[WebAssembly] Make shift values unsigned in wasm_simd128.h

[tlively]

Summary

On some platforms, negative shift values mean to shift in the opposite
direction, but this is not true with WebAssembly. To avoid confusion, make the
shift values in the shift intrinsics unsigned.

clang/lib/Headers/wasm_simd128.h

static __inline__ uint32_t __DEFAULT_FN_ATTRS wasm_i8x16_bitmask(v128_t __a) {
   return __builtin_wasm_bitmask_i8x16((__i8x16)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_popcnt(v128_t __a) {
   return (v128_t)__builtin_wasm_popcnt_i8x16((__i8x16)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_shl(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__i8x16)__a << __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_shr(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__i8x16)__a >> __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_shr(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_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__ bool __DEFAULT_FN_ATTRS wasm_i16x8_all_true(v128_t __a) {
   return __builtin_wasm_all_true_i16x8((__i16x8)__a);
 }
 
 static __inline__ uint32_t __DEFAULT_FN_ATTRS wasm_i16x8_bitmask(v128_t __a) {
   return __builtin_wasm_bitmask_i16x8((__i16x8)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_shl(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__i16x8)__a << __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_shr(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__i16x8)__a >> __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u16x8_shr(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_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__ bool __DEFAULT_FN_ATTRS wasm_i32x4_all_true(v128_t __a) {
   return __builtin_wasm_all_true_i32x4((__i32x4)__a);
 }
 
 static __inline__ uint32_t __DEFAULT_FN_ATTRS wasm_i32x4_bitmask(v128_t __a) {
   return __builtin_wasm_bitmask_i32x4((__i32x4)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i32x4_shl(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__i32x4)__a << __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i32x4_shr(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__i32x4)__a >> __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u32x4_shr(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__u32x4)__a >> __b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i32x4_add(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)((__u32x4)__a + (__u32x4)__b);
 }
 
static __inline__ bool __DEFAULT_FN_ATTRS wasm_i64x2_all_true(v128_t __a) {
   return __builtin_wasm_all_true_i64x2((__i64x2)__a);
 }
 
 static __inline__ uint32_t __DEFAULT_FN_ATTRS wasm_i64x2_bitmask(v128_t __a) {
   return __builtin_wasm_bitmask_i64x2((__i64x2)__a);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i64x2_shl(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__i64x2)__a << (int64_t)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i64x2_shr(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__i64x2)__a >> (int64_t)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u64x2_shr(v128_t __a,
-                                                           int32_t __b) {
+                                                           uint32_t __b) {
   return (v128_t)((__u64x2)__a >> (int64_t)__b);
 }
 
 static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i64x2_add(v128_t __a,
                                                            v128_t __b) {
   return (v128_t)((__u64x2)__a + (__u64x2)__b);
 }
 

clang/test/Headers/wasm.c

 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <16 x i8>
 // CHECK-NEXT:    [[TMP1:%.*]] = trunc i32 [[B:%.*]] to i8
 // CHECK-NEXT:    [[TMP2:%.*]] = insertelement <16 x i8> undef, i8 [[TMP1]], i32 0
 // CHECK-NEXT:    [[SH_PROM_I:%.*]] = shufflevector <16 x i8> [[TMP2]], <16 x i8> undef, <16 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHL_I:%.*]] = shl <16 x i8> [[TMP0]], [[SH_PROM_I]]
 // CHECK-NEXT:    [[TMP3:%.*]] = bitcast <16 x i8> [[SHL_I]] to <4 x i32>
 // CHECK-NEXT:    ret <4 x i32> [[TMP3]]
 //
-v128_t test_i8x16_shl(v128_t a, int32_t b) {
+v128_t test_i8x16_shl(v128_t a, uint32_t b) {
   return wasm_i8x16_shl(a, b);
 }
 
