vendor/clang/clang-trunk-r302418

39 files changed, 1219 insertions, 173 deletions

diff --git a/test/CodeGen/aarch64-args.cpp b/test/CodeGen/aarch64-args.cpp
new file mode 100644
index 000000000000..409773627261
--- /dev/null
+++ b/test/CodeGen/aarch64-args.cpp
@@ -0,0 +1,67 @@
+// RUN: %clang_cc1 -triple arm64-apple-ios7.0 -target-abi darwinpcs -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple aarch64-linux-gnu -emit-llvm -o - -x c %s | FileCheck %s --check-prefix=CHECK-GNU-C
+// RUN: %clang_cc1 -triple aarch64-linux-gnu -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-GNU-CXX
+
+// Empty structs are ignored for PCS purposes on Darwin and in C mode elsewhere.
+// In C++ mode on ELF they consume a register slot though. Functions are
+// slightly bigger than minimal to make confirmation against actual GCC
+// behaviour easier.
+
+#if __cplusplus
+#define EXTERNC extern "C"
+#else
+#define EXTERNC
+#endif
+
+struct Empty {};
+
+// CHECK: define i32 @empty_arg(i32 %a)
+// CHECK-GNU-C: define i32 @empty_arg(i32 %a)
+// CHECK-GNU-CXX: define i32 @empty_arg(i8 %e.coerce, i32 %a)
+EXTERNC int empty_arg(struct Empty e, int a) {
+  return a;
+}
+
+// CHECK: define void @empty_ret()
+// CHECK-GNU-C: define void @empty_ret()
+// CHECK-GNU-CXX: define void @empty_ret()
+EXTERNC struct Empty empty_ret() {
+  struct Empty e;
+  return e;
+}
+
+// However, what counts as "empty" is a baroque mess. This is super-empty, it's
+// ignored even in C++ mode. It also has sizeof == 0, violating C++, but that's
+// legacy for you:
+
+struct SuperEmpty {
+  int arr[0];
+};
+
+// CHECK: define i32 @super_empty_arg(i32 %a)
+// CHECK-GNU-C: define i32 @super_empty_arg(i32 %a)
+// CHECK-GNU-CXX: define i32 @super_empty_arg(i32 %a)
+EXTERNC int super_empty_arg(struct SuperEmpty e, int a) {
+  return a;
+}
+
+// This is not empty. It has 0 size but consumes a register slot for GCC.
+
+struct SortOfEmpty {
+  struct SuperEmpty e;
+};
+
+// CHECK: define i32 @sort_of_empty_arg(i32 %a)
+// CHECK-GNU-C: define i32 @sort_of_empty_arg(i32 %a)
+// CHECK-GNU-CXX: define i32 @sort_of_empty_arg(i8 %e.coerce, i32 %a)
+EXTERNC int sort_of_empty_arg(struct Empty e, int a) {
+  return a;
+}
+
+// CHECK: define void @sort_of_empty_ret()
+// CHECK-GNU-C: define void @sort_of_empty_ret()
+// CHECK-GNU-CXX: define void @sort_of_empty_ret()
+EXTERNC struct SortOfEmpty sort_of_empty_ret() {
+  struct SortOfEmpty e;
+  return e;
+}
diff --git a/test/CodeGen/arm_acle.c b/test/CodeGen/arm_acle.c
index b4f39bef1572..7c8a5aa8adb0 100644
--- a/test/CodeGen/arm_acle.c
+++ b/test/CodeGen/arm_acle.c
@@ -76,7 +76,7 @@ void test_dbg(void) {
 // AArch32: call i32 @llvm.arm.strex
 // AArch64: call i64 @llvm.aarch64.ldxr
 // AArch64: call i32 @llvm.aarch64.stxr
-uint32_t test_swp(uint32_t x, volatile void *p) {
+void test_swp(uint32_t x, volatile void *p) {
   __swp(x, p);
 }
 
@@ -118,6 +118,7 @@ void test_nop(void) {
 }
 
 /* 9 DATA-PROCESSING INTRINSICS */
+
 /* 9.2 Miscellaneous data-processing intrinsics */
 // ARM-LABEL: test_ror
 // ARM: lshr
@@ -266,8 +267,7 @@ uint64_t test_rbitll(uint64_t t) {
 }
 
 /* 9.4 Saturating intrinsics */
-#ifdef __ARM_32BIT_STATE
-
+#ifdef __ARM_FEATURE_SAT
 /* 9.4.1 Width-specified saturation intrinsics */
 // AArch32-LABEL: test_ssat
 // AArch32: call i32 @llvm.arm.ssat(i32 %t, i32 1)
@@ -277,11 +277,13 @@ int32_t test_ssat(int32_t t) {
 
 // AArch32-LABEL: test_usat
 // AArch32: call i32 @llvm.arm.usat(i32 %t, i32 2)
-int32_t test_usat(int32_t t) {
+uint32_t test_usat(int32_t t) {
   return __usat(t, 2);
 }
+#endif
 
 /* 9.4.2 Saturating addition and subtraction intrinsics */
+#ifdef __ARM_FEATURE_DSP
 // AArch32-LABEL: test_qadd
 // AArch32: call i32 @llvm.arm.qadd(i32 %a, i32 %b)
 int32_t test_qadd(int32_t a, int32_t b) {
@@ -304,6 +306,389 @@ int32_t test_qdbl() {
 }
 #endif
 
