Merged main:73e0aa58666f235bef091735a5f189882acc1148 into amd-gfx:e64f6fcf29c6

Local branch amd-gfx e64f6fc Merged main:fee48365b44d161575314c67328fa21104c4537d into amd-gfx:0447d312fac8
Remote branch main 73e0aa5 [CodeGen] Create IFUNCs in the program address space, not hard-coded 0 (llvm#105726)

Author: SC llvm team

clang/lib/CodeGen/CodeGenModule.cpp

@@ -4455,12 +4455,13 @@ void CodeGenModule::emitCPUDispatchDefinition(GlobalDecl GD) {
   if (getTarget().supportsIFunc()) {
     llvm::GlobalValue::LinkageTypes Linkage = getMultiversionLinkage(*this, GD);
     auto *IFunc = cast<llvm::GlobalValue>(GetOrCreateMultiVersionResolver(GD));
+    unsigned AS = IFunc->getType()->getPointerAddressSpace();
 
     // Fix up function declarations that were created for cpu_specific before
     // cpu_dispatch was known
     if (!isa<llvm::GlobalIFunc>(IFunc)) {
-      auto *GI = llvm::GlobalIFunc::create(DeclTy, 0, Linkage, "", ResolverFunc,
-                                           &getModule());
+      auto *GI = llvm::GlobalIFunc::create(DeclTy, AS, Linkage, "",
+                                           ResolverFunc, &getModule());
       replaceDeclarationWith(IFunc, GI);
       IFunc = GI;
     }
@@ -4469,8 +4470,8 @@ void CodeGenModule::emitCPUDispatchDefinition(GlobalDecl GD) {
         *this, GD, FD, /*OmitMultiVersionMangling=*/true);
     llvm::Constant *AliasFunc = GetGlobalValue(AliasName);
     if (!AliasFunc) {
-      auto *GA = llvm::GlobalAlias::create(DeclTy, 0, Linkage, AliasName, IFunc,
-                                           &getModule());
+      auto *GA = llvm::GlobalAlias::create(DeclTy, AS, Linkage, AliasName,
+                                           IFunc, &getModule());
       SetCommonAttributes(GD, GA);
     }
   }
@@ -4542,15 +4543,14 @@ llvm::Constant *CodeGenModule::GetOrCreateMultiVersionResolver(GlobalDecl GD) {
   // For cpu_specific, don't create an ifunc yet because we don't know if the
   // cpu_dispatch will be emitted in this translation unit.
   if (getTarget().supportsIFunc() && !FD->isCPUSpecificMultiVersion()) {
-    llvm::Type *ResolverType = llvm::FunctionType::get(
-        llvm::PointerType::get(DeclTy,
-                               getTypes().getTargetAddressSpace(FD->getType())),
-        false);
+    unsigned AS = getTypes().getTargetAddressSpace(FD->getType());
+    llvm::Type *ResolverType =
+        llvm::FunctionType::get(llvm::PointerType::get(DeclTy, AS), false);
     llvm::Constant *Resolver = GetOrCreateLLVMFunction(
         MangledName + ".resolver", ResolverType, GlobalDecl{},
         /*ForVTable=*/false);
     llvm::GlobalIFunc *GIF =
-        llvm::GlobalIFunc::create(DeclTy, 0, getMultiversionLinkage(*this, GD),
+        llvm::GlobalIFunc::create(DeclTy, AS, getMultiversionLinkage(*this, GD),
                                   "", Resolver, &getModule());
     GIF->setName(ResolverName);
     SetCommonAttributes(FD, GIF);
@@ -6160,9 +6160,9 @@ void CodeGenModule::emitIFuncDefinition(GlobalDecl GD) {
       GetOrCreateLLVMFunction(IFA->getResolver(), VoidTy, {},
                               /*ForVTable=*/false);
   llvm::Type *DeclTy = getTypes().ConvertTypeForMem(D->getType());
-  llvm::GlobalIFunc *GIF =
-      llvm::GlobalIFunc::create(DeclTy, 0, llvm::Function::ExternalLinkage,
-                                "", Resolver, &getModule());
+  unsigned AS = getTypes().getTargetAddressSpace(D->getType());
+  llvm::GlobalIFunc *GIF = llvm::GlobalIFunc::create(
+      DeclTy, AS, llvm::Function::ExternalLinkage, "", Resolver, &getModule());
   if (Entry) {
     if (GIF->getResolver() == Entry) {
       Diags.Report(IFA->getLocation(), diag::err_cyclic_alias) << 1;