 // CHECK-LABEL: @test_i8x16_shr(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <16 x i8>
 // CHECK-NEXT:    [[TMP1:%.*]] = trunc i32 [[B:%.*]] to i8
 // CHECK-NEXT:    [[TMP2:%.*]] = insertelement <16 x i8> undef, i8 [[TMP1]], i32 0
 // CHECK-NEXT:    [[SH_PROM_I:%.*]] = shufflevector <16 x i8> [[TMP2]], <16 x i8> undef, <16 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHR_I:%.*]] = ashr <16 x i8> [[TMP0]], [[SH_PROM_I]]
 // CHECK-NEXT:    [[TMP3:%.*]] = bitcast <16 x i8> [[SHR_I]] to <4 x i32>
 // CHECK-NEXT:    ret <4 x i32> [[TMP3]]
 //
-v128_t test_i8x16_shr(v128_t a, int32_t b) {
+v128_t test_i8x16_shr(v128_t a, uint32_t b) {
   return wasm_i8x16_shr(a, b);
 }
 
 // CHECK-LABEL: @test_u8x16_shr(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <16 x i8>
 // CHECK-NEXT:    [[TMP1:%.*]] = trunc i32 [[B:%.*]] to i8
 // CHECK-NEXT:    [[TMP2:%.*]] = insertelement <16 x i8> undef, i8 [[TMP1]], i32 0
 // CHECK-NEXT:    [[SH_PROM_I:%.*]] = shufflevector <16 x i8> [[TMP2]], <16 x i8> undef, <16 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHR_I:%.*]] = lshr <16 x i8> [[TMP0]], [[SH_PROM_I]]
 // CHECK-NEXT:    [[TMP3:%.*]] = bitcast <16 x i8> [[SHR_I]] to <4 x i32>
 // CHECK-NEXT:    ret <4 x i32> [[TMP3]]
 //
-v128_t test_u8x16_shr(v128_t a, int32_t b) {
+v128_t test_u8x16_shr(v128_t a, uint32_t b) {
   return wasm_u8x16_shr(a, b);
 }
 
 // CHECK-LABEL: @test_i8x16_add(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <16 x i8>
 // CHECK-NEXT:    [[TMP1:%.*]] = bitcast <4 x i32> [[B:%.*]] to <16 x i8>
 // CHECK-NEXT:    [[ADD_I:%.*]] = add <16 x i8> [[TMP1]], [[TMP0]]

 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <8 x i16>
 // CHECK-NEXT:    [[TMP1:%.*]] = trunc i32 [[B:%.*]] to i16
 // CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x i16> undef, i16 [[TMP1]], i32 0
 // CHECK-NEXT:    [[SH_PROM_I:%.*]] = shufflevector <8 x i16> [[TMP2]], <8 x i16> undef, <8 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHL_I:%.*]] = shl <8 x i16> [[TMP0]], [[SH_PROM_I]]
 // CHECK-NEXT:    [[TMP3:%.*]] = bitcast <8 x i16> [[SHL_I]] to <4 x i32>
 // CHECK-NEXT:    ret <4 x i32> [[TMP3]]
 //
-v128_t test_i16x8_shl(v128_t a, int32_t b) {
+v128_t test_i16x8_shl(v128_t a, uint32_t b) {
   return wasm_i16x8_shl(a, b);
 }
 
 // CHECK-LABEL: @test_i16x8_shr(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <8 x i16>
 // CHECK-NEXT:    [[TMP1:%.*]] = trunc i32 [[B:%.*]] to i16
 // CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x i16> undef, i16 [[TMP1]], i32 0
 // CHECK-NEXT:    [[SH_PROM_I:%.*]] = shufflevector <8 x i16> [[TMP2]], <8 x i16> undef, <8 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHR_I:%.*]] = ashr <8 x i16> [[TMP0]], [[SH_PROM_I]]
 // CHECK-NEXT:    [[TMP3:%.*]] = bitcast <8 x i16> [[SHR_I]] to <4 x i32>
 // CHECK-NEXT:    ret <4 x i32> [[TMP3]]
 //
-v128_t test_i16x8_shr(v128_t a, int32_t b) {
+v128_t test_i16x8_shr(v128_t a, uint32_t b) {
   return wasm_i16x8_shr(a, b);
 }
 
