16 files changed, 82 insertions, 85 deletions
diff --git a/clang/test/CodeGen/2008-07-30-implicit-initialization.c b/clang/test/CodeGen/2008-07-30-implicit-initialization.c
index e77c70a140f..f2621f4560e 100644
--- a/clang/test/CodeGen/2008-07-30-implicit-initialization.c
+++ b/clang/test/CodeGen/2008-07-30-implicit-initialization.c
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -triple i386-unknown-unknown -O1 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple i386-unknown-unknown -O2 -emit-llvm -o - %s | FileCheck %s
 // CHECK-LABEL: define i32 @f0()
 // CHECK:   ret i32 0
 // CHECK-LABEL: define i32 @f1()
diff --git a/clang/test/CodeGen/arm-fp16-arguments.c b/clang/test/CodeGen/arm-fp16-arguments.c
index d739f4b9c66..34dc1a1cbf6 100644
--- a/clang/test/CodeGen/arm-fp16-arguments.c
+++ b/clang/test/CodeGen/arm-fp16-arguments.c
@@ -1,6 +1,6 @@
-// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi soft -fallow-half-arguments-and-returns -emit-llvm -o - -O1 %s | FileCheck %s --check-prefix=CHECK --check-prefix=SOFT
-// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi hard -fallow-half-arguments-and-returns -emit-llvm -o - -O1 %s | FileCheck %s --check-prefix=CHECK --check-prefix=HARD
-// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi soft -fnative-half-arguments-and-returns -emit-llvm -o - -O1 %s | FileCheck %s --check-prefix=NATIVE
+// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi soft -fallow-half-arguments-and-returns -emit-llvm -o - -O2 %s | FileCheck %s --check-prefix=CHECK --check-prefix=SOFT
+// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi hard -fallow-half-arguments-and-returns -emit-llvm -o - -O2 %s | FileCheck %s --check-prefix=CHECK --check-prefix=HARD
+// RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs -mfloat-abi soft -fnative-half-arguments-and-returns -emit-llvm -o - -O2 %s | FileCheck %s --check-prefix=NATIVE
 
 __fp16 g;
 
diff --git a/clang/test/CodeGen/arm-vfp16-arguments2.cpp b/clang/test/CodeGen/arm-vfp16-arguments2.cpp
index 4f75971d832..e436a5ecd6a 100644
--- a/clang/test/CodeGen/arm-vfp16-arguments2.cpp
+++ b/clang/test/CodeGen/arm-vfp16-arguments2.cpp
@@ -1,12 +1,12 @@
 // RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs \
-// RUN:   -mfloat-abi soft -target-feature +neon -emit-llvm -o - -O1 %s \
+// RUN:   -mfloat-abi soft -target-feature +neon -emit-llvm -o - -O2 %s \
 // RUN:   | FileCheck %s --check-prefix=CHECK-SOFT
 // RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs \
-// RUN:   -mfloat-abi hard -target-feature +neon -emit-llvm -o - -O1 %s \
+// RUN:   -mfloat-abi hard -target-feature +neon -emit-llvm -o - -O2 %s \
 // RUN:   | FileCheck %s --check-prefix=CHECK-HARD
 // RUN: %clang_cc1 -triple armv7a--none-eabi -target-abi aapcs \
 // RUN:   -mfloat-abi hard -target-feature +neon -target-feature +fullfp16 \
-// RUN:   -emit-llvm -o - -O1 %s \
+// RUN:   -emit-llvm -o - -O2 %s \
 // RUN:   | FileCheck %s --check-prefix=CHECK-FULL
 
 typedef float float32_t;
diff --git a/clang/test/CodeGen/atomic-ops-libcall.c b/clang/test/CodeGen/atomic-ops-libcall.c
index c673b07f8ed..ca79688c8a0 100644
--- a/clang/test/CodeGen/atomic-ops-libcall.c
+++ b/clang/test/CodeGen/atomic-ops-libcall.c
@@ -10,109 +10,109 @@ enum memory_order {
 
 int *test_c11_atomic_fetch_add_int_ptr(_Atomic(int *) *p) {
   // CHECK: test_c11_atomic_fetch_add_int_ptr
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_add_4(i8* {{%[0-9]+}}, i32 12, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_add_4(i8* {{%[0-9]+}}, i32 12, i32 5)
   return __c11_atomic_fetch_add(p, 3, memory_order_seq_cst);
 }
 
 int *test_c11_atomic_fetch_sub_int_ptr(_Atomic(int *) *p) {
   // CHECK: test_c11_atomic_fetch_sub_int_ptr
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 20, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 20, i32 5)
   return __c11_atomic_fetch_sub(p, 5, memory_order_seq_cst);
 }
 
 int test_c11_atomic_fetch_add_int(_Atomic(int) *p) {
   // CHECK: test_c11_atomic_fetch_add_int
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_add_4(i8* {{%[0-9]+}}, i32 3, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_add_4(i8* {{%[0-9]+}}, i32 3, i32 5)
   return __c11_atomic_fetch_add(p, 3, memory_order_seq_cst);
 }
 
