diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -781,7 +781,7 @@
     emitGenericVarsEpilog(CGF);
 
   CGBuilderTy &Bld = CGF.Builder;
-  OMPBuilder.createTargetDeinit(Bld, IsSPMD);
+  OMPBuilder.createTargetDeinit(Bld);
 }
 
 void CGOpenMPRuntimeGPU::emitSPMDKernel(const OMPExecutableDirective &D,
diff --git a/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h b/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
--- a/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
+++ b/llvm/include/llvm/Frontend/OpenMP/OMPIRBuilder.h
@@ -1461,8 +1461,7 @@
   /// Create a runtime call for kmpc_target_deinit
   ///
   /// \param Loc The insert and source location description.
-  /// \param IsSPMD Flag to indicate if the kernel is an SPMD kernel or not.
-  void createTargetDeinit(const LocationDescription &Loc, bool IsSPMD);
+  void createTargetDeinit(const LocationDescription &Loc);
 
   ///}
 
diff --git a/llvm/include/llvm/Frontend/OpenMP/OMPKinds.def b/llvm/include/llvm/Frontend/OpenMP/OMPKinds.def
--- a/llvm/include/llvm/Frontend/OpenMP/OMPKinds.def
+++ b/llvm/include/llvm/Frontend/OpenMP/OMPKinds.def
@@ -96,6 +96,10 @@
 		  Int64, Int64, Int32Arr3Ty, Int32Arr3Ty, Int32)
 __OMP_STRUCT_TYPE(AsyncInfo, __tgt_async_info, false, Int8Ptr)
 __OMP_STRUCT_TYPE(DependInfo, kmp_dep_info, false, SizeTy, SizeTy, Int8)
+__OMP_STRUCT_TYPE(ConfigurationEnvironmentTy, ConfigurationEnvironmentTy, false,
+                  Int8, Int8, Int8)
+__OMP_STRUCT_TYPE(KernelEnvironmentTy, KernelEnvironmentTy, false,
+                  ConfigurationEnvironmentTy, IdentPtr, Int16)
 
 #undef __OMP_STRUCT_TYPE
 #undef OMP_STRUCT_TYPE
@@ -452,8 +456,8 @@
           /* Int */ Int32, /* kmp_task_t */ VoidPtr)
 
 /// OpenMP Device runtime functions
-__OMP_RTL(__kmpc_target_init, false, Int32, IdentPtr, Int8, Int1)
-__OMP_RTL(__kmpc_target_deinit, false, Void, IdentPtr, Int8)
+__OMP_RTL(__kmpc_target_init, false, Int32, KernelEnvironmentTyPtr)
+__OMP_RTL(__kmpc_target_deinit, false, Void,)
 __OMP_RTL(__kmpc_kernel_prepare_parallel, false, Void, VoidPtr)
 __OMP_RTL(__kmpc_parallel_51, false, Void, IdentPtr, Int32, Int32, Int32, Int32,
           VoidPtr, VoidPtr, VoidPtrPtr, SizeTy)
@@ -1012,9 +1016,9 @@
                 ReturnPtrAttrs, ParamAttrs(ReadOnlyPtrAttrs, SExt))
 
 __OMP_RTL_ATTRS(__kmpc_target_init, AttributeSet(), SExt,
-                ParamAttrs(AttributeSet(), SExt, SExt))
+                ParamAttrs(AttributeSet()))
 __OMP_RTL_ATTRS(__kmpc_target_deinit, AttributeSet(), AttributeSet(),
-                ParamAttrs(AttributeSet(), SExt))
+                ParamAttrs())
 __OMP_RTL_ATTRS(__kmpc_parallel_51, AlwaysInlineAttrs, AttributeSet(),
                 ParamAttrs(AttributeSet(), SExt, SExt, SExt, SExt,
                            AttributeSet(), AttributeSet(), AttributeSet(),
diff --git a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
--- a/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
+++ b/llvm/lib/Frontend/OpenMP/OMPIRBuilder.cpp
@@ -3878,14 +3878,39 @@
   ConstantInt *IsSPMDVal = ConstantInt::getSigned(
       IntegerType::getInt8Ty(Int8->getContext()),
       IsSPMD ? OMP_TGT_EXEC_MODE_SPMD : OMP_TGT_EXEC_MODE_GENERIC);
-  ConstantInt *UseGenericStateMachine =
-      ConstantInt::getBool(Int32->getContext(), !IsSPMD);
-
+  ConstantInt *UseGenericStateMachineVal = ConstantInt::getSigned(
+      IntegerType::getInt8Ty(Int8->getContext()), !IsSPMD);
+  ConstantInt *MayUseNestedParallelismVal =
+      ConstantInt::getSigned(IntegerType::getInt8Ty(Int8->getContext()), true);
+  ConstantInt *DebugIndentionLevelVal =
+      ConstantInt::getSigned(IntegerType::getInt16Ty(Int8->getContext()), 0);
+
+  Function *Kernel = Builder.GetInsertBlock()->getParent();
   Function *Fn = getOrCreateRuntimeFunctionPtr(
       omp::RuntimeFunction::OMPRTL___kmpc_target_init);
-
-  CallInst *ThreadKind = Builder.CreateCall(
-      Fn, {Ident, IsSPMDVal, UseGenericStateMachine});
+  const DataLayout &DL = Fn->getParent()->getDataLayout();
+
+  Constant *ConfigurationEnvironmentInitializer = ConstantStruct::get(
+      ConfigurationEnvironmentTy, {
+                                      UseGenericStateMachineVal,
+                                      MayUseNestedParallelismVal,
+                                      IsSPMDVal,
+                                  });
+  Constant *KernelEnvironmentInitializer = ConstantStruct::get(
+      KernelEnvironmentTy, {
+                               ConfigurationEnvironmentInitializer,
+                               Ident,
+                               DebugIndentionLevelVal,
+                           });
+  Twine KernelEnvironmentName = Kernel->getName() + "_kernel_info";
+  GlobalVariable *KernelEnvironment = new GlobalVariable(
+      M, KernelEnvironmentTy, /* IsConstant */ true,
+      GlobalValue::ExternalLinkage, KernelEnvironmentInitializer,
+      KernelEnvironmentName,
+      /* InsertBefore */ nullptr, llvm::GlobalValue::NotThreadLocal,
+      DL.getDefaultGlobalsAddressSpace());
+
+  CallInst *ThreadKind = Builder.CreateCall(Fn, {KernelEnvironment});
 
