Index: cfe/trunk/lib/Headers/avx2intrin.h
===================================================================
--- cfe/trunk/lib/Headers/avx2intrin.h
+++ cfe/trunk/lib/Headers/avx2intrin.h
@@ -208,7 +208,9 @@
 static __inline__ __m256i __DEFAULT_FN_ATTRS
 _mm256_cmpgt_epi8(__m256i __a, __m256i __b)
 {
-  return (__m256i)((__v32qi)__a > (__v32qi)__b);
+  /* This function always performs a signed comparison, but __v32qi is a char
+     which may be signed or unsigned, so use __v32qs. */
+  return (__m256i)((__v32qs)__a > (__v32qs)__b);
 }
 
 static __inline__ __m256i __DEFAULT_FN_ATTRS
Index: cfe/trunk/lib/Headers/avxintrin.h
===================================================================
--- cfe/trunk/lib/Headers/avxintrin.h
+++ cfe/trunk/lib/Headers/avxintrin.h
@@ -35,6 +35,10 @@
 typedef short __v16hi __attribute__ ((__vector_size__ (32)));
 typedef char __v32qi __attribute__ ((__vector_size__ (32)));
 
+/* We need an explicitly signed variant for char. Note that this shouldn't
+ * appear in the interface though. */
+typedef signed char __v32qs __attribute__((__vector_size__(32)));
+
 typedef float __m256 __attribute__ ((__vector_size__ (32)));
 typedef double __m256d __attribute__((__vector_size__(32)));
 typedef long long __m256i __attribute__((__vector_size__(32)));
Index: cfe/trunk/lib/Headers/emmintrin.h
===================================================================
--- cfe/trunk/lib/Headers/emmintrin.h
+++ cfe/trunk/lib/Headers/emmintrin.h
@@ -35,6 +35,10 @@
 typedef short __v8hi __attribute__((__vector_size__(16)));
 typedef char __v16qi __attribute__((__vector_size__(16)));
 
+/* We need an explicitly signed variant for char. Note that this shouldn't
+ * appear in the interface though. */
+typedef signed char __v16qs __attribute__((__vector_size__(16)));
+
 #include <f16cintrin.h>
 
 /* Define the default attributes for the functions in this file. */
@@ -996,8 +1000,7 @@
 _mm_cmpgt_epi8(__m128i __a, __m128i __b)
 {
   /* This function always performs a signed comparison, but __v16qi is a char
-     which may be signed or unsigned. */
-  typedef signed char __v16qs __attribute__((__vector_size__(16)));
+     which may be signed or unsigned, so use __v16qs. */
   return (__m128i)((__v16qs)__a > (__v16qs)__b);
 }
 
Index: cfe/trunk/lib/Headers/smmintrin.h
===================================================================
--- cfe/trunk/lib/Headers/smmintrin.h
+++ cfe/trunk/lib/Headers/smmintrin.h
@@ -286,34 +286,26 @@
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepi8_epi16(__m128i __V)
 {
-  /* We need a local definitively signed typedef similar to __v16qi even in the
-   * presence of __UNSIGNED_CHAR__.
-   * FIXME: __v16qi should almost certainly be definitively signed.
-   */
-  typedef signed char __signed_v16qi __attribute__((__vector_size__(16)));
-  return (__m128i)__builtin_convertvector(__builtin_shufflevector((__signed_v16qi)__V, (__signed_v16qi)__V, 0, 1, 2, 3, 4, 5, 6, 7), __v8hi);
+  /* This function always performs a signed extension, but __v16qi is a char
+     which may be signed or unsigned, so use __v16qs. */
+  return (__m128i)__builtin_convertvector(__builtin_shufflevector((__v16qs)__V, (__v16qs)__V, 0, 1, 2, 3, 4, 5, 6, 7), __v8hi);
 }
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepi8_epi32(__m128i __V)
 {
-  /* We need a local definitively signed typedef similar to __v16qi even in the
-   * presence of __UNSIGNED_CHAR__.
-   * FIXME: __v16qi should almost certainly be definitively signed.
-   */
-  typedef signed char __signed_v16qi __attribute__((__vector_size__(16)));
-  return (__m128i)__builtin_convertvector(__builtin_shufflevector((__signed_v16qi)__V, (__signed_v16qi)__V, 0, 1, 2, 3), __v4si);
+  /* This function always performs a signed extension, but __v16qi is a char
+     which may be signed or unsigned, so use __v16qs. */
+  return (__m128i)__builtin_convertvector(__builtin_shufflevector((__v16qs)__V, (__v16qs)__V, 0, 1, 2, 3), __v4si);
 }
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS
 _mm_cvtepi8_epi64(__m128i __V)
 {
-  /* We need a local definitively signed typedef similar to __v16qi even in the
-   * presence of __UNSIGNED_CHAR__.
-   * FIXME: __v16qi should almost certainly be definitively signed.
-   */
-  typedef signed char __signed_v16qi __attribute__((__vector_size__(16)));
-  return (__m128i)__builtin_convertvector(__builtin_shufflevector((__signed_v16qi)__V, (__signed_v16qi)__V, 0, 1), __v2di);
+  /* This function always performs a signed extension, but __v16qi is a char
+     which may be signed or unsigned, so use __v16qs. */
+  typedef signed char __v16qs __attribute__((__vector_size__(16)));
+  return (__m128i)__builtin_convertvector(__builtin_shufflevector((__v16qs)__V, (__v16qs)__V, 0, 1), __v2di);
 }
 