 int test_c11_atomic_fetch_sub_int(_Atomic(int) *p) {
   // CHECK: test_c11_atomic_fetch_sub_int
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 5, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 5, i32 5)
   return __c11_atomic_fetch_sub(p, 5, memory_order_seq_cst);
 }
 
 int *fp2a(int **p) {
   // CHECK: @fp2a
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 4, i32 0)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 4, i32 0)
   // Note, the GNU builtins do not multiply by sizeof(T)!
   return __atomic_fetch_sub(p, 4, memory_order_relaxed);
 }
 
 int test_atomic_fetch_add(int *p) {
   // CHECK: test_atomic_fetch_add
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_add_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_add_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   return __atomic_fetch_add(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_fetch_sub(int *p) {
   // CHECK: test_atomic_fetch_sub
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   return __atomic_fetch_sub(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_fetch_and(int *p) {
   // CHECK: test_atomic_fetch_and
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_and_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_and_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   return __atomic_fetch_and(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_fetch_or(int *p) {
   // CHECK: test_atomic_fetch_or
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_or_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_or_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   return __atomic_fetch_or(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_fetch_xor(int *p) {
   // CHECK: test_atomic_fetch_xor
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_xor_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_xor_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   return __atomic_fetch_xor(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_fetch_nand(int *p) {
   // CHECK: test_atomic_fetch_nand
-  // CHECK: {{%[^ ]*}} = tail call i32 @__atomic_fetch_nand_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: {{%[^ ]*}} = call i32 @__atomic_fetch_nand_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   return __atomic_fetch_nand(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_add_fetch(int *p) {
   // CHECK: test_atomic_add_fetch
-  // CHECK: [[CALL:%[^ ]*]] = tail call i32 @__atomic_fetch_add_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: [[CALL:%[^ ]*]] = call i32 @__atomic_fetch_add_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   // CHECK: {{%[^ ]*}} = add i32 [[CALL]], 55
   return __atomic_add_fetch(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_sub_fetch(int *p) {
   // CHECK: test_atomic_sub_fetch
-  // CHECK: [[CALL:%[^ ]*]] = tail call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: [[CALL:%[^ ]*]] = call i32 @__atomic_fetch_sub_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   // CHECK: {{%[^ ]*}} = add i32 [[CALL]], -55
   return __atomic_sub_fetch(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_and_fetch(int *p) {
   // CHECK: test_atomic_and_fetch
-  // CHECK: [[CALL:%[^ ]*]] = tail call i32 @__atomic_fetch_and_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: [[CALL:%[^ ]*]] = call i32 @__atomic_fetch_and_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   // CHECK: {{%[^ ]*}} = and i32 [[CALL]], 55
   return __atomic_and_fetch(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_or_fetch(int *p) {
   // CHECK: test_atomic_or_fetch
-  // CHECK: [[CALL:%[^ ]*]] = tail call i32 @__atomic_fetch_or_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: [[CALL:%[^ ]*]] = call i32 @__atomic_fetch_or_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   // CHECK: {{%[^ ]*}} = or i32 [[CALL]], 55
   return __atomic_or_fetch(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_xor_fetch(int *p) {
   // CHECK: test_atomic_xor_fetch
-  // CHECK: [[CALL:%[^ ]*]] = tail call i32 @__atomic_fetch_xor_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: [[CALL:%[^ ]*]] = call i32 @__atomic_fetch_xor_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   // CHECK: {{%[^ ]*}} = xor i32 [[CALL]], 55
   return __atomic_xor_fetch(p, 55, memory_order_seq_cst);
 }
 
 int test_atomic_nand_fetch(int *p) {
   // CHECK: test_atomic_nand_fetch
-  // CHECK: [[CALL:%[^ ]*]] = tail call i32 @__atomic_fetch_nand_4(i8* {{%[0-9]+}}, i32 55, i32 5)
+  // CHECK: [[CALL:%[^ ]*]] = call i32 @__atomic_fetch_nand_4(i8* {{%[0-9]+}}, i32 55, i32 5)
   // FIXME: We should not be checking optimized IR. It changes independently of clang.
   // FIXME-CHECK: [[AND:%[^ ]*]] = and i32 [[CALL]], 55
   // FIXME-CHECK: {{%[^ ]*}} = xor i32 [[AND]], -1
diff --git a/clang/test/CodeGenCXX/atomicinit.cpp b/clang/test/CodeGenCXX/atomicinit.cpp
index 85ec74593fe..657ade588fd 100644
--- a/clang/test/CodeGenCXX/atomicinit.cpp
+++ b/clang/test/CodeGenCXX/atomicinit.cpp
@@ -31,7 +31,7 @@ _Atomic(B) b;
 // CHECK-LABEL: define void @_Z11atomic_initR1Ai
 void atomic_init(A& a, int i) {
   // CHECK-NOT: atomic
-  // CHECK: tail call void @_ZN1BC1Ei
+  // CHECK: call void @_ZN1BC1Ei
   __c11_atomic_init(&b, B(i));
   // CHECK-NEXT: ret void
 }
diff --git a/clang/test/CodeGenCXX/auto-var-init.cpp b/clang/test/CodeGenCXX/auto-var-init.cpp
index a2cb2c8352b..9cd71bdfd1a 100644
--- a/clang/test/CodeGenCXX/auto-var-init.cpp
+++ b/clang/test/CodeGenCXX/auto-var-init.cpp
@@ -645,7 +645,7 @@ TEST_UNINIT(smallpartinit, smallpartinit);
 // ZERO-LABEL: @test_smallpartinit_uninit()
 // ZERO-O0: call void @llvm.memset{{.*}}, i8 0,
 // ZERO-O1-LEGACY: store i16 0, i16* %uninit, align 2
-// ZERO-O1-NEWPM: store i16 42, i16* %uninit, align 2
+// ZERO-O1-NEWPM: store i16 0, i16* %uninit, align 2
 