   Value *ExecUserCode = Builder.CreateICmpEQ(
       ThreadKind, ConstantInt::get(ThreadKind->getType(), -1),
@@ -3918,22 +3943,14 @@
   return InsertPointTy(UserCodeEntryBB, UserCodeEntryBB->getFirstInsertionPt());
 }
 
-void OpenMPIRBuilder::createTargetDeinit(const LocationDescription &Loc,
-                                         bool IsSPMD) {
+void OpenMPIRBuilder::createTargetDeinit(const LocationDescription &Loc) {
   if (!updateToLocation(Loc))
     return;
 
-  uint32_t SrcLocStrSize;
-  Constant *SrcLocStr = getOrCreateSrcLocStr(Loc, SrcLocStrSize);
-  Value *Ident = getOrCreateIdent(SrcLocStr, SrcLocStrSize);
-  ConstantInt *IsSPMDVal = ConstantInt::getSigned(
-      IntegerType::getInt8Ty(Int8->getContext()),
-      IsSPMD ? OMP_TGT_EXEC_MODE_SPMD : OMP_TGT_EXEC_MODE_GENERIC);
-
   Function *Fn = getOrCreateRuntimeFunctionPtr(
       omp::RuntimeFunction::OMPRTL___kmpc_target_deinit);
 
-  Builder.CreateCall(Fn, {Ident, IsSPMDVal});
+  Builder.CreateCall(Fn, {});
 }
 
 void OpenMPIRBuilder::setOutlinedTargetRegionFunctionAttributes(
diff --git a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
--- a/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
+++ b/llvm/lib/Transforms/IPO/OpenMPOpt.cpp
@@ -44,6 +44,7 @@
 #include "llvm/IR/IntrinsicsAMDGPU.h"
 #include "llvm/IR/IntrinsicsNVPTX.h"
 #include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/Value.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
@@ -588,6 +589,10 @@
   /// one we abort as the kernel is malformed.
   CallBase *KernelInitCB = nullptr;
 
+  /// The constant kernel environement as taken from and passed to
+  /// __kmpc_target_init.
+  ConstantStruct *KernelEnvC = nullptr;
+
   /// The __kmpc_target_deinit call in this kernel, if any. If we find more than
   /// one we abort as the kernel is malformed.
   CallBase *KernelDeinitCB = nullptr;
@@ -692,6 +697,12 @@
                          "assumptions.");
       KernelDeinitCB = KIS.KernelDeinitCB;
     }
+    if (KIS.KernelEnvC) {
+      if (KernelEnvC && KernelEnvC != KIS.KernelEnvC)
+        llvm_unreachable("Kernel that calls another kernel violates OpenMP-Opt "
+                         "assumptions.");
+      KernelEnvC = KIS.KernelEnvC;
+    }
     SPMDCompatibilityTracker ^= KIS.SPMDCompatibilityTracker;
     ReachedKnownParallelRegions ^= KIS.ReachedKnownParallelRegions;
     ReachedUnknownParallelRegions ^= KIS.ReachedUnknownParallelRegions;
@@ -3386,6 +3397,50 @@
   static const char ID;
 };
 
+/// Return the \p IdentTy pointer from the constant kernel environment \p
+/// KernelEnvC.
+Constant *getIdentFromKernelEnvironment(ConstantStruct *KernelEnvC) {
+  constexpr const unsigned IdentIdx = 1;
+  return KernelEnvC->getAggregateElement(IdentIdx);
+}
+
+/// Return the \p Configurationnvironment struct from the constant kernel
+/// environment \p KernelEnvC.
+ConstantStruct *
+getConfigurationFromKernelEnvironment(ConstantStruct *KernelEnvC) {
+  constexpr const unsigned ConfigurationIdx = 0;
+  return dyn_cast<ConstantStruct>(
+      KernelEnvC->getAggregateElement(ConfigurationIdx));
+}
+
+/// Return the \p UseGenericStateMachine flag from the constant kernel
+/// environment \p KernelEnvC.
+ConstantInt *
+getUseGenericStateMachineFromKernelEnvironment(ConstantStruct *KernelEnvC) {
+  ConstantStruct *ConfigC = getConfigurationFromKernelEnvironment(KernelEnvC);
+  constexpr const unsigned UseGenericStateMachineIdx = 0;
+  return dyn_cast<ConstantInt>(
+      ConfigC->getAggregateElement(UseGenericStateMachineIdx));
+}
+
+/// Return the \p MayUseNestedParallelism flag from the constant kernel
+/// environment \p KernelEnvC.
+ConstantInt *
+getMayUseNestedParallelismFromKernelEnvironment(ConstantStruct *KernelEnvC) {
+  ConstantStruct *ConfigC = getConfigurationFromKernelEnvironment(KernelEnvC);
+  constexpr const unsigned MayUseNestedParallelismIdx = 1;
+  return cast<ConstantInt>(
+      ConfigC->getAggregateElement(MayUseNestedParallelismIdx));
+}
+
+/// Return the \p ExecMode flag from the constant kernel environment \p
+/// KernelEnvC.
+ConstantInt *getExecModeFromKernelEnvironment(ConstantStruct *KernelEnvC) {
+  ConstantStruct *ConfigC = getConfigurationFromKernelEnvironment(KernelEnvC);
+  constexpr const unsigned ExecModeIdx = 2;
+  return dyn_cast<ConstantInt>(ConfigC->getAggregateElement(ExecModeIdx));
+}
+
 /// The function kernel info abstract attribute, basically, what can we say
 /// about a function with regards to the KernelInfoState.
 struct AAKernelInfoFunction : AAKernelInfo {
@@ -3398,6 +3453,48 @@
     return GuardedInstructions;
   }
 
