[WebAssembly] Use "signed char" instead of "char" in SIMD intrinsics.

[sunfish]

Summary

This allows people to use int8_t instead of char, -funsigned-char,
and generally decouples SIMD from the specialness of char.

And it makes intrinsics like __builtin_wasm_add_saturate_s_i8x16
and __builtin_wasm_add_saturate_u_i8x16 use signed and unsigned
element types, respectively.

[tlively]

Nice! Thanks for doing that :)

[sunfish]

• Update clang/test/CodeGen/builtins-wasm.c.

clang/include/clang/Basic/BuiltinsWebAssembly.def

 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_s_i32_f64, "id", "nc", "nontrapping-fptoint")
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_u_i32_f64, "id", "nc", "nontrapping-fptoint")
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_s_i64_f32, "LLif", "nc", "nontrapping-fptoint")
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_u_i64_f32, "LLif", "nc", "nontrapping-fptoint")
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_s_i64_f64, "LLid", "nc", "nontrapping-fptoint")
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_u_i64_f64, "LLid", "nc", "nontrapping-fptoint")
 
 // SIMD builtins
-TARGET_BUILTIN(__builtin_wasm_swizzle_v8x16, "V16cV16cV16c", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_swizzle_v8x16, "V16ScV16ScV16Sc", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_extract_lane_s_i8x16, "iV16cIi", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_extract_lane_u_i8x16, "iV16cIi", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_extract_lane_s_i8x16, "iV16ScIi", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_extract_lane_u_i8x16, "iV16UcIUi", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_extract_lane_s_i16x8, "iV8sIi", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_extract_lane_u_i16x8, "iV8sIi", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_extract_lane_u_i16x8, "iV8UsIUi", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_extract_lane_i32x4, "iV4iIi", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_extract_lane_i64x2, "LLiV2LLiIi", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_extract_lane_f32x4, "fV4fIi", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_extract_lane_f64x2, "dV2dIi", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_replace_lane_i8x16, "V16cV16cIii", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_replace_lane_i8x16, "V16ScV16ScIii", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_replace_lane_i16x8, "V8sV8sIii", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_replace_lane_i32x4, "V4iV4iIii", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_replace_lane_i64x2, "V2LLiV2LLiIiLLi", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_replace_lane_f32x4, "V4fV4fIif", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_replace_lane_f64x2, "V2dV2dIid", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_add_saturate_s_i8x16, "V16cV16cV16c", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_add_saturate_u_i8x16, "V16cV16cV16c", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_add_saturate_s_i8x16, "V16ScV16ScV16Sc", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_add_saturate_u_i8x16, "V16UcV16UcV16Uc", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_add_saturate_s_i16x8, "V8sV8sV8s", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_add_saturate_u_i16x8, "V8sV8sV8s", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_add_saturate_u_i16x8, "V8UsV8UsV8Us", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_sub_saturate_s_i8x16, "V16cV16cV16c", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_sub_saturate_u_i8x16, "V16cV16cV16c", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_sub_saturate_s_i8x16, "V16ScV16ScV16Sc", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_sub_saturate_u_i8x16, "V16UcV16UcV16Uc", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_sub_saturate_s_i16x8, "V8sV8sV8s", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_sub_saturate_u_i16x8, "V8sV8sV8s", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_sub_saturate_u_i16x8, "V8UsV8UsV8Us", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_abs_i8x16, "V16cV16c", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_abs_i8x16, "V16ScV16Sc", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_abs_i16x8, "V8sV8s", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_abs_i32x4, "V4iV4i", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_min_s_i8x16, "V16cV16cV16c", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_min_u_i8x16, "V16cV16cV16c", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_max_s_i8x16, "V16cV16cV16c", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_max_u_i8x16, "V16cV16cV16c", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_min_s_i8x16, "V16ScV16ScV16Sc", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_min_u_i8x16, "V16UcV16UcV16Uc", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_max_s_i8x16, "V16ScV16ScV16Sc", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_max_u_i8x16, "V16UcV16UcV16Uc", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_min_s_i16x8, "V8sV8sV8s", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_min_u_i16x8, "V8sV8sV8s", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_min_u_i16x8, "V8UsV8UsV8Us", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_max_s_i16x8, "V8sV8sV8s", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_max_u_i16x8, "V8sV8sV8s", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_max_u_i16x8, "V8UsV8UsV8Us", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_min_s_i32x4, "V4iV4iV4i", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_min_u_i32x4, "V4iV4iV4i", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_min_u_i32x4, "V4UiV4UiV4Ui", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_max_s_i32x4, "V4iV4iV4i", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_max_u_i32x4, "V4iV4iV4i", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_max_u_i32x4, "V4UiV4UiV4Ui", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_avgr_u_i8x16, "V16cV16cV16c", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_avgr_u_i16x8, "V8sV8sV8s", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_avgr_u_i8x16, "V16UcV16UcV16Uc", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_avgr_u_i16x8, "V8UsV8UsV8Us", "nc", "simd128")
 