 TEST_BRACES(smallpartinit, smallpartinit);
 // CHECK-LABEL: @test_smallpartinit_braces()
@@ -718,7 +718,7 @@ TEST_UNINIT(paddednullinit, paddednullinit);
 // PATTERN-LABEL: @test_paddednullinit_uninit()
 // PATTERN-O0: call void @llvm.memcpy{{.*}} @__const.test_paddednullinit_uninit.uninit
 // PATTERN-O1-LEGACY: store i64 [[I64]], i64* %uninit, align 8
-// PATTERN-O1-NEWPM: store i64 2863311360, i64* %uninit, align 8
+// PATTERN-O1-NEWPM: store i64 [[I64]], i64* %uninit, align 8
 // ZERO-LABEL: @test_paddednullinit_uninit()
 // ZERO-O0: call void @llvm.memset{{.*}}, i8 0,
 // ZERO-O1: store i64 0, i64* %uninit, align 8
@@ -1344,10 +1344,7 @@ TEST_UNINIT(virtualderived, virtualderived);
 // ZERO-LABEL: @test_virtualderived_uninit()
 // ZERO-O0: call void @llvm.memset{{.*}}, i8 0,
 // ZERO-O1-LEGACY: call void @llvm.memset{{.*}}, i8 0,
-// ZERO-O1-NEWPM: [[FIELD1:%.*]] = getelementptr inbounds %struct.virtualderived, %struct.virtualderived* %uninit, i64 0, i32 1, i32 0, i32 0
-// ZERO-O1-NEWPM: [[FIELD0:%.*]] = getelementptr inbounds %struct.virtualderived, %struct.virtualderived* %uninit, i64 0, i32 0, i32 0
-// ZERO-O1-NEWPM: store i32 (...)** bitcast (i8** getelementptr inbounds ({ [7 x i8*], [5 x i8*] }, { [7 x i8*], [5 x i8*] }* @_ZTV14virtualderived, i64 0, inrange i32 0, i64 5) to i32 (...)**), i32 (...)*** [[FIELD0]], align 8
-// ZERO-O1-NEWPM: store i32 (...)** bitcast (i8** getelementptr inbounds ({ [7 x i8*], [5 x i8*] }, { [7 x i8*], [5 x i8*] }* @_ZTV14virtualderived, i64 0, inrange i32 1, i64 3) to i32 (...)**), i32 (...)*** [[FIELD1]], align 8
+// ZERO-O1-NEWPM: call void @llvm.memset{{.*}}, i8 0,
 
 TEST_BRACES(virtualderived, virtualderived);
 // CHECK-LABEL: @test_virtualderived_braces()
diff --git a/clang/test/CodeGenCXX/discard-name-values.cpp b/clang/test/CodeGenCXX/discard-name-values.cpp
index aa30dae7501..91328a4ddad 100644
--- a/clang/test/CodeGenCXX/discard-name-values.cpp
+++ b/clang/test/CodeGenCXX/discard-name-values.cpp
@@ -11,11 +11,11 @@ bool test(bool pred) {
 
   if (pred) {
     // DISCARDVALUE: 2:
-    // DISCARDVALUE-NEXT: tail call void @branch()
+    // DISCARDVALUE-NEXT: call void @branch()
     // DISCARDVALUE-NEXT: br label %3
 
     // CHECK: if.then:
-    // CHECK-NEXT: tail call void @branch()
+    // CHECK-NEXT: call void @branch()
     // CHECK-NEXT: br label %if.end
     branch();
   }
diff --git a/clang/test/CodeGenCXX/microsoft-abi-dynamic-cast.cpp b/clang/test/CodeGenCXX/microsoft-abi-dynamic-cast.cpp
index c99df0e88b4..a07114dce7d 100644
--- a/clang/test/CodeGenCXX/microsoft-abi-dynamic-cast.cpp
+++ b/clang/test/CodeGenCXX/microsoft-abi-dynamic-cast.cpp
@@ -13,7 +13,7 @@ T* test0() { return dynamic_cast<T*>((B*)0); }
 T* test1(V* x) { return &dynamic_cast<T&>(*x); }
 // CHECK-LABEL: define dso_local %struct.T* @"?test1@@YAPAUT@@PAUV@@@Z"(%struct.V* %x)
 // CHECK:        [[CAST:%.*]] = bitcast %struct.V* %x to i8*
-// CHECK-NEXT:   [[CALL:%.*]] = tail call i8* @__RTDynamicCast(i8* [[CAST]], i32 0, i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUV@@@8" to i8*), i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 1)
+// CHECK-NEXT:   [[CALL:%.*]] = call i8* @__RTDynamicCast(i8* [[CAST]], i32 0, i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUV@@@8" to i8*), i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 1)
 // CHECK-NEXT:   [[RET:%.*]] = bitcast i8* [[CALL]] to %struct.T*
 // CHECK-NEXT:   ret %struct.T* [[RET]]
 