+  GlobalVariable *getKernelEnvironementGlobalVariable() {
+    constexpr const int InitKernelEnvironmentArgNo = 0;
+    return cast<GlobalVariable>(
+        KernelInitCB->getArgOperand(InitKernelEnvironmentArgNo)
+            ->stripPointerCasts());
+  }
+
+  void setConfigurationOfKernelEnvironment(ConstantStruct *ConfigC) {
+    constexpr const unsigned ConfigurationIdx = 0;
+    Constant *NewKernelEnvC = ConstantFoldInsertValueInstruction(
+        KernelEnvC, ConfigC, {ConfigurationIdx});
+    assert(NewKernelEnvC && "Failed to create new kernel environment");
+    KernelEnvC = cast<ConstantStruct>(NewKernelEnvC);
+  }
+
+  void setUseGenericStateMachineOfKernelEnvironment(ConstantInt *NewVal) {
+    ConstantStruct *ConfigC = getConfigurationFromKernelEnvironment(KernelEnvC);
+    constexpr const unsigned UseGenericStateMachineIdx = 2;
+    Constant *NewConfigC = ConstantFoldInsertValueInstruction(
+        ConfigC, NewVal, {UseGenericStateMachineIdx});
+    assert(NewConfigC && "Failed to create new configuration environment");
+    setConfigurationOfKernelEnvironment(cast<ConstantStruct>(NewConfigC));
+  }
+
+  void setMayUseNestedParallelismOfKernelEnvironment(ConstantInt *NewVal) {
+    ConstantStruct *ConfigC = getConfigurationFromKernelEnvironment(KernelEnvC);
+    constexpr const unsigned ExecModeIdx = 1;
+    Constant *NewConfigC =
+        ConstantFoldInsertValueInstruction(ConfigC, NewVal, {ExecModeIdx});
+    assert(NewConfigC && "Failed to create new configuration environment");
+    setConfigurationOfKernelEnvironment(cast<ConstantStruct>(NewConfigC));
+  }
+
+  void setExecModeOfKernelEnvironment(ConstantInt *NewVal) {
+    ConstantStruct *ConfigC = getConfigurationFromKernelEnvironment(KernelEnvC);
+    constexpr const unsigned ExecModeIdx = 2;
+    Constant *NewConfigC =
+        ConstantFoldInsertValueInstruction(ConfigC, NewVal, {ExecModeIdx});
+    assert(NewConfigC && "Failed to create new configuration environment");
+    setConfigurationOfKernelEnvironment(cast<ConstantStruct>(NewConfigC));
+  }
+
   /// See AbstractAttribute::initialize(...).
   void initialize(Attributor &A) override {
     // This is a high-level transform that might change the constant arguments
@@ -3446,6 +3543,9 @@
     ReachingKernelEntries.insert(Fn);
     IsKernelEntry = true;
 
+    GlobalVariable *KernelEnvGV = getKernelEnvironementGlobalVariable();
+    KernelEnvC = cast<ConstantStruct>(KernelEnvGV->getInitializer());
+
     // For kernels we might need to initialize/finalize the IsSPMD state and
     // we need to register a simplification callback so that the Attributor
     // knows the constant arguments to __kmpc_target_init and
@@ -3495,27 +3595,30 @@
       return Val;
     };
 
-    constexpr const int InitModeArgNo = 1;
-    constexpr const int DeinitModeArgNo = 1;
-    constexpr const int InitUseStateMachineArgNo = 2;
-    A.registerSimplificationCallback(
-        IRPosition::callsite_argument(*KernelInitCB, InitUseStateMachineArgNo),
-        StateMachineSimplifyCB);
-    A.registerSimplificationCallback(
-        IRPosition::callsite_argument(*KernelInitCB, InitModeArgNo),
-        ModeSimplifyCB);
+    Attributor::SimplifictionCallbackTy KernelConfigurationSimplifyCB =
+        [&](const IRPosition &IRP, const AbstractAttribute *AA,
+            bool &UsedAssumedInformation) -> std::optional<Value *> {
+      return KernelEnvC;
+    };
+
     A.registerSimplificationCallback(
-        IRPosition::callsite_argument(*KernelDeinitCB, DeinitModeArgNo),
-        ModeSimplifyCB);
+        IRPosition::value(*KernelEnvGV->getInitializer()),
+        KernelConfigurationSimplifyCB);
+
+    ConstantInt *ExecModeC = getExecModeFromKernelEnvironment(KernelEnvC);
+    auto *AssumedExecModeC = ConstantInt::get(
+        ExecModeC->getType(),
+        ExecModeC->getZExtValue() | OMP_TGT_EXEC_MODE_GENERIC_SPMD);
 
     // Check if we know we are in SPMD-mode already.
-    ConstantInt *ModeArg =
-        dyn_cast<ConstantInt>(KernelInitCB->getArgOperand(InitModeArgNo));
-    if (ModeArg && (ModeArg->getSExtValue() & OMP_TGT_EXEC_MODE_SPMD))
+    if (ExecModeC->getSExtValue() & OMP_TGT_EXEC_MODE_SPMD)
       SPMDCompatibilityTracker.indicateOptimisticFixpoint();
-    // This is a generic region but SPMDization is disabled so stop tracking.
     else if (DisableOpenMPOptSPMDization)
+      // This is a generic region but SPMDization is disabled so stop
+      // tracking.
       SPMDCompatibilityTracker.indicatePessimisticFixpoint();
+    else
+      setExecModeOfKernelEnvironment(AssumedExecModeC);
 
     // Register virtual uses of functions we might need to preserve.
     auto RegisterVirtualUse = [&](RuntimeFunction RFKind,
@@ -3616,21 +3719,29 @@
     if (!KernelInitCB || !KernelDeinitCB)
       return ChangeStatus::UNCHANGED;
 