 // CHECK-LABEL: @test_u16x8_shr(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <8 x i16>
 // CHECK-NEXT:    [[TMP1:%.*]] = trunc i32 [[B:%.*]] to i16
 // CHECK-NEXT:    [[TMP2:%.*]] = insertelement <8 x i16> undef, i16 [[TMP1]], i32 0
 // CHECK-NEXT:    [[SH_PROM_I:%.*]] = shufflevector <8 x i16> [[TMP2]], <8 x i16> undef, <8 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHR_I:%.*]] = lshr <8 x i16> [[TMP0]], [[SH_PROM_I]]
 // CHECK-NEXT:    [[TMP3:%.*]] = bitcast <8 x i16> [[SHR_I]] to <4 x i32>
 // CHECK-NEXT:    ret <4 x i32> [[TMP3]]
 //
-v128_t test_u16x8_shr(v128_t a, int32_t b) {
+v128_t test_u16x8_shr(v128_t a, uint32_t b) {
   return wasm_u16x8_shr(a, b);
 }
 
 // CHECK-LABEL: @test_i16x8_add(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <8 x i16>
 // CHECK-NEXT:    [[TMP1:%.*]] = bitcast <4 x i32> [[B:%.*]] to <8 x i16>
 // CHECK-NEXT:    [[ADD_I:%.*]] = add <8 x i16> [[TMP1]], [[TMP0]]

 
 // CHECK-LABEL: @test_i32x4_shl(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <4 x i32> poison, i32 [[B:%.*]], i32 0
 // CHECK-NEXT:    [[SPLAT_SPLAT_I:%.*]] = shufflevector <4 x i32> [[SPLAT_SPLATINSERT_I]], <4 x i32> poison, <4 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHL_I:%.*]] = shl <4 x i32> [[A:%.*]], [[SPLAT_SPLAT_I]]
 // CHECK-NEXT:    ret <4 x i32> [[SHL_I]]
 //
-v128_t test_i32x4_shl(v128_t a, int32_t b) {
+v128_t test_i32x4_shl(v128_t a, uint32_t b) {
   return wasm_i32x4_shl(a, b);
 }
 
 // CHECK-LABEL: @test_i32x4_shr(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <4 x i32> poison, i32 [[B:%.*]], i32 0
 // CHECK-NEXT:    [[SPLAT_SPLAT_I:%.*]] = shufflevector <4 x i32> [[SPLAT_SPLATINSERT_I]], <4 x i32> poison, <4 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHR_I:%.*]] = ashr <4 x i32> [[A:%.*]], [[SPLAT_SPLAT_I]]
 // CHECK-NEXT:    ret <4 x i32> [[SHR_I]]
 //
-v128_t test_i32x4_shr(v128_t a, int32_t b) {
+v128_t test_i32x4_shr(v128_t a, uint32_t b) {
   return wasm_i32x4_shr(a, b);
 }
 
 // CHECK-LABEL: @test_u32x4_shr(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <4 x i32> poison, i32 [[B:%.*]], i32 0
 // CHECK-NEXT:    [[SPLAT_SPLAT_I:%.*]] = shufflevector <4 x i32> [[SPLAT_SPLATINSERT_I]], <4 x i32> poison, <4 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHR_I:%.*]] = lshr <4 x i32> [[A:%.*]], [[SPLAT_SPLAT_I]]
 // CHECK-NEXT:    ret <4 x i32> [[SHR_I]]
 //
-v128_t test_u32x4_shr(v128_t a, int32_t b) {
+v128_t test_u32x4_shr(v128_t a, uint32_t b) {
   return wasm_u32x4_shr(a, b);
 }
 
 // CHECK-LABEL: @test_i32x4_add(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[ADD_I:%.*]] = add <4 x i32> [[B:%.*]], [[A:%.*]]
 // CHECK-NEXT:    ret <4 x i32> [[ADD_I]]
 //