@@ -25,7 +25,7 @@ T* test2(A* x) { return &dynamic_cast<T&>(*x); }
 // CHECK-NEXT:   [[VBOFFP:%.*]] = getelementptr inbounds i32, i32* [[VBTBL]], i32 1
 // CHECK-NEXT:   [[VBOFFS:%.*]] = load i32, i32* [[VBOFFP]], align 4
 // CHECK-NEXT:   [[ADJ:%.*]] = getelementptr inbounds i8, i8* [[CAST]], i32 [[VBOFFS]]
-// CHECK-NEXT:   [[CALL:%.*]] = tail call i8* @__RTDynamicCast(i8* [[ADJ]], i32 [[VBOFFS]], i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUA@@@8" to i8*), i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 1)
+// CHECK-NEXT:   [[CALL:%.*]] = call i8* @__RTDynamicCast(i8* [[ADJ]], i32 [[VBOFFS]], i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUA@@@8" to i8*), i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 1)
 // CHECK-NEXT:   [[RET:%.*]] = bitcast i8* [[CALL]] to %struct.T*
 // CHECK-NEXT:   ret %struct.T* [[RET]]
 
@@ -39,14 +39,14 @@ T* test3(B* x) { return &dynamic_cast<T&>(*x); }
 // CHECK-NEXT:   [[VBOFFS:%.*]] = load i32, i32* [[VBOFFP]], align 4
 // CHECK-NEXT:   [[DELTA:%.*]] = add nsw i32 [[VBOFFS]], 4
 // CHECK-NEXT:   [[ADJ:%.*]] = getelementptr inbounds i8, i8* [[VOIDP]], i32 [[DELTA]]
-// CHECK-NEXT:   [[CALL:%.*]] = tail call i8* @__RTDynamicCast(i8* [[ADJ]], i32 [[DELTA]], i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUB@@@8" to i8*), i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 1)
+// CHECK-NEXT:   [[CALL:%.*]] = call i8* @__RTDynamicCast(i8* [[ADJ]], i32 [[DELTA]], i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUB@@@8" to i8*), i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 1)
 // CHECK-NEXT:   [[RET:%.*]] = bitcast i8* [[CALL]] to %struct.T*
 // CHECK-NEXT:   ret %struct.T* [[RET]]
 
 T* test4(V* x) { return dynamic_cast<T*>(x); }
 // CHECK-LABEL: define dso_local %struct.T* @"?test4@@YAPAUT@@PAUV@@@Z"(%struct.V* %x)
 // CHECK:        [[CAST:%.*]] = bitcast %struct.V* %x to i8*
-// CHECK-NEXT:   [[CALL:%.*]] = tail call i8* @__RTDynamicCast(i8* [[CAST]], i32 0, i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUV@@@8" to i8*), i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 0)
+// CHECK-NEXT:   [[CALL:%.*]] = call i8* @__RTDynamicCast(i8* [[CAST]], i32 0, i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUV@@@8" to i8*), i8* bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 0)
 // CHECK-NEXT:   [[RET:%.*]] = bitcast i8* [[CALL]] to %struct.T*
 // CHECK-NEXT:   ret %struct.T* [[RET]]
 