clang/test/CodeGen/ifunc.c

@@ -11,6 +11,7 @@
 // RUN: %clang_cc1 -triple x86_64-apple-macosx -fsanitize=thread -O2 -emit-llvm -o - %s | FileCheck %s --check-prefix=SAN
 // RUN: %clang_cc1 -triple arm64-apple-macosx -fsanitize=address -O2 -emit-llvm -o - %s | FileCheck %s --check-prefix=SAN
 // RUN: %clang_cc1 -triple x86_64-apple-macosx -fsanitize=address -O2 -emit-llvm -o - %s | FileCheck %s --check-prefix=SAN
+// RUN: %clang_cc1 -triple avr-unknown-unknown -emit-llvm -o - %s | FileCheck %s --check-prefix=AVR
 
 /// The ifunc is emitted before its resolver.
 int foo(int) __attribute__ ((ifunc("foo_ifunc")));
@@ -55,6 +56,10 @@ extern void hoo(int) __attribute__ ((ifunc("hoo_ifunc")));
 // CHECK: @goo = ifunc void (), ptr @goo_ifunc
 // CHECK: @hoo = ifunc void (i32), ptr @hoo_ifunc
 
+// AVR: @foo = ifunc i16 (i16), ptr addrspace(1) @foo_ifunc
+// AVR: @goo = ifunc void (), ptr addrspace(1) @goo_ifunc
+// AVR: @hoo = ifunc void (i16), ptr addrspace(1) @hoo_ifunc
+
 // CHECK: call i32 @foo(i32
 // CHECK: call void @goo()
 

flang/include/flang/Tools/TargetSetup.h

@@ -11,6 +11,7 @@
 
 #include "flang/Evaluate/target.h"
 #include "llvm/Target/TargetMachine.h"
+#include <cfloat>
 
 namespace Fortran::tools {
 
@@ -21,9 +22,25 @@ namespace Fortran::tools {
 
   const llvm::Triple &targetTriple{targetMachine.getTargetTriple()};
   // FIXME: Handle real(3) ?
-  if (targetTriple.getArch() != llvm::Triple::ArchType::x86_64)
+  if (targetTriple.getArch() != llvm::Triple::ArchType::x86_64) {
     targetCharacteristics.DisableType(
         Fortran::common::TypeCategory::Real, /*kind=*/10);
+  }
+
+  // Figure out if we can support F128: see
+  // flang/runtime/Float128Math/math-entries.h
+#ifdef FLANG_RUNTIME_F128_MATH_LIB
+  // we can use libquadmath wrappers
+  constexpr bool f128Support = true;
+#elif LDBL_MANT_DIG == 113
+  // we can use libm wrappers
+  constexpr bool f128Support = true;
+#else
+  constexpr bool f128Support = false;
+#endif
+
+  if constexpr (!f128Support)
+    targetCharacteristics.DisableType(Fortran::common::TypeCategory::Real, 16);
 
   targetCharacteristics.set_compilerOptionsString(compilerOptions)
       .set_compilerVersionString(compilerVersion);

flang/module/ieee_arithmetic.f90

@@ -161,19 +161,33 @@ end function ieee_round_ne
   G(1) G(2) G(4) G(8) G(16)
 #define SPECIFICS_L(G) \
   G(1) G(2) G(4) G(8)
+
+#if FLANG_SUPPORT_R16
 #if __x86_64__
 #define SPECIFICS_R(G) \
   G(2) G(3) G(4) G(8) G(10) G(16)
 #else
 #define SPECIFICS_R(G) \
   G(2) G(3) G(4) G(8) G(16)
 #endif
+#else
+#if __x86_64__
+#define SPECIFICS_R(G) \
+  G(2) G(3) G(4) G(8) G(10)
+#else
+#define SPECIFICS_R(G) \
+  G(2) G(3) G(4) G(8)
+#endif
+#endif
+
 #define SPECIFICS_II(G) \
   G(1,1) G(1,2) G(1,4) G(1,8) G(1,16) \
   G(2,1) G(2,2) G(2,4) G(2,8) G(2,16) \
   G(4,1) G(4,2) G(4,4) G(4,8) G(4,16) \
   G(8,1) G(8,2) G(8,4) G(8,8) G(8,16) \
   G(16,1) G(16,2) G(16,4) G(16,8) G(16,16)
+
+#if FLANG_SUPPORT_R16
 #if __x86_64__
 #define SPECIFICS_RI(G) \
   G(2,1) G(2,2) G(2,4) G(2,8) G(2,16) \
@@ -190,7 +204,24 @@ end function ieee_round_ne
   G(8,1) G(8,2) G(8,4) G(8,8) G(8,16) \
   G(16,1) G(16,2) G(16,4) G(16,8) G(16,16)
 #endif
+#else
+#if __x86_64__
+#define SPECIFICS_RI(G) \
+  G(2,1) G(2,2) G(2,4) G(2,8) \
+  G(3,1) G(3,2) G(3,4) G(3,8) \
+  G(4,1) G(4,2) G(4,4) G(4,8) \
+  G(8,1) G(8,2) G(8,4) G(8,8) \
+  G(10,1) G(10,2) G(10,4) G(10,8)
+#else
+#define SPECIFICS_RI(G) \
+  G(2,1) G(2,2) G(2,4) G(2,8) \
+  G(3,1) G(3,2) G(3,4) G(3,8) \
+  G(4,1) G(4,2) G(4,4) G(4,8) \
+  G(8,1) G(8,2) G(8,4) G(8,8)
+#endif
+#endif
 