+/*
+ * 9.3 16-bit multiplications
+ */
+#if __ARM_FEATURE_DSP
+// AArch32-LABEL: test_smulbb
+// AArch32: call i32 @llvm.arm.smulbb
+int32_t test_smulbb(int32_t a, int32_t b) {
+  return __smulbb(a, b);
+}
+// AArch32-LABEL: test_smulbt
+// AArch32: call i32 @llvm.arm.smulbt
+int32_t test_smulbt(int32_t a, int32_t b) {
+  return __smulbt(a, b);
+}
+// AArch32-LABEL: test_smultb
+// AArch32: call i32 @llvm.arm.smultb
+int32_t test_smultb(int32_t a, int32_t b) {
+  return __smultb(a, b);
+}
+// AArch32-LABEL: test_smultt
+// AArch32: call i32 @llvm.arm.smultt
+int32_t test_smultt(int32_t a, int32_t b) {
+  return __smultt(a, b);
+}
+// AArch32-LABEL: test_smulwb
+// AArch32: call i32 @llvm.arm.smulwb
+int32_t test_smulwb(int32_t a, int32_t b) {
+  return __smulwb(a, b);
+}
+// AArch32-LABEL: test_smulwt
+// AArch32: call i32 @llvm.arm.smulwt
+int32_t test_smulwt(int32_t a, int32_t b) {
+  return __smulwt(a, b);
+}
+#endif
+
+/* 9.4.3 Accumultating multiplications */
+#if __ARM_FEATURE_DSP
+// AArch32-LABEL: test_smlabb
+// AArch32: call i32 @llvm.arm.smlabb(i32 %a, i32 %b, i32 %c)
+int32_t test_smlabb(int32_t a, int32_t b, int32_t c) {
+  return __smlabb(a, b, c);
+}
+// AArch32-LABEL: test_smlabt
+// AArch32: call i32 @llvm.arm.smlabt(i32 %a, i32 %b, i32 %c)
+int32_t test_smlabt(int32_t a, int32_t b, int32_t c) {
+  return __smlabt(a, b, c);
+}
+// AArch32-LABEL: test_smlatb
+// AArch32: call i32 @llvm.arm.smlatb(i32 %a, i32 %b, i32 %c)
+int32_t test_smlatb(int32_t a, int32_t b, int32_t c) {
+  return __smlatb(a, b, c);
+}
+// AArch32-LABEL: test_smlatt
+// AArch32: call i32 @llvm.arm.smlatt(i32 %a, i32 %b, i32 %c)
+int32_t test_smlatt(int32_t a, int32_t b, int32_t c) {
+  return __smlatt(a, b, c);
+}
+// AArch32-LABEL: test_smlawb
+// AArch32: call i32 @llvm.arm.smlawb(i32 %a, i32 %b, i32 %c)
+int32_t test_smlawb(int32_t a, int32_t b, int32_t c) {
+  return __smlawb(a, b, c);
+}
+// AArch32-LABEL: test_smlawt
+// AArch32: call i32 @llvm.arm.smlawt(i32 %a, i32 %b, i32 %c)
+int32_t test_smlawt(int32_t a, int32_t b, int32_t c) {
+  return __smlawt(a, b, c);
+}
+#endif
+
+/* 9.5.4 Parallel 16-bit saturation */
+#if __ARM_FEATURE_SIMD32
+// AArch32-LABEL: test_ssat16
+// AArch32: call i32 @llvm.arm.ssat16
+int16x2_t test_ssat16(int16x2_t a) {
+  return __ssat16(a, 15);
+}
+// AArch32-LABEL: test_usat16
+// AArch32: call i32 @llvm.arm.usat16
+uint16x2_t test_usat16(int16x2_t a) {
+  return __usat16(a, 15);
+}
+#endif
+
+/* 9.5.5 Packing and unpacking */
+#if __ARM_FEATURE_SIMD32
+// AArch32-LABEL: test_sxtab16
+// AArch32: call i32 @llvm.arm.sxtab16
+int16x2_t test_sxtab16(int16x2_t a, int8x4_t b) {
+  return __sxtab16(a, b);
+}
+// AArch32-LABEL: test_sxtb16
+// AArch32: call i32 @llvm.arm.sxtb16
+int16x2_t test_sxtb16(int8x4_t a) {
+  return __sxtb16(a);
+}
+// AArch32-LABEL: test_uxtab16
+// AArch32: call i32 @llvm.arm.uxtab16
+int16x2_t test_uxtab16(int16x2_t a, int8x4_t b) {
+  return __uxtab16(a, b);
+}
+// AArch32-LABEL: test_uxtb16
+// AArch32: call i32 @llvm.arm.uxtb16
+int16x2_t test_uxtb16(int8x4_t a) {
+  return __uxtb16(a);
+}
+#endif
+
+/* 9.5.6 Parallel selection */
+#if __ARM_FEATURE_SIMD32
+// AArch32-LABEL: test_sel
+// AArch32: call i32 @llvm.arm.sel
+uint8x4_t test_sel(uint8x4_t a, uint8x4_t b) {
+  return __sel(a, b);
+}
+#endif
+
+/* 9.5.7 Parallel 8-bit addition and subtraction */
+#if __ARM_FEATURE_SIMD32
+// AArch32-LABEL: test_qadd8
+// AArch32: call i32 @llvm.arm.qadd8
+int16x2_t test_qadd8(int8x4_t a, int8x4_t b) {
+  return __qadd8(a, b);
+}
+// AArch32-LABEL: test_qsub8
+// AArch32: call i32 @llvm.arm.qsub8
+int8x4_t test_qsub8(int8x4_t a, int8x4_t b) {
+  return __qsub8(a, b);
+}
+// AArch32-LABEL: test_sadd8
+// AArch32: call i32 @llvm.arm.sadd8
+int8x4_t test_sadd8(int8x4_t a, int8x4_t b) {
+  return __sadd8(a, b);
+}
+// AArch32-LABEL: test_shadd8
+// AArch32: call i32 @llvm.arm.shadd8
+int8x4_t test_shadd8(int8x4_t a, int8x4_t b) {
+  return __shadd8(a, b);
+}
+// AArch32-LABEL: test_shsub8
+// AArch32: call i32 @llvm.arm.shsub8
+int8x4_t test_shsub8(int8x4_t a, int8x4_t b) {
+  return __shsub8(a, b);
+}
+// AArch32-LABEL: test_ssub8
+// AArch32: call i32 @llvm.arm.ssub8
+int8x4_t test_ssub8(int8x4_t a, int8x4_t b) {
+  return __ssub8(a, b);
+}
+// AArch32-LABEL: test_uadd8
+// AArch32: call i32 @llvm.arm.uadd8
+uint8x4_t test_uadd8(uint8x4_t a, uint8x4_t b) {
+  return __uadd8(a, b);
+}
+// AArch32-LABEL: test_uhadd8
+// AArch32: call i32 @llvm.arm.uhadd8
+uint8x4_t test_uhadd8(uint8x4_t a, uint8x4_t b) {
+  return __uhadd8(a, b);
+}
+// AArch32-LABEL: test_uhsub8
+// AArch32: call i32 @llvm.arm.uhsub8
+uint8x4_t test_uhsub8(uint8x4_t a, uint8x4_t b) {
+  return __uhsub8(a, b);
+}
+// AArch32-LABEL: test_uqadd8
+// AArch32: call i32 @llvm.arm.uqadd8
+uint8x4_t test_uqadd8(uint8x4_t a, uint8x4_t b) {
+  return __uqadd8(a, b);
+}
+// AArch32-LABEL: test_uqsub8
+// AArch32: call i32 @llvm.arm.uqsub8
+uint8x4_t test_uqsub8(uint8x4_t a, uint8x4_t b) {
+  return __uqsub8(a, b);
+}
+// AArch32-LABEL: test_usub8
+// AArch32: call i32 @llvm.arm.usub8
+uint8x4_t test_usub8(uint8x4_t a, uint8x4_t b) {
+  return __usub8(a, b);
+}
+#endif
+
+/* 9.5.8 Sum of 8-bit absolute differences */
+#if __ARM_FEATURE_SIMD32
+// AArch32-LABEL: test_usad8
+// AArch32: call i32 @llvm.arm.usad8
+uint32_t test_usad8(uint8x4_t a, uint8x4_t b) {
+  return __usad8(a, b);
+}
+// AArch32-LABEL: test_usada8
+// AArch32: call i32 @llvm.arm.usada8
+uint32_t test_usada8(uint8_t a, uint8_t b, uint8_t c) {
+  return __usada8(a, b, c);
+}
+#endif
+
+/* 9.5.9 Parallel 16-bit addition and subtraction */
+#if __ARM_FEATURE_SIMD32
+// AArch32-LABEL: test_qadd16
+// AArch32: call i32 @llvm.arm.qadd16
+int16x2_t test_qadd16(int16x2_t a, int16x2_t b) {
+  return __qadd16(a, b);
+}
+// AArch32-LABEL: test_qasx
+// AArch32: call i32 @llvm.arm.qasx
+int16x2_t test_qasx(int16x2_t a, int16x2_t b) {
+  return __qasx(a, b);
+}
+// AArch32-LABEL: test_qsax
+// AArch32: call i32 @llvm.arm.qsax
+int16x2_t test_qsax(int16x2_t a, int16x2_t b) {
+  return __qsax(a, b);
+}
+// AArch32-LABEL: test_qsub16
+// AArch32: call i32 @llvm.arm.qsub16
+int16x2_t test_qsub16(int16x2_t a, int16x2_t b) {
+  return __qsub16(a, b);
+}
+// AArch32-LABEL: test_sadd16
+// AArch32: call i32 @llvm.arm.sadd16
+int16x2_t test_sadd16(int16x2_t a, int16x2_t b) {
+  return __sadd16(a, b);
+}
+// AArch32-LABEL: test_sasx
+// AArch32: call i32 @llvm.arm.sasx
+int16x2_t test_sasx(int16x2_t a, int16x2_t b) {
+  return __sasx(a, b);
+}
+// AArch32-LABEL: test_shadd16
+// AArch32: call i32 @llvm.arm.shadd16
+int16x2_t test_shadd16(int16x2_t a, int16x2_t b) {
+  return __shadd16(a, b);
+}
+// AArch32-LABEL: test_shasx
+// AArch32: call i32 @llvm.arm.shasx
+int16x2_t test_shasx(int16x2_t a, int16x2_t b) {
+  return __shasx(a, b);
+}
+// AArch32-LABEL: test_shsax
+// AArch32: call i32 @llvm.arm.shsax
+int16x2_t test_shsax(int16x2_t a, int16x2_t b) {
+  return __shsax(a, b);
+}
+// AArch32-LABEL: test_shsub16
+// AArch32: call i32 @llvm.arm.shsub16
+int16x2_t test_shsub16(int16x2_t a, int16x2_t b) {
+  return __shsub16(a, b);
+}
+// AArch32-LABEL: test_ssax
+// AArch32: call i32 @llvm.arm.ssax
+int16x2_t test_ssax(int16x2_t a, int16x2_t b) {
+  return __ssax(a, b);
+}
+// AArch32-LABEL: test_ssub16
+// AArch32: call i32 @llvm.arm.ssub16
+int16x2_t test_ssub16(int16x2_t a, int16x2_t b) {
+  return __ssub16(a, b);
+}
+// AArch32-LABEL: test_uadd16
+// AArch32: call i32 @llvm.arm.uadd16
+uint16x2_t test_uadd16(uint16x2_t a, uint16x2_t b) {
+  return __uadd16(a, b);
+}
+// AArch32-LABEL: test_uasx
+// AArch32: call i32 @llvm.arm.uasx
+uint16x2_t test_uasx(uint16x2_t a, uint16x2_t b) {
+  return __uasx(a, b);
+}
+// AArch32-LABEL: test_uhadd16
+// AArch32: call i32 @llvm.arm.uhadd16
+uint16x2_t test_uhadd16(uint16x2_t a, uint16x2_t b) {
+  return __uhadd16(a, b);
+}
+// AArch32-LABEL: test_uhasx
+// AArch32: call i32 @llvm.arm.uhasx
+uint16x2_t test_uhasx(uint16x2_t a, uint16x2_t b) {
+  return __uhasx(a, b);
+}
+// AArch32-LABEL: test_uhsax
+// AArch32: call i32 @llvm.arm.uhsax
+uint16x2_t test_uhsax(uint16x2_t a, uint16x2_t b) {
+  return __uhsax(a, b);
+}
+// AArch32-LABEL: test_uhsub16
+// AArch32: call i32 @llvm.arm.uhsub16
+uint16x2_t test_uhsub16(uint16x2_t a, uint16x2_t b) {
+  return __uhsub16(a, b);
+}
+// AArch32-LABEL: test_uqadd16
+// AArch32: call i32 @llvm.arm.uqadd16
+uint16x2_t test_uqadd16(uint16x2_t a, uint16x2_t b) {
+  return __uqadd16(a, b);
+}
+// AArch32-LABEL: test_uqasx
+// AArch32: call i32 @llvm.arm.uqasx
+uint16x2_t test_uqasx(uint16x2_t a, uint16x2_t b) {
+  return __uqasx(a, b);
+}
+// AArch32-LABEL: test_uqsax
+// AArch32: call i32 @llvm.arm.uqsax
+uint16x2_t test_uqsax(uint16x2_t a, uint16x2_t b) {
+  return __uqsax(a, b);
+}
+// AArch32-LABEL: test_uqsub16
+// AArch32: call i32 @llvm.arm.uqsub16
+uint16x2_t test_uqsub16(uint16x2_t a, uint16x2_t b) {
+  return __uqsub16(a, b);
+}
+// AArch32-LABEL: test_usax
+// AArch32: call i32 @llvm.arm.usax
+uint16x2_t test_usax(uint16x2_t a, uint16x2_t b) {
+  return __usax(a, b);
+}
+// AArch32-LABEL: test_usub16
+// AArch32: call i32 @llvm.arm.usub16
+uint16x2_t test_usub16(uint16x2_t a, uint16x2_t b) {
+  return __usub16(a, b);
+}
+#endif
+
+/* 9.5.10 Parallel 16-bit multiplications */
+#if __ARM_FEATURE_SIMD32
+// AArch32-LABEL: test_smlad
+// AArch32: call i32 @llvm.arm.smlad
+int32_t test_smlad(int16x2_t a, int16x2_t b, int32_t c) {
+  return __smlad(a, b, c);
+}
+// AArch32-LABEL: test_smladx
+// AArch32: call i32 @llvm.arm.smladx
+int32_t test_smladx(int16x2_t a, int16x2_t b, int32_t c) {
+  return __smladx(a, b, c);
+}
+// AArch32-LABEL: test_smlald
+// AArch32: call i64 @llvm.arm.smlald
+int64_t test_smlald(int16x2_t a, int16x2_t b, int64_t c) {
+  return __smlald(a, b, c);
+}
+// AArch32-LABEL: test_smlaldx
+// AArch32: call i64 @llvm.arm.smlaldx
+int64_t test_smlaldx(int16x2_t a, int16x2_t b, int64_t c) {
+  return __smlaldx(a, b, c);
+}
+// AArch32-LABEL: test_smlsd
+// AArch32: call i32 @llvm.arm.smlsd
+int32_t test_smlsd(int16x2_t a, int16x2_t b, int32_t c) {
+  return __smlsd(a, b, c);
+}
+// AArch32-LABEL: test_smlsdx
+// AArch32: call i32 @llvm.arm.smlsdx
+int32_t test_smlsdx(int16x2_t a, int16x2_t b, int32_t c) {
+  return __smlsdx(a, b, c);
+}
+// AArch32-LABEL: test_smlsld
+// AArch32: call i64 @llvm.arm.smlsld
+int64_t test_smlsld(int16x2_t a, int16x2_t b, int64_t c) {
+  return __smlsld(a, b, c);
+}
+// AArch32-LABEL: test_smlsldx
+// AArch32: call i64 @llvm.arm.smlsldx
+int64_t test_smlsldx(int16x2_t a, int16x2_t b, int64_t c) {
+  return __smlsldx(a, b, c);
+}
+// AArch32-LABEL: test_smuad
+// AArch32: call i32 @llvm.arm.smuad
+int32_t test_smuad(int16x2_t a, int16x2_t b) {
+  return __smuad(a, b);
+}
+// AArch32-LABEL: test_smuadx
+// AArch32: call i32 @llvm.arm.smuadx
+int32_t test_smuadx(int16x2_t a, int16x2_t b) {
+  return __smuadx(a, b);
+}
+// AArch32-LABEL: test_smusd
+// AArch32: call i32 @llvm.arm.smusd
+int32_t test_smusd(int16x2_t a, int16x2_t b) {
+  return __smusd(a, b);
+}
+// AArch32-LABEL: test_smusdx
+// AArch32: call i32 @llvm.arm.smusdx
+int32_t test_smusdx(int16x2_t a, int16x2_t b) {
+  return __smusdx(a, b);
+}
+#endif
+
 /* 9.7 CRC32 intrinsics */
 // ARM-LABEL: test_crc32b
 // AArch32: call i32 @llvm.arm.crc32b
diff --git a/test/CodeGen/lwp-builtins.c b/test/CodeGen/lwp-builtins.c
new file mode 100644
index 000000000000..c689c3974d4b
--- /dev/null
+++ b/test/CodeGen/lwp-builtins.c
@@ -0,0 +1,39 @@
+// RUN: %clang_cc1 -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +lwp -emit-llvm -o - -Wall -Werror | FileCheck %s
+
+#include <x86intrin.h>
+
+void test_llwpcb(void *ptr) {
+  // CHECK-LABEL: @test_llwpcb
+  // CHECK: call void @llvm.x86.llwpcb(i8* %{{.*}})
+  __llwpcb(ptr);
+}
+
+void* test_slwpcb() {
+  // CHECK-LABEL: @test_slwpcb
+  // CHECK: call i8* @llvm.x86.slwpcb()
+  return __slwpcb();
+}
+
+unsigned char test_lwpins32(unsigned val2, unsigned val1) {
+  // CHECK-LABEL: @test_lwpins32
+  // CHECK: call i8 @llvm.x86.lwpins32(i32
+  return __lwpins32(val2, val1, 0x01234);
+}
+
+unsigned char test_lwpins64(unsigned long long val2, unsigned val1) {
+  // CHECK-LABEL: @test_lwpins64
+  // CHECK: call i8 @llvm.x86.lwpins64(i64
+  return __lwpins64(val2, val1, 0x56789);
+}
+
+void test_lwpval32(unsigned val2, unsigned val1) {
+  // CHECK-LABEL: @test_lwpval32
+  // CHECK: call void @llvm.x86.lwpval32(i32
+  __lwpval32(val2, val1, 0x01234);
+}
+
+void test_lwpval64(unsigned long long val2, unsigned val1) {
+  // CHECK-LABEL: @test_lwpval64
+  // CHECK: call void @llvm.x86.lwpval64(i64
+  __lwpval64(val2, val1, 0xABCDEF);
+}
diff --git a/test/CodeGen/mozilla-ms-inline-asm.c b/test/CodeGen/mozilla-ms-inline-asm.c
index 3335a87fefe5..26e8ebce1e28 100644
--- a/test/CodeGen/mozilla-ms-inline-asm.c
+++ b/test/CodeGen/mozilla-ms-inline-asm.c
@@ -18,25 +18,25 @@ void invoke(void* that, unsigned methodIndex,
 // CHECK: store i32 %2, i32* %7, align 4
 // CHECK: store i8* %3, i8** %8, align 4
 // CHECK: call void asm sideeffect inteldialect
-// CHECK: mov edx,dword ptr $1
-// CHECK: test edx,edx
-// CHECK: jz {{[^_]*}}__MSASMLABEL_.${:uid}__noparams
-//             ^ Can't use {{.*}} here because the matching is greedy.
-// CHECK: mov eax,edx
-// CHECK: shl eax,$$3
-// CHECK: sub esp,eax
-// CHECK: mov ecx,esp
-// CHECK: push dword ptr $0
-// CHECK: call dword ptr $2
-// CHECK: {{.*}}__MSASMLABEL_.${:uid}__noparams:
-// CHECK: mov ecx,dword ptr $3
-// CHECK: push ecx
-// CHECK: mov edx,[ecx]
-// CHECK: mov eax,dword ptr $4
-// CHECK: call dword ptr[edx+eax*$$4]
-// CHECK: mov esp,ebp
-// CHECK: pop ebp
-// CHECK: ret
+// CHECK-SAME: mov edx,$1
+// CHECK-SAME: test edx,edx
+// CHECK-SAME: jz {{[^_]*}}__MSASMLABEL_.${:uid}__noparams
+//                ^ Can't use {{.*}} here because the matching is greedy.
+// CHECK-SAME: mov eax,edx
+// CHECK-SAME: shl eax,$$3
+// CHECK-SAME: sub esp,eax
+// CHECK-SAME: mov ecx,esp
+// CHECK-SAME: push $0
+// CHECK-SAME: call dword ptr $2
+// CHECK-SAME: {{.*}}__MSASMLABEL_.${:uid}__noparams:
+// CHECK-SAME: mov ecx,$3
+// CHECK-SAME: push ecx
+// CHECK-SAME: mov edx,[ecx]
+// CHECK-SAME: mov eax,$4
+// CHECK-SAME: call dword ptr[edx+eax*$$4]
+// CHECK-SAME: mov esp,ebp
+// CHECK-SAME: pop ebp
+// CHECK-SAME: ret
 // CHECK: "=*m,*m,*m,*m,*m,~{eax},~{ebp},~{ecx},~{edx},~{flags},~{esp},~{dirflag},~{fpsr},~{flags}"
 // CHECK: (i8** %8, i32* %7, void (...)* bitcast (void ()* @invoke_copy_to_stack to void (...)*), i8** %5, i32* %6)
 // CHECK: ret void
diff --git a/test/CodeGen/ms-inline-asm-64.c b/test/CodeGen/ms-inline-asm-64.c
index d6f6e2ee0e0e..69828feb3623 100644
--- a/test/CodeGen/ms-inline-asm-64.c
+++ b/test/CodeGen/ms-inline-asm-64.c
@@ -5,14 +5,18 @@ void t1() {
   int var = 10;
   __asm mov rax, offset var ; rax = address of myvar
 // CHECK: t1
-// CHECK: call void asm sideeffect inteldialect "mov rax, $0", "r,~{rax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: mov rax, $0
+// CHECK-SAME: "r,~{rax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
 }
 
 void t2() {
   int var = 10;
   __asm mov [eax], offset var
 // CHECK: t2
-// CHECK: call void asm sideeffect inteldialect "mov [eax], $0", "r,~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: mov [eax], $0
+// CHECK-SAME: "r,~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
 }
 
 struct t3_type { int a, b; };
@@ -28,7 +32,11 @@ int t3() {
   }
   return foo.b;
 // CHECK: t3
-// CHECK: call void asm sideeffect inteldialect "lea ebx, qword ptr $0\0A\09mov eax, [ebx].0\0A\09mov [ebx].4, ecx", "*m,~{eax},~{ebx},~{dirflag},~{fpsr},~{flags}"(%struct.t3_type* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: lea ebx, $0
+// CHECK-SAME: mov eax, [ebx].0
+// CHECK-SAME: mov [ebx].4, ecx
+// CHECK-SAME: "*m,~{eax},~{ebx},~{dirflag},~{fpsr},~{flags}"(%struct.t3_type* %{{.*}})
 }
 