 TARGET_BUILTIN(__builtin_wasm_bitselect, "V4iV4iV4iV4i", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_shuffle_v8x16, "V16cV16cV16cIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIi", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_shuffle_v8x16, "V16ScV16ScV16ScIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIi", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_any_true_i8x16, "iV16c", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_any_true_i8x16, "iV16Sc", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_any_true_i16x8, "iV8s", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_any_true_i32x4, "iV4i", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_any_true_i64x2, "iV2LLi", "nc", "unimplemented-simd128")
-TARGET_BUILTIN(__builtin_wasm_all_true_i8x16, "iV16c", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_all_true_i8x16, "iV16Sc", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_all_true_i16x8, "iV8s", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_all_true_i32x4, "iV4i", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_all_true_i64x2, "iV2LLi", "nc", "unimplemented-simd128")
 
-TARGET_BUILTIN(__builtin_wasm_bitmask_i8x16, "iV16c", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_bitmask_i8x16, "iV16Sc", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_bitmask_i16x8, "iV8s", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_bitmask_i32x4, "iV4i", "nc", "simd128")
 
 TARGET_BUILTIN(__builtin_wasm_abs_f32x4, "V4fV4f", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_abs_f64x2, "V2dV2d", "nc", "simd128")
 
 TARGET_BUILTIN(__builtin_wasm_min_f32x4, "V4fV4fV4f", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_max_f32x4, "V4fV4fV4f", "nc", "simd128")

 TARGET_BUILTIN(__builtin_wasm_qfma_f32x4, "V4fV4fV4fV4f", "nc", "unimplemented-simd128")
 TARGET_BUILTIN(__builtin_wasm_qfms_f32x4, "V4fV4fV4fV4f", "nc", "unimplemented-simd128")
 TARGET_BUILTIN(__builtin_wasm_qfma_f64x2, "V2dV2dV2dV2d", "nc", "unimplemented-simd128")
 TARGET_BUILTIN(__builtin_wasm_qfms_f64x2, "V2dV2dV2dV2d", "nc", "unimplemented-simd128")
 
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_s_i32x4_f32x4, "V4iV4f", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_trunc_saturate_u_i32x4_f32x4, "V4iV4f", "nc", "simd128")
 
-TARGET_BUILTIN(__builtin_wasm_narrow_s_i8x16_i16x8, "V16cV8sV8s", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_narrow_u_i8x16_i16x8, "V16cV8sV8s", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_narrow_s_i8x16_i16x8, "V16ScV8sV8s", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_narrow_u_i8x16_i16x8, "V16UcV8UsV8Us", "nc", "simd128")
 TARGET_BUILTIN(__builtin_wasm_narrow_s_i16x8_i32x4, "V8sV4iV4i", "nc", "simd128")
-TARGET_BUILTIN(__builtin_wasm_narrow_u_i16x8_i32x4, "V8sV4iV4i", "nc", "simd128")
+TARGET_BUILTIN(__builtin_wasm_narrow_u_i16x8_i32x4, "V8UsV4UiV4Ui", "nc", "simd128")
 