 //
 uint32_t test_i64x2_bitmask(v128_t a) {
   return wasm_i64x2_bitmask(a);
 }
 
 // CHECK-LABEL: @test_i64x2_shl(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <2 x i64>
-// CHECK-NEXT:    [[CONV_I:%.*]] = sext i32 [[B:%.*]] to i64
+// CHECK-NEXT:    [[CONV_I:%.*]] = zext i32 [[B:%.*]] to i64
 // CHECK-NEXT:    [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <2 x i64> poison, i64 [[CONV_I]], i32 0
 // CHECK-NEXT:    [[SPLAT_SPLAT_I:%.*]] = shufflevector <2 x i64> [[SPLAT_SPLATINSERT_I]], <2 x i64> poison, <2 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHL_I:%.*]] = shl <2 x i64> [[TMP0]], [[SPLAT_SPLAT_I]]
 // CHECK-NEXT:    [[TMP1:%.*]] = bitcast <2 x i64> [[SHL_I]] to <4 x i32>
 // CHECK-NEXT:    ret <4 x i32> [[TMP1]]
 //
-v128_t test_i64x2_shl(v128_t a, int32_t b) {
+v128_t test_i64x2_shl(v128_t a, uint32_t b) {
   return wasm_i64x2_shl(a, b);
 }
 
 // CHECK-LABEL: @test_i64x2_shr(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <2 x i64>
-// CHECK-NEXT:    [[CONV_I:%.*]] = sext i32 [[B:%.*]] to i64
+// CHECK-NEXT:    [[CONV_I:%.*]] = zext i32 [[B:%.*]] to i64
 // CHECK-NEXT:    [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <2 x i64> poison, i64 [[CONV_I]], i32 0
 // CHECK-NEXT:    [[SPLAT_SPLAT_I:%.*]] = shufflevector <2 x i64> [[SPLAT_SPLATINSERT_I]], <2 x i64> poison, <2 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHR_I:%.*]] = ashr <2 x i64> [[TMP0]], [[SPLAT_SPLAT_I]]
 // CHECK-NEXT:    [[TMP1:%.*]] = bitcast <2 x i64> [[SHR_I]] to <4 x i32>
 // CHECK-NEXT:    ret <4 x i32> [[TMP1]]
 //
-v128_t test_i64x2_shr(v128_t a, int32_t b) {
+v128_t test_i64x2_shr(v128_t a, uint32_t b) {
   return wasm_i64x2_shr(a, b);
 }
 
 // CHECK-LABEL: @test_u64x2_shr(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <2 x i64>
-// CHECK-NEXT:    [[CONV_I:%.*]] = sext i32 [[B:%.*]] to i64
+// CHECK-NEXT:    [[CONV_I:%.*]] = zext i32 [[B:%.*]] to i64
 // CHECK-NEXT:    [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <2 x i64> poison, i64 [[CONV_I]], i32 0
 // CHECK-NEXT:    [[SPLAT_SPLAT_I:%.*]] = shufflevector <2 x i64> [[SPLAT_SPLATINSERT_I]], <2 x i64> poison, <2 x i32> zeroinitializer
 // CHECK-NEXT:    [[SHR_I:%.*]] = lshr <2 x i64> [[TMP0]], [[SPLAT_SPLAT_I]]
 // CHECK-NEXT:    [[TMP1:%.*]] = bitcast <2 x i64> [[SHR_I]] to <4 x i32>
 // CHECK-NEXT:    ret <4 x i32> [[TMP1]]
 //
-v128_t test_u64x2_shr(v128_t a, int32_t b) {
+v128_t test_u64x2_shr(v128_t a, uint32_t b) {
   return wasm_u64x2_shr(a, b);
 }
 
 // CHECK-LABEL: @test_i64x2_add(
 // CHECK-NEXT:  entry:
 // CHECK-NEXT:    [[TMP0:%.*]] = bitcast <4 x i32> [[A:%.*]] to <2 x i64>
 // CHECK-NEXT:    [[TMP1:%.*]] = bitcast <4 x i32> [[B:%.*]] to <2 x i64>
 // CHECK-NEXT:    [[ADD_I:%.*]] = add <2 x i64> [[TMP1]], [[TMP0]]