 int t4() {
@@ -44,5 +52,9 @@ int t4() {
   }
   return foo.b;
 // CHECK: t4
-// CHECK: call void asm sideeffect inteldialect "lea ebx, qword ptr $0\0A\09mov eax, [ebx].0\0A\09mov [ebx].4, ecx", "*m,~{eax},~{ebx},~{dirflag},~{fpsr},~{flags}"(%struct.t3_type* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: lea ebx, $0
+// CHECK-SAME: mov eax, [ebx].0
+// CHECK-SAME: mov [ebx].4, ecx
+// CHECK-SAME: "*m,~{eax},~{ebx},~{dirflag},~{fpsr},~{flags}"(%struct.t3_type* %{{.*}})
 }
diff --git a/test/CodeGen/ms-inline-asm-avx512.c b/test/CodeGen/ms-inline-asm-avx512.c
index c1b783a2107c..6189e50d2116 100644
--- a/test/CodeGen/ms-inline-asm-avx512.c
+++ b/test/CodeGen/ms-inline-asm-avx512.c
@@ -1,5 +1,5 @@
 // REQUIRES: x86-registered-target
-// RUN: %clang_cc1 %s -triple x86_64-pc-windows-msvc -target-cpu knl -fasm-blocks -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 %s -triple x86_64-pc-windows-msvc -target-cpu skylake-avx512 -fasm-blocks -emit-llvm -o - | FileCheck %s
 
 void t1() {
 // CHECK: @t1
@@ -19,3 +19,16 @@ void t2() {
 	  vaddpd zmm8 {k1}, zmm27, zmm6
   }
 }
+
+void ignore_fe_size() {
+  // CHECK-LABEL: define void @ignore_fe_size()
+  char c;
+  // CHECK: vaddps xmm1, xmm2, $1{1to4}
+  __asm vaddps xmm1, xmm2, [c]{1to4}
+  // CHECK: vaddps xmm1, xmm2, $2
+  __asm vaddps xmm1, xmm2, [c]
+  // CHECK: mov eax, $3
+  __asm mov eax, [c]
+  // CHECK: mov $0, rax
+  __asm mov [c], rax
+}
diff --git a/test/CodeGen/ms-inline-asm.c b/test/CodeGen/ms-inline-asm.c
index c4fe08a3e13b..5182d7f2e81a 100644
--- a/test/CodeGen/ms-inline-asm.c
+++ b/test/CodeGen/ms-inline-asm.c
@@ -92,7 +92,11 @@ void t9() {
     __asm { pop ebx }
   }
 // CHECK: t9
-// CHECK: call void asm sideeffect inteldialect "push ebx\0A\09mov ebx, $$0x07\0A\09pop ebx\0A\09", "~{ebx},~{esp},~{dirflag},~{fpsr},~{flags}"()
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: push ebx
+// CHECK-SAME: mov ebx, $$0x07
+// CHECK-SAME: pop ebx
+// CHECK-SAME: "~{ebx},~{esp},~{dirflag},~{fpsr},~{flags}"()
 }
 
 unsigned t10(void) {
@@ -107,7 +111,10 @@ unsigned t10(void) {
 // CHECK: [[I:%[a-zA-Z0-9]+]] = alloca i32, align 4
 // CHECK: [[J:%[a-zA-Z0-9]+]] = alloca i32, align 4
 // CHECK: store i32 1, i32* [[I]], align 4
-// CHECK: call i32 asm sideeffect inteldialect "mov eax, dword ptr $2\0A\09mov dword ptr $0, eax", "=*m,={eax},*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}}, i32* %{{.*}})
+// CHECK: call i32 asm sideeffect inteldialect
+// CHECK-SAME: mov eax, $2
+// CHECK-SAME: mov $0, eax
+// CHECK-SAME: "=*m,={eax},*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}}, i32* %{{.*}})
 // CHECK: [[RET:%[a-zA-Z0-9]+]] = load i32, i32* [[J]], align 4
 // CHECK: ret i32 [[RET]]
 }
@@ -128,7 +135,12 @@ unsigned t12(void) {
   }
   return j + m;
 // CHECK: t12
-// CHECK: call i32 asm sideeffect inteldialect "mov eax, dword ptr $3\0A\09mov dword ptr $0, eax\0A\09mov eax, dword ptr $4\0A\09mov dword ptr $1, eax", "=*m,=*m,={eax},*m,*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}}, i32* %{{.*}}, i32* %{{.*}}, i32* %{{.*}})
+// CHECK: call i32 asm sideeffect inteldialect
+// CHECK-SAME: mov eax, $3
+// CHECK-SAME: mov $0, eax
+// CHECK-SAME: mov eax, $4
+// CHECK-SAME: mov $1, eax
+// CHECK-SAME: "=*m,=*m,={eax},*m,*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}}, i32* %{{.*}}, i32* %{{.*}}, i32* %{{.*}})
 }
 
 void t13() {
@@ -136,8 +148,23 @@ void t13() {
   short j = 2;
   __asm movzx eax, i
   __asm movzx eax, j
-// CHECK: t13
-// CHECK: call void asm sideeffect inteldialect "movzx eax, byte ptr $0\0A\09movzx eax, word ptr $1", "*m,*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i8* %{{.*}}i, i16* %{{.*}}j)
+// CHECK-LABEL: define void @t13()
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: movzx eax, byte ptr $0
+// CHECK-SAME: movzx eax, word ptr $1
+// CHECK-SAME: "*m,*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i8* %{{.*}}i, i16* %{{.*}}j)
+}
+
+void t13_brac() {
+  char i = 1;
+  short j = 2;
+  __asm movzx eax, [i]
+  __asm movzx eax, [j]
+// CHECK-LABEL: define void @t13_brac()
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: movzx eax, byte ptr $0
+// CHECK-SAME: movzx eax, word ptr $1
+// CHECK-SAME: "*m,*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i8* %{{.*}}i, i16* %{{.*}}j)
 }
 
 void t14() {
@@ -150,7 +177,7 @@ void t14() {
     .endif
   }
 // CHECK: t14
-// CHECK: call void asm sideeffect inteldialect ".if 1\0A\09mov eax, dword ptr $0\0A\09.else\0A\09mov ebx, j\0A\09.endif", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect ".if 1\0A\09mov eax, $0\0A\09.else\0A\09mov ebx, j\0A\09.endif", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
 }
 
 int gvar = 10;
@@ -158,7 +185,7 @@ void t15() {
 // CHECK: t15
   int lvar = 10;
   __asm mov eax, lvar        ; eax = 10
-// CHECK: mov eax, dword ptr $0
+// CHECK: mov eax, $0
   __asm mov eax, offset lvar ; eax = address of lvar
 // CHECK: mov eax, $1
   __asm mov eax, offset gvar ; eax = address of gvar
@@ -236,7 +263,11 @@ void t21() {
     __asm pop ebx
   }
 // CHECK: t21
-// CHECK: call void asm sideeffect inteldialect "push ebx\0A\09mov ebx, $$07H\0A\09pop ebx", "~{ebx},~{esp},~{dirflag},~{fpsr},~{flags}"()
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: push ebx
+// CHECK-SAME: mov ebx, $$07H
+// CHECK-SAME: pop ebx
+// CHECK-SAME: "~{ebx},~{esp},~{dirflag},~{fpsr},~{flags}"()
 }
 
 extern void t22_helper(int x);
@@ -252,9 +283,15 @@ void t22() {
     __asm pop ebx
   }
 // CHECK: t22
-// CHECK: call void asm sideeffect inteldialect "push ebx\0A\09mov ebx, esp", "~{ebx},~{esp},~{dirflag},~{fpsr},~{flags}"()
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: push ebx
+// CHECK-SAME: mov ebx, esp
+// CHECK-SAME: "~{ebx},~{esp},~{dirflag},~{fpsr},~{flags}"()
 // CHECK: call void @t22_helper
-// CHECK: call void asm sideeffect inteldialect "mov esp, ebx\0A\09pop ebx", "~{ebx},~{esp},~{dirflag},~{fpsr},~{flags}"()
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: mov esp, ebx
+// CHECK-SAME: pop ebx
+// CHECK-SAME: "~{ebx},~{esp},~{dirflag},~{fpsr},~{flags}"()
 }
 
 void t23() {
@@ -342,9 +379,9 @@ int *t30()
 {
   int *res;
   __asm lea edi, results
-// CHECK: lea edi, dword ptr $2
+// CHECK: lea edi, $2
   __asm mov res, edi
-// CHECK: mov dword ptr $0, edi
+// CHECK: mov $0, edi
   return res;
 // CHECK: "=*m,={eax},*m,~{edi},~{dirflag},~{fpsr},~{flags}"(i32** %{{.*}}, [2 x i32]* @{{.*}})
 }
@@ -362,7 +399,7 @@ void t32() {
 // CHECK: t32
   int i;
   __asm mov eax, i
-// CHECK: mov eax, dword ptr $0
+// CHECK: mov eax, $0
   __asm mov eax, dword ptr i
 // CHECK: mov eax, dword ptr $1
   __asm mov ax, word ptr i
@@ -376,7 +413,7 @@ void t33() {
 // CHECK: t33
   int i;
   __asm mov eax, [i]
-// CHECK: mov eax, dword ptr $0
+// CHECK: mov eax, $0
   __asm mov eax, dword ptr [i]
 // CHECK: mov eax, dword ptr $1
   __asm mov ax, word ptr [i]
@@ -409,31 +446,31 @@ void t36() {
   int arr[4];
   // Work around PR20368: These should be single line blocks
   __asm { mov eax, 4[arr] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 4[arr + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 8[arr + 4 + 32*2 - 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$72$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$72$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 12[4 + arr] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$16$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$16$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 4[4 + arr + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$12$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$12$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 4[64 + arr + (2*32)] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$132$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$132$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 4[64 + arr - 2*32] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, [arr + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, [arr + 4 + 32*2 - 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$64$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$64$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, [4 + arr] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, [4 + arr + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, [64 + arr + (2*32)] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$128$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$128$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, [64 + arr - 2*32] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
 }
 
 void t37() {
@@ -464,21 +501,21 @@ void t38() {
   int arr[4];
   // Work around PR20368: These should be single line blocks
   __asm { mov eax, 4+4[arr] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, (4+4)[arr + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$12$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$12$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 8*2[arr + 4 + 32*2 - 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$80$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$80$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 12+20[4 + arr] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$36$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$36$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 4*16+4[4 + arr + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$76$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$76$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 4*4[64 + arr + (2*32)] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$144$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$144$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 4*(4-2)[64 + arr - 2*32] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
   __asm { mov eax, 32*(4-2)[arr - 2*32] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$0$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$0$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"([4 x i32]* %{{.*}})
 }
 
 void cpuid() {
@@ -554,7 +591,7 @@ void t42() {
 // CHECK-LABEL: define void @t42
   int flags;
   __asm mov flags, eax
-// CHECK: mov dword ptr $0, eax
+// CHECK: mov $0, eax
 // CHECK: "=*m,~{dirflag},~{fpsr},~{flags}"(i32* %flags)
 }
 
@@ -563,31 +600,31 @@ void t43() {
   C strct;
 // Work around PR20368: These should be single line blocks
  __asm { mov eax, 4[strct.c1] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, 4[strct.c3 + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, 8[strct.c2.a + 4 + 32*2 - 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$72$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$72$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, 12[4 + strct.c2.b] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$16$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$16$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, 4[4 + strct.c4.b2.b + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$12$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$12$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, 4[64 + strct.c1 + (2*32)] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$132$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$132$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, 4[64 + strct.c2.a - 2*32] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, [strct.c4.b1 + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, [strct.c4.b2.a + 4 + 32*2 - 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$64$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$64$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, [4 + strct.c1] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$4$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, [4 + strct.c2.b + 4] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$8$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, [64 + strct.c3 + (2*32)] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $$128$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $$128$0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
   __asm { mov eax, [64 + strct.c4.b2.b - 2*32] }
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
+// CHECK: call void asm sideeffect inteldialect "mov eax, $0", "*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* %{{.*}})
 }
 
 void call_clobber() {
@@ -662,7 +699,7 @@ void mxcsr() {
   __asm fxrstor buf
 }
 // CHECK-LABEL: define void @mxcsr
-// CHECK: call void asm sideeffect inteldialect "fxrstor byte ptr $0", "=*m,~{dirflag},~{fpsr},~{flags}"
+// CHECK: call void asm sideeffect inteldialect "fxrstor $0", "=*m,~{dirflag},~{fpsr},~{flags}"
 
 typedef union _LARGE_INTEGER {
   struct {
@@ -680,7 +717,7 @@ int test_indirect_field(LARGE_INTEGER LargeInteger) {
     __asm mov     eax, LargeInteger.LowPart
 }
 // CHECK-LABEL: define i32 @test_indirect_field(
-// CHECK: call i32 asm sideeffect inteldialect "mov eax, dword ptr $1",
+// CHECK: call i32 asm sideeffect inteldialect "mov eax, $1",
 
 // MS ASM containing labels must not be duplicated (PR23715).
 // CHECK: attributes [[ATTR1]] = {
diff --git a/test/CodeGen/ms-inline-asm.cpp b/test/CodeGen/ms-inline-asm.cpp
index 424c1992cc2c..a435e4b826d8 100644
--- a/test/CodeGen/ms-inline-asm.cpp
+++ b/test/CodeGen/ms-inline-asm.cpp
@@ -14,15 +14,21 @@ struct Foo {
 };
 
 void t1() {
+// CHECK-LABEL: define void @_Z2t1v()
   Foo::ptr = (int *)0xDEADBEEF;
   Foo::Bar::ptr = (int *)0xDEADBEEF;
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: mov eax, $0
+// CHECK-SAME: mov eax, $1
+// CHECK-SAME: mov eax, $2
+// CHECK-SAME: mov eax, dword ptr $3
+// CHECK-SAME: mov eax, dword ptr $4
+// CHECK-SAME: "*m,*m,*m,*m,*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32** @_ZN3Foo3ptrE, i32** @_ZN3Foo3Bar3ptrE, i32** @_ZN3Foo3ptrE, i32** @_ZN3Foo3ptrE, i32** @_ZN3Foo3ptrE)
   __asm mov eax, Foo ::ptr
   __asm mov eax, Foo :: Bar :: ptr
   __asm mov eax, [Foo:: ptr]
   __asm mov eax, dword ptr [Foo :: ptr]
   __asm mov eax, dword ptr [Foo :: ptr]
-// CHECK: @_Z2t1v
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $0\0A\09mov eax, dword ptr $1\0A\09mov eax, dword ptr $2\0A\09mov eax, dword ptr $3\0A\09mov eax, dword ptr $4", "*m,*m,*m,*m,*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32** @_ZN3Foo3ptrE, i32** @_ZN3Foo3Bar3ptrE, i32** @_ZN3Foo3ptrE, i32** @_ZN3Foo3ptrE, i32** @_ZN3Foo3ptrE)
 }
 
 int gvar = 10;
@@ -30,8 +36,11 @@ void t2() {
   int lvar = 10;
   __asm mov eax, offset Foo::ptr
   __asm mov eax, offset Foo::Bar::ptr
-// CHECK: t2
-// CHECK: call void asm sideeffect inteldialect "mov eax, $0\0A\09mov eax, $1", "r,r,~{eax},~{dirflag},~{fpsr},~{flags}"(i32** @_ZN3Foo3ptrE, i32** @_ZN3Foo3Bar3ptrE)
+// CHECK-LABEL: define void @_Z2t2v()
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: mov eax, $0
+// CHECK-SAME: mov eax, $1
+// CHECK-SAME: "r,r,~{eax},~{dirflag},~{fpsr},~{flags}"(i32** @_ZN3Foo3ptrE, i32** @_ZN3Foo3Bar3ptrE)
 }
 