@@ -60,7 +60,7 @@ T* test5(A* x) { return dynamic_cast<T*>(x); }
 // CHECK-NEXT:   [[VBOFFP:%.*]] = getelementptr inbounds i32, i32* [[VBTBL]], i32 1
 // CHECK-NEXT:   [[VBOFFS:%.*]] = load i32, i32* [[VBOFFP]], align 4
 // CHECK-NEXT:   [[ADJ:%.*]] = getelementptr inbounds i8, i8* [[VOIDP]], i32 [[VBOFFS]]
-// CHECK-NEXT:   [[CALL:%.*]] = tail call i8* @__RTDynamicCast(i8* nonnull [[ADJ]], i32 [[VBOFFS]], i8* {{.*}}bitcast (%rtti.TypeDescriptor7* @"??_R0?AUA@@@8" to i8*), i8* {{.*}}bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 0)
+// CHECK-NEXT:   [[CALL:%.*]] = call i8* @__RTDynamicCast(i8* nonnull [[ADJ]], i32 [[VBOFFS]], i8* {{.*}}bitcast (%rtti.TypeDescriptor7* @"??_R0?AUA@@@8" to i8*), i8* {{.*}}bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 0)
 // CHECK-NEXT:   [[RES:%.*]] = bitcast i8* [[CALL]] to %struct.T*
 // CHECK-NEXT:   br label
 // CHECK:        [[RET:%.*]] = phi %struct.T*
@@ -78,7 +78,7 @@ T* test6(B* x) { return dynamic_cast<T*>(x); }
 // CHECK-NEXT:   [[VBOFFS:%.*]] = load i32, i32* [[VBOFFP]], align 4
 // CHECK-NEXT:   [[DELTA:%.*]] = add nsw i32 [[VBOFFS]], 4
 // CHECK-NEXT:   [[ADJ:%.*]] = getelementptr inbounds i8, i8* [[CAST]], i32 [[DELTA]]
-// CHECK-NEXT:   [[CALL:%.*]] = tail call i8* @__RTDynamicCast(i8* [[ADJ]], i32 [[DELTA]], i8* {{.*}}bitcast (%rtti.TypeDescriptor7* @"??_R0?AUB@@@8" to i8*), i8* {{.*}}bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 0)
+// CHECK-NEXT:   [[CALL:%.*]] = call i8* @__RTDynamicCast(i8* [[ADJ]], i32 [[DELTA]], i8* {{.*}}bitcast (%rtti.TypeDescriptor7* @"??_R0?AUB@@@8" to i8*), i8* {{.*}}bitcast (%rtti.TypeDescriptor7* @"??_R0?AUT@@@8" to i8*), i32 0)
 // CHECK-NEXT:   [[RES:%.*]] = bitcast i8* [[CALL]] to %struct.T*
 // CHECK-NEXT:   br label
 // CHECK:        [[RET:%.*]] = phi %struct.T*
@@ -87,7 +87,7 @@ T* test6(B* x) { return dynamic_cast<T*>(x); }
 void* test7(V* x) { return dynamic_cast<void*>(x); }
 // CHECK-LABEL: define dso_local i8* @"?test7@@YAPAXPAUV@@@Z"(%struct.V* %x)
 // CHECK:        [[CAST:%.*]] = bitcast %struct.V* %x to i8*
-// CHECK-NEXT:   [[RET:%.*]] = tail call i8* @__RTCastToVoid(i8* [[CAST]])
+// CHECK-NEXT:   [[RET:%.*]] = call i8* @__RTCastToVoid(i8* [[CAST]])
 // CHECK-NEXT:   ret i8* [[RET]]
 
 void* test8(A* x) { return dynamic_cast<void*>(x); }
@@ -100,7 +100,7 @@ void* test8(A* x) { return dynamic_cast<void*>(x); }
 // CHECK-NEXT:   [[VBOFFP:%.*]] = getelementptr inbounds i32, i32* [[VBTBL]], i32 1
 // CHECK-NEXT:   [[VBOFFS:%.*]] = load i32, i32* [[VBOFFP]], align 4
 // CHECK-NEXT:   [[ADJ:%.*]] = getelementptr inbounds i8, i8* [[VOIDP]], i32 [[VBOFFS]]
-// CHECK-NEXT:   [[RES:%.*]] = tail call i8* @__RTCastToVoid(i8* nonnull [[ADJ]])
+// CHECK-NEXT:   [[RES:%.*]] = call i8* @__RTCastToVoid(i8* nonnull [[ADJ]])
 // CHECK-NEXT:   br label
 // CHECK:        [[RET:%.*]] = phi i8*
 // CHECK-NEXT:   ret i8* [[RET]]
@@ -117,7 +117,7 @@ void* test9(B* x) { return dynamic_cast<void*>(x); }
 // CHECK-NEXT:   [[VBOFFS:%.*]] = load i32, i32* [[VBOFFP]], align 4
 // CHECK-NEXT:   [[DELTA:%.*]] = add nsw i32 [[VBOFFS]], 4
 // CHECK-NEXT:   [[ADJ:%.*]] = getelementptr inbounds i8, i8* [[CAST]], i32 [[DELTA]]
-// CHECK-NEXT:   [[CALL:%.*]] = tail call i8* @__RTCastToVoid(i8* [[ADJ]])
+// CHECK-NEXT:   [[CALL:%.*]] = call i8* @__RTCastToVoid(i8* [[ADJ]])
 // CHECK-NEXT:   br label
 // CHECK:        [[RET:%.*]] = phi i8*
 // CHECK-NEXT:   ret i8* [[RET]]
diff --git a/clang/test/CodeGenCXX/microsoft-abi-typeid.cpp b/clang/test/CodeGenCXX/microsoft-abi-typeid.cpp
index 848e280cd9f..f3bd7e6fd6c 100644
--- a/clang/test/CodeGenCXX/microsoft-abi-typeid.cpp
+++ b/clang/test/CodeGenCXX/microsoft-abi-typeid.cpp
@@ -25,10 +25,10 @@ const std::type_info* test2_typeid() { return &typeid(&a); }
 