 #undef BUILTIN
 #undef TARGET_BUILTIN

clang/lib/Headers/wasm_simd128.h

 #include <stdbool.h>
 #include <stdint.h>
 
 // User-facing type
 typedef int32_t v128_t __attribute__((__vector_size__(16), __aligned__(16)));
 
 // Internal types determined by clang builtin definitions
 typedef int32_t __v128_u __attribute__((__vector_size__(16), __aligned__(1)));
-typedef char __i8x16 __attribute__((__vector_size__(16), __aligned__(16)));
-typedef signed char __s8x16
+typedef signed char __i8x16
     __attribute__((__vector_size__(16), __aligned__(16)));
 typedef unsigned char __u8x16
     __attribute__((__vector_size__(16), __aligned__(16)));
 typedef short __i16x8 __attribute__((__vector_size__(16), __aligned__(16)));
 typedef unsigned short __u16x8
     __attribute__((__vector_size__(16), __aligned__(16)));
 typedef int __i32x4 __attribute__((__vector_size__(16), __aligned__(16)));
 typedef unsigned int __u32x4

 #define wasm_f64x2_extract_lane(__a, __i)                                      \
   (__builtin_wasm_extract_lane_f64x2((__f64x2)(__a), __i))
 
 #define wasm_f64x2_replace_lane(__a, __i, __b)                                 \
   ((v128_t)__builtin_wasm_replace_lane_f64x2((__f64x2)(__a), __i, __b))
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_eq(v128_t __a,
                                                           v128_t __b) {
-  return (v128_t)((__s8x16)__a == (__s8x16)__b);
+  return (v128_t)((__i8x16)__a == (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_ne(v128_t __a,
                                                           v128_t __b) {
-  return (v128_t)((__s8x16)__a != (__s8x16)__b);
+  return (v128_t)((__i8x16)__a != (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_lt(v128_t __a,
                                                           v128_t __b) {
-  return (v128_t)((__s8x16)__a < (__s8x16)__b);
+  return (v128_t)((__i8x16)__a < (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_lt(v128_t __a,
                                                           v128_t __b) {
   return (v128_t)((__u8x16)__a < (__u8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_gt(v128_t __a,
                                                           v128_t __b) {
-  return (v128_t)((__s8x16)__a > (__s8x16)__b);
+  return (v128_t)((__i8x16)__a > (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_gt(v128_t __a,
                                                           v128_t __b) {
   return (v128_t)((__u8x16)__a > (__u8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_le(v128_t __a,
                                                           v128_t __b) {
-  return (v128_t)((__s8x16)__a <= (__s8x16)__b);
+  return (v128_t)((__i8x16)__a <= (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_le(v128_t __a,
                                                           v128_t __b) {
   return (v128_t)((__u8x16)__a <= (__u8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_ge(v128_t __a,
                                                           v128_t __b) {
-  return (v128_t)((__s8x16)__a >= (__s8x16)__b);
+  return (v128_t)((__i8x16)__a >= (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_ge(v128_t __a,
                                                           v128_t __b) {
   return (v128_t)((__u8x16)__a >= (__u8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_eq(v128_t __a,