 // CHECK-LABEL: define void @_Z2t3v()
@@ -50,7 +59,20 @@ void t3() {
   __asm mov eax, SIZE Foo::Bar::ptr
   __asm mov eax, SIZE Foo::arr
   __asm mov eax, SIZE Foo::Bar::arr
-// CHECK: call void asm sideeffect inteldialect "mov eax, $$1\0A\09mov eax, $$1\0A\09mov eax, $$4\0A\09mov eax, $$2\0A\09mov eax, $$4\0A\09mov eax, $$4\0A\09mov eax, $$4\0A\09mov eax, $$1\0A\09mov eax, $$4\0A\09mov eax, $$4\0A\09mov eax, $$16\0A\09mov eax, $$2", "~{eax},~{dirflag},~{fpsr},~{flags}"()
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: mov eax, $$1
+// CHECK-SAME: mov eax, $$1
+// CHECK-SAME: mov eax, $$4
+// CHECK-SAME: mov eax, $$2
+// CHECK-SAME: mov eax, $$4
+// CHECK-SAME: mov eax, $$4
+// CHECK-SAME: mov eax, $$4
+// CHECK-SAME: mov eax, $$1
+// CHECK-SAME: mov eax, $$4
+// CHECK-SAME: mov eax, $$4
+// CHECK-SAME: mov eax, $$16
+// CHECK-SAME: mov eax, $$2
+// CHECK-SAME: "~{eax},~{dirflag},~{fpsr},~{flags}"()
 
 }
 
@@ -67,7 +89,10 @@ void T4::test() {
 // CHECK: [[X:%.*]] = getelementptr inbounds [[T4]], [[T4]]* [[THIS]], i32 0, i32 0
   __asm mov eax, x;
   __asm mov y, eax;
-// CHECK: call void asm sideeffect inteldialect "mov eax, dword ptr $1\0A\09mov dword ptr $0, eax", "=*m,*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* @_ZN2T41yE, i32* {{.*}})
+// CHECK: call void asm sideeffect inteldialect
+// CHECK-SAME: mov eax, $1
+// CHECK-SAME: mov $0, eax
+// CHECK-SAME: "=*m,*m,~{eax},~{dirflag},~{fpsr},~{flags}"(i32* @_ZN2T41yE, i32* {{.*}})
 }
 
 template <class T> struct T5 {
@@ -82,7 +107,11 @@ void test5() {
   __asm push y
   __asm call T5<int>::create<float>
   __asm mov x, eax
-  // CHECK: call void asm sideeffect inteldialect "push dword ptr $0\0A\09call dword ptr $2\0A\09mov dword ptr $1, eax", "=*m,=*m,*m,~{esp},~{dirflag},~{fpsr},~{flags}"(i32* %y, i32* %x, i32 (float)* @_ZN2T5IiE6createIfEEiT_)
+  // CHECK: call void asm sideeffect inteldialect
+  // CHECK-SAME: push $0
+  // CHECK-SAME: call dword ptr $2
+  // CHECK-SAME: mov $1, eax
+  // CHECK-SAME: "=*m,=*m,*m,~{esp},~{dirflag},~{fpsr},~{flags}"(i32* %y, i32* %x, i32 (float)* @_ZN2T5IiE6createIfEEiT_)
 }
 
 // Just verify this doesn't emit an error.
@@ -100,7 +129,9 @@ void t7_struct() {
   };
   __asm mov eax, [eax].A.b
   // CHECK-LABEL: define void @_Z9t7_structv
-  // CHECK: call void asm sideeffect inteldialect "mov eax, [eax].4", "~{eax},~{dirflag},~{fpsr},~{flags}"()
+  // CHECK: call void asm sideeffect inteldialect
+  // CHECK-SAME: mov eax, [eax].4
+  // CHECK-SAME: "~{eax},~{dirflag},~{fpsr},~{flags}"()
 }
 
 void t7_typedef() {
@@ -110,7 +141,9 @@ void t7_typedef() {
   } A;
   __asm mov eax, [eax].A.b
   // CHECK-LABEL: define void @_Z10t7_typedefv
-  // CHECK: call void asm sideeffect inteldialect "mov eax, [eax].4", "~{eax},~{dirflag},~{fpsr},~{flags}"()
+  // CHECK: call void asm sideeffect inteldialect
+  // CHECK-SAME: mov eax, [eax].4
+  // CHECK-SAME: "~{eax},~{dirflag},~{fpsr},~{flags}"()
 }
 
 void t7_using() {
@@ -120,20 +153,28 @@ void t7_using() {
   };
   __asm mov eax, [eax].A.b
   // CHECK-LABEL: define void @_Z8t7_usingv
-  // CHECK: call void asm sideeffect inteldialect "mov eax, [eax].4", "~{eax},~{dirflag},~{fpsr},~{flags}"()
+  // CHECK: call void asm sideeffect inteldialect
+  // CHECK-SAME: mov eax, [eax].4
+  // CHECK-SAME: "~{eax},~{dirflag},~{fpsr},~{flags}"()
 }
 
 void t8() {
   __asm some_label:
   // CHECK-LABEL: define void @_Z2t8v()
-  // CHECK: call void asm sideeffect inteldialect "L__MSASMLABEL_.${:uid}__some_label:", "~{dirflag},~{fpsr},~{flags}"()
+  // CHECK: call void asm sideeffect inteldialect
+  // CHECK-SAME: L__MSASMLABEL_.${:uid}__some_label:
+  // CHECK-SAME: "~{dirflag},~{fpsr},~{flags}"()
   struct A {
     static void g() {
       __asm jmp some_label ; This should jump forwards
       __asm some_label:
       __asm nop
       // CHECK-LABEL: define internal void @_ZZ2t8vEN1A1gEv()
-      // CHECK: call void asm sideeffect inteldialect "jmp L__MSASMLABEL_.${:uid}__some_label\0A\09L__MSASMLABEL_.${:uid}__some_label:\0A\09nop", "~{dirflag},~{fpsr},~{flags}"()
+      // CHECK: call void asm sideeffect inteldialect
+      // CHECK-SAME: jmp L__MSASMLABEL_.${:uid}__some_label
+      // CHECK-SAME: L__MSASMLABEL_.${:uid}__some_label:
+      // CHECK-SAME: nop
+      // CHECK-SAME: "~{dirflag},~{fpsr},~{flags}"()
     }
   };
   A::g();
diff --git a/test/CodeGen/thinlto_backend.ll b/test/CodeGen/thinlto_backend.ll
index ac0b3b76ef7d..813bb62c1a29 100644
--- a/test/CodeGen/thinlto_backend.ll
+++ b/test/CodeGen/thinlto_backend.ll
@@ -35,8 +35,12 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 declare void @f2()
+declare i8* @f3()
 
 define void @f1() {
   call void @f2()
+  ; Make sure that the backend can handle undefined references.
+  ; Do an indirect call so that the undefined ref shows up in the combined index.
+  call void bitcast (i8*()* @f3 to void()*)()
   ret void
 }
diff --git a/test/CodeGenCXX/ms-inline-asm-fields.cpp b/test/CodeGenCXX/ms-inline-asm-fields.cpp
index 6f329330bda4..5ee6acf57466 100644
--- a/test/CodeGenCXX/ms-inline-asm-fields.cpp
+++ b/test/CodeGenCXX/ms-inline-asm-fields.cpp
@@ -17,14 +17,14 @@ A a_global;
 extern "C" int test_param_field(A p) {
 // CHECK: define i32 @test_param_field(%struct.A* byval align 4 %p)
 // CHECK: getelementptr inbounds %struct.A, %struct.A* %p, i32 0, i32 0
-// CHECK: call i32 asm sideeffect inteldialect "mov eax, dword ptr $1"
+// CHECK: call i32 asm sideeffect inteldialect "mov eax, $1"
 // CHECK: ret i32
   __asm mov eax, p.a1
 }
 
 extern "C" int test_namespace_global() {
 // CHECK: define i32 @test_namespace_global()
-// CHECK: call i32 asm sideeffect inteldialect "mov eax, dword ptr $1", "{{.*}}"(i32* getelementptr inbounds (%struct.A, %struct.A* @_ZN4asdf8a_globalE, i32 0, i32 2, i32 1))
+// CHECK: call i32 asm sideeffect inteldialect "mov eax, $1", "{{.*}}"(i32* getelementptr inbounds (%struct.A, %struct.A* @_ZN4asdf8a_globalE, i32 0, i32 2, i32 1))
 // CHECK: ret i32
   __asm mov eax, asdf::a_global.a3.b2
 }
diff --git a/test/CodeGenObjC/arc-foreach.m b/test/CodeGenObjC/arc-foreach.m
index e34445704e37..e3b3f1aa5ce4 100644
--- a/test/CodeGenObjC/arc-foreach.m
+++ b/test/CodeGenObjC/arc-foreach.m
@@ -1,5 +1,5 @@
-// RUN: %clang_cc1 -fblocks -fobjc-arc -fobjc-runtime-has-weak -triple x86_64-apple-darwin -emit-llvm %s -o %t-64.s
-// RUN: FileCheck -check-prefix CHECK-LP64 --input-file=%t-64.s %s
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -fblocks -fobjc-arc -fobjc-runtime-has-weak -emit-llvm %s -o - | FileCheck -check-prefix CHECK-LP64 %s
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -O1 -fblocks -fobjc-arc -fobjc-runtime-has-weak -emit-llvm %s -o - | FileCheck -check-prefix CHECK-LP64-OPT %s
 // rdar://9503326
 // rdar://9606600
 
@@ -29,6 +29,11 @@ void test0(NSArray *array) {
 // CHECK-LP64-NEXT: [[BUFFER:%.*]] = alloca [16 x i8*], align 8
 // CHECK-LP64-NEXT: [[BLOCK:%.*]] = alloca [[BLOCK_T:<{.*}>]],
 
+// CHECK-LP64-OPT-LABEL: define void @test0
+// CHECK-LP64-OPT: [[STATE:%.*]] = alloca [[STATE_T:%.*]], align 8
+// CHECK-LP64-OPT-NEXT: [[BUFFER:%.*]] = alloca [16 x i8*], align 8
+// CHECK-LP64-OPT-NEXT: [[BLOCK:%.*]] = alloca [[BLOCK_T:<{.*}>]], align 8
+
 // Initialize 'array'.
 // CHECK-LP64-NEXT: store [[ARRAY_T]]* null, [[ARRAY_T]]** [[ARRAY]]
 // CHECK-LP64-NEXT: [[ZERO:%.*]] = bitcast [[ARRAY_T]]** [[ARRAY]] to i8**
@@ -66,8 +71,12 @@ void test0(NSArray *array) {
 // CHECK-LP64-NEXT: store i8* [[T1]], i8** [[T0]]
 // CHECK-LP64-NEXT: [[BLOCK1:%.*]] = bitcast [[BLOCK_T]]* [[BLOCK]]
 // CHECK-LP64-NEXT: call void @use_block(void ()* [[BLOCK1]])
-// CHECK-LP64-NEXT: [[CAPTURE:%.*]] = load i8*, i8** [[D0]]
-// CHECK-LP64: call void (...) @clang.arc.use(i8* [[CAPTURE]])
+// CHECK-LP64-NEXT: call void @objc_storeStrong(i8** [[D0]], i8* null)
+// CHECK-LP64-NOT:  call void (...) @clang.arc.use(i8* [[CAPTURE]])
+
+// CHECK-LP64-OPT: [[D0:%.*]] = getelementptr inbounds [[BLOCK_T]], [[BLOCK_T]]* [[BLOCK]], i64 0, i32 5
+// CHECK-LP64-OPT: [[CAPTURE:%.*]] = load i8*, i8** [[D0]]
+// CHECK-LP64-OPT: call void (...) @clang.arc.use(i8* [[CAPTURE]])
 
 // CHECK-LP64:      [[T0:%.*]] = load i8*, i8** @OBJC_SELECTOR_REFERENCES_
 // CHECK-LP64-NEXT: [[T1:%.*]] = bitcast [[ARRAY_T]]* [[SAVED_ARRAY]] to i8*
@@ -200,15 +209,24 @@ NSArray *array4;
 // CHECK-LP64:         [[T0:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, [[TY]]* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, [[TY]]* }>* [[BLOCK]], i32 0, i32 5
 // CHECK-LP64:         [[BC:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, [[TY]]* }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, [[TY]]* }>* [[BLOCK]], i32 0, i32 5
 // CHECK-LP64:         [[T1:%.*]] = load [[TY]]*, [[TY]]** [[SELF_ADDR]]
-// CHECK-LP64:         store [[TY]]* [[T1]], [[TY]]** [[BC]]
+// CHECK-LP64:         store [[TY]]* [[T1]], [[TY]]** [[BC]], align 8
 
-// CHECK-LP64:         [[T5:%.*]] = load [[TY]]*, [[TY]]** [[T0]]
-// CHECK-LP64:         call void (...) @clang.arc.use([[TY]]* [[T5]])
+// CHECK-LP64-OPT-LABEL: define internal void @"\01-[I1 foo2]"(
+// CHECK-LP64-OPT: [[TY:%.*]]* %self
+// CHECK-LP64-OPT: [[BLOCK:%.*]] = alloca [[BLOCK_T:<{.*}>]],
+// CHECK-LP64-OPT: [[T0:%.*]] = getelementptr inbounds [[BLOCK_T]], [[BLOCK_T]]* [[BLOCK]], i64 0, i32 5
+
+// CHECK-LP64:         [[T5:%.*]] = bitcast [[TY]]** [[T0]] to i8**
+// CHECK-LP64:         call void @objc_storeStrong(i8** [[T5]], i8* null)
+// CHECK-LP64-NOT:     call void (...) @clang.arc.use([[TY]]* [[T5]])
 // CHECK-LP64:         switch i32 {{%.*}}, label %[[UNREACHABLE:.*]] [
 // CHECK-LP64-NEXT:      i32 0, label %[[CLEANUP_CONT:.*]]
 // CHECK-LP64-NEXT:      i32 2, label %[[FORCOLL_END:.*]]
 // CHECK-LP64-NEXT:    ]
 
