Index: clang/lib/CodeGen/CGCall.cpp
===================================================================
--- clang/lib/CodeGen/CGCall.cpp
+++ clang/lib/CodeGen/CGCall.cpp
@@ -1802,6 +1802,8 @@
     FuncAttrs.addAttribute("indirect-tls-seg-refs");
   if (CodeGenOpts.NoImplicitFloat)
     FuncAttrs.addAttribute(llvm::Attribute::NoImplicitFloat);
+  if (Context.getLangOpts().PICLevel > 0)
+    FuncAttrs.addAttribute("tls-load-hoist");
 
   if (AttrOnCallSite) {
     // Attributes that should go on the call site only.
Index: clang/test/CodeGen/X86/tls_loads.cpp
===================================================================
--- /dev/null
+++ clang/test/CodeGen/X86/tls_loads.cpp
@@ -0,0 +1,44 @@
+// RUN: %clang -target x86_64-unknown-unknown -fPIC -O2 -S -o - %s -emit-llvm | FileCheck %s --check-prefix=HOIST
+// RUN: %clang -target x86_64-unknown-unknown -O2 -S -o - %s -emit-llvm | FileCheck %s --check-prefix=NOHOIST
+
+// Use this test generate IR test for llvm/test/CodeGen/X86/intel-tls-loads-control*.ll
+thread_local int thl_x;
+thread_local int thl_x2;
+
+struct SS {
+  char thl_c;
+  int num;
+};
+
+int gfunc();
+int gfunc2(int);
+
+int f1(int c) {
+  int *px = &thl_x;
+  while (c--)
+    *px += gfunc2(thl_x2);
+  return *px;
+}
+
+int f2(int c) {
+  thread_local struct SS st;
+  while (c--) {
+    thl_x += gfunc();
+    st.thl_c += (char)gfunc();
+    st.num += gfunc();
+  }
+  return thl_x;
+}
+
+int f3(int c) {
+  int *px = &thl_x;
+  gfunc2(*px);
+  gfunc2(*px);
+  return 1;
+}
+
+// HOIST: attributes {{.*}}"tls-load-hoist"
+// HOIST: attributes {{.*}}"tls-load-hoist"
+// HOIST: attributes {{.*}}"tls-load-hoist"
+
+// NOHOIST-NOT: attributes {{.*}}"tls-load-hoist"
Index: llvm/docs/LangRef.rst
===================================================================
--- llvm/docs/LangRef.rst
+++ llvm/docs/LangRef.rst
@@ -2125,7 +2125,7 @@
 
 ``"tls-load-hoist"``
     This attribute indicates that the function will try to reduce redundant
-    tls address caculation by hoisting tls variable.
+    tls address calculation by hoisting tls variable.
 
 ``uwtable[(sync|async)]``
     This attribute indicates that the ABI being targeted requires that
Index: llvm/lib/Transforms/Scalar/TLSVariableHoist.cpp
===================================================================
--- llvm/lib/Transforms/Scalar/TLSVariableHoist.cpp
+++ llvm/lib/Transforms/Scalar/TLSVariableHoist.cpp
@@ -40,16 +40,10 @@
 
 #define DEBUG_TYPE "tlshoist"
 
-// TODO: Support "strict" model if we need to strictly load TLS address,
-// because "non-optimize" may also do some optimization in other passes.
-static cl::opt<std::string> TLSLoadHoist(
-    "tls-load-hoist",
-    cl::desc(
-        "hoist the TLS loads in PIC model: "
-        "tls-load-hoist=optimize: Eleminate redundant TLS load(s)."
-        "tls-load-hoist=strict: Strictly load TLS address before every use."
-        "tls-load-hoist=non-optimize: Generally load TLS before use(s)."),
-    cl::init("non-optimize"), cl::Hidden);
+static cl::opt<bool> TLSLoadHoist(
+    "tls-load-hoist", cl::init(false), cl::Hidden,
+    cl::desc("hoist the TLS loads in PIC model to eleminate redundant "
+             "TLS address calculation."));
 
 namespace {
 
@@ -282,8 +276,7 @@
   if (Fn.hasOptNone())
     return false;
 
-  if (TLSLoadHoist != "optimize" &&
-      !Fn.getAttributes().hasFnAttr("tls-load-hoist"))
+  if (!TLSLoadHoist && !Fn.getAttributes().hasFnAttr("tls-load-hoist"))
     return false;
 
   this->LI = &LI;
Index: llvm/test/CodeGen/X86/tls-loads-control.ll
===================================================================
--- llvm/test/CodeGen/X86/tls-loads-control.ll
+++ llvm/test/CodeGen/X86/tls-loads-control.ll
@@ -1,4 +1,4 @@
-; RUN: llc -mtriple=x86_64-unknown-unknown -O2 --relocation-model=pic --tls-load-hoist=optimize --stop-after=tlshoist -o - %s | FileCheck %s
+; RUN: llc -mtriple=x86_64-unknown-unknown -O2 --relocation-model=pic --tls-load-hoist=true --stop-after=tlshoist -o - %s | FileCheck %s
 ; RUN: llc -mtriple=x86_64-unknown-unknown -O2 --relocation-model=pic --stop-after=tlshoist -o - %s | FileCheck %s
 
 ; This test come from compiling clang/test/CodeGen/intel/tls_loads.cpp with:
Index: llvm/test/CodeGen/X86/tls-loads-control2.ll
===================================================================
--- llvm/test/CodeGen/X86/tls-loads-control2.ll
+++ llvm/test/CodeGen/X86/tls-loads-control2.ll
@@ -1,5 +1,4 @@
-; RUN: opt -S -mtriple=x86_64-unknown-unknown -tlshoist --relocation-model=pic --tls-load-hoist=optimize -o - %s | FileCheck %s --check-prefix=HOIST0
-; RUN: opt -S -mtriple=x86_64-unknown-unknown -tlshoist --relocation-model=pic --tls-load-hoist=non-optimize -o - %s | FileCheck %s --check-prefix=HOIST2
+; RUN: opt -S -mtriple=x86_64-unknown-unknown -tlshoist --relocation-model=pic --tls-load-hoist=true -o - %s | FileCheck %s --check-prefix=HOIST0
 ; RUN: opt -S -mtriple=x86_64-unknown-unknown -tlshoist --relocation-model=pic -o - %s | FileCheck %s --check-prefix=HOIST2
 
 $_ZTW5thl_x = comdat any
Index: llvm/test/CodeGen/X86/tls-loads-control3.ll
===================================================================
--- llvm/test/CodeGen/X86/tls-loads-control3.ll
+++ llvm/test/CodeGen/X86/tls-loads-control3.ll
@@ -1,6 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=x86_64-unknown-unknown -O2 --relocation-model=pic --tls-load-hoist=optimize -o - %s | FileCheck %s --check-prefix=HOIST0
-; RUN: llc -mtriple=x86_64-unknown-unknown -O2 --relocation-model=pic --tls-load-hoist=non-optimize -o - %s | FileCheck %s --check-prefix=HOIST2
+; RUN: llc -mtriple=x86_64-unknown-unknown -O2 --relocation-model=pic --tls-load-hoist=true -o - %s | FileCheck %s --check-prefix=HOIST0
 ; RUN: llc -mtriple=x86_64-unknown-unknown -O2 --relocation-model=pic -o - %s | FileCheck %s --check-prefix=HOIST2
 
 ; This test has no module flag {"tls-load-hoist", i32 0}, so use --tls-load-hoist=x