 const std::type_info* test3_typeid() { return &typeid(*fn()); }
 // CHECK-LABEL: define dso_local %struct.type_info* @"?test3_typeid@@YAPBUtype_info@@XZ"()
-// CHECK:        [[CALL:%.*]] = tail call %struct.A* @"?fn@@YAPAUA@@XZ"()
+// CHECK:        [[CALL:%.*]] = call %struct.A* @"?fn@@YAPAUA@@XZ"()
 // CHECK-NEXT:   [[CMP:%.*]] = icmp eq %struct.A* [[CALL]], null
 // CHECK-NEXT:   br i1 [[CMP]]
-// CHECK:        tail call i8* @__RTtypeid(i8* null)
+// CHECK:        call i8* @__RTtypeid(i8* null)
 // CHECK-NEXT:   unreachable
 // CHECK:        [[THIS:%.*]] = bitcast %struct.A* [[CALL]] to i8*
 // CHECK-NEXT:   [[VBTBLP:%.*]] = getelementptr %struct.A, %struct.A* [[CALL]], i32 0, i32 0
@@ -36,7 +36,7 @@ const std::type_info* test3_typeid() { return &typeid(*fn()); }
 // CHECK-NEXT:   [[VBSLOT:%.*]] = getelementptr inbounds i32, i32* [[VBTBL]], i32 1
 // CHECK-NEXT:   [[VBASE_OFFS:%.*]] = load i32, i32* [[VBSLOT]], align 4
 // CHECK-NEXT:   [[ADJ:%.*]] = getelementptr inbounds i8, i8* [[THIS]], i32 [[VBASE_OFFS]]
-// CHECK-NEXT:   [[RT:%.*]] = tail call i8* @__RTtypeid(i8* nonnull [[ADJ]])
+// CHECK-NEXT:   [[RT:%.*]] = call i8* @__RTtypeid(i8* nonnull [[ADJ]])
 // CHECK-NEXT:   [[RET:%.*]] = bitcast i8* [[RT]] to %struct.type_info*
 // CHECK-NEXT:   ret %struct.type_info* [[RET]]
 
@@ -46,7 +46,7 @@ const std::type_info* test4_typeid() { return &typeid(b); }
 
 const std::type_info* test5_typeid() { return &typeid(v); }
 // CHECK: define dso_local %struct.type_info* @"?test5_typeid@@YAPBUtype_info@@XZ"()
-// CHECK:        [[RT:%.*]] = tail call i8* @__RTtypeid(i8* bitcast (%struct.V* @"?v@@3UV@@A" to i8*))
+// CHECK:        [[RT:%.*]] = call i8* @__RTtypeid(i8* bitcast (%struct.V* @"?v@@3UV@@A" to i8*))
 // CHECK-NEXT:   [[RET:%.*]] = bitcast i8* [[RT]] to %struct.type_info*
 // CHECK-NEXT:   ret %struct.type_info* [[RET]]
 
diff --git a/clang/test/CodeGenCXX/nrvo.cpp b/clang/test/CodeGenCXX/nrvo.cpp
index aab26890ea9..74a5af765d1 100644
--- a/clang/test/CodeGenCXX/nrvo.cpp
+++ b/clang/test/CodeGenCXX/nrvo.cpp
@@ -33,13 +33,13 @@ X test0() {
 // CHECK-LABEL: define void @_Z5test1b(
 // CHECK-EH-LABEL: define void @_Z5test1b(
 X test1(bool B) {
-  // CHECK:      tail call {{.*}} @_ZN1XC1Ev
+  // CHECK:      call {{.*}} @_ZN1XC1Ev
   // CHECK-NEXT: ret void
   X x;
   if (B)
     return (x);
   return x;
-  // CHECK-EH:      tail call {{.*}} @_ZN1XC1Ev
+  // CHECK-EH:      call {{.*}} @_ZN1XC1Ev
   // CHECK-EH-NEXT: ret void
 }
 
@@ -130,7 +130,7 @@ X test2(bool B) {
 
 // CHECK-LABEL: define void @_Z5test3b
 X test3(bool B) {
-  // CHECK: tail call {{.*}} @_ZN1XC1Ev
+  // CHECK: call {{.*}} @_ZN1XC1Ev
   // CHECK-NOT: call {{.*}} @_ZN1XC1ERKS_
   // CHECK: call {{.*}} @_ZN1XC1Ev
   // CHECK: call {{.*}} @_ZN1XC1ERKS_
@@ -148,14 +148,14 @@ extern "C" void exit(int) throw();
 // CHECK-LABEL: define void @_Z5test4b
 X test4(bool B) {
   {
-    // CHECK: tail call {{.*}} @_ZN1XC1Ev
+    // CHECK: call {{.*}} @_ZN1XC1Ev
     X x;
     // CHECK: br i1
     if (B)
       return x;
   }
-  // CHECK: tail call {{.*}} @_ZN1XD1Ev
-  // CHECK: tail call void @exit(i32 1)
+  // CHECK: call {{.*}} @_ZN1XD1Ev
+  // CHECK: call void @exit(i32 1)
   exit(1);
 }
 
