   }
   return FeaturesMask;
 }
 
 Value *CodeGenFunction::EmitX86CpuSupports(ArrayRef<StringRef> FeatureStrs) {
   return EmitX86CpuSupports(GetX86CpuSupportsMask(FeatureStrs));
 }
 
-llvm::Value *CodeGenFunction::EmitX86CpuSupports(uint32_t FeaturesMask) {
+llvm::Value *CodeGenFunction::EmitX86CpuSupports(uint64_t FeaturesMask) {
+  uint32_t Features1 = Lo_32(FeaturesMask);
+  uint32_t Features2 = Hi_32(FeaturesMask);
+
+  Value *Result = Builder.getTrue();
+
+  if (Features1 != 0) {
     // Matching the struct layout from the compiler-rt/libgcc structure that is
     // filled in:
     // unsigned int __cpu_vendor;
     // unsigned int __cpu_type;
     // unsigned int __cpu_subtype;
     // unsigned int __cpu_features[1];
     llvm::Type *STy = llvm::StructType::get(Int32Ty, Int32Ty, Int32Ty,
                                             llvm::ArrayType::get(Int32Ty, 1));
 
     // Grab the global __cpu_model.
     llvm::Constant *CpuModel = CGM.CreateRuntimeVariable(STy, "__cpu_model");
 
     // Grab the first (0th) element from the field __cpu_features off of the
     // global in the struct STy.
-  Value *Idxs[] = {ConstantInt::get(Int32Ty, 0), ConstantInt::get(Int32Ty, 3),
-                   ConstantInt::get(Int32Ty, 0)};
+    Value *Idxs[] = {Builder.getInt32(0), Builder.getInt32(3),
+                     Builder.getInt32(0)};
     Value *CpuFeatures = Builder.CreateGEP(STy, CpuModel, Idxs);
     Value *Features =
         Builder.CreateAlignedLoad(CpuFeatures, CharUnits::fromQuantity(4));
 
     // Check the value of the bit corresponding to the feature requested.
     Value *Bitset = Builder.CreateAnd(
-      Features, llvm::ConstantInt::get(Int32Ty, FeaturesMask));
-  return Builder.CreateICmpNE(Bitset, llvm::ConstantInt::get(Int32Ty, 0));
+        Features, llvm::ConstantInt::get(Int32Ty, Features1));
+    Value *Cmp = Builder.CreateICmpNE(Bitset, Builder.getInt32(0));
+    Result = Builder.CreateAnd(Result, Cmp);
+  }
+
+  if (Features2 != 0) {
+    llvm::Constant *CpuFeatures2 = CGM.CreateRuntimeVariable(Int32Ty,
+                                                             "__cpu_features2");
+    Value *Features =
+        Builder.CreateAlignedLoad(CpuFeatures2, CharUnits::fromQuantity(4));
+
+    // Check the value of the bit corresponding to the feature requested.
+    Value *Bitset = Builder.CreateAnd(
+        Features, llvm::ConstantInt::get(Int32Ty, Features2));
+    Value *Cmp = Builder.CreateICmpNE(Bitset, Builder.getInt32(0));
+    Result = Builder.CreateAnd(Result, Cmp);
+  }
+
+  return Result;
 }
 
 Value *CodeGenFunction::EmitX86CpuInit() {
   llvm::FunctionType *FTy = llvm::FunctionType::get(VoidTy,
                                                     /*Variadic*/ false);
   llvm::Constant *Func = CGM.CreateRuntimeFunction(FTy, "__cpu_indicator_init");
   return Builder.CreateCall(Func);
 }

lib/CodeGen/CodeGenFunction.h

CPUDispatchMultiVersionResolverOption(llvm::Function *F, uint64_t Mask)
         : Function(F), FeatureMask(static_cast<uint32_t>(Mask)) {}
     bool operator>(const CPUDispatchMultiVersionResolverOption &Other) const {
       return FeatureMask > Other.FeatureMask;
     }
   };
   void EmitCPUDispatchMultiVersionResolver(
       llvm::Function *Resolver,
       ArrayRef<CPUDispatchMultiVersionResolverOption> Options);
-  static uint32_t GetX86CpuSupportsMask(ArrayRef<StringRef> FeatureStrs);
+  static uint64_t GetX86CpuSupportsMask(ArrayRef<StringRef> FeatureStrs);
 
 private:
   QualType getVarArgType(const Expr *Arg);
 
   void EmitDeclMetadata();
 