 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_v128_andnot(v128_t __a,
                                                              v128_t __b) {
   return __a & ~__b;
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_v128_bitselect(v128_t __a,
                                                                 v128_t __b,
                                                                 v128_t __mask) {
   return (v128_t)__builtin_wasm_bitselect((__i32x4)__a, (__i32x4)__b,
                                           (__i32x4)__mask);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_abs(v128_t __a) {
   return (v128_t)__builtin_wasm_abs_i8x16((__i8x16)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_neg(v128_t __a) {
   return (v128_t)(-(__u8x16)__a);
 }
 
 static __inline__ bool __DEFAULT_FN_ATTRS wasm_i8x16_any_true(v128_t __a) {
   return __builtin_wasm_any_true_i8x16((__i8x16)__a);
 }
 
 static __inline__ bool __DEFAULT_FN_ATTRS wasm_i8x16_all_true(v128_t __a) {
   return __builtin_wasm_all_true_i8x16((__i8x16)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_shl(v128_t __a,
                                                            int32_t __b) {
   return (v128_t)((__i8x16)__a << __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_shr(v128_t __a,
                                                            int32_t __b) {
-  return (v128_t)((__s8x16)__a >> __b);
+  return (v128_t)((__i8x16)__a >> __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_shr(v128_t __a,
                                                            int32_t __b) {
   return (v128_t)((__u8x16)__a >> __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_add(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)((__u8x16)__a + (__u8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS
 wasm_i8x16_add_saturate(v128_t __a, v128_t __b) {
   return (v128_t)__builtin_wasm_add_saturate_s_i8x16((__i8x16)__a,
                                                      (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS
 wasm_u8x16_add_saturate(v128_t __a, v128_t __b) {
   return (v128_t)__builtin_wasm_add_saturate_u_i8x16((__i8x16)__a,
                                                      (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_sub(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)((__u8x16)__a - (__u8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS
 wasm_i8x16_sub_saturate(v128_t __a, v128_t __b) {
   return (v128_t)__builtin_wasm_sub_saturate_s_i8x16((__i8x16)__a,
                                                      (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS
 wasm_u8x16_sub_saturate(v128_t __a, v128_t __b) {
   return (v128_t)__builtin_wasm_sub_saturate_u_i8x16((__i8x16)__a,
                                                      (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_min(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)__builtin_wasm_min_s_i8x16((__i8x16)__a, (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_min(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)__builtin_wasm_min_u_i8x16((__i8x16)__a, (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_max(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)__builtin_wasm_max_s_i8x16((__i8x16)__a, (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_max(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)__builtin_wasm_max_u_i8x16((__i8x16)__a, (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_avgr(v128_t __a,
                                                             v128_t __b) {
   return (v128_t)__builtin_wasm_avgr_u_i8x16((__i8x16)__a, (__i8x16)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_abs(v128_t __a) {
   return (v128_t)__builtin_wasm_abs_i16x8((__i16x8)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_neg(v128_t __a) {
   return (v128_t)(-(__u16x8)__a);
 }
 
 static __inline__ bool __DEFAULT_FN_ATTRS wasm_i16x8_any_true(v128_t __a) {
   return __builtin_wasm_any_true_i16x8((__i16x8)__a);
 }
 
 static __inline__ bool __DEFAULT_FN_ATTRS wasm_i16x8_all_true(v128_t __a) {
   return __builtin_wasm_all_true_i16x8((__i16x8)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_shl(v128_t __a,
                                                            int32_t __b) {
   return (v128_t)((__i16x8)__a << __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_shr(v128_t __a,
                                                            int32_t __b) {
   return (v128_t)((__i16x8)__a >> __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u16x8_shr(v128_t __a,
                                                            int32_t __b) {
   return (v128_t)((__u16x8)__a >> __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_add(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)((__u16x8)__a + (__u16x8)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS
 wasm_i16x8_add_saturate(v128_t __a, v128_t __b) {
   return (v128_t)__builtin_wasm_add_saturate_s_i16x8((__i16x8)__a,
                                                      (__i16x8)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS
 wasm_u16x8_add_saturate(v128_t __a, v128_t __b) {
   return (v128_t)__builtin_wasm_add_saturate_u_i16x8((__i16x8)__a,
                                                      (__i16x8)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_sub(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)((__i16x8)__a - (__i16x8)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS
 wasm_i16x8_sub_saturate(v128_t __a, v128_t __b) {
   return (v128_t)__builtin_wasm_sub_saturate_s_i16x8((__i16x8)__a,
                                                      (__i16x8)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS
 wasm_u16x8_sub_saturate(v128_t __a, v128_t __b) {
   return (v128_t)__builtin_wasm_sub_saturate_u_i16x8((__i16x8)__a,
                                                      (__i16x8)__b);
 }