-    /// Insert nested Parallelism global variable
-    Function *Kernel = getAnchorScope();
-    Module &M = *Kernel->getParent();
-    Type *Int8Ty = Type::getInt8Ty(M.getContext());
-    new GlobalVariable(M, Int8Ty, /* isConstant */ true,
-                       GlobalValue::WeakAnyLinkage,
-                       ConstantInt::get(Int8Ty, NestedParallelism ? 1 : 0),
-                       Kernel->getName() + "_nested_parallelism");
+    ChangeStatus Changed = ChangeStatus::UNCHANGED;
 
     // If we can we change the execution mode to SPMD-mode otherwise we build a
     // custom state machine.
-    ChangeStatus Changed = ChangeStatus::UNCHANGED;
     if (!changeToSPMDMode(A, Changed)) {
       if (!KernelInitCB->getCalledFunction()->isDeclaration())
-        return buildCustomStateMachine(A);
+        Changed |= buildCustomStateMachine(A);
+    }
+
+    if (KernelEnvC) {
+      ConstantInt *MayUseNestedParallelismC =
+          getMayUseNestedParallelismFromKernelEnvironment(KernelEnvC);
+      ConstantInt *NewMayUseNestedParallelismC = ConstantInt::get(
+          MayUseNestedParallelismC->getType(), NestedParallelism);
+      setMayUseNestedParallelismOfKernelEnvironment(
+          NewMayUseNestedParallelismC);
+
+      // At last, update the KernelEnvc
+      GlobalVariable *KernelEnvGV = getKernelEnvironementGlobalVariable();
+      if (KernelEnvGV->getInitializer() != KernelEnvC) {
+        KernelEnvGV->setInitializer(KernelEnvC);
+        Changed = ChangeStatus::CHANGED;
+      }
     }
 
     return Changed;
@@ -3952,16 +4063,8 @@
     assert(OMPInfoCache.Kernels.count(Kernel) && "Expected kernel function!");
 
     // Check if the kernel is already in SPMD mode, if so, return success.
-    GlobalVariable *ExecMode = Kernel->getParent()->getGlobalVariable(
-        (Kernel->getName() + "_exec_mode").str());
-    assert(ExecMode && "Kernel without exec mode?");
-    assert(ExecMode->getInitializer() && "ExecMode doesn't have initializer!");
-
-    // Set the global exec mode flag to indicate SPMD-Generic mode.
-    assert(isa<ConstantInt>(ExecMode->getInitializer()) &&
-           "ExecMode is not an integer!");
-    const int8_t ExecModeVal =
-        cast<ConstantInt>(ExecMode->getInitializer())->getSExtValue();
+    auto *ExecModeC = getExecModeFromKernelEnvironment(KernelEnvC);
+    const int8_t ExecModeVal = ExecModeC->getSExtValue();
     if (ExecModeVal != OMP_TGT_EXEC_MODE_GENERIC)
       return true;
 
@@ -3979,27 +4082,8 @@
     // kernel is executed in.
     assert(ExecModeVal == OMP_TGT_EXEC_MODE_GENERIC &&
            "Initially non-SPMD kernel has SPMD exec mode!");
-    ExecMode->setInitializer(
-        ConstantInt::get(ExecMode->getInitializer()->getType(),
-                         ExecModeVal | OMP_TGT_EXEC_MODE_GENERIC_SPMD));
-
-    // Next rewrite the init and deinit calls to indicate we use SPMD-mode now.
-    const int InitModeArgNo = 1;
-    const int DeinitModeArgNo = 1;
-    const int InitUseStateMachineArgNo = 2;
-
-    auto &Ctx = getAnchorValue().getContext();
-    A.changeUseAfterManifest(
-        KernelInitCB->getArgOperandUse(InitModeArgNo),
-        *ConstantInt::getSigned(IntegerType::getInt8Ty(Ctx),
-                                OMP_TGT_EXEC_MODE_SPMD));
-    A.changeUseAfterManifest(
-        KernelInitCB->getArgOperandUse(InitUseStateMachineArgNo),
-        *ConstantInt::getBool(Ctx, false));
-    A.changeUseAfterManifest(
-        KernelDeinitCB->getArgOperandUse(DeinitModeArgNo),
-        *ConstantInt::getSigned(IntegerType::getInt8Ty(Ctx),
-                                OMP_TGT_EXEC_MODE_SPMD));
+    setExecModeOfKernelEnvironment(ConstantInt::get(
+        ExecModeC->getType(), ExecModeVal | OMP_TGT_EXEC_MODE_GENERIC_SPMD));
 
     ++NumOpenMPTargetRegionKernelsSPMD;
 
@@ -4019,30 +4103,29 @@
     if (!ReachedKnownParallelRegions.isValidState())
       return ChangeStatus::UNCHANGED;
 
-    const int InitModeArgNo = 1;
-    const int InitUseStateMachineArgNo = 2;
+    GlobalVariable *KernelEnvGV = getKernelEnvironementGlobalVariable();
+    assert(KernelEnvGV && "missing kernel environment global variable");
+    auto *ExistingKernelEnvC =
+        cast<ConstantStruct>(KernelEnvGV->getInitializer());
 
     // Check if the current configuration is non-SPMD and generic state machine.
     // If we already have SPMD mode or a custom state machine we do not need to
     // go any further. If it is anything but a constant something is weird and
     // we give up.
-    ConstantInt *UseStateMachine = dyn_cast<ConstantInt>(
-        KernelInitCB->getArgOperand(InitUseStateMachineArgNo));
-    ConstantInt *Mode =
-        dyn_cast<ConstantInt>(KernelInitCB->getArgOperand(InitModeArgNo));
+    ConstantInt *UseStateMachineC =
+        getUseGenericStateMachineFromKernelEnvironment(ExistingKernelEnvC);
+    ConstantInt *ModeC = getExecModeFromKernelEnvironment(ExistingKernelEnvC);
 
     // If we are stuck with generic mode, try to create a custom device (=GPU)
     // state machine which is specialized for the parallel regions that are
     // reachable by the kernel.
-    if (!UseStateMachine || UseStateMachine->isZero() || !Mode ||
-        (Mode->getSExtValue() & OMP_TGT_EXEC_MODE_SPMD))
+    if (!UseStateMachineC->isZero() ||
+        (ModeC->getSExtValue() & OMP_TGT_EXEC_MODE_SPMD))
       return ChangeStatus::UNCHANGED;
 