+// CHECK-LP64-OPT: [[T5:%.*]] = load [[TY]]*, [[TY]]** [[T0]]
+// CHECK-LP64-OPT: call void (...) @clang.arc.use([[TY]]* [[T5]])
+
 // CHECK-LP64:       {{^|:}}[[CLEANUP_CONT]]
 // CHECK-LP64-NEXT:    br label %[[FORCOLL_END]]
 
diff --git a/test/CodeGenOpenCL/kernel-attributes.cl b/test/CodeGenOpenCL/kernel-attributes.cl
index 4a116dd08551..e61a75f7b537 100644
--- a/test/CodeGenOpenCL/kernel-attributes.cl
+++ b/test/CodeGenOpenCL/kernel-attributes.cl
@@ -8,7 +8,11 @@ kernel  __attribute__((vec_type_hint(int))) __attribute__((reqd_work_group_size(
 kernel __attribute__((vec_type_hint(uint4))) __attribute__((work_group_size_hint(8,16,32))) void kernel2(int a) {}
 // CHECK: define void @kernel2(i32 {{[^%]*}}%a) {{[^{]+}} !vec_type_hint ![[MD3:[0-9]+]] !work_group_size_hint ![[MD4:[0-9]+]]
 
+kernel __attribute__((intel_reqd_sub_group_size(8))) void kernel3(int a) {}
+// CHECK: define void @kernel3(i32 {{[^%]*}}%a) {{[^{]+}} !intel_reqd_sub_group_size ![[MD5:[0-9]+]]
+
 // CHECK: [[MD1]] = !{i32 undef, i32 1}
 // CHECK: [[MD2]] = !{i32 1, i32 2, i32 4}
 // CHECK: [[MD3]] = !{<4 x i32> undef, i32 0}
 // CHECK: [[MD4]] = !{i32 8, i32 16, i32 32}
+// CHECK: [[MD5]] = !{i32 8}
diff --git a/test/Driver/android-ndk-standalone.cpp b/test/Driver/android-ndk-standalone.cpp
index 7fe6d3c3c2ca..86ab85269f76 100644
--- a/test/Driver/android-ndk-standalone.cpp
+++ b/test/Driver/android-ndk-standalone.cpp
@@ -172,6 +172,20 @@
 // CHECK-ARMV7THUMB-NOT: "-L{{.*}}/lib/gcc/arm-linux-androideabi/4.9/../{{[^ ]*}}/lib/armv7-a"
 // CHECK-ARMV7THUMB-NOT: "-L{{.*}}/lib/gcc/arm-linux-androideabi/4.9/../{{[^ ]*}}/lib"
 // CHECK-ARMV7THUMB: "-L{{.*}}/sysroot/usr/lib"
+
+// RUN: %clang -no-canonical-prefixes %s -### -o %t.o 2>&1 \
+// RUN:     -target arm-linux-androideabi -stdlib=libstdc++ \
+// RUN:     -march=armv7-a -mthumb \
+// RUN:     -B%S/Inputs/basic_android_ndk_tree \
+// RUN:     --sysroot=%S/Inputs/basic_android_ndk_tree/sysroot \
+// RUN:     -print-multi-lib \
+// RUN:   | FileCheck  --check-prefix=CHECK-ARM-MULTILIBS %s
+
+// CHECK-ARM-MULTILIBS:      thumb;@mthumb
+// CHECK-ARM-MULTILIBS-NEXT: armv7-a;@march=armv7-a
+// CHECK-ARM-MULTILIBS-NEXT: armv7-a/thumb;@march=armv7-a@mthumb
+// CHECK-ARM-MULTILIBS-NEXT: .;
+
 //
 // RUN: %clang -no-canonical-prefixes %s -### -o %t.o 2>&1 \
 // RUN:     -target armv7a-none-linux-androideabi -stdlib=libstdc++ \
diff --git a/test/Driver/darwin-version.c b/test/Driver/darwin-version.c
index 009f8483a000..8f08bb9dec4a 100644
--- a/test/Driver/darwin-version.c
+++ b/test/Driver/darwin-version.c
@@ -29,9 +29,13 @@
 // RUN:   FileCheck --check-prefix=CHECK-VERSION-OSX10 %s
 // RUN: %clang -target x86_64-apple-macosx -mmacosx-version-min=10.10 -c %s -### 2>&1 | \
 // RUN:   FileCheck --check-prefix=CHECK-VERSION-OSX10 %s
+// RUN: %clang -target x86_64-apple-macosx -mmacos-version-min=10.10 -c %s -### 2>&1 | \
+// RUN:   FileCheck --check-prefix=CHECK-VERSION-OSX10 %s
 // CHECK-VERSION-OSX10: "x86_64-apple-macosx10.10.0"
 // RUN: %clang -target x86_64-apple-macosx -mmacosx-version-min= -c %s -### 2>&1 | \
 // RUN:   FileCheck --check-prefix=CHECK-VERSION-MISSING %s
+// RUN: %clang -target x86_64-apple-macosx -mmacos-version-min= -c %s -### 2>&1 | \
+// RUN:   FileCheck --check-prefix=CHECK-VERSION-MISSING %s
 // CHECK-VERSION-MISSING: invalid version number
 // RUN: %clang -target armv7k-apple-darwin -mwatchos-version-min=2.0 -c %s -### 2>&1 | \
 // RUN:   FileCheck --check-prefix=CHECK-VERSION-WATCHOS20 %s
diff --git a/test/Driver/fsanitize-coverage.c b/test/Driver/fsanitize-coverage.c
index 22c26be99b69..cf0941477bba 100644
--- a/test/Driver/fsanitize-coverage.c
+++ b/test/Driver/fsanitize-coverage.c
@@ -80,6 +80,10 @@
 // CHECK-EXTEND-LEGACY: -fsanitize-coverage-type=1
 // CHECK-EXTEND-LEGACY: -fsanitize-coverage-trace-cmp
 
+// RUN: %clang -target x86_64-linux-gnu -fsanitize-coverage=no-prune,trace-pc %s -### 2>&1 | FileCheck %s --check-prefix=CHECK_NOPRUNE
+// RUN: %clang -target x86_64-linux-gnu -fsanitize-coverage=no-prune,func,trace-pc-guard %s -### 2>&1 | FileCheck %s --check-prefix=CHECK_NOPRUNE
+// CHECK_NOPRUNE: -fsanitize-coverage-no-prune
+
 // RUN: %clang_cl --target=i386-pc-win32 -fsanitize=address -fsanitize-coverage=func,trace-pc-guard -c -### -- %s 2>&1 | FileCheck %s -check-prefix=CLANG-CL-COVERAGE
 // CLANG-CL-COVERAGE-NOT: error:
 // CLANG-CL-COVERAGE-NOT: warning:
diff --git a/test/Driver/windows-cross.c b/test/Driver/windows-cross.c
index de6fcba7a504..90fefbadfea1 100644
--- a/test/Driver/windows-cross.c
+++ b/test/Driver/windows-cross.c
@@ -1,12 +1,17 @@
-// RUN: %clang -### -target armv7-windows-itanium --sysroot %S/Inputs/Windows/ARM/8.1 -B %S/Inputs/Windows/ARM/8.1/usr/bin -fuse-ld=ld -stdlib=libstdc++ -rtlib=platform -o /dev/null %s 2>&1 \
-// RUN:   | FileCheck %s --check-prefix CHECK-BASIC
+// RUN: %clang -### --driver-mode=g++ -target armv7-windows-itanium --sysroot %S/Inputs/Windows/ARM/8.1 -B %S/Inputs/Windows/ARM/8.1/usr/bin -fuse-ld=ld -stdlib=libstdc++ -rtlib=platform -o /dev/null %s 2>&1 \
+// RUN:   | FileCheck %s --check-prefix CHECK-BASIC-LIBSTDCXX
 
-// CHECK-BASIC: armv7-windows-itanium-ld" "--sysroot={{.*}}/Inputs/Windows/ARM/8.1" "-m" "thumb2pe" "-Bdynamic" "--entry" "mainCRTStartup" "--allow-multiple-definition" "-o" "{{[^"]*}}" "-L{{.*}}/Inputs/Windows/ARM/8.1/usr/lib" "-L{{.*}}/Inputs/Windows/ARM/8.1/usr/lib/gcc" "{{.*}}.o" "-lmsvcrt" "-lgcc" "--as-needed" "-lgcc_s" "--no-as-needed"
+// CHECK-BASIC-LIBSTDCXX: armv7-windows-itanium-ld" "--sysroot={{.*}}/Inputs/Windows/ARM/8.1" "-m" "thumb2pe" "-Bdynamic" "--entry" "mainCRTStartup" "--allow-multiple-definition" "-o" "{{[^"]*}}" "-L{{.*}}/Inputs/Windows/ARM/8.1/usr/lib" "-L{{.*}}/Inputs/Windows/ARM/8.1/usr/lib/gcc" "{{.*}}.o" "-lstdc++" "-lmingw32" "-lmingwex" "-lgcc" "-lmoldname" "-lmingw32" "-lmsvcrt" "-lgcc_s" "-lgcc"
+
+// RUN: %clang -### -target armv7-windows-itanium --sysroot %S/Inputs/Windows/ARM/8.1 -B %S/Inputs/Windows/ARM/8.1/usr/bin -fuse-ld=ld -stdlib=libstdc++ -rtlib=compiler-rt -o /dev/null %s 2>&1 \
+// RUN:   | FileCheck %s --check-prefix CHECK-BASIC-LIBCXX
+
+// CHECK-BASIC-LIBCXX: armv7-windows-itanium-ld" "--sysroot={{.*}}/Inputs/Windows/ARM/8.1" "-m" "thumb2pe" "-Bdynamic" "--entry" "mainCRTStartup" "--allow-multiple-definition" "-o" "{{[^"]*}}" "{{[^"]*}}.o" "-lmsvcrt"
 
 // RUN: %clang -### -target armv7-windows-itanium --sysroot %s/Inputs/Windows/ARM/8.1 -B %S/Inputs/Windows/ARM/8.1/usr/bin -fuse-ld=ld -rtlib=compiler-rt -stdlib=libstdc++ -o /dev/null %s 2>&1 \
 // RUN:   | FileCheck %s --check-prefix CHECK-RTLIB
 
-// CHECK-RTLIB: armv7-windows-itanium-ld" "--sysroot={{.*}}/Inputs/Windows/ARM/8.1" "-m" "thumb2pe" "-Bdynamic" "--entry" "mainCRTStartup" "--allow-multiple-definition" "-o" "{{[^"]*}}" "-L{{.*}}/Inputs/Windows/ARM/8.1/usr/lib" "-L{{.*}}/Inputs/Windows/ARM/8.1/usr/lib/gcc" "{{.*}}.o" "-lmsvcrt" "{{.*[\\/]}}clang_rt.builtins-arm.lib"
+// CHECK-RTLIB: armv7-windows-itanium-ld" "--sysroot={{.*}}/Inputs/Windows/ARM/8.1" "-m" "thumb2pe" "-Bdynamic" "--entry" "mainCRTStartup" "--allow-multiple-definition" "-o" "{{[^"]*}}" "{{.*}}.o" "-lmsvcrt" "{{.*[\\/]}}clang_rt.builtins-arm.lib"
 