clang/test/CodeGen/builtins-wasm.c

 // RUN: %clang_cc1 -triple wasm32-unknown-unknown -target-feature +unimplemented-simd128 -target-feature +nontrapping-fptoint -target-feature +exception-handling -target-feature +bulk-memory -target-feature +atomics -flax-vector-conversions=none -O3 -emit-llvm -o - %s | FileCheck %s -check-prefixes WEBASSEMBLY,WEBASSEMBLY32
 // RUN: %clang_cc1 -triple wasm64-unknown-unknown -target-feature +unimplemented-simd128 -target-feature +nontrapping-fptoint -target-feature +exception-handling -target-feature +bulk-memory -target-feature +atomics -flax-vector-conversions=none -O3 -emit-llvm -o - %s | FileCheck %s -check-prefixes WEBASSEMBLY,WEBASSEMBLY64
 // RUN: not %clang_cc1 -triple wasm64-unknown-unknown -target-feature +nontrapping-fptoint -target-feature +exception-handling -target-feature +bulk-memory -target-feature +atomics -flax-vector-conversions=none -O3 -emit-llvm -o - %s 2>&1 | FileCheck %s -check-prefixes MISSING-SIMD
 
 // SIMD convenience types
-typedef char i8x16 __attribute((vector_size(16)));
+typedef signed char i8x16 __attribute((vector_size(16)));
 typedef short i16x8 __attribute((vector_size(16)));
 typedef int i32x4 __attribute((vector_size(16)));
 typedef long long i64x2 __attribute((vector_size(16)));
 typedef unsigned char u8x16 __attribute((vector_size(16)));
 typedef unsigned short u16x8 __attribute((vector_size(16)));
 typedef unsigned int u32x4 __attribute((vector_size(16)));
 typedef unsigned long long u64x2 __attribute((vector_size(16)));
 typedef float f32x4 __attribute((vector_size(16)));

 int extract_lane_s_i8x16(i8x16 v) {
   return __builtin_wasm_extract_lane_s_i8x16(v, 13);
   // MISSING-SIMD: error: '__builtin_wasm_extract_lane_s_i8x16' needs target feature simd128
   // WEBASSEMBLY: extractelement <16 x i8> %v, i32 13
   // WEBASSEMBLY-NEXT: sext
   // WEBASSEMBLY-NEXT: ret
 }
 
-int extract_lane_u_i8x16(i8x16 v) {
+int extract_lane_u_i8x16(u8x16 v) {
   return __builtin_wasm_extract_lane_u_i8x16(v, 13);
   // WEBASSEMBLY: extractelement <16 x i8> %v, i32 13
   // WEBASSEMBLY-NEXT: zext
   // WEBASSEMBLY-NEXT: ret
 }
 
 int extract_lane_s_i16x8(i16x8 v) {
   return __builtin_wasm_extract_lane_s_i16x8(v, 7);
   // WEBASSEMBLY: extractelement <8 x i16> %v, i32 7
   // WEBASSEMBLY-NEXT: sext
   // WEBASSEMBLY-NEXT: ret
 }
 
