[clang] f253bb6 - [WebAssembly] Fix simd bit shift intrinsics codegen
Jun Ma via cfe-commits
cfe-commits at lists.llvm.org
Thu Feb 16 17:18:06 PST 2023
Author: Jun Ma
Date: 2023-02-17T09:17:47+08:00
New Revision: f253bb640d97756d2808bb7c7b2bb31b1090a654
URL: https://github.com/llvm/llvm-project/commit/f253bb640d97756d2808bb7c7b2bb31b1090a654
DIFF: https://github.com/llvm/llvm-project/commit/f253bb640d97756d2808bb7c7b2bb31b1090a654.diff
LOG: [WebAssembly] Fix simd bit shift intrinsics codegen
According to github.com/WebAssembly/simd/blob/main/proposals/simd/SIMD.md,
the shift count of bit shift instructions is taken modulo lane width.
This patch adds such operation.
Fixes PR#60655
Differential Revision: https://reviews.llvm.org/D144169
Added:
Modified:
clang/lib/Headers/wasm_simd128.h
clang/test/Headers/wasm.c
Removed:
################################################################################
diff --git a/clang/lib/Headers/wasm_simd128.h b/clang/lib/Headers/wasm_simd128.h
index f93de129f9577..a099ab57dc68b 100644
--- a/clang/lib/Headers/wasm_simd128.h
+++ b/clang/lib/Headers/wasm_simd128.h
@@ -961,17 +961,17 @@ static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_popcnt(v128_t __a) {
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_shl(v128_t __a,
uint32_t __b) {
- return (v128_t)((__i8x16)__a << __b);
+ return (v128_t)((__i8x16)__a << (__b & 0x7));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_shr(v128_t __a,
uint32_t __b) {
- return (v128_t)((__i8x16)__a >> __b);
+ return (v128_t)((__i8x16)__a >> (__b & 0x7));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u8x16_shr(v128_t __a,
uint32_t __b) {
- return (v128_t)((__u8x16)__a >> __b);
+ return (v128_t)((__u8x16)__a >> (__b & 0x7));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i8x16_add(v128_t __a,
@@ -1047,17 +1047,17 @@ static __inline__ uint32_t __DEFAULT_FN_ATTRS wasm_i16x8_bitmask(v128_t __a) {
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_shl(v128_t __a,
uint32_t __b) {
- return (v128_t)((__i16x8)__a << __b);
+ return (v128_t)((__i16x8)__a << (__b & 0xF));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_shr(v128_t __a,
uint32_t __b) {
- return (v128_t)((__i16x8)__a >> __b);
+ return (v128_t)((__i16x8)__a >> (__b & 0xF));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u16x8_shr(v128_t __a,
uint32_t __b) {
- return (v128_t)((__u16x8)__a >> __b);
+ return (v128_t)((__u16x8)__a >> (__b & 0xF));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i16x8_add(v128_t __a,
@@ -1138,17 +1138,17 @@ static __inline__ uint32_t __DEFAULT_FN_ATTRS wasm_i32x4_bitmask(v128_t __a) {
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i32x4_shl(v128_t __a,
uint32_t __b) {
- return (v128_t)((__i32x4)__a << __b);
+ return (v128_t)((__i32x4)__a << (__b & 0x1F));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i32x4_shr(v128_t __a,
uint32_t __b) {
- return (v128_t)((__i32x4)__a >> __b);
+ return (v128_t)((__i32x4)__a >> (__b & 0x1F));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u32x4_shr(v128_t __a,
uint32_t __b) {
- return (v128_t)((__u32x4)__a >> __b);
+ return (v128_t)((__u32x4)__a >> (__b & 0x1F));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i32x4_add(v128_t __a,
@@ -1209,17 +1209,17 @@ static __inline__ uint32_t __DEFAULT_FN_ATTRS wasm_i64x2_bitmask(v128_t __a) {
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i64x2_shl(v128_t __a,
uint32_t __b) {
- return (v128_t)((__i64x2)__a << (int64_t)__b);
+ return (v128_t)((__i64x2)__a << ((int64_t)__b & 0x3F));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i64x2_shr(v128_t __a,
uint32_t __b) {
- return (v128_t)((__i64x2)__a >> (int64_t)__b);
+ return (v128_t)((__i64x2)__a >> ((int64_t)__b & 0x3F));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_u64x2_shr(v128_t __a,
uint32_t __b) {
- return (v128_t)((__u64x2)__a >> (int64_t)__b);
+ return (v128_t)((__u64x2)__a >> ((int64_t)__b & 0x3F));
}
static __inline__ v128_t __DEFAULT_FN_ATTRS wasm_i64x2_add(v128_t __a,