   BlockByrefHelpers *buildByrefHelpers(llvm::StructType &byrefType,
                                   const AutoVarEmission &emission);
 
   void AddObjCARCExceptionMetadata(llvm::Instruction *Inst);
 
   llvm::Value *GetValueForARMHint(unsigned BuiltinID);
   llvm::Value *EmitX86CpuIs(const CallExpr *E);
   llvm::Value *EmitX86CpuIs(StringRef CPUStr);
   llvm::Value *EmitX86CpuSupports(const CallExpr *E);
   llvm::Value *EmitX86CpuSupports(ArrayRef<StringRef> FeatureStrs);
-  llvm::Value *EmitX86CpuSupports(uint32_t Mask);
+  llvm::Value *EmitX86CpuSupports(uint64_t Mask);
   llvm::Value *EmitX86CpuInit();
   llvm::Value *FormResolverCondition(const MultiVersionResolverOption &RO);
 };
 
 inline DominatingLLVMValue::saved_type
 DominatingLLVMValue::save(CodeGenFunction &CGF, llvm::Value *value) {
   if (!needsSaving(value)) return saved_type(value, false);
 

test/CodeGen/builtin-cpu-supports.c

int main() {
 
   if (__builtin_cpu_supports("sse4.2"))
     a("sse4.2");
 
   // CHECK: [[LOAD:%[^ ]+]] = load i32, i32* getelementptr inbounds ({ i32, i32, i32, [1 x i32] }, { i32, i32, i32, [1 x i32] }* @__cpu_model, i32 0, i32 3, i32 0)
   // CHECK: [[AND:%[^ ]+]] = and i32 [[LOAD]], 256
   // CHECK: = icmp ne i32 [[AND]], 0
 
+  if (__builtin_cpu_supports("gfni"))
+    a("gfni");
+
+  // CHECK: [[LOAD:%[^ ]+]] = load i32, i32* @__cpu_features2
+  // CHECK: [[AND:%[^ ]+]] = and i32 [[LOAD]], 1
+  // CHECK: = icmp ne i32 [[AND]], 0
+
   return 0;
 }

test/CodeGen/target-builtin-noerror.c

void verifyfeaturestrings() {
   (void)__builtin_cpu_supports("avx512cd");
   (void)__builtin_cpu_supports("avx512er");
   (void)__builtin_cpu_supports("avx512pf");
   (void)__builtin_cpu_supports("avx512vbmi");
   (void)__builtin_cpu_supports("avx512ifma");
   (void)__builtin_cpu_supports("avx5124vnniw");
   (void)__builtin_cpu_supports("avx5124fmaps");
   (void)__builtin_cpu_supports("avx512vpopcntdq");
+  (void)__builtin_cpu_supports("avx512vbmi2");
+  (void)__builtin_cpu_supports("gfni");
+  (void)__builtin_cpu_supports("vpclmulqdq");
+  (void)__builtin_cpu_supports("avx512vnni");
+  (void)__builtin_cpu_supports("avx512bitalg");
 }
 
 void verifycpustrings() {
   (void)__builtin_cpu_is("amd");
   (void)__builtin_cpu_is("amdfam10h");
   (void)__builtin_cpu_is("amdfam15h");
   (void)__builtin_cpu_is("amdfam17h");
   (void)__builtin_cpu_is("atom");
   (void)__builtin_cpu_is("barcelona");
   (void)__builtin_cpu_is("bdver1");
   (void)__builtin_cpu_is("bdver2");
   (void)__builtin_cpu_is("bdver3");
   (void)__builtin_cpu_is("bdver4");
   (void)__builtin_cpu_is("bonnell");
   (void)__builtin_cpu_is("broadwell");
   (void)__builtin_cpu_is("btver1");
   (void)__builtin_cpu_is("btver2");
   (void)__builtin_cpu_is("cannonlake");
   (void)__builtin_cpu_is("core2");
   (void)__builtin_cpu_is("corei7");
+  (void)__builtin_cpu_is("goldmont");
+  (void)__builtin_cpu_is("goldmont-plus");
   (void)__builtin_cpu_is("haswell");
+  (void)__builtin_cpu_is("icelake-client");
+  (void)__builtin_cpu_is("icelake-server");
   (void)__builtin_cpu_is("intel");
   (void)__builtin_cpu_is("istanbul");
   (void)__builtin_cpu_is("ivybridge");
   (void)__builtin_cpu_is("knl");
   (void)__builtin_cpu_is("knm");
   (void)__builtin_cpu_is("nehalem");
   (void)__builtin_cpu_is("sandybridge");
   (void)__builtin_cpu_is("shanghai");
   (void)__builtin_cpu_is("silvermont");
   (void)__builtin_cpu_is("skylake");
   (void)__builtin_cpu_is("skylake-avx512");
   (void)__builtin_cpu_is("slm");
+  (void)__builtin_cpu_is("tremont");
   (void)__builtin_cpu_is("westmere");
   (void)__builtin_cpu_is("znver1");
 }