     // If not SPMD mode, indicate we use a custom state machine now.
-    auto &Ctx = getAnchorValue().getContext();
-    auto *FalseVal = ConstantInt::getBool(Ctx, false);
-    A.changeUseAfterManifest(
-        KernelInitCB->getArgOperandUse(InitUseStateMachineArgNo), *FalseVal);
+    setUseGenericStateMachineOfKernelEnvironment(
+        ConstantInt::get(UseStateMachineC->getType(), false));
 
     // If we don't actually need a state machine we are done here. This can
     // happen if there simply are no parallel regions. In the resulting kernel
@@ -4121,6 +4204,7 @@
     // UserCodeEntryBB:      // user code
     //                       __kmpc_target_deinit(...)
     //
+    auto &Ctx = getAnchorValue().getContext();
     Function *Kernel = getAssociatedFunction();
     assert(Kernel && "Expected an associated function!");
 
@@ -4204,7 +4288,7 @@
                                      StateMachineBeginBB->end()),
             DLoc));
 
-    Value *Ident = KernelInitCB->getArgOperand(0);
+    Value *Ident = getIdentFromKernelEnvironment(KernelEnvC);
     Value *GTid = KernelInitCB;
 
     FunctionCallee BarrierFn =
@@ -4334,6 +4418,39 @@
   ChangeStatus updateImpl(Attributor &A) override {
     KernelInfoState StateBefore = getState();
 
+    // When we leave this function this RAII will make sure the member
+    // KernelEnvC is updated properly depending on the state. That member is
+    // used for simplification of values and needs to be up to date at all
+    // times.
+    struct UpdateKernelEnvCRAII {
+      AAKernelInfoFunction &AA;
+
+      UpdateKernelEnvCRAII(AAKernelInfoFunction &AA) : AA(AA) {}
+
+      ~UpdateKernelEnvCRAII() {
+        if (!AA.KernelEnvC)
+          return;
+
+        GlobalVariable *KernelEnvGV = AA.getKernelEnvironementGlobalVariable();
+        ConstantStruct *ExistingKernelEnvC =
+            cast<ConstantStruct>(KernelEnvGV->getInitializer());
+
+        if (!AA.isValidState()) {
+          AA.KernelEnvC = ExistingKernelEnvC;
+          return;
+        }
+
+        if (!AA.ReachedKnownParallelRegions.isValidState())
+          AA.setUseGenericStateMachineOfKernelEnvironment(
+              getUseGenericStateMachineFromKernelEnvironment(
+                  ExistingKernelEnvC));
+
+        if (!AA.SPMDCompatibilityTracker.isValidState())
+          AA.setExecModeOfKernelEnvironment(
+              getExecModeFromKernelEnvironment(ExistingKernelEnvC));
+      }
+    } RAII(*this);
+
     // Callback to check a read/write instruction.
     auto CheckRWInst = [&](Instruction &I) {
       // We handle calls later.
diff --git a/openmp/libomptarget/DeviceRTL/CMakeLists.txt b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
--- a/openmp/libomptarget/DeviceRTL/CMakeLists.txt
+++ b/openmp/libomptarget/DeviceRTL/CMakeLists.txt
@@ -128,6 +128,7 @@
              -nocudalib -nogpulib -nostdinc
              -fopenmp -fopenmp-cuda-mode
              -Wno-unknown-cuda-version
+             -DOMPTARGET_DEVICE_RUNTIME
              -I${include_directory}
              -I${devicertl_base_directory}/../include
              ${LIBOMPTARGET_LLVM_INCLUDE_DIRS_DEVICERTL}
diff --git a/openmp/libomptarget/DeviceRTL/include/Debug.h b/openmp/libomptarget/DeviceRTL/include/Debug.h
--- a/openmp/libomptarget/DeviceRTL/include/Debug.h
+++ b/openmp/libomptarget/DeviceRTL/include/Debug.h
@@ -50,8 +50,6 @@
 struct DebugEntryRAII {
   DebugEntryRAII(const char *File, const unsigned Line, const char *Function);
   ~DebugEntryRAII();
-
-  static void init();
 };
 
 #endif
diff --git a/openmp/libomptarget/DeviceRTL/include/Interface.h b/openmp/libomptarget/DeviceRTL/include/Interface.h
--- a/openmp/libomptarget/DeviceRTL/include/Interface.h
+++ b/openmp/libomptarget/DeviceRTL/include/Interface.h
@@ -214,12 +214,14 @@
 /// Kernel
 ///
 ///{
+// Forward declaration
+struct KernelEnvironmentTy;
+
 int8_t __kmpc_is_spmd_exec_mode();
 
-int32_t __kmpc_target_init(IdentTy *Ident, int8_t Mode,
-                           bool UseGenericStateMachine);
+int32_t __kmpc_target_init(KernelEnvironmentTy &KernelEnvironment);
 
-void __kmpc_target_deinit(IdentTy *Ident, int8_t Mode);
+void __kmpc_target_deinit();
 
 ///}
 
diff --git a/openmp/libomptarget/DeviceRTL/include/State.h b/openmp/libomptarget/DeviceRTL/include/State.h
--- a/openmp/libomptarget/DeviceRTL/include/State.h
+++ b/openmp/libomptarget/DeviceRTL/include/State.h
@@ -17,6 +17,9 @@
 #include "Types.h"
 #include "Utils.h"
 
+// Forward declaration.
+struct KernelEnvironmentTy;
+
 #pragma omp begin declare target device_type(nohost)
 
 namespace ompx {
@@ -113,7 +116,10 @@
 #pragma omp allocate(ThreadStates) allocator(omp_pteam_mem_alloc)
 
 /// Initialize the state machinery. Must be called by all threads.
-void init(bool IsSPMD);
+void init(bool IsSPMD, KernelEnvironmentTy &KernelEnvironment);
+
+/// Return the kernel environment associated with the current kernel.
+KernelEnvironmentTy &getKernelEnvironment();
 