@@ -191,7 +191,7 @@ X test6() {
 
 // CHECK-LABEL: define void @_Z5test7b
 X test7(bool b) {
-  // CHECK: tail call {{.*}} @_ZN1XC1Ev
+  // CHECK: call {{.*}} @_ZN1XC1Ev
   // CHECK-NEXT: ret
   if (b) {
     X x;
@@ -202,7 +202,7 @@ X test7(bool b) {
 
 // CHECK-LABEL: define void @_Z5test8b
 X test8(bool b) {
-  // CHECK: tail call {{.*}} @_ZN1XC1Ev
+  // CHECK: call {{.*}} @_ZN1XC1Ev
   // CHECK-NEXT: ret
   if (b) {
     X x;
@@ -218,6 +218,6 @@ Y<int> test9() {
 }
 
 // CHECK-LABEL: define linkonce_odr void @_ZN1YIiE1fEv
-// CHECK: tail call {{.*}} @_ZN1YIiEC1Ev
+// CHECK: call {{.*}} @_ZN1YIiEC1Ev
 
 // CHECK-EH-03: attributes [[NR_NUW]] = { noreturn nounwind }
diff --git a/clang/test/CodeGenCXX/stack-reuse.cpp b/clang/test/CodeGenCXX/stack-reuse.cpp
index 8325604391a..35dcb5b349c 100644
--- a/clang/test/CodeGenCXX/stack-reuse.cpp
+++ b/clang/test/CodeGenCXX/stack-reuse.cpp
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -triple armv7-unknown-linux-gnueabihf %s -o - -emit-llvm -O1 | FileCheck %s
+// RUN: %clang_cc1 -triple armv7-unknown-linux-gnueabihf %s -o - -emit-llvm -O2 | FileCheck %s
 
 // Stack should be reused when possible, no need to allocate two separate slots
 // if they have disjoint lifetime.
diff --git a/clang/test/CodeGenCXX/wasm-args-returns.cpp b/clang/test/CodeGenCXX/wasm-args-returns.cpp
index 5718223f9f7..c547eb85390 100644
--- a/clang/test/CodeGenCXX/wasm-args-returns.cpp
+++ b/clang/test/CodeGenCXX/wasm-args-returns.cpp
@@ -19,8 +19,8 @@ test(one_field);
 // CHECK: define double @_Z7forward9one_field(double returned %{{.*}})
 //
 // CHECK: define void @_Z14test_one_fieldv()
-// CHECK: %[[call:.*]] = tail call double @_Z13def_one_fieldv()
-// CHECK: tail call void @_Z3use9one_field(double %[[call]])
+// CHECK: %[[call:.*]] = call double @_Z13def_one_fieldv()
+// CHECK: call void @_Z3use9one_field(double %[[call]])
 // CHECK: ret void
 //
 // CHECK: declare void @_Z3use9one_field(double)
@@ -82,8 +82,8 @@ test(empty);
 // CHECK: define void @_Z7forward5empty()
 //
 // CHECK: define void @_Z10test_emptyv()
-// CHECK: tail call void @_Z9def_emptyv()
-// CHECK: tail call void @_Z3use5empty()
+// CHECK: call void @_Z9def_emptyv()
+// CHECK: call void @_Z3use5empty()
 // CHECK: ret void
 //
 // CHECK: declare void @_Z3use5empty()
@@ -96,8 +96,8 @@ test(one_bitfield);
 // CHECK: define i32 @_Z7forward12one_bitfield(i32 returned %{{.*}})
 //
 // CHECK: define void @_Z17test_one_bitfieldv()
-// CHECK: %[[call:.*]] = tail call i32 @_Z16def_one_bitfieldv()
-// CHECK: tail call void @_Z3use12one_bitfield(i32 %[[call]])
+// CHECK: %[[call:.*]] = call i32 @_Z16def_one_bitfieldv()
+// CHECK: call void @_Z3use12one_bitfield(i32 %[[call]])
 // CHECK: ret void
 //
 // CHECK: declare void @_Z3use12one_bitfield(i32)
diff --git a/clang/test/CodeGenObjCXX/arc-blocks.mm b/clang/test/CodeGenObjCXX/arc-blocks.mm
index 24697cf1bd3..d29491ed077 100644
--- a/clang/test/CodeGenObjCXX/arc-blocks.mm
+++ b/clang/test/CodeGenObjCXX/arc-blocks.mm
@@ -122,7 +122,7 @@ namespace test1 {
 // CHECK: call void @__clang_call_terminate(
 
 // CHECK-O1-LABEL: define linkonce_odr hidden void @__copy_helper_block_ea8_32s40r48w56c15_ZTSN5test12S0E60c15_ZTSN5test12S0E(
-// CHECK-O1: tail call void @llvm.objc.release({{.*}}) {{.*}} !clang.imprecise_release
+// CHECK-O1: call void @llvm.objc.release({{.*}}) {{.*}} !clang.imprecise_release
 // CHECK-NOEXCP: define linkonce_odr hidden void @__copy_helper_block_8_32s40r48w56c15_ZTSN5test12S0E60c15_ZTSN5test12S0E(
 