-int extract_lane_u_i16x8(i16x8 v) {
+int extract_lane_u_i16x8(u16x8 v) {
   return __builtin_wasm_extract_lane_u_i16x8(v, 7);
   // WEBASSEMBLY: extractelement <8 x i16> %v, i32 7
   // WEBASSEMBLY-NEXT: zext
   // WEBASSEMBLY-NEXT: ret
 }
 
 int extract_lane_i32x4(i32x4 v) {
   return __builtin_wasm_extract_lane_i32x4(v, 3);

 
 i8x16 add_saturate_s_i8x16(i8x16 x, i8x16 y) {
   return __builtin_wasm_add_saturate_s_i8x16(x, y);
   // WEBASSEMBLY: call <16 x i8> @llvm.sadd.sat.v16i8(
   // WEBASSEMBLY-SAME: <16 x i8> %x, <16 x i8> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
-i8x16 add_saturate_u_i8x16(i8x16 x, i8x16 y) {
+u8x16 add_saturate_u_i8x16(u8x16 x, u8x16 y) {
   return __builtin_wasm_add_saturate_u_i8x16(x, y);
   // WEBASSEMBLY: call <16 x i8> @llvm.uadd.sat.v16i8(
   // WEBASSEMBLY-SAME: <16 x i8> %x, <16 x i8> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
 i16x8 add_saturate_s_i16x8(i16x8 x, i16x8 y) {
   return __builtin_wasm_add_saturate_s_i16x8(x, y);
   // WEBASSEMBLY: call <8 x i16> @llvm.sadd.sat.v8i16(
   // WEBASSEMBLY-SAME: <8 x i16> %x, <8 x i16> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
-i16x8 add_saturate_u_i16x8(i16x8 x, i16x8 y) {
+u16x8 add_saturate_u_i16x8(u16x8 x, u16x8 y) {
   return __builtin_wasm_add_saturate_u_i16x8(x, y);
   // WEBASSEMBLY: call <8 x i16> @llvm.uadd.sat.v8i16(
   // WEBASSEMBLY-SAME: <8 x i16> %x, <8 x i16> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
 i8x16 sub_saturate_s_i8x16(i8x16 x, i8x16 y) {
   return __builtin_wasm_sub_saturate_s_i8x16(x, y);
   // WEBASSEMBLY: call <16 x i8> @llvm.wasm.sub.saturate.signed.v16i8(
   // WEBASSEMBLY-SAME: <16 x i8> %x, <16 x i8> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
-i8x16 sub_saturate_u_i8x16(i8x16 x, i8x16 y) {
+u8x16 sub_saturate_u_i8x16(u8x16 x, u8x16 y) {
   return __builtin_wasm_sub_saturate_u_i8x16(x, y);
   // WEBASSEMBLY: call <16 x i8> @llvm.wasm.sub.saturate.unsigned.v16i8(
   // WEBASSEMBLY-SAME: <16 x i8> %x, <16 x i8> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
 i8x16 abs_i8x16(i8x16 v) {
   return __builtin_wasm_abs_i8x16(v);

 
 i8x16 min_s_i8x16(i8x16 x, i8x16 y) {
   return __builtin_wasm_min_s_i8x16(x, y);
   // WEBASSEMBLY: %0 = icmp slt <16 x i8> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <16 x i1> %0, <16 x i8> %x, <16 x i8> %y
   // WEBASSEMBLY-NEXT: ret <16 x i8> %1
 }
 
-i8x16 min_u_i8x16(i8x16 x, i8x16 y) {
+u8x16 min_u_i8x16(u8x16 x, u8x16 y) {
   return __builtin_wasm_min_u_i8x16(x, y);
   // WEBASSEMBLY: %0 = icmp ult <16 x i8> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <16 x i1> %0, <16 x i8> %x, <16 x i8> %y
   // WEBASSEMBLY-NEXT: ret <16 x i8> %1
 }
 
 i8x16 max_s_i8x16(i8x16 x, i8x16 y) {
   return __builtin_wasm_max_s_i8x16(x, y);
   // WEBASSEMBLY: %0 = icmp sgt <16 x i8> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <16 x i1> %0, <16 x i8> %x, <16 x i8> %y
   // WEBASSEMBLY-NEXT: ret <16 x i8> %1
 }
 