 static __inline__ __m128i __DEFAULT_FN_ATTRS
Index: cfe/trunk/test/CodeGen/avx2-builtins.c
===================================================================
--- cfe/trunk/test/CodeGen/avx2-builtins.c
+++ cfe/trunk/test/CodeGen/avx2-builtins.c
@@ -1,5 +1,7 @@
 // RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -target-feature +avx2 -emit-llvm -o - -Werror | FileCheck %s
+// RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -target-feature +avx2 -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s
 // RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -target-feature +avx2 -S -o - -Werror | FileCheck %s --check-prefix=CHECK-ASM
+// RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -target-feature +avx2 -fno-signed-char -S -o - -Werror | FileCheck %s --check-prefix=CHECK-ASM
 
 // REQUIRES: x86-registered-target
 
Index: cfe/trunk/test/CodeGen/avx512bw-builtins.c
===================================================================
--- cfe/trunk/test/CodeGen/avx512bw-builtins.c
+++ cfe/trunk/test/CodeGen/avx512bw-builtins.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -ffreestanding -target-feature +avx512bw -emit-llvm -o - -Werror | FileCheck %s
+// RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -ffreestanding -target-feature +avx512bw -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s
 
 #include <immintrin.h>
 
Index: cfe/trunk/test/CodeGen/avx512vlbw-builtins.c
===================================================================
--- cfe/trunk/test/CodeGen/avx512vlbw-builtins.c
+++ cfe/trunk/test/CodeGen/avx512vlbw-builtins.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -ffreestanding -target-feature +avx512bw -target-feature +avx512vl -emit-llvm -o - -Werror | FileCheck %s
+// RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -ffreestanding -target-feature +avx512bw -target-feature +avx512vl -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s
 
 #include <immintrin.h>
 
Index: cfe/trunk/test/CodeGen/mmx-builtins.c
===================================================================
--- cfe/trunk/test/CodeGen/mmx-builtins.c
+++ cfe/trunk/test/CodeGen/mmx-builtins.c
@@ -1,5 +1,6 @@
 // REQUIRES: x86-registered-target
 // RUN: %clang_cc1 %s -O3 -triple=x86_64-apple-darwin -target-feature +ssse3 -S -o - | FileCheck %s
+// RUN: %clang_cc1 %s -O3 -triple=x86_64-apple-darwin -target-feature +ssse3 -fno-signed-char -S -o - | FileCheck %s
 
 // FIXME: Disable inclusion of mm_malloc.h, our current implementation is broken
 // on win32 since we don't generally know how to find errno.h.
Index: cfe/trunk/test/CodeGen/sse42-builtins.c
===================================================================
--- cfe/trunk/test/CodeGen/sse42-builtins.c
+++ cfe/trunk/test/CodeGen/sse42-builtins.c
@@ -1,12 +1,35 @@
 // REQUIRES: x86-registered-target
 // RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -target-feature +sse4.2 -emit-llvm -o - -Werror | FileCheck %s
+// RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -target-feature +sse4.2 -fno-signed-char -emit-llvm -o - -Werror | FileCheck %s
 // RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -target-feature +sse4.2 -S -o - -Werror | FileCheck %s --check-prefix=CHECK-ASM
+// RUN: %clang_cc1 %s -O0 -triple=x86_64-apple-darwin -target-feature +sse4.2 -fno-signed-char -S -o - -Werror | FileCheck %s --check-prefix=CHECK-ASM
 
 // Don't include mm_malloc.h, it's system specific.
 #define __MM_MALLOC_H
 
 #include <x86intrin.h>
 
+__m128i test_mm_cmpgt_epi8(__m128i A, __m128i B) {
+  // CHECK-LABEL: test_mm_cmpgt_epi8
+  // CHECK: icmp sgt <16 x i8>
+  // CHECK-ASM: pcmpgtb %xmm{{.*}}, %xmm{{.*}}
+  return _mm_cmpgt_epi8(A, B);
+}
+
+__m128i test_mm_cmpgt_epi16(__m128i A, __m128i B) {
+  // CHECK-LABEL: test_mm_cmpgt_epi16
+  // CHECK: icmp sgt <8 x i16>
+  // CHECK-ASM: pcmpgtw %xmm{{.*}}, %xmm{{.*}}
+  return _mm_cmpgt_epi16(A, B);
+}
+
+__m128i test_mm_cmpgt_epi32(__m128i A, __m128i B) {
+  // CHECK-LABEL: test_mm_cmpgt_epi32
+  // CHECK: icmp sgt <4 x i32>
+  // CHECK-ASM: pcmpgtd %xmm{{.*}}, %xmm{{.*}}
+  return _mm_cmpgt_epi32(A, B);
+}
+
 __m128i test_mm_cmpgt_epi64(__m128i A, __m128i B) {
   // CHECK-LABEL: test_mm_cmpgt_epi64
   // CHECK: icmp sgt <2 x i64>