 // RUN: %clang -### -target armv7-windows-itanium --sysroot %S/Inputs/Windows/ARM/8.1 -B %S/Inputs/Windows/ARM/8.1/usr/bin -fuse-ld=ld -rtlib=compiler-rt -stdlib=libc++ -o /dev/null %s 2>&1 \
 // RUN:   | FileCheck %s --check-prefix CHECK-C-LIBCXX
diff --git a/test/FixIt/fixit-availability.c b/test/FixIt/fixit-availability.c
new file mode 100644
index 000000000000..fa641b4b98c6
--- /dev/null
+++ b/test/FixIt/fixit-availability.c
@@ -0,0 +1,10 @@
+// RUN: %clang_cc1 -fsyntax-only -Wunguarded-availability -fdiagnostics-parseable-fixits -triple x86_64-apple-darwin9 %s 2>&1 | FileCheck %s
+
+__attribute__((availability(macos, introduced=10.12)))
+int function(void);
+
+void use() {
+  function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (__builtin_available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:14-[[@LINE-2]]:14}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+}
diff --git a/test/FixIt/fixit-availability.mm b/test/FixIt/fixit-availability.mm
new file mode 100644
index 000000000000..6bf8f49ddc0d
--- /dev/null
+++ b/test/FixIt/fixit-availability.mm
@@ -0,0 +1,111 @@
+// RUN: %clang_cc1 -fsyntax-only -Wunguarded-availability -fdiagnostics-parseable-fixits -triple x86_64-apple-darwin9 %s 2>&1 | FileCheck %s
+
+__attribute__((availability(macos, introduced=10.12)))
+int function(void);
+
+void anotherFunction(int function);
+
+int use() {
+  function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:14-[[@LINE-2]]:14}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+  int y = function(), x = 0;
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:29-[[@LINE-2]]:29}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+  x += function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:19-[[@LINE-2]]:19}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+  if (1) {
+    x = function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:5-[[@LINE-1]]:5}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:20-[[@LINE-2]]:20}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+  }
+  anotherFunction(function());
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:31-[[@LINE-2]]:31}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+  if (function()) {
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE+1]]:4-[[@LINE+1]]:4}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+  }
+  while (function())
+    // CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+    // CHECK-NEXT: fix-it:{{.*}}:{[[@LINE+1]]:6-[[@LINE+1]]:6}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+    ;
+  do
+    function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:5-[[@LINE-1]]:5}:"if (@available(macos 10.12, *)) {\n        "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:16-[[@LINE-2]]:16}:"\n    } else {\n        // Fallback on earlier versions\n    }"
+  while (1);
+  for (int i = 0; i < 10; ++i)
+    function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:5-[[@LINE-1]]:5}:"if (@available(macos 10.12, *)) {\n        "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:16-[[@LINE-2]]:16}:"\n    } else {\n        // Fallback on earlier versions\n    }"
+  switch (x) {
+  case 0:
+    function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:5-[[@LINE-1]]:5}:"if (@available(macos 10.12, *)) {\n        "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:16-[[@LINE-2]]:16}:"\n    } else {\n        // Fallback on earlier versions\n    }"
+  case 2:
+    anotherFunction(1);
+    function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:5-[[@LINE-1]]:5}:"if (@available(macos 10.12, *)) {\n        "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:16-[[@LINE-2]]:16}:"\n    } else {\n        // Fallback on earlier versions\n    }"
+    break;
+  default:
+    function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:5-[[@LINE-1]]:5}:"if (@available(macos 10.12, *)) {\n        "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:16-[[@LINE-2]]:16}:"\n    } else {\n        // Fallback on earlier versions\n    }"
+    break;
+  }
+  return function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:21-[[@LINE-2]]:21}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+}
+
+#define MYFUNCTION function
+
+#define MACRO_ARGUMENT(X) X
+#define MACRO_ARGUMENT_SEMI(X) X;
+#define MACRO_ARGUMENT_2(X) if (1) X;
+
+#define INNER_MACRO if (1) MACRO_ARGUMENT(function()); else ;
+
+void useInMacros() {
+  MYFUNCTION();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:16-[[@LINE-2]]:16}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+
+  MACRO_ARGUMENT_SEMI(function())
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:34-[[@LINE-2]]:34}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+  MACRO_ARGUMENT(function());
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:30-[[@LINE-2]]:30}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+  MACRO_ARGUMENT_2(function());
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:32-[[@LINE-2]]:32}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+
+  INNER_MACRO
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:14-[[@LINE-2]]:14}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+}
+
+void wrapDeclStmtUses() {
+  int x = 0, y = function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:3-[[@LINE-1]]:3}:"if (@available(macos 10.12, *)) {\n      "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE+13]]:22-[[@LINE+13]]:22}:"\n  } else {\n      // Fallback on earlier versions\n  }"
+  {
+    int z = function();
+    if (z) {
+
+    }
+// CHECK: fix-it:{{.*}}:{[[@LINE-4]]:5-[[@LINE-4]]:5}:"if (@available(macos 10.12, *)) {\n        "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:6-[[@LINE-2]]:6}:"\n    } else {\n        // Fallback on earlier versions\n    }"
+  }
+  if (y)
+    int z = function();
+// CHECK: fix-it:{{.*}}:{[[@LINE-1]]:5-[[@LINE-1]]:5}:"if (@available(macos 10.12, *)) {\n        "
+// CHECK-NEXT: fix-it:{{.*}}:{[[@LINE-2]]:24-[[@LINE-2]]:24}:"\n    } else {\n        // Fallback on earlier versions\n    }"
+  anotherFunction(y);
+  anotherFunction(x);
+}
diff --git a/test/Index/Core/index-source.cpp b/test/Index/Core/index-source.cpp
index 7bb366c53611..6f902610e673 100644
--- a/test/Index/Core/index-source.cpp
+++ b/test/Index/Core/index-source.cpp
@@ -139,13 +139,13 @@ class PseudoOverridesInSpecializations {
 template<>
 class PseudoOverridesInSpecializations<double, int> {
   void function() { }
-// CHECK: [[@LINE-1]]:8 | instance-method/C++ | function | c:@S@PseudoOverridesInSpecializations>#d#I@F@function# | __ZN32PseudoOverridesInSpecializationsIdiE8functionEv | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:8 | instance-method/C++ | function | c:@S@PseudoOverridesInSpecializations>#d#I@F@function# | __ZN32PseudoOverridesInSpecializationsIdiE8functionEv | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | function | c:@ST>2#T#T@PseudoOverridesInSpecializations@F@function#
+// CHECK-NEXT: RelSpecialization | function | c:@ST>2#T#T@PseudoOverridesInSpecializations@F@function#
 
   void staticFunction() { }
 // CHECK: [[@LINE-1]]:8 | instance-method/C++ | staticFunction | c:@S@PseudoOverridesInSpecializations>#d#I@F@staticFunction# | __ZN32PseudoOverridesInSpecializationsIdiE14staticFunctionEv | Def,RelChild | rel: 1
-// CHECK-NOT: RelOver
+// CHECK-NOT: RelSpecialization
 
   int notOverridingField = 0;
 
@@ -153,57 +153,56 @@ class PseudoOverridesInSpecializations<double, int> {
   int checLabelBreak = 0;
 
   int field = 0;
-// CHECK: [[@LINE-1]]:7 | field/C++ | field | c:@S@PseudoOverridesInSpecializations>#d#I@FI@field | <no-cgname> | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:7 | field/C++ | field | c:@S@PseudoOverridesInSpecializations>#d#I@FI@field | <no-cgname> | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | field | c:@ST>2#T#T@PseudoOverridesInSpecializations@FI@field
+// CHECK-NEXT: RelSpecialization | field | c:@ST>2#T#T@PseudoOverridesInSpecializations@FI@field
 
   static double variable;
-// CHECK: [[@LINE-1]]:17 | static-property/C++ | variable | c:@S@PseudoOverridesInSpecializations>#d#I@variable | __ZN32PseudoOverridesInSpecializationsIdiE8variableE | Decl,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:17 | static-property/C++ | variable | c:@S@PseudoOverridesInSpecializations>#d#I@variable | __ZN32PseudoOverridesInSpecializationsIdiE8variableE | Decl,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | variable | c:@ST>2#T#T@PseudoOverridesInSpecializations@variable
+// CHECK-NEXT: RelSpecialization | variable | c:@ST>2#T#T@PseudoOverridesInSpecializations@variable
 
   typedef double TypeDef;
-// CHECK: [[@LINE-1]]:18 | type-alias/C | TypeDef | c:index-source.cpp@S@PseudoOverridesInSpecializations>#d#I@T@TypeDef | <no-cgname> | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:18 | type-alias/C | TypeDef | c:index-source.cpp@S@PseudoOverridesInSpecializations>#d#I@T@TypeDef | <no-cgname> | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | TypeDef | c:index-source.cpp@ST>2#T#T@PseudoOverridesInSpecializations@T@TypeDef
+// CHECK-NEXT: RelSpecialization | TypeDef | c:index-source.cpp@ST>2#T#T@PseudoOverridesInSpecializations@T@TypeDef
 
   using TypeAlias = int;
-// CHECK: [[@LINE-1]]:9 | type-alias/C++ | TypeAlias | c:@S@PseudoOverridesInSpecializations>#d#I@TypeAlias | <no-cgname> | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:9 | type-alias/C++ | TypeAlias | c:@S@PseudoOverridesInSpecializations>#d#I@TypeAlias | <no-cgname> | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | TypeAlias | c:@ST>2#T#T@PseudoOverridesInSpecializations@TypeAlias
+// CHECK-NEXT: RelSpecialization | TypeAlias | c:@ST>2#T#T@PseudoOverridesInSpecializations@TypeAlias
 
   enum anEnum { };
-// CHECK: [[@LINE-1]]:8 | enum/C | anEnum | c:@S@PseudoOverridesInSpecializations>#d#I@E@anEnum | <no-cgname> | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:8 | enum/C | anEnum | c:@S@PseudoOverridesInSpecializations>#d#I@E@anEnum | <no-cgname> | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | anEnum | c:@ST>2#T#T@PseudoOverridesInSpecializations@E@anEnum
+// CHECK-NEXT: RelSpecialization | anEnum | c:@ST>2#T#T@PseudoOverridesInSpecializations@E@anEnum
   class Struct { };
-// CHECK: [[@LINE-1]]:9 | class/C++ | Struct | c:@S@PseudoOverridesInSpecializations>#d#I@S@Struct | <no-cgname> | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:9 | class/C++ | Struct | c:@S@PseudoOverridesInSpecializations>#d#I@S@Struct | <no-cgname> | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | Struct | c:@ST>2#T#T@PseudoOverridesInSpecializations@S@Struct
+// CHECK-NEXT: RelSpecialization | Struct | c:@ST>2#T#T@PseudoOverridesInSpecializations@S@Struct
   union Union { };
-// CHECK: [[@LINE-1]]:9 | union/C | Union | c:@S@PseudoOverridesInSpecializations>#d#I@U@Union | <no-cgname> | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:9 | union/C | Union | c:@S@PseudoOverridesInSpecializations>#d#I@U@Union | <no-cgname> | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | Union | c:@ST>2#T#T@PseudoOverridesInSpecializations@U@Union
+// CHECK-NEXT: RelSpecialization | Union | c:@ST>2#T#T@PseudoOverridesInSpecializations@U@Union
 
   struct TypealiasOrRecord { };
-// CHECK: [[@LINE-1]]:10 | struct/C | TypealiasOrRecord | c:@S@PseudoOverridesInSpecializations>#d#I@S@TypealiasOrRecord | <no-cgname> | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:10 | struct/C | TypealiasOrRecord | c:@S@PseudoOverridesInSpecializations>#d#I@S@TypealiasOrRecord | <no-cgname> | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | TypealiasOrRecord | c:@ST>2#T#T@PseudoOverridesInSpecializations@TypealiasOrRecord
+// CHECK-NEXT: RelSpecialization | TypealiasOrRecord | c:@ST>2#T#T@PseudoOverridesInSpecializations@TypealiasOrRecord
 
   template<typename U> struct InnerTemplate { };
-// CHECK: [[@LINE-1]]:31 | struct(Gen)/C++ | InnerTemplate | c:@S@PseudoOverridesInSpecializations>#d#I@ST>1#T@InnerTemplate | <no-cgname> | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:31 | struct(Gen)/C++ | InnerTemplate | c:@S@PseudoOverridesInSpecializations>#d#I@ST>1#T@InnerTemplate | <no-cgname> | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | InnerTemplate | c:@ST>2#T#T@PseudoOverridesInSpecializations@ST>1#T@InnerTemplate
+// CHECK-NEXT: RelSpecialization | InnerTemplate | c:@ST>2#T#T@PseudoOverridesInSpecializations@ST>1#T@InnerTemplate
   template<typename U> struct InnerTemplate <U*> { };
-// CHECK-NOT: RelOver
 };
 
 template<typename S>
 class PseudoOverridesInSpecializations<float, S> {
   typedef float TypealiasOrRecord;
-// CHECK: [[@LINE-1]]:17 | type-alias/C | TypealiasOrRecord | c:index-source.cpp@SP>1#T@PseudoOverridesInSpecializations>#f#t0.0@T@TypealiasOrRecord | <no-cgname> | Def,RelChild,RelOver,RelSpecialization | rel: 2
+// CHECK: [[@LINE-1]]:17 | type-alias/C | TypealiasOrRecord | c:index-source.cpp@SP>1#T@PseudoOverridesInSpecializations>#f#t0.0@T@TypealiasOrRecord | <no-cgname> | Def,RelChild,RelSpecialization | rel: 2
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | TypealiasOrRecord | c:@ST>2#T#T@PseudoOverridesInSpecializations@TypealiasOrRecord
+// CHECK-NEXT: RelSpecialization | TypealiasOrRecord | c:@ST>2#T#T@PseudoOverridesInSpecializations@TypealiasOrRecord
 };
 
 template<typename T, typename U>
@@ -215,10 +214,10 @@ class ConflictingPseudoOverridesInSpecialization {
 template<typename T>
 class ConflictingPseudoOverridesInSpecialization<int, T> {
   void foo(T x);
-// CHECK: [[@LINE-1]]:8 | instance-method/C++ | foo | c:@SP>1#T@ConflictingPseudoOverridesInSpecialization>#I#t0.0@F@foo#S0_# | <no-cgname> | Decl,RelChild,RelOver,RelSpecialization | rel: 3
+// CHECK: [[@LINE-1]]:8 | instance-method/C++ | foo | c:@SP>1#T@ConflictingPseudoOverridesInSpecialization>#I#t0.0@F@foo#S0_# | <no-cgname> | Decl,RelChild,RelSpecialization | rel: 3
 // CHECK-NEXT: RelChild
-// CHECK-NEXT: RelOver,RelSpecialization | foo | c:@ST>2#T#T@ConflictingPseudoOverridesInSpecialization@F@foo#t0.0#
-// CHECK-NEXT: RelOver,RelSpecialization | foo | c:@ST>2#T#T@ConflictingPseudoOverridesInSpecialization@F@foo#t0.1#
+// CHECK-NEXT: RelSpecialization | foo | c:@ST>2#T#T@ConflictingPseudoOverridesInSpecialization@F@foo#t0.0#
+// CHECK-NEXT: RelSpecialization | foo | c:@ST>2#T#T@ConflictingPseudoOverridesInSpecialization@F@foo#t0.1#
 };
 
 template<typename T, typename U, int x>
diff --git a/test/Index/KeepGoingWithLotsOfErrors.mm b/test/Index/KeepGoingWithLotsOfErrors.mm
new file mode 100644
index 000000000000..078ea6e2ea14
--- /dev/null
+++ b/test/Index/KeepGoingWithLotsOfErrors.mm
@@ -0,0 +1,29 @@
+// RUN: env CINDEXTEST_KEEP_GOING=1 c-index-test -code-completion-at=%s:25:1 %s
+// Shouldn't crash!
+// This is the minimized test that triggered an infinite recursion:
+
++(BOOL) onEntity {
+}
+
+-(const Object &) a_200 {
+}
+
+-(int) struct {
+}
+
+-(int) bar {
+}
+
+-(int) part {
+}
+
++(some_type_t) piece {
+}
+
++(void) z_Z_42 {
+  ([self onEntity: [] { 42];
+  } class: ^ {  }
+];
+  [super];
+  BOOL struct;
+}
diff --git a/test/Misc/pragma-attribute-supported-attributes-list.test b/test/Misc/pragma-attribute-supported-attributes-list.test
index f6a7ce2869ac..0db17bdf4026 100644
--- a/test/Misc/pragma-attribute-supported-attributes-list.test
+++ b/test/Misc/pragma-attribute-supported-attributes-list.test
@@ -2,7 +2,7 @@
 
 // The number of supported attributes should never go down!
 