-i8x16 max_u_i8x16(i8x16 x, i8x16 y) {
+u8x16 max_u_i8x16(u8x16 x, u8x16 y) {
   return __builtin_wasm_max_u_i8x16(x, y);
   // WEBASSEMBLY: %0 = icmp ugt <16 x i8> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <16 x i1> %0, <16 x i8> %x, <16 x i8> %y
   // WEBASSEMBLY-NEXT: ret <16 x i8> %1
 }
 
 i16x8 min_s_i16x8(i16x8 x, i16x8 y) {
   return __builtin_wasm_min_s_i16x8(x, y);
   // WEBASSEMBLY: %0 = icmp slt <8 x i16> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <8 x i1> %0, <8 x i16> %x, <8 x i16> %y
   // WEBASSEMBLY-NEXT: ret <8 x i16> %1
 }
 
-i16x8 min_u_i16x8(i16x8 x, i16x8 y) {
+u16x8 min_u_i16x8(u16x8 x, u16x8 y) {
   return __builtin_wasm_min_u_i16x8(x, y);
   // WEBASSEMBLY: %0 = icmp ult <8 x i16> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <8 x i1> %0, <8 x i16> %x, <8 x i16> %y
   // WEBASSEMBLY-NEXT: ret <8 x i16> %1
 }
 
 i16x8 max_s_i16x8(i16x8 x, i16x8 y) {
   return __builtin_wasm_max_s_i16x8(x, y);
   // WEBASSEMBLY: %0 = icmp sgt <8 x i16> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <8 x i1> %0, <8 x i16> %x, <8 x i16> %y
   // WEBASSEMBLY-NEXT: ret <8 x i16> %1
 }
 
-i16x8 max_u_i16x8(i16x8 x, i16x8 y) {
+u16x8 max_u_i16x8(u16x8 x, u16x8 y) {
   return __builtin_wasm_max_u_i16x8(x, y);
   // WEBASSEMBLY: %0 = icmp ugt <8 x i16> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <8 x i1> %0, <8 x i16> %x, <8 x i16> %y
   // WEBASSEMBLY-NEXT: ret <8 x i16> %1
 }
 
 i32x4 min_s_i32x4(i32x4 x, i32x4 y) {
   return __builtin_wasm_min_s_i32x4(x, y);
   // WEBASSEMBLY: %0 = icmp slt <4 x i32> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <4 x i1> %0, <4 x i32> %x, <4 x i32> %y
   // WEBASSEMBLY-NEXT: ret <4 x i32> %1
 }
 
-i32x4 min_u_i32x4(i32x4 x, i32x4 y) {
+u32x4 min_u_i32x4(u32x4 x, u32x4 y) {
   return __builtin_wasm_min_u_i32x4(x, y);
   // WEBASSEMBLY: %0 = icmp ult <4 x i32> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <4 x i1> %0, <4 x i32> %x, <4 x i32> %y
   // WEBASSEMBLY-NEXT: ret <4 x i32> %1
 }
 
 i32x4 max_s_i32x4(i32x4 x, i32x4 y) {
   return __builtin_wasm_max_s_i32x4(x, y);
   // WEBASSEMBLY: %0 = icmp sgt <4 x i32> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <4 x i1> %0, <4 x i32> %x, <4 x i32> %y
   // WEBASSEMBLY-NEXT: ret <4 x i32> %1
 }
 
-i32x4 max_u_i32x4(i32x4 x, i32x4 y) {
+u32x4 max_u_i32x4(u32x4 x, u32x4 y) {
   return __builtin_wasm_max_u_i32x4(x, y);
   // WEBASSEMBLY: %0 = icmp ugt <4 x i32> %x, %y
   // WEBASSEMBLY-NEXT: %1 = select <4 x i1> %0, <4 x i32> %x, <4 x i32> %y
   // WEBASSEMBLY-NEXT: ret <4 x i32> %1
 }
 
