diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -24545,6 +24545,30 @@
 mask argument does not match the pointer size of the target, the mask is
 zero-extended or truncated accordingly.
 
+.. _int_threadlocal_address:
+
+'``llvm.threadlocal.address``' Intrinsic
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+Syntax:
+"""""""
+
+::
+
+      declare ptr @llvm.threadlocal.address(ptr) nounwind readnone willreturn
+
+Arguments:
+""""""""""
+
+The first argument is a pointer, which refers to a thread local global.
+
+Semantics:
+""""""""""
+
+The address of a thread local global is not a constant, since it depends on
+the calling thread. The `llvm.threadlocal.address` intrinsic returns the
+address of the given thread local global in the calling thread.
+
 .. _int_vscale:
 
 '``llvm.vscale``' Intrinsic
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
--- a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -650,6 +650,7 @@
     case Intrinsic::coro_align:
     case Intrinsic::coro_suspend:
     case Intrinsic::coro_subfn_addr:
+    case Intrinsic::threadlocal_address:
       // These intrinsics don't actually represent code after lowering.
       return 0;
     }
diff --git a/llvm/include/llvm/IR/IRBuilder.h b/llvm/include/llvm/IR/IRBuilder.h
--- a/llvm/include/llvm/IR/IRBuilder.h
+++ b/llvm/include/llvm/IR/IRBuilder.h
@@ -753,6 +753,9 @@
   /// If the pointer isn't i8* it will be converted.
   CallInst *CreateInvariantStart(Value *Ptr, ConstantInt *Size = nullptr);
 
+  /// Create a call to llvm.threadlocal.address intrinsic.
+  CallInst *CreateThreadLocalAddress(Value *Ptr);
+
   /// Create a call to Masked Load intrinsic
   CallInst *CreateMaskedLoad(Type *Ty, Value *Ptr, Align Alignment, Value *Mask,
                              Value *PassThru = nullptr, const Twine &Name = "");
diff --git a/llvm/include/llvm/IR/Intrinsics.td b/llvm/include/llvm/IR/Intrinsics.td
--- a/llvm/include/llvm/IR/Intrinsics.td
+++ b/llvm/include/llvm/IR/Intrinsics.td
@@ -1404,6 +1404,10 @@
 def int_ptrmask: DefaultAttrsIntrinsic<[llvm_anyptr_ty], [LLVMMatchType<0>, llvm_anyint_ty],
                            [IntrNoMem, IntrSpeculatable, IntrWillReturn]>;
 
+// Intrinsic to wrap a thread local variable.
+def int_threadlocal_address : DefaultAttrsIntrinsic<[llvm_anyptr_ty], [LLVMMatchType<0>],
+                           [IntrNoMem, IntrSpeculatable, IntrWillReturn]>;
+
 def int_experimental_stepvector : DefaultAttrsIntrinsic<[llvm_anyvector_ty],
                                                         [], [IntrNoMem]>;
 
diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -7178,6 +7178,10 @@
                              DAG.getZExtOrTrunc(Const, sdl, PtrVT)));
     return;
   }
+  case Intrinsic::threadlocal_address: {
+    setValue(&I, getValue(I.getOperand(0)));
+    return;
+  }
   case Intrinsic::get_active_lane_mask: {
     EVT CCVT = TLI.getValueType(DAG.getDataLayout(), I.getType());
     SDValue Index = getValue(I.getOperand(0));
diff --git a/llvm/lib/IR/IRBuilder.cpp b/llvm/lib/IR/IRBuilder.cpp
--- a/llvm/lib/IR/IRBuilder.cpp
+++ b/llvm/lib/IR/IRBuilder.cpp
@@ -526,6 +526,13 @@
   return CreateCall(TheFn, Ops);
 }
 
+CallInst *IRBuilderBase::CreateThreadLocalAddress(Value *Ptr) {
+  assert(isa<GlobalValue>(Ptr) && cast<GlobalValue>(Ptr)->isThreadLocal() &&
+         "threadlocal_address only applies to thread local variables.");
+  return CreateIntrinsic(llvm::Intrinsic::threadlocal_address, {Ptr->getType()},
+                         {Ptr});
+}
+
 CallInst *
 IRBuilderBase::CreateAssumption(Value *Cond,
                                 ArrayRef<OperandBundleDef> OpBundles) {
diff --git a/llvm/test/CodeGen/X86/threadlocal_address.ll b/llvm/test/CodeGen/X86/threadlocal_address.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/X86/threadlocal_address.ll
@@ -0,0 +1,41 @@
+; RUN: llc -mtriple=x86_64-unknown-linux-gnu -stop-after=finalize-isel %s -o - | FileCheck %s
+
+@i = thread_local global i32 0, align 4
+
+define noundef i32 @foo() {
+; CHECK: %0:gr64 = MOV64rm $rip, 1, $noreg, target-flags(x86-gottpoff) @i, $noreg :: (load (s64) from got)
+; CHECK: %1:gr32 = MOV32rm %0, 1, $noreg, 0, $fs :: (load (s32) from %ir.0)
+; CHECK: %2:gr32 = nsw INC32r %1, implicit-def dead $eflags
+; CHECK: MOV32mr %0, 1, $noreg, 0, $fs, %2 :: (store (s32) into %ir.0)
+; CHECK: $eax = COPY %2
+; CHECK: RET 0, $eax
+entry:
+  %0 = call ptr @llvm.threadlocal.address(ptr @i)
+  %1 = load i32, ptr %0, align 4
+  %inc = add nsw i32 %1, 1
+  store i32 %inc, ptr %0, align 4
+  %2 = call ptr @llvm.threadlocal.address(ptr @i)
+  %3 = load i32, ptr %2, align 4
+  ret i32 %3
+}
+
+@j =  thread_local addrspace(1) global  i32 addrspace(0)* @i, align 4
+define noundef i32 @bar() {
+; CHECK: %0:gr64 = MOV64rm $rip, 1, $noreg, target-flags(x86-gottpoff) @j, $noreg :: (load (s64) from got)
+; CHECK: %1:gr32 = MOV32rm %0, 1, $noreg, 0, $fs :: (load (s32) from %ir.0, addrspace 1)
+; CHECK: %2:gr32 = nsw INC32r %1, implicit-def dead $eflags
+; CHECK: MOV32mr %0, 1, $noreg, 0, $fs, %2 :: (store (s32) into %ir.0, addrspace 1)
+; CHECK: $eax = COPY %2
+; CHECK: RET 0, $eax
+entry:
+  %0 = call ptr addrspace(1) @llvm.threadlocal.address.p1(ptr addrspace(1) @j)
+  %1 = load i32, ptr addrspace(1) %0, align 4
+  %inc = add nsw i32 %1, 1
+  store i32 %inc, ptr addrspace(1) %0, align 4
+  %2 = call ptr addrspace(1) @llvm.threadlocal.address.p1(ptr addrspace(1) @j)
+  %3 = load i32, ptr addrspace(1) %2, align 4
+  ret i32 %3
+}
+
+declare ptr @llvm.threadlocal.address(ptr) nounwind readnone willreturn
+declare ptr addrspace(1) @llvm.threadlocal.address.p1(ptr addrspace(1)) nounwind readnone willreturn