+#if FLANG_SUPPORT_R16
 #if __x86_64__
 #define SPECIFICS_RR(G) \
   G(2,2) G(2,3) G(2,4) G(2,8) G(2,10) G(2,16) \
@@ -207,6 +238,22 @@ end function ieee_round_ne
   G(8,2) G(8,3) G(8,4) G(8,8) G(8,16) \
   G(16,2) G(16,3) G(16,4) G(16,8) G(16,16)
 #endif
+#else
+#if __x86_64__
+#define SPECIFICS_RR(G) \
+  G(2,2) G(2,3) G(2,4) G(2,8) G(2,10) \
+  G(3,2) G(3,3) G(3,4) G(3,8) G(3,10) \
+  G(4,2) G(4,3) G(4,4) G(4,8) G(4,10) \
+  G(8,2) G(8,3) G(8,4) G(8,8) G(8,10) \
+  G(10,2) G(10,3) G(10,4) G(10,8) G(10,10)
+#else
+#define SPECIFICS_RR(G) \
+  G(2,2) G(2,3) G(2,4) G(2,8) \
+  G(3,2) G(3,3) G(3,4) G(3,8) \
+  G(4,2) G(4,3) G(4,4) G(4,8) \
+  G(8,2) G(8,3) G(8,4) G(8,8)
+#endif
+#endif
 
 #define IEEE_CLASS_R(XKIND) \
   elemental type(ieee_class_type) function ieee_class_a##XKIND(x); \
@@ -462,8 +509,10 @@ end function ieee_real_a##AKIND##_i##KKIND;
   interface ieee_real
     SPECIFICS_I(IEEE_REAL_I)
     SPECIFICS_R(IEEE_REAL_R)
+#if FLANG_SUPPORT_R16
     SPECIFICS_II(IEEE_REAL_II)
     SPECIFICS_RI(IEEE_REAL_RI)
+#endif
   end interface ieee_real
   public :: ieee_real
 #undef IEEE_REAL_I

flang/test/CMakeLists.txt

@@ -11,6 +11,16 @@ llvm_canonicalize_cmake_booleans(
 
 set(FLANG_TOOLS_DIR ${FLANG_BINARY_DIR}/bin)
 
+# Check if 128-bit float computations can be done via long double
+check_cxx_source_compiles(
+  "#include <cfloat>
+   #if LDBL_MANT_DIG != 113
+   #error LDBL_MANT_DIG != 113
+   #endif
+   int main() { return 0; }
+  "
+  HAVE_LDBL_MANT_DIG_113)
+
 # FIXME In out-of-tree builds, "SHLIBDIR" is undefined and passing it to
 # `configure_lit_site_cfg` leads to a configuration error. This is currently
 # only required by plugins/examples, which are not supported in out-of-tree

flang/test/Evaluate/fold-out_of_range.f90

@@ -1,6 +1,7 @@
 ! RUN: %python %S/test_folding.py %s %flang_fc1 -pedantic -triple x86_64-unknown-linux-gnu
 ! UNSUPPORTED: system-windows
 ! REQUIRES: target=x86_64{{.*}}
+! REQUIRES: flang-supports-f128-math
 ! Tests folding of OUT_OF_RANGE().
 module m
   integer(1),  parameter :: i1v(*)  = [ -huge(1_1)  - 1_1,  huge(1_1) ]

flang/test/Evaluate/folding07.f90

@@ -1,3 +1,4 @@
+! REQUIRES: flang-supports-f128-math
 ! RUN: %python %S/test_folding.py %s %flang_fc1
 ! Test numeric model inquiry intrinsics
 

flang/test/Lower/Intrinsics/ieee_class_queries.f90

@@ -1,3 +1,4 @@
+! REQUIRES: flang-supports-f128-math
 ! RUN: bbc -emit-fir -o - %s | FileCheck %s
 