 /// TODO
 enum ValueKind {
diff --git a/openmp/libomptarget/DeviceRTL/src/Configuration.cpp b/openmp/libomptarget/DeviceRTL/src/Configuration.cpp
--- a/openmp/libomptarget/DeviceRTL/src/Configuration.cpp
+++ b/openmp/libomptarget/DeviceRTL/src/Configuration.cpp
@@ -12,7 +12,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "Configuration.h"
-#include "DeviceEnvironment.h"
+#include "Environment.h"
 #include "State.h"
 #include "Types.h"
 
@@ -23,7 +23,6 @@
 // defined by CGOpenMPRuntimeGPU
 extern uint32_t __omp_rtl_debug_kind;
 extern uint32_t __omp_rtl_assume_no_thread_state;
-extern uint32_t __omp_rtl_assume_no_nested_parallelism;
 
 // This variable should be visibile to the plugin so we override the default
 // hidden visibility.
@@ -53,7 +52,7 @@
 bool config::mayUseThreadStates() { return !__omp_rtl_assume_no_thread_state; }
 
 bool config::mayUseNestedParallelism() {
-  return !__omp_rtl_assume_no_nested_parallelism;
+  return state::getKernelEnvironment().Configuration.MayUseNestedParallelism;
 }
 
 #pragma omp end declare target
diff --git a/openmp/libomptarget/DeviceRTL/src/Debug.cpp b/openmp/libomptarget/DeviceRTL/src/Debug.cpp
--- a/openmp/libomptarget/DeviceRTL/src/Debug.cpp
+++ b/openmp/libomptarget/DeviceRTL/src/Debug.cpp
@@ -12,8 +12,10 @@
 
 #include "Debug.h"
 #include "Configuration.h"
+#include "Environment.h"
 #include "Interface.h"
 #include "Mapping.h"
+#include "State.h"
 #include "Types.h"
 
 using namespace ompx;
@@ -31,15 +33,13 @@
 }
 }
 
-/// Current indentation level for the function trace. Only accessed by thread 0.
-__attribute__((loader_uninitialized)) static uint32_t Level;
-#pragma omp allocate(Level) allocator(omp_pteam_mem_alloc)
-
 DebugEntryRAII::DebugEntryRAII(const char *File, const unsigned Line,
                                const char *Function) {
   if (config::isDebugMode(config::DebugKind::FunctionTracing) &&
       mapping::getThreadIdInBlock() == 0 && mapping::getBlockId() == 0) {
 
+    uint16_t &Level = state::getKernelEnvironment().DebugIndentionLevel;
+
     for (int I = 0; I < Level; ++I)
       PRINTF("%s", "  ");
 
@@ -51,10 +51,10 @@
 
 DebugEntryRAII::~DebugEntryRAII() {
   if (config::isDebugMode(config::DebugKind::FunctionTracing) &&
-      mapping::getThreadIdInBlock() == 0 && mapping::getBlockId() == 0)
+      mapping::getThreadIdInBlock() == 0 && mapping::getBlockId() == 0) {
+    uint16_t &Level = state::getKernelEnvironment().DebugIndentionLevel;
     Level--;
+  }
 }
 
-void DebugEntryRAII::init() { Level = 0; }
-
 #pragma omp end declare target
diff --git a/openmp/libomptarget/DeviceRTL/src/Kernel.cpp b/openmp/libomptarget/DeviceRTL/src/Kernel.cpp
--- a/openmp/libomptarget/DeviceRTL/src/Kernel.cpp
+++ b/openmp/libomptarget/DeviceRTL/src/Kernel.cpp
@@ -11,6 +11,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "Debug.h"
+#include "Environment.h"
 #include "Interface.h"
 #include "Mapping.h"
 #include "State.h"
@@ -23,11 +24,12 @@
 
 #pragma omp begin declare target device_type(nohost)
 
-static void inititializeRuntime(bool IsSPMD) {
+static void inititializeRuntime(bool IsSPMD,
+                                KernelEnvironmentTy &KernelEnvironment) {
   // Order is important here.
   synchronize::init(IsSPMD);
   mapping::init(IsSPMD);
-  state::init(IsSPMD);
+  state::init(IsSPMD, KernelEnvironment);
 }
 
 /// Simple generic state machine for worker threads.
@@ -67,16 +69,17 @@
 ///
 /// \param Ident               Source location identification, can be NULL.
 ///
-int32_t __kmpc_target_init(IdentTy *Ident, int8_t Mode,
-                           bool UseGenericStateMachine) {
+int32_t __kmpc_target_init(KernelEnvironmentTy &KernelEnvironment) {
   FunctionTracingRAII();
-  const bool IsSPMD =
-      Mode & llvm::omp::OMPTgtExecModeFlags::OMP_TGT_EXEC_MODE_SPMD;
+  ConfigurationEnvironmentTy &Configuration = KernelEnvironment.Configuration;
+  bool IsSPMD = Configuration.ExecMode &
+                llvm::omp::OMPTgtExecModeFlags::OMP_TGT_EXEC_MODE_SPMD;
+  bool UseGenericStateMachine = Configuration.UseGenericStateMachine;
   if (IsSPMD) {
-    inititializeRuntime(/* IsSPMD */ true);
+    inititializeRuntime(/* IsSPMD */ true, KernelEnvironment);
     synchronize::threadsAligned();
   } else {
-    inititializeRuntime(/* IsSPMD */ false);
+    inititializeRuntime(/* IsSPMD */ false, KernelEnvironment);
     // No need to wait since only the main threads will execute user
     // code and workers will run into a barrier right away.
   }
@@ -104,7 +107,7 @@
   // thread's warp, so none of its threads can ever be active worker threads.
   if (UseGenericStateMachine &&
       mapping::getThreadIdInBlock() < mapping::getBlockSize(IsSPMD)) {
-    genericStateMachine(Ident);
+    genericStateMachine(KernelEnvironment.Ident);
   } else {
     // Retrieve the work function just to ensure we always call
     // __kmpc_kernel_parallel even if a custom state machine is used.
@@ -128,10 +131,9 @@
 ///
 /// \param Ident Source location identification, can be NULL.
 ///
-void __kmpc_target_deinit(IdentTy *Ident, int8_t Mode) {
+void __kmpc_target_deinit() {
   FunctionTracingRAII();
-  const bool IsSPMD =
-      Mode & llvm::omp::OMPTgtExecModeFlags::OMP_TGT_EXEC_MODE_SPMD;
+  bool IsSPMD = mapping::isSPMDMode();
   state::assumeInitialState(IsSPMD);
   if (IsSPMD)
     return;
diff --git a/openmp/libomptarget/DeviceRTL/src/State.cpp b/openmp/libomptarget/DeviceRTL/src/State.cpp
--- a/openmp/libomptarget/DeviceRTL/src/State.cpp
+++ b/openmp/libomptarget/DeviceRTL/src/State.cpp
@@ -9,8 +9,8 @@
 //===----------------------------------------------------------------------===//
 