 i16x8 sub_saturate_s_i16x8(i16x8 x, i16x8 y) {
   return __builtin_wasm_sub_saturate_s_i16x8(x, y);
   // WEBASSEMBLY: call <8 x i16> @llvm.wasm.sub.saturate.signed.v8i16(
   // WEBASSEMBLY-SAME: <8 x i16> %x, <8 x i16> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
-i16x8 sub_saturate_u_i16x8(i16x8 x, i16x8 y) {
+u16x8 sub_saturate_u_i16x8(u16x8 x, u16x8 y) {
   return __builtin_wasm_sub_saturate_u_i16x8(x, y);
   // WEBASSEMBLY: call <8 x i16> @llvm.wasm.sub.saturate.unsigned.v8i16(
   // WEBASSEMBLY-SAME: <8 x i16> %x, <8 x i16> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
-i8x16 avgr_u_i8x16(i8x16 x, i8x16 y) {
+u8x16 avgr_u_i8x16(u8x16 x, u8x16 y) {
   return __builtin_wasm_avgr_u_i8x16(x, y);
   // WEBASSEMBLY: call <16 x i8> @llvm.wasm.avgr.unsigned.v16i8(
   // WEBASSEMBLY-SAME: <16 x i8> %x, <16 x i8> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
-i16x8 avgr_u_i16x8(i16x8 x, i16x8 y) {
+u16x8 avgr_u_i16x8(u16x8 x, u16x8 y) {
   return __builtin_wasm_avgr_u_i16x8(x, y);
   // WEBASSEMBLY: call <8 x i16> @llvm.wasm.avgr.unsigned.v8i16(
   // WEBASSEMBLY-SAME: <8 x i16> %x, <8 x i16> %y)
   // WEBASSEMBLY-NEXT: ret
 }
 
 i32x4 dot_i16x8_s(i16x8 x, i16x8 y) {
   return __builtin_wasm_dot_s_i32x4_i16x8(x, y);

 
 i8x16 narrow_s_i8x16_i16x8(i16x8 low, i16x8 high) {
   return __builtin_wasm_narrow_s_i8x16_i16x8(low, high);
   // WEBASSEMBLY: call <16 x i8> @llvm.wasm.narrow.signed.v16i8.v8i16(
   // WEBASSEMBLY-SAME: <8 x i16> %low, <8 x i16> %high)
   // WEBASSEMBLY: ret
 }
 
-i8x16 narrow_u_i8x16_i16x8(i16x8 low, i16x8 high) {
+u8x16 narrow_u_i8x16_i16x8(u16x8 low, u16x8 high) {
   return __builtin_wasm_narrow_u_i8x16_i16x8(low, high);
   // WEBASSEMBLY: call <16 x i8> @llvm.wasm.narrow.unsigned.v16i8.v8i16(
   // WEBASSEMBLY-SAME: <8 x i16> %low, <8 x i16> %high)
   // WEBASSEMBLY: ret
 }
 
 i16x8 narrow_s_i16x8_i32x4(i32x4 low, i32x4 high) {
   return __builtin_wasm_narrow_s_i16x8_i32x4(low, high);
   // WEBASSEMBLY: call <8 x i16> @llvm.wasm.narrow.signed.v8i16.v4i32(
   // WEBASSEMBLY-SAME: <4 x i32> %low, <4 x i32> %high)
   // WEBASSEMBLY: ret
 }
 
-i16x8 narrow_u_i16x8_i32x4(i32x4 low, i32x4 high) {
+u16x8 narrow_u_i16x8_i32x4(u32x4 low, u32x4 high) {
   return __builtin_wasm_narrow_u_i16x8_i32x4(low, high);
   // WEBASSEMBLY: call <8 x i16> @llvm.wasm.narrow.unsigned.v8i16.v4i32(
   // WEBASSEMBLY-SAME: <4 x i32> %low, <4 x i32> %high)
   // WEBASSEMBLY: ret
 }
 
 i8x16 swizzle_v8x16(i8x16 x, i8x16 y) {
   return __builtin_wasm_swizzle_v8x16(x, y);