   ! CHECK-LABEL: func @_QQmain

flang/test/Lower/Intrinsics/ieee_unordered.f90

@@ -1,3 +1,4 @@
+! REQUIRES: flang-supports-f128-math
 ! RUN: bbc -emit-fir -hlfir=false -o - %s | FileCheck %s
 
 ! CHECK-LABEL: func @_QQmain

flang/test/Lower/common-block.f90

@@ -1,3 +1,4 @@
+! REQUIRES: flang-supports-f128-math
 ! RUN: bbc %s -o - | tco | FileCheck %s
 ! RUN: %flang -emit-llvm -S -mmlir -disable-external-name-interop %s -o - | FileCheck %s
 
@@ -78,4 +79,3 @@ subroutine s7()
   real(16) r16
   common /co1/ r16
 end subroutine
-

flang/test/Semantics/kinds03.f90

@@ -1,3 +1,4 @@
+! REQUIRES: flang-supports-f128-math
 ! RUN: %python %S/test_symbols.py %s %flang_fc1
  !DEF: /MainProgram1/ipdt DerivedType
  !DEF: /MainProgram1/ipdt/k TypeParam INTEGER(4)

flang/test/Semantics/modfile26.f90

@@ -1,3 +1,4 @@
+! REQUIRES: flang-supports-f128-math
 ! RUN: %python %S/test_modfile.py %s %flang_fc1
 ! Intrinsics SELECTED_INT_KIND, SELECTED_REAL_KIND, PRECISION, RANGE,
 ! RADIX, DIGITS

flang/test/Semantics/realkinds-aarch64-01.f90

@@ -1,4 +1,5 @@
 ! REQUIRES: aarch64-registered-target
+! REQUIRES: flang-supports-f128-math
 ! RUN: %python %S/test_modfile.py %s %flang_fc1 -triple aarch64-unknown-linux-gnu
 
 module m1

flang/test/lit.cfg.py

@@ -216,8 +216,9 @@
 # Add features and substitutions to test F128 math support.
 # %f128-lib substitution may be used to generate check prefixes
 # for LIT tests checking for F128 library support.
-if config.flang_runtime_f128_math_lib:
+if config.flang_runtime_f128_math_lib or config.have_ldbl_mant_dig_113:
     config.available_features.add("flang-supports-f128-math")
+if config.flang_runtime_f128_math_lib:
     config.available_features.add(
         "flang-f128-math-lib-" + config.flang_runtime_f128_math_lib
     )

flang/test/lit.site.cfg.py.in

@@ -31,6 +31,7 @@ if "openmp" in "@LLVM_ENABLE_RUNTIMES@".lower().split(";"):
 else:
     config.openmp_module_dir = None
 config.flang_runtime_f128_math_lib = "@FLANG_RUNTIME_F128_MATH_LIB@"
+config.have_ldbl_mant_dig_113 = "@HAVE_LDBL_MANT_DIG_113@"
 
 import lit.llvm
 lit.llvm.initialize(lit_config, config)

flang/tools/f18/CMakeLists.txt

@@ -31,6 +31,25 @@ set(MODULES_WITHOUT_IMPLEMENTATION
 
 set(MODULES ${MODULES_WITH_IMPLEMENTATION} ${MODULES_WITHOUT_IMPLEMENTATION})
 
+# Check if 128-bit float computations can be done via long double.
+check_cxx_source_compiles(
+  "#include <cfloat>
+   #if LDBL_MANT_DIG != 113
+   #error LDBL_MANT_DIG != 113
+   #endif
+   int main() { return 0; }
+  "
+  HAVE_LDBL_MANT_DIG_113)
+
+# Figure out whether we can support REAL(KIND=16)
+if (FLANG_RUNTIME_F128_MATH_LIB)
+  set(FLANG_SUPPORT_R16 "1")
+elseif (HAVE_LDBL_MANT_DIG_113)
+  set(FLANG_SUPPORT_R16 "1")
+else()
+  set(FLANG_SUPPORT_R16 "0")
+endif()
+
 # Init variable to hold extra object files coming from the Fortran modules;
 # these module files will be contributed from the CMakeLists in flang/tools/f18.
 set(module_objects "")
@@ -76,6 +95,10 @@ if (NOT CMAKE_CROSSCOMPILING)
       endif()
     endif()
 