 #include "State.h"
-#include "Configuration.h"
 #include "Debug.h"
+#include "Environment.h"
 #include "Interface.h"
 #include "Mapping.h"
 #include "Synchronization.h"
@@ -34,6 +34,9 @@
 extern unsigned char DynamicSharedBuffer[] __attribute__((aligned(Alignment)));
 #pragma omp allocate(DynamicSharedBuffer) allocator(omp_pteam_mem_alloc)
 
+/// The kernel environment passed to the init method by the compiler.
+static KernelEnvironmentTy *SHARED(KernelEnvironmentPtr);
+
 namespace {
 
 /// Fallback implementations are missing to trigger a link time error.
@@ -241,15 +244,19 @@
 
 } // namespace
 
-void state::init(bool IsSPMD) {
+void state::init(bool IsSPMD, KernelEnvironmentTy &KernelEnvironment) {
   SharedMemorySmartStack.init(IsSPMD);
   if (mapping::isInitialThreadInLevel0(IsSPMD)) {
     TeamState.init(IsSPMD);
-    DebugEntryRAII::init();
     ThreadStates = nullptr;
+    KernelEnvironmentPtr = &KernelEnvironment;
   }
 }
 
+KernelEnvironmentTy &state::getKernelEnvironment() {
+  return *KernelEnvironmentPtr;
+}
+
 void state::enterDataEnvironment(IdentTy *Ident) {
   ASSERT(config::mayUseThreadStates() &&
          "Thread state modified while explicitly disabled!");
diff --git a/openmp/libomptarget/include/DeviceEnvironment.h b/openmp/libomptarget/include/DeviceEnvironment.h
deleted file mode 100644
--- a/openmp/libomptarget/include/DeviceEnvironment.h
+++ /dev/null
@@ -1,25 +0,0 @@
-//===---- device_environment.h - OpenMP GPU device environment ---- C++ -*-===//
-//
-// 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
-//
-//===----------------------------------------------------------------------===//
-//
-// Global device environment
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef _OMPTARGET_DEVICE_ENVIRONMENT_H_
-#define _OMPTARGET_DEVICE_ENVIRONMENT_H_
-
-// deviceRTL uses <stdint> and DeviceRTL uses explicit definitions
-
-struct DeviceEnvironmentTy {
-  uint32_t DebugKind;
-  uint32_t NumDevices;
-  uint32_t DeviceNum;
-  uint32_t DynamicMemSize;
-};
-
-#endif
diff --git a/openmp/libomptarget/include/Environment.h b/openmp/libomptarget/include/Environment.h
new file mode 100644
--- /dev/null
+++ b/openmp/libomptarget/include/Environment.h
@@ -0,0 +1,53 @@
+//===------------ Environment.h - OpenMP GPU environments --------- C++ -*-===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+//
+// Environments shared between host and device.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _OMPTARGET_ENVIRONMENT_H_
+#define _OMPTARGET_ENVIRONMENT_H_
+
+#ifdef OMPTARGET_DEVICE_RUNTIME
+#include "Types.h"
+#else
+#include "SourceInfo.h"
+
+#include <cstdint>
+
+using IdentTy = ident_t;
+#endif
+
+#include "llvm/Frontend/OpenMP/OMPDeviceConstants.h"
+
+struct DeviceEnvironmentTy {
+  uint32_t DebugKind;
+  uint32_t NumDevices;
+  uint32_t DeviceNum;
+  uint32_t DynamicMemSize;
+};
+
+// NOTE: Please don't change the order of those members as they are used in the
+// middle end. Always add the new data member at the end.
+struct ConfigurationEnvironmentTy {
+  uint8_t UseGenericStateMachine;
+  uint8_t MayUseNestedParallelism;
+  llvm::omp::OMPTgtExecModeFlags ExecMode;
+};
+
+// NOTE: Please don't change the order of those members as they are used in the
+// middle end. Always add the new data member at the end.
+struct KernelEnvironmentTy {
+  ConfigurationEnvironmentTy Configuration;
+  IdentTy *Ident;
+  /// Current indentation level for the function trace. Only accessed by thread
+  /// 0.
+  uint16_t DebugIndentionLevel;
+};
+
+#endif // _OMPTARGET_ENVIRONMENT_H_
diff --git a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
--- a/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
+++ b/openmp/libomptarget/plugins-nextgen/amdgpu/src/rtl.cpp
@@ -21,7 +21,7 @@
 #include <unordered_map>
 
 #include "Debug.h"
-#include "DeviceEnvironment.h"
+#include "Environment.h"
 #include "GlobalHandler.h"
 #include "PluginInterface.h"
 #include "Utilities.h"
@@ -431,7 +431,7 @@
 
   /// Launch the AMDGPU kernel function.
   Error launchImpl(GenericDeviceTy &GenericDevice, uint32_t NumThreads,
-                   uint64_t NumBlocks, 
+                   uint64_t NumBlocks,
                    KernelArgsTy &KernelArgs, void *Args,
                    AsyncInfoWrapperTy &AsyncInfoWrapper) const override;
 
diff --git a/openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.h b/openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.h
--- a/openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.h
+++ b/openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.h
@@ -19,7 +19,7 @@
 #include <vector>
 