-// CHECK: #pragma clang attribute supports 59 attributes:
+// CHECK: #pragma clang attribute supports 60 attributes:
 // CHECK-NEXT: AMDGPUFlatWorkGroupSize (SubjectMatchRule_function)
 // CHECK-NEXT: AMDGPUNumSGPR (SubjectMatchRule_function)
 // CHECK-NEXT: AMDGPUNumVGPR (SubjectMatchRule_function)
@@ -42,6 +42,7 @@
 // CHECK-NEXT: ObjCRuntimeName (SubjectMatchRule_objc_interface, SubjectMatchRule_objc_protocol)
 // CHECK-NEXT: ObjCRuntimeVisible (SubjectMatchRule_objc_interface)
 // CHECK-NEXT: ObjCSubclassingRestricted (SubjectMatchRule_objc_interface)
+// CHECK-NEXT: OpenCLIntelReqdSubGroupSize (SubjectMatchRule_function)
 // CHECK-NEXT: OpenCLNoSVM (SubjectMatchRule_variable)
 // CHECK-NEXT: OptimizeNone (SubjectMatchRule_function, SubjectMatchRule_objc_method)
 // CHECK-NEXT: Overloadable (SubjectMatchRule_function)
diff --git a/test/Modules/Inputs/preprocess/file2.h b/test/Modules/Inputs/preprocess/file2.h
new file mode 100644
index 000000000000..04bf796d1e9e
--- /dev/null
+++ b/test/Modules/Inputs/preprocess/file2.h
@@ -0,0 +1,2 @@
+#include "file.h"
+extern int file2;
diff --git a/test/Modules/Inputs/preprocess/module.modulemap b/test/Modules/Inputs/preprocess/module.modulemap
index a5c5b61dddc5..943435a953d0 100644
--- a/test/Modules/Inputs/preprocess/module.modulemap
+++ b/test/Modules/Inputs/preprocess/module.modulemap
@@ -1,2 +1,2 @@
 module fwd { header "fwd.h" export * }
-module file { header "file.h" export * }
+module file { header "file.h" header "file2.h" export * }
diff --git a/test/Modules/preprocess-module.cpp b/test/Modules/preprocess-module.cpp
index 99fe8cf8c30b..a3b789238388 100644
--- a/test/Modules/preprocess-module.cpp
+++ b/test/Modules/preprocess-module.cpp
@@ -1,12 +1,101 @@
 // RUN: rm -rf %t
+// RUN: mkdir %t
 
 // RUN: not %clang_cc1 -fmodules -fmodule-name=file -I%S/Inputs/preprocess -x c++-module-map %S/Inputs/preprocess/module.modulemap -E 2>&1 | FileCheck %s --check-prefix=MISSING-FWD
 // MISSING-FWD: module 'fwd' is needed
 
-// RUN: %clang_cc1 -fmodules -fmodule-name=file -fmodules-cache-path=%t -I%S/Inputs/preprocess -x c++-module-map %S/Inputs/preprocess/module.modulemap -E | FileCheck %s
+// RUN: %clang_cc1 -fmodules -fmodule-name=fwd -I%S/Inputs/preprocess -x c++-module-map %S/Inputs/preprocess/module.modulemap -emit-module -o %t/fwd.pcm
+
+// Check that we can preprocess modules, and get the expected output.
+// RUN: %clang_cc1 -fmodules -fmodule-name=file -fmodule-file=%t/fwd.pcm -I%S/Inputs/preprocess -x c++-module-map %S/Inputs/preprocess/module.modulemap -E -o %t/no-rewrite.ii
+// RUN: %clang_cc1 -fmodules -fmodule-name=file -fmodule-file=%t/fwd.pcm -I%S/Inputs/preprocess -x c++-module-map %S/Inputs/preprocess/module.modulemap -E -frewrite-includes -o %t/rewrite.ii
+//
+// RUN: FileCheck %s --input-file %t/no-rewrite.ii --check-prefix=CHECK --check-prefix=NO-REWRITE
+// RUN: FileCheck %s --input-file %t/rewrite.ii    --check-prefix=CHECK --check-prefix=REWRITE
+
+// Check that we can build a module from the preprocessed output.
+// FIXME: For now, we need the headers to exist.
+// RUN: touch %t/file.h %t/file2.h
+// RUN: %clang_cc1 -fmodules -fmodule-name=file -fmodule-file=%t/fwd.pcm -x c++-module-map-cpp-output %t/no-rewrite.ii -emit-module -o %t/no-rewrite.pcm
+// RUN: %clang_cc1 -fmodules -fmodule-name=file -fmodule-file=%t/fwd.pcm -x c++-module-map-cpp-output %t/rewrite.ii -emit-module -o %t/rewrite.pcm
+
+// Check the module we built works.
+// RUN: %clang_cc1 -fmodules -fmodule-file=%t/no-rewrite.pcm %s -verify
+// RUN: %clang_cc1 -fmodules -fmodule-file=%t/rewrite.pcm %s -verify
+
+
+// == module map
+// CHECK: # 1 "{{.*}}module.modulemap"
+// CHECK: module file {
+// CHECK:   header "file.h"
+// CHECK:   header "file2.h"
+// CHECK: }
+
+// == file.h
 // CHECK: # 1 "<module-includes>"
+// REWRITE: #if 0
+// REWRITE: #include "file.h"
+// REWRITE: #endif
+//
+// FIXME: It would be preferable to consistently put the module begin/end in
+// the same file, but the relative ordering of PP callbacks and module
+// begin/end tokens makes that difficult.
+//
+// REWRITE: #pragma clang module begin file
 // CHECK: # 1 "{{.*}}file.h" 1
+// NO-REWRITE: #pragma clang module begin file
+// NO-REWRITE: # 1 "{{.*}}file.h"{{$}}
+//
 // CHECK: struct __FILE;
-// CHECK: #pragma clang module import fwd /* clang -E: implicit import for #include "fwd.h" */
+// CHECK: #pragma clang module import fwd /* clang {{-E|-frewrite-includes}}: implicit import
 // CHECK: typedef struct __FILE FILE;
+//
+// REWRITE: #pragma clang module end
 // CHECK: # 2 "<module-includes>" 2
+// NO-REWRITE: #pragma clang module end
+
+// == file2.h
+// REWRITE: #if 0
+// REWRITE: #include "file2.h"
+// REWRITE: #endif
+//
+// REWRITE: #pragma clang module begin file
+// CHECK: # 1 "{{.*}}file2.h" 1
+// NO-REWRITE: #pragma clang module begin file
+//
+// ==== recursively re-enter file.h
+// REWRITE: #if 0
+// REWRITE: #include "file.h"
+// REWRITE: #endif
+//
+// REWRITE: #pragma clang module begin file
+// CHECK: # 1 "{{.*}}file.h" 1
+// NO-REWRITE: #pragma clang module begin file
+// NO-REWRITE: # 1 "{{.*}}file.h"{{$}}
+//
+// CHECK: struct __FILE;
+// CHECK: #pragma clang module import fwd /* clang {{-E|-frewrite-includes}}: implicit import
+// CHECK: typedef struct __FILE FILE;
+//
+// REWRITE: #pragma clang module end
+// CHECK: # 2 "{{.*}}file2.h" 2
+// NO-REWRITE: #pragma clang module end
+// NO-REWRITE: # 2 "{{.*}}file2.h"{{$}}
+// ==== return to file2.h
+//
+// CHECK: extern int file2;
+//
+// REWRITE: #pragma clang module end
+// CHECK: # 3 "<module-includes>" 2
+// NO-REWRITE: #pragma clang module end
+
+
+// expected-no-diagnostics
+
+// FIXME: This should be rejected: we have not imported the submodule defining it yet.
+__FILE *a;
+
+#pragma clang module import file
+
+FILE *b;
+int x = file2;
diff --git a/test/OpenMP/varargs.cpp b/test/OpenMP/varargs.cpp
new file mode 100644
index 000000000000..7738f83fab24
--- /dev/null
+++ b/test/OpenMP/varargs.cpp
@@ -0,0 +1,8 @@
+// RUN: %clang_cc1 -verify -fopenmp %s
+void f(int a, ...) {
+#pragma omp parallel for
+  for (int i = 0; i < 100; ++i) {
+    __builtin_va_list ap;
+    __builtin_va_start(ap, a); // expected-error {{'va_start' cannot be used in a captured statement}}
+  }
+};
diff --git a/test/Parser/MicrosoftExtensions.cpp b/test/Parser/MicrosoftExtensions.cpp
index 830412ed474f..74f4bb3268de 100644
--- a/test/Parser/MicrosoftExtensions.cpp
+++ b/test/Parser/MicrosoftExtensions.cpp
@@ -60,7 +60,7 @@ struct struct_without_uuid { };
 struct __declspec(uuid("000000A0-0000-0000-C000-000000000049"))
 struct_with_uuid2;
 
-[uuid("000000A0-0000-0000-C000-000000000049")] struct struct_with_uuid3;
+[uuid("000000A0-0000-0000-C000-000000000049")] struct struct_with_uuid3; // expected-warning{{specifying 'uuid' as an ATL attribute is deprecated; use __declspec instead}}
 
 struct
 struct_with_uuid2 {} ;
diff --git a/test/Parser/ms-square-bracket-attributes.mm b/test/Parser/ms-square-bracket-attributes.mm
index 98b2f6c2d3ea..a158cf7b2b90 100644
--- a/test/Parser/ms-square-bracket-attributes.mm
+++ b/test/Parser/ms-square-bracket-attributes.mm
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -fsyntax-only -std=c++14 -verify -fms-extensions %s
+// RUN: %clang_cc1 -fsyntax-only -std=c++14 -verify -fms-extensions %s -Wno-deprecated-declarations
 
 typedef struct _GUID {
   unsigned long Data1;
diff --git a/test/Preprocessor/aarch64-target-features.c b/test/Preprocessor/aarch64-target-features.c
index c9c7f2dc4a4e..43a050b14c06 100644
--- a/test/Preprocessor/aarch64-target-features.c
+++ b/test/Preprocessor/aarch64-target-features.c
@@ -109,7 +109,7 @@
 // CHECK-MCPU-THUNDERX2T99: "-cc1"{{.*}} "-triple" "aarch64{{.*}}" "-target-feature" "+neon" "-target-feature" "+crc" "-target-feature" "+crypto"
 
 // RUN: %clang -target x86_64-apple-macosx -arch arm64 -### -c %s 2>&1 | FileCheck --check-prefix=CHECK-ARCH-ARM64 %s
-// CHECK-ARCH-ARM64: "-target-cpu" "cyclone" "-target-feature" "+neon" "-target-feature" "+crypto" "-target-feature" "+zcm" "-target-feature" "+zcz"
+// CHECK-ARCH-ARM64: "-target-cpu" "cyclone" "-target-feature" "+fp-armv8" "-target-feature" "+neon" "-target-feature" "+crypto" "-target-feature" "+zcm" "-target-feature" "+zcz"
 
 // RUN: %clang -target aarch64 -march=armv8-a+fp+simd+crc+crypto -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-MARCH-1 %s
 // RUN: %clang -target aarch64 -march=armv8-a+nofp+nosimd+nocrc+nocrypto+fp+simd+crc+crypto -### -c %s 2>&1 | FileCheck -check-prefix=CHECK-MARCH-1 %s
diff --git a/test/Preprocessor/macro_paste_commaext.c b/test/Preprocessor/macro_paste_commaext.c
index fdb8f982a929..60418effe7c3 100644
--- a/test/Preprocessor/macro_paste_commaext.c
+++ b/test/Preprocessor/macro_paste_commaext.c
@@ -1,13 +1,20 @@
-// RUN: %clang_cc1 %s -E | grep 'V);'
-// RUN: %clang_cc1 %s -E | grep 'W, 1, 2);'
-// RUN: %clang_cc1 %s -E | grep 'X, 1, 2);'
-// RUN: %clang_cc1 %s -E | grep 'Y,);'
-// RUN: %clang_cc1 %s -E | grep 'Z,);'
+// RUN: %clang_cc1 %s -E | FileCheck --strict-whitespace --match-full-lines %s
+
+// In the following tests, note that the output is sensitive to the
+// whitespace *preceeding* the varargs argument, as well as to
+// interior whitespace. AFAIK, this is the only case where whitespace
+// preceeding an argument matters, and might be considered a bug in
+// GCC. Nevertheless, since this feature is a GCC extension in the
+// first place, we'll follow along.
 
 #define debug(format, ...) format, ## __VA_ARGS__)
+// CHECK:V);
 debug(V);
-debug(W, 1, 2);
+// CHECK:W,1, 2);
+debug(W,1, 2);
+// CHECK:X, 1, 2);
 debug(X, 1, 2 );
+// CHECK:Y,);
 debug(Y, );
+// CHECK:Z,);
 debug(Z,);
-
diff --git a/test/Preprocessor/pragma_module.c b/test/Preprocessor/pragma_module.c
index d734f66efcef..90aa9481fb13 100644
--- a/test/Preprocessor/pragma_module.c
+++ b/test/Preprocessor/pragma_module.c
@@ -1,11 +1,52 @@
-// RUN: %clang -cc1 -E -fmodules %s -verify
+// RUN: rm -rf %t
+// RUN: mkdir %t
+// RUN: echo 'module foo { module a {} module b {} } module bar {} module if {}' > %t/module.map
+// RUN: %clang -cc1 -fmodules -fmodule-name=if -x c %t/module.map -emit-module -o %t/if.pcm
+// RUN: %clang -cc1 -E -fmodules %s -fmodule-file=%t/if.pcm -verify -fmodule-name=foo -fmodule-map-file=%t/module.map
+// RUN: %clang -cc1 -E -fmodules %s -fmodule-file=%t/if.pcm -verify -fmodule-name=foo -fmodule-map-file=%t/module.map -fmodules-local-submodule-visibility -DLOCAL_VIS
 
 // Just checking the syntax here; the semantics are tested elsewhere.
-#pragma clang module import // expected-error {{expected identifier in module name}}
-#pragma clang module import ! // expected-error {{expected identifier in module name}}
-#pragma clang module import if // expected-error {{expected identifier in module name}}
-#pragma clang module import foo ? bar // expected-error {{expected '.' or end of directive after module name}}
-#pragma clang module import foo. // expected-error {{expected identifier}}
-#pragma clang module import foo.bar.baz.quux // expected-error {{module 'foo' not found}}
+#pragma clang module import // expected-error {{expected module name}}
+#pragma clang module import ! // expected-error {{expected module name}}
+#pragma clang module import if // ok
+#pragma clang module import foo ? bar // expected-warning {{extra tokens at end of #pragma}}
+#pragma clang module import foo. // expected-error {{expected identifier after '.' in module name}}
+#pragma clang module import foo.bar.baz.quux // expected-error {{no submodule named 'bar' in module 'foo'}}
 