+    set(decls "")
+    if (FLANG_SUPPORT_R16)
+      set(decls "-DFLANG_SUPPORT_R16")
+    endif()
 
     # Some modules have an implementation part that needs to be added to the
     # FortranRuntime library.
@@ -92,7 +115,7 @@ if (NOT CMAKE_CROSSCOMPILING)
     # TODO: We may need to flag this with conditional, in case Flang is built w/o OpenMP support
     add_custom_command(OUTPUT ${base}.mod ${object_output}
       COMMAND ${CMAKE_COMMAND} -E make_directory ${FLANG_INTRINSIC_MODULES_DIR}
-      COMMAND flang-new ${opts} -cpp ${compile_with} -module-dir ${FLANG_INTRINSIC_MODULES_DIR}
+      COMMAND flang-new ${opts} ${decls} -cpp ${compile_with} -module-dir ${FLANG_INTRINSIC_MODULES_DIR}
         ${FLANG_SOURCE_DIR}/module/${filename}.f90
       DEPENDS flang-new ${FLANG_SOURCE_DIR}/module/${filename}.f90 ${FLANG_SOURCE_DIR}/module/__fortran_builtins.f90 ${depends}
     )

lldb/test/API/tools/lldb-dap/variables/TestDAP_variables.py

@@ -200,11 +200,19 @@ def do_test_scopes_variables_setVariable_evaluate(
             verify_locals["pt"]["$__lldb_extensions"] = {
                 "equals": {"autoSummary": "{x:11, y:22}"}
             }
+
         verify_globals = {
             "s_local": {"equals": {"type": "float", "value": "2.25"}},
-            "::g_global": {"equals": {"type": "int", "value": "123"}},
-            "s_global": {"equals": {"type": "int", "value": "234"}},
         }
+        s_global = {"equals": {"type": "int", "value": "234"}}
+        g_global = {"equals": {"type": "int", "value": "123"}}
+        if lldbplatformutil.getHostPlatform() == "windows":
+            verify_globals["::s_global"] = s_global
+            verify_globals["g_global"] = g_global
+        else:
+            verify_globals["s_global"] = s_global
+            verify_globals["::g_global"] = g_global
+
         varref_dict = {}
         self.verify_variables(verify_locals, locals, varref_dict)
         self.verify_variables(verify_globals, globals, varref_dict)
@@ -393,13 +401,11 @@ def do_test_scopes_variables_setVariable_evaluate(
 
         self.verify_variables(verify_locals, locals)
 
-    @skipIfWindows
     def test_scopes_variables_setVariable_evaluate(self):
         self.do_test_scopes_variables_setVariable_evaluate(
             enableAutoVariableSummaries=False
         )
 
-    @skipIfWindows
     def test_scopes_variables_setVariable_evaluate_with_descriptive_summaries(self):
         self.do_test_scopes_variables_setVariable_evaluate(
             enableAutoVariableSummaries=True
@@ -600,11 +606,9 @@ def do_test_scopes_and_evaluate_expansion(self, enableAutoVariableSummaries: boo
             if scope["name"] == "Registers":
                 self.assertEqual(scope.get("presentationHint"), "registers")
 
-    @skipIfWindows
     def test_scopes_and_evaluate_expansion(self):
         self.do_test_scopes_and_evaluate_expansion(enableAutoVariableSummaries=False)
 
-    @skipIfWindows
     def test_scopes_and_evaluate_expansion_with_descriptive_summaries(self):
         self.do_test_scopes_and_evaluate_expansion(enableAutoVariableSummaries=True)
 

llvm/include/llvm/Config/llvm-config.h.cmake

@@ -16,7 +16,7 @@
 
 /* Indicate that this is LLVM compiled from the amd-gfx branch. */
 #define LLVM_HAVE_BRANCH_AMD_GFX
-#define LLVM_MAIN_REVISION 509912
+#define LLVM_MAIN_REVISION 509920
 
 /* Define if LLVM_ENABLE_DUMP is enabled */
 #cmakedefine LLVM_ENABLE_DUMP