 #include "Debug.h"
-#include "DeviceEnvironment.h"
+#include "Environment.h"
 #include "GlobalHandler.h"
 #include "JIT.h"
 #include "MemoryManager.h"
@@ -627,6 +627,11 @@
 
   /// Map of host pinned allocations used for optimize device transfers.
   PinnedAllocationMapTy PinnedAllocs;
+
+private:
+  /// Return the kernel environment object for kernel \p Name.
+  Expected<KernelEnvironmentTy>
+  getKernelEnvironmentForKernel(StringRef Name, DeviceImageTy &Image);
 };
 
 /// Class implementing common functionalities of offload plugins. Each plugin
diff --git a/openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.cpp b/openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.cpp
--- a/openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.cpp
+++ b/openmp/libomptarget/plugins-nextgen/common/PluginInterface/PluginInterface.cpp
@@ -554,32 +554,43 @@
   return Plugin::success();
 }
 
-Expected<OMPTgtExecModeFlags>
-GenericDeviceTy::getExecutionModeForKernel(StringRef Name,
-                                           DeviceImageTy &Image) {
-  // Create a metadata object for the exec mode global (auto-generated).
-  StaticGlobalTy<llvm::omp::OMPTgtExecModeFlags> ExecModeGlobal(Name.data(),
-                                                                "_exec_mode");
+Expected<KernelEnvironmentTy>
+GenericDeviceTy::getKernelEnvironmentForKernel(StringRef Name,
+                                               DeviceImageTy &Image) {
+  // Create a metadata object for the kernel environment object.
+  StaticGlobalTy<KernelEnvironmentTy> KernelEnv(Name.data(), "_kernel_info");
 
-  // Retrieve execution mode for the kernel. This may fail since some kernels
-  // may not have an execution mode.
+  // Retrieve kernel environment object for the kernel.
   GenericGlobalHandlerTy &GHandler = Plugin::get().getGlobalHandler();
-  if (auto Err = GHandler.readGlobalFromImage(*this, Image, ExecModeGlobal)) {
+  if (auto Err = GHandler.readGlobalFromImage(*this, Image, KernelEnv)) {
     // Consume the error since it is acceptable to fail.
     [[maybe_unused]] std::string ErrStr = toString(std::move(Err));
-    DP("Failed to read execution mode for '%s': %s\n"
-       "Using default SPMD (2) execution mode\n",
-       Name.data(), ErrStr.data());
+    DP("Failed to read kernel environment object for '%s': %s\n", Name.data(),
+       ErrStr.data());
 
-    return OMP_TGT_EXEC_MODE_SPMD;
+    return createStringError(inconvertibleErrorCode(), ErrStr);
   }
 
+  return KernelEnv.getValue();
+}
+
+Expected<OMPTgtExecModeFlags>
+GenericDeviceTy::getExecutionModeForKernel(StringRef Name,
+                                           DeviceImageTy &Image) {
+  auto KernelEnvOrError = getKernelEnvironmentForKernel(Name, Image);
+  // We error out directly if we can't read the kernel environment object.
+  if (!KernelEnvOrError)
+    return KernelEnvOrError.takeError();
+
+  auto &KernelEnv = *KernelEnvOrError;
+  auto ExecMode = KernelEnv.Configuration.ExecMode;
+
   // Check that the retrieved execution mode is valid.
-  if (!GenericKernelTy::isValidExecutionMode(ExecModeGlobal.getValue()))
-    return Plugin::error("Invalid execution mode %d for '%s'",
-                         ExecModeGlobal.getValue(), Name.data());
+  if (!GenericKernelTy::isValidExecutionMode(ExecMode))
+    return Plugin::error("Invalid execution mode %d for '%s'", ExecMode,
+                         Name.data());
 
-  return ExecModeGlobal.getValue();
+  return ExecMode;
 }
 
 Error PinnedAllocationMapTy::registerHostBuffer(void *HstPtr,
diff --git a/openmp/libomptarget/plugins-nextgen/cuda/src/rtl.cpp b/openmp/libomptarget/plugins-nextgen/cuda/src/rtl.cpp
--- a/openmp/libomptarget/plugins-nextgen/cuda/src/rtl.cpp
+++ b/openmp/libomptarget/plugins-nextgen/cuda/src/rtl.cpp
@@ -17,7 +17,7 @@
 #include <unordered_map>
 
 #include "Debug.h"
-#include "DeviceEnvironment.h"
+#include "Environment.h"
 #include "GlobalHandler.h"
 #include "PluginInterface.h"
 
diff --git a/openmp/libomptarget/plugins-nextgen/generic-elf-64bit/src/rtl.cpp b/openmp/libomptarget/plugins-nextgen/generic-elf-64bit/src/rtl.cpp
--- a/openmp/libomptarget/plugins-nextgen/generic-elf-64bit/src/rtl.cpp
+++ b/openmp/libomptarget/plugins-nextgen/generic-elf-64bit/src/rtl.cpp
@@ -17,7 +17,7 @@
 #include <unordered_map>
 
 #include "Debug.h"
-#include "DeviceEnvironment.h"
+#include "Environment.h"
 #include "GlobalHandler.h"
 #include "PluginInterface.h"
 #include "omptarget.h"
diff --git a/openmp/libomptarget/plugins/amdgpu/src/rtl.cpp b/openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
--- a/openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
+++ b/openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
@@ -37,7 +37,7 @@
 #include "internal.h"
 #include "rt.h"
 
-#include "DeviceEnvironment.h"
+#include "Environment.h"
 #include "get_elf_mach_gfx_name.h"
 #include "omptargetplugin.h"
 #include "print_tracing.h"
diff --git a/openmp/libomptarget/plugins/cuda/src/rtl.cpp b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
--- a/openmp/libomptarget/plugins/cuda/src/rtl.cpp
+++ b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
@@ -23,7 +23,7 @@
 #include <vector>
 
 #include "Debug.h"
-#include "DeviceEnvironment.h"
+#include "Environment.h"
 #include "omptarget.h"
 #include "omptargetplugin.h"