-#error here // expected-error {{here}}
+#pragma clang module begin ! // expected-error {{expected module name}}
+
+#pragma clang module begin foo.a blah // expected-warning {{extra tokens}}
+ #pragma clang module begin foo.a // nesting is OK
+  #define X 1 // expected-note 0-1{{previous}}
+  #ifndef X
+  #error X should be defined here
+  #endif
+ #pragma clang module end
+ 
+ #ifndef X
+ #error X should still be defined
+ #endif
+#pragma clang module end foo.a // expected-warning {{extra tokens}}
+
+// #pragma clang module begin/end also import the module into the enclosing context
+#ifndef X
+#error X should still be defined
+#endif
+
+#pragma clang module begin foo.b
+ #if defined(X) && defined(LOCAL_VIS)
+ #error under -fmodules-local-submodule-visibility, X should not be defined
+ #endif
+
+ #if !defined(X) && !defined(LOCAL_VIS)
+ #error without -fmodules-local-submodule-visibility, X should still be defined
+ #endif
+
+ #pragma clang module import foo.a
+ #ifndef X
+ #error X should be defined here
+ #endif
+#pragma clang module end
+
+#pragma clang module end // expected-error {{no matching '#pragma clang module begin'}}
+#pragma clang module begin foo.a // expected-error {{no matching '#pragma clang module end'}}
diff --git a/test/Preprocessor/stringize_space.c b/test/Preprocessor/stringize_space.c
index ae70bf18187c..cbc7386cd09b 100644
--- a/test/Preprocessor/stringize_space.c
+++ b/test/Preprocessor/stringize_space.c
@@ -18,3 +18,14 @@ f(
     1)
 
 // CHECK: {{^}}"-1"
+
+#define paste(a,b) str(a<b##ld)
+paste(hello1, wor)
+paste(hello2,
+      wor)
+paste(hello3,
+wor)
+
+// CHECK: {{^}}"hello1<world"
+// CHECK: {{^}}"hello2<world"
+// CHECK: {{^}}"hello3<world"
diff --git a/test/Sema/arm-interrupt-attr.c b/test/Sema/arm-interrupt-attr.c
index 3a6cdbe0e072..60691ab7f8e8 100644
--- a/test/Sema/arm-interrupt-attr.c
+++ b/test/Sema/arm-interrupt-attr.c
@@ -1,7 +1,8 @@
-// RUN: %clang_cc1 %s -triple arm-apple-darwin -verify -fsyntax-only
-// RUN: %clang_cc1 %s -triple thumb-apple-darwin -verify -fsyntax-only
-// RUN: %clang_cc1 %s -triple armeb-none-eabi -verify -fsyntax-only
-// RUN: %clang_cc1 %s -triple thumbeb-none-eabi -verify -fsyntax-only
+// RUN: %clang_cc1 %s -triple arm-apple-darwin  -target-feature +vfp2 -verify -fsyntax-only
+// RUN: %clang_cc1 %s -triple thumb-apple-darwin  -target-feature +vfp3 -verify -fsyntax-only
+// RUN: %clang_cc1 %s -triple armeb-none-eabi  -target-feature +vfp4 -verify -fsyntax-only
+// RUN: %clang_cc1 %s -triple thumbeb-none-eabi  -target-feature +neon -verify -fsyntax-only
+// RUN: %clang_cc1 %s -triple thumbeb-none-eabi -target-feature +neon -target-feature +soft-float -DSOFT -verify -fsyntax-only
 
 __attribute__((interrupt(IRQ))) void foo() {} // expected-error {{'interrupt' attribute requires a string}}
 __attribute__((interrupt("irq"))) void foo1() {} // expected-warning {{'interrupt' attribute argument not supported: irq}}
@@ -24,6 +25,8 @@ void caller1() {
   callee1();
   callee2();
 }
+
+#ifndef SOFT
 __attribute__((interrupt("IRQ"))) void caller2() {
   callee1(); // expected-warning {{call to function without interrupt attribute could clobber interruptee's VFP registers}}
   callee2();
@@ -33,3 +36,14 @@ void (*callee3)();
 __attribute__((interrupt("IRQ"))) void caller3() {
   callee3(); // expected-warning {{call to function without interrupt attribute could clobber interruptee's VFP registers}}
 }
+#else
+__attribute__((interrupt("IRQ"))) void caller2() {
+  callee1();
+  callee2();
+}
+
+void (*callee3)();
+__attribute__((interrupt("IRQ"))) void caller3() {
+  callee3();
+}
+#endif
diff --git a/test/Sema/attr-availability.c b/test/Sema/attr-availability.c
index c4133e3b9bc6..e105037c8ed0 100644
--- a/test/Sema/attr-availability.c
+++ b/test/Sema/attr-availability.c
@@ -30,7 +30,7 @@ void test_10095131() {
   ATSFontGetPostScriptName(100); // expected-error {{'ATSFontGetPostScriptName' is unavailable: obsoleted in macOS 9.0 - use ATSFontGetFullPostScriptName}}
 
 #if defined(WARN_PARTIAL)
-  // expected-warning@+2 {{is only available on macOS 10.8 or newer}} expected-note@+2 {{enclose 'PartiallyAvailable' in an @available check to silence this warning}}
+  // expected-warning@+2 {{is only available on macOS 10.8 or newer}} expected-note@+2 {{enclose 'PartiallyAvailable' in a __builtin_available check to silence this warning}}
 #endif
   PartiallyAvailable();
 }
diff --git a/test/SemaCXX/ms-uuid.cpp b/test/SemaCXX/ms-uuid.cpp
index 461e3c12ff8a..e29dda878e68 100644
--- a/test/SemaCXX/ms-uuid.cpp
+++ b/test/SemaCXX/ms-uuid.cpp
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -fsyntax-only -verify -fms-extensions %s
+// RUN: %clang_cc1 -fsyntax-only -verify -fms-extensions %s -Wno-deprecated-declarations
 
 typedef struct _GUID {
   unsigned long Data1;
diff --git a/test/SemaCXX/varargs.cpp b/test/SemaCXX/varargs.cpp
index 6a1883786a33..f9027c247993 100644
--- a/test/SemaCXX/varargs.cpp
+++ b/test/SemaCXX/varargs.cpp
@@ -1,12 +1,59 @@
-// RUN: %clang_cc1 -fsyntax-only -std=c++03 -verify %s
+// RUN: %clang_cc1 -std=c++03 -verify %s
+// RUN: %clang_cc1 -std=c++11 -verify %s
+
+__builtin_va_list ap;
 
 class string;
 void f(const string& s, ...) {  // expected-note {{parameter of type 'const string &' is declared here}}
-  __builtin_va_list ap;
   __builtin_va_start(ap, s); // expected-warning {{passing an object of reference type to 'va_start' has undefined behavior}}
 }
 
 void g(register int i, ...) {
-  __builtin_va_list ap;
-  __builtin_va_start(ap, i); // okay
+  __builtin_va_start(ap, i); // UB in C, OK in C++
+}
+
+// Don't crash when there is no last parameter.
+void no_params(...) {
+  int a;
+  __builtin_va_start(ap, a); // expected-warning {{second argument to 'va_start' is not the last named parameter}}
+}
+
+// Reject this. The __builtin_va_start would execute in Foo's non-variadic
+// default ctor.
+void record_context(int a, ...) {
+  struct Foo {
+    // expected-error@+1 {{'va_start' cannot be used outside a function}}
+    void meth(int a, int b = (__builtin_va_start(ap, a), 0)) {}
+  };
+}
+
+#if __cplusplus >= 201103L
+// We used to have bugs identifying the correct enclosing function scope in a
+// lambda.
+
+void fixed_lambda_varargs_function(int a, ...) {
+  [](int b) {
+    __builtin_va_start(ap, b); // expected-error {{'va_start' used in function with fixed args}}
+  }(42);
+}
+void varargs_lambda_fixed_function(int a) {
+  [](int b, ...) {
+    __builtin_va_start(ap, b); // correct
+  }(42);
+}
+
+auto fixed_lambda_global = [](int f) {
+  __builtin_va_start(ap, f); // expected-error {{'va_start' used in function with fixed args}}
+};
+auto varargs_lambda_global = [](int f, ...) {
+  __builtin_va_start(ap, f); // correct
+};
+
+void record_member_init(int a, ...) {
+  struct Foo {
+    int a = 0;
+    // expected-error@+1 {{'va_start' cannot be used outside a function}}
+    int b = (__builtin_va_start(ap, a), 0);
+  };
 }
+#endif
diff --git a/test/SemaCXX/warn-zero-nullptr.cpp b/test/SemaCXX/warn-zero-nullptr.cpp
new file mode 100644
index 000000000000..edd2a759b70f
--- /dev/null
+++ b/test/SemaCXX/warn-zero-nullptr.cpp
@@ -0,0 +1,27 @@
+// RUN: %clang_cc1 -fsyntax-only -verify %s -Wzero-as-null-pointer-constant -std=c++11
+
+struct S {};
+
+int (S::*mp0) = nullptr;
+void (*fp0)() = nullptr;
+void* p0 = nullptr;
+
+int (S::*mp1) = 0; // expected-warning{{zero as null pointer constant}}
+void (*fp1)() = 0; // expected-warning{{zero as null pointer constant}}
+void* p1 = 0; // expected-warning{{zero as null pointer constant}}
+
+// NULL is an integer constant expression, so warn on it too:
+void* p2 = __null; // expected-warning{{zero as null pointer constant}}
+void (*fp2)() = __null; // expected-warning{{zero as null pointer constant}}
+int (S::*mp2) = __null; // expected-warning{{zero as null pointer constant}}
+
+void f0(void* v = 0); // expected-warning{{zero as null pointer constant}}
+void f1(void* v);
+
+void g() {
+  f1(0); // expected-warning{{zero as null pointer constant}}
+}
+
+// Warn on these too. Matches gcc and arguably makes sense.
+void* pp = (decltype(nullptr))0; // expected-warning{{zero as null pointer constant}}
+void* pp2 = static_cast<decltype(nullptr)>(0); // expected-warning{{zero as null pointer constant}}
diff --git a/test/SemaObjC/x86-method-vector-values.m b/test/SemaObjC/x86-method-vector-values.m
index 6c5189d08427..23d07b1b41fa 100644
--- a/test/SemaObjC/x86-method-vector-values.m
+++ b/test/SemaObjC/x86-method-vector-values.m
@@ -68,6 +68,8 @@ struct AggregateFloat { float v; };
 
 #else
 
+// expected-no-diagnostics
+
 -(void)takeVector:(float3)v {
 }
 
@@ -84,15 +86,9 @@ struct AggregateFloat { float v; };
 }
 
 -(void)takeVector2:(float3)v AVAILABLE_MACOS_10_10 {
-#ifdef MAC
-// expected-error@-2 {{'float3' (vector of 3 'float' values) parameter type is unsupported}}
-#endif
 }
 
 - (__m128)retM128_2 AVAILABLE_MACOS_10_10 {
-#ifdef MAC
-// expected-error@-2 {{'__m128' (vector of 4 'float' values) return type is unsupported}}
-#endif
   __m128 value;
   return value;
 }
@@ -101,9 +97,6 @@ struct AggregateFloat { float v; };
 }
 
 -(void)takeVector4:(float3)v AVAILABLE_IOS_8 {
-#ifdef IOS
-  // expected-error@-2 {{'float3' (vector of 3 'float' values) parameter type is unsupported}}
-#endif
 }
 
 -(void)takeVector5:(float3)v AVAILABLE_IOS_9 { // no error
diff --git a/test/SemaOpenCL/invalid-kernel-attrs.cl b/test/SemaOpenCL/invalid-kernel-attrs.cl
index cedbb0664675..1f1359cceead 100644
--- a/test/SemaOpenCL/invalid-kernel-attrs.cl
+++ b/test/SemaOpenCL/invalid-kernel-attrs.cl
@@ -33,3 +33,7 @@ void f_kernel_image2d_t( kernel image2d_t image ) { // expected-error {{'kernel'
 kernel __attribute__((reqd_work_group_size(1,2,0))) void kernel11(){} // expected-error {{'reqd_work_group_size' attribute must be greater than 0}}
 kernel __attribute__((reqd_work_group_size(1,0,2))) void kernel12(){} // expected-error {{'reqd_work_group_size' attribute must be greater than 0}}
 kernel __attribute__((reqd_work_group_size(0,1,2))) void kernel13(){} // expected-error {{'reqd_work_group_size' attribute must be greater than 0}}
+
+__attribute__((intel_reqd_sub_group_size(8))) void kernel14(){} // expected-error {{attribute 'intel_reqd_sub_group_size' can only be applied to a kernel}}
+kernel __attribute__((intel_reqd_sub_group_size(0))) void kernel15(){} // expected-error {{'intel_reqd_sub_group_size' attribute must be greater than 0}}
+kernel __attribute__((intel_reqd_sub_group_size(8))) __attribute__((intel_reqd_sub_group_size(16))) void kernel16() {}  //expected-warning{{attribute 'intel_reqd_sub_group_size' is already applied with different parameters}}
diff --git a/test/SemaOpenCL/sampler_t.cl b/test/SemaOpenCL/sampler_t.cl
index 0dddeeb39013..4d68dd20a17e 100644
--- a/test/SemaOpenCL/sampler_t.cl
+++ b/test/SemaOpenCL/sampler_t.cl
@@ -9,7 +9,8 @@
 
 constant sampler_t glb_smp = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_LINEAR;
 constant sampler_t glb_smp2; // expected-error{{variable in constant address space must be initialized}}
-global sampler_t glb_smp3 = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_NEAREST; // expected-error{{sampler type cannot be used with the __local and __global address space qualifiers}}
+global sampler_t glb_smp3 = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_NEAREST; // expected-error{{sampler type cannot be used with the __local and __global address space qualifiers}} expected-error {{global sampler requires a const or constant address space qualifier}}
+const global sampler_t glb_smp3_const = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_LINEAR;  // expected-error{{sampler type cannot be used with the __local and __global address space qualifiers}}
 
 constant sampler_t glb_smp4 = 0;
 #ifdef CHECK_SAMPLER_VALUE
@@ -38,6 +39,11 @@ constant struct sampler_s {
 
 sampler_t bad(void); //expected-error{{declaring function return value of type 'sampler_t' is not allowed}}
 
+sampler_t global_nonconst_smp = 0; // expected-error {{global sampler requires a const or constant address space qualifier}}
+
+const sampler_t glb_smp10 = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_LINEAR;
+const constant sampler_t glb_smp11 = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_LINEAR;
+
 void kernel ker(sampler_t argsmp) {
   local sampler_t smp; // expected-error{{sampler type cannot be used with the __local and __global address space qualifiers}}
   const sampler_t const_smp = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_LINEAR;