diff --git a/clang/test/Headers/wasm.c b/clang/test/Headers/wasm.c
index 42e11e412ea4a..a755499c6c797 100644
--- a/clang/test/Headers/wasm.c
+++ b/clang/test/Headers/wasm.c
@@ -1584,11 +1584,12 @@ v128_t test_i8x16_popcnt(v128_t a) {
// 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]], i64 0
-// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <16 x i8> [[TMP2]], <16 x i8> poison, <16 x i32> zeroinitializer
+// CHECK-NEXT: [[TMP2:%.*]] = and i8 [[TMP1]], 7
+// CHECK-NEXT: [[TMP3:%.*]] = insertelement <16 x i8> undef, i8 [[TMP2]], i64 0
+// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <16 x i8> [[TMP3]], <16 x i8> poison, <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]]
+// CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x i8> [[SHL_I]] to <4 x i32>
+// CHECK-NEXT: ret <4 x i32> [[TMP4]]
//
v128_t test_i8x16_shl(v128_t a, uint32_t b) {
return wasm_i8x16_shl(a, b);
@@ -1598,11 +1599,12 @@ v128_t test_i8x16_shl(v128_t a, uint32_t b) {
// 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]], i64 0
-// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <16 x i8> [[TMP2]], <16 x i8> poison, <16 x i32> zeroinitializer
+// CHECK-NEXT: [[TMP2:%.*]] = and i8 [[TMP1]], 7
+// CHECK-NEXT: [[TMP3:%.*]] = insertelement <16 x i8> undef, i8 [[TMP2]], i64 0
+// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <16 x i8> [[TMP3]], <16 x i8> poison, <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]]
+// CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x i8> [[SHR_I]] to <4 x i32>
+// CHECK-NEXT: ret <4 x i32> [[TMP4]]
//
v128_t test_i8x16_shr(v128_t a, uint32_t b) {
return wasm_i8x16_shr(a, b);
@@ -1612,11 +1614,12 @@ v128_t test_i8x16_shr(v128_t a, uint32_t b) {
// 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]], i64 0
-// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <16 x i8> [[TMP2]], <16 x i8> poison, <16 x i32> zeroinitializer
+// CHECK-NEXT: [[TMP2:%.*]] = and i8 [[TMP1]], 7
+// CHECK-NEXT: [[TMP3:%.*]] = insertelement <16 x i8> undef, i8 [[TMP2]], i64 0
+// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <16 x i8> [[TMP3]], <16 x i8> poison, <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]]
+// CHECK-NEXT: [[TMP4:%.*]] = bitcast <16 x i8> [[SHR_I]] to <4 x i32>
+// CHECK-NEXT: ret <4 x i32> [[TMP4]]
//
v128_t test_u8x16_shr(v128_t a, uint32_t b) {
return wasm_u8x16_shr(a, b);
@@ -1801,11 +1804,12 @@ uint32_t test_i16x8_bitmask(v128_t a) {
// 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]], i64 0
-// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <8 x i16> [[TMP2]], <8 x i16> poison, <8 x i32> zeroinitializer
+// CHECK-NEXT: [[TMP2:%.*]] = and i16 [[TMP1]], 15
+// CHECK-NEXT: [[TMP3:%.*]] = insertelement <8 x i16> undef, i16 [[TMP2]], i64 0
+// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <8 x i16> [[TMP3]], <8 x i16> poison, <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]]
+// CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i16> [[SHL_I]] to <4 x i32>
+// CHECK-NEXT: ret <4 x i32> [[TMP4]]
//
v128_t test_i16x8_shl(v128_t a, uint32_t b) {
return wasm_i16x8_shl(a, b);
@@ -1815,11 +1819,12 @@ v128_t test_i16x8_shl(v128_t a, uint32_t b) {
// 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]], i64 0
-// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <8 x i16> [[TMP2]], <8 x i16> poison, <8 x i32> zeroinitializer
+// CHECK-NEXT: [[TMP2:%.*]] = and i16 [[TMP1]], 15
+// CHECK-NEXT: [[TMP3:%.*]] = insertelement <8 x i16> undef, i16 [[TMP2]], i64 0
+// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <8 x i16> [[TMP3]], <8 x i16> poison, <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]]
+// CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i16> [[SHR_I]] to <4 x i32>
+// CHECK-NEXT: ret <4 x i32> [[TMP4]]
//
v128_t test_i16x8_shr(v128_t a, uint32_t b) {
return wasm_i16x8_shr(a, b);
@@ -1829,11 +1834,12 @@ v128_t test_i16x8_shr(v128_t a, uint32_t b) {
// 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]], i64 0
-// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <8 x i16> [[TMP2]], <8 x i16> poison, <8 x i32> zeroinitializer
+// CHECK-NEXT: [[TMP2:%.*]] = and i16 [[TMP1]], 15
+// CHECK-NEXT: [[TMP3:%.*]] = insertelement <8 x i16> undef, i16 [[TMP2]], i64 0
+// CHECK-NEXT: [[SH_PROM_I:%.*]] = shufflevector <8 x i16> [[TMP3]], <8 x i16> poison, <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]]
+// CHECK-NEXT: [[TMP4:%.*]] = bitcast <8 x i16> [[SHR_I]] to <4 x i32>
+// CHECK-NEXT: ret <4 x i32> [[TMP4]]
//
v128_t test_u16x8_shr(v128_t a, uint32_t b) {
return wasm_u16x8_shr(a, b);
@@ -2022,7 +2028,8 @@ uint32_t test_i32x4_bitmask(v128_t a) {
// CHECK-LABEL: @test_i32x4_shl(
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <4 x i32> poison, i32 [[B:%.*]], i64 0
+// CHECK-NEXT: [[REM_I:%.*]] = and i32 [[B:%.*]], 31
+// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <4 x i32> poison, i32 [[REM_I]], i64 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]]
@@ -2033,7 +2040,8 @@ v128_t test_i32x4_shl(v128_t a, uint32_t b) {
// CHECK-LABEL: @test_i32x4_shr(
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <4 x i32> poison, i32 [[B:%.*]], i64 0
+// CHECK-NEXT: [[REM_I:%.*]] = and i32 [[B:%.*]], 31
+// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <4 x i32> poison, i32 [[REM_I]], i64 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]]
@@ -2044,7 +2052,8 @@ v128_t test_i32x4_shr(v128_t a, uint32_t b) {
// CHECK-LABEL: @test_u32x4_shr(
// CHECK-NEXT: entry:
-// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <4 x i32> poison, i32 [[B:%.*]], i64 0
+// CHECK-NEXT: [[REM_I:%.*]] = and i32 [[B:%.*]], 31
+// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <4 x i32> poison, i32 [[REM_I]], i64 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]]
@@ -2173,12 +2182,13 @@ uint32_t test_i64x2_bitmask(v128_t 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:%.*]] = zext i32 [[B:%.*]] to i64
-// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <2 x i64> poison, i64 [[CONV_I]], i64 0
+// CHECK-NEXT: [[TMP1:%.*]] = and i32 [[B:%.*]], 63
+// CHECK-NEXT: [[REM_I:%.*]] = zext i32 [[TMP1]] to i64
+// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <2 x i64> poison, i64 [[REM_I]], i64 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]]
+// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[SHL_I]] to <4 x i32>
+// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
v128_t test_i64x2_shl(v128_t a, uint32_t b) {
return wasm_i64x2_shl(a, b);
@@ -2187,12 +2197,13 @@ v128_t test_i64x2_shl(v128_t a, uint32_t 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:%.*]] = zext i32 [[B:%.*]] to i64
-// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <2 x i64> poison, i64 [[CONV_I]], i64 0
+// CHECK-NEXT: [[TMP1:%.*]] = and i32 [[B:%.*]], 63
+// CHECK-NEXT: [[REM_I:%.*]] = zext i32 [[TMP1]] to i64
+// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <2 x i64> poison, i64 [[REM_I]], i64 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]]
+// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[SHR_I]] to <4 x i32>
+// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
v128_t test_i64x2_shr(v128_t a, uint32_t b) {
return wasm_i64x2_shr(a, b);
@@ -2201,12 +2212,13 @@ v128_t test_i64x2_shr(v128_t a, uint32_t 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:%.*]] = zext i32 [[B:%.*]] to i64
-// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <2 x i64> poison, i64 [[CONV_I]], i64 0
+// CHECK-NEXT: [[TMP1:%.*]] = and i32 [[B:%.*]], 63
+// CHECK-NEXT: [[REM_I:%.*]] = zext i32 [[TMP1]] to i64
+// CHECK-NEXT: [[SPLAT_SPLATINSERT_I:%.*]] = insertelement <2 x i64> poison, i64 [[REM_I]], i64 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]]
+// CHECK-NEXT: [[TMP2:%.*]] = bitcast <2 x i64> [[SHR_I]] to <4 x i32>
+// CHECK-NEXT: ret <4 x i32> [[TMP2]]
//
v128_t test_u64x2_shr(v128_t a, uint32_t b) {
return wasm_u64x2_shr(a, b);
More information about the cfe-commits
mailing list