 // CHECK: define linkonce_odr hidden void @__destroy_helper_block_ea8_32s40r48w56c15_ZTSN5test12S0E60c15_ZTSN5test12S0E(
@@ -170,8 +170,8 @@ namespace test1 {
 // CHECK: call void @__clang_call_terminate(
 
 // CHECK-O1-LABEL: define linkonce_odr hidden void @__destroy_helper_block_ea8_32s40r48w56c15_ZTSN5test12S0E60c15_ZTSN5test12S0E(
-// CHECK-O1: tail call void @llvm.objc.release({{.*}}) {{.*}} !clang.imprecise_release
-// CHECK-O1: tail call void @llvm.objc.release({{.*}}) {{.*}} !clang.imprecise_release
+// CHECK-O1: call void @llvm.objc.release({{.*}}) {{.*}} !clang.imprecise_release
+// CHECK-O1: call void @llvm.objc.release({{.*}}) {{.*}} !clang.imprecise_release
 // CHECK-NOEXCP: define linkonce_odr hidden void @__destroy_helper_block_8_32s40r48w56c15_ZTSN5test12S0E60c15_ZTSN5test12S0E(
 
 namespace {
diff --git a/clang/test/CodeGenObjCXX/nrvo.mm b/clang/test/CodeGenObjCXX/nrvo.mm
index 1ad5f79ad12..a02b38b820a 100644
--- a/clang/test/CodeGenObjCXX/nrvo.mm
+++ b/clang/test/CodeGenObjCXX/nrvo.mm
@@ -14,7 +14,7 @@ struct X {
 // CHECK: define internal void @"\01-[NRVO getNRVO]"
 - (X)getNRVO { 
   X x;
-  // CHECK: tail call void @_ZN1XC1Ev
+  // CHECK: call void @_ZN1XC1Ev
   // CHECK-NEXT: ret void
   return x;
 }
@@ -24,7 +24,7 @@ X blocksNRVO() {
   return ^{
     // CHECK-LABEL: define internal void @___Z10blocksNRVOv_block_invoke
     X x;
-    // CHECK: tail call void @_ZN1XC1Ev
+    // CHECK: call void @_ZN1XC1Ev
     // CHECK-NEXT: ret void
     return x;
   }() ;
diff --git a/clang/test/Lexer/minimize_source_to_dependency_directives_invalid_error.c b/clang/test/Lexer/minimize_source_to_dependency_directives_invalid_error.c
index c4a4cf3d975..020912a4965 100644
--- a/clang/test/Lexer/minimize_source_to_dependency_directives_invalid_error.c
+++ b/clang/test/Lexer/minimize_source_to_dependency_directives_invalid_error.c
@@ -1,16 +1,16 @@
-// Test CF+LF are properly handled along with quoted, multi-line #error
-// RUN: %clang_cc1 -DOTHER -print-dependency-directives-minimized-source %s 2>&1 | FileCheck %s
-
-#ifndef TEST
-#error "message \
-   more message \
-   even more"
-#endif
-
-#ifdef OTHER
-#include <string>
-#endif
-
-// CHECK:      #ifdef OTHER
-// CHECK-NEXT: #include <string>
-// CHECK-NEXT: #endif
+// Test CF+LF are properly handled along with quoted, multi-line #error
+// RUN: %clang_cc1 -DOTHER -print-dependency-directives-minimized-source %s 2>&1 | FileCheck %s
+
+#ifndef TEST
+#error "message \
+   more message \
+   even more"
+#endif
+
+#ifdef OTHER
+#include <string>
+#endif
+
+// CHECK:      #ifdef OTHER
+// CHECK-NEXT: #include <string>
+// CHECK-NEXT: #endif
diff --git a/clang/test/PCH/no-escaping-block-tail-calls.cpp b/clang/test/PCH/no-escaping-block-tail-calls.cpp
index 5ae8108f387..bf197267d67 100644
--- a/clang/test/PCH/no-escaping-block-tail-calls.cpp
+++ b/clang/test/PCH/no-escaping-block-tail-calls.cpp
@@ -1,5 +1,5 @@
-// RUN: %clang_cc1 -x c++-header -triple x86_64-apple-darwin11 -emit-pch -O1 -fblocks -fno-escaping-block-tail-calls -o %t %S/no-escaping-block-tail-calls.h
-// RUN: %clang_cc1 -triple x86_64-apple-darwin11 -include-pch %t -emit-llvm -O1 -fblocks -fno-escaping-block-tail-calls -o - %s | FileCheck %s
+// RUN: %clang_cc1 -x c++-header -triple x86_64-apple-darwin11 -emit-pch -O2 -fblocks -fno-escaping-block-tail-calls -o %t %S/no-escaping-block-tail-calls.h
+// RUN: %clang_cc1 -triple x86_64-apple-darwin11 -include-pch %t -emit-llvm -O2 -fblocks -fno-escaping-block-tail-calls -o - %s | FileCheck %s
 
 // Check that -fno-escaping-block-tail-calls doesn't disable tail-call
 // optimization if the block is non-escaping.