Skip to content

[ARM][AARCH64][NEON]: Wrong return type of NEON intrinsic vqrshrunh_n_s16, vqrshruns_n_s32, and vqrshrund_n_s64 in arm_neon.h #80819

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 6, 2024
Merged

[ARM][AARCH64][NEON]: Wrong return type of NEON intrinsic vqrshrunh_n_s16, vqrshruns_n_s32, and vqrshrund_n_s64 in arm_neon.h #80819

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions clang/include/clang/Basic/arm_neon.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1354,9 +1354,9 @@ let isScalarNarrowShift = 1 in {
// Signed/Unsigned Saturating Rounded Shift Right Narrow (Immediate)
def SCALAR_SQRSHRN_N: SInst<"vqrshrn_n", "(1<)1I", "SsSiSlSUsSUiSUl">;
// Signed Saturating Shift Right Unsigned Narrow (Immediate)
def SCALAR_SQSHRUN_N: SInst<"vqshrun_n", "(1<)1I", "SsSiSl">;
def SCALAR_SQSHRUN_N: SInst<"vqshrun_n", "(1<U)1I", "SsSiSl">;
// Signed Saturating Rounded Shift Right Unsigned Narrow (Immediate)
def SCALAR_SQRSHRUN_N: SInst<"vqrshrun_n", "(1<)1I", "SsSiSl">;
def SCALAR_SQRSHRUN_N: SInst<"vqrshrun_n", "(1<U)1I", "SsSiSl">;
}

////////////////////////////////////////////////////////////////////////////////
Expand Down
12 changes: 6 additions & 6 deletions clang/test/CodeGen/aarch64-neon-intrinsics.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14132,24 +14132,24 @@ int32_t test_vqshrund_n_s64(int64_t a) {
// CHECK: [[VQRSHRUNH_N_S16:%.*]] = call <8 x i8> @llvm.aarch64.neon.sqrshrun.v8i8(<8 x i16> [[TMP0]], i32 8)
// CHECK: [[TMP1:%.*]] = extractelement <8 x i8> [[VQRSHRUNH_N_S16]], i64 0
// CHECK: ret i8 [[TMP1]]
int8_t test_vqrshrunh_n_s16(int16_t a) {
return (int8_t)vqrshrunh_n_s16(a, 8);
uint8_t test_vqrshrunh_n_s16(int16_t a) {
return (uint8_t)vqrshrunh_n_s16(a, 8);
}

// CHECK-LABEL: @test_vqrshruns_n_s32(
// CHECK: [[TMP0:%.*]] = insertelement <4 x i32> poison, i32 %a, i64 0
// CHECK: [[VQRSHRUNS_N_S32:%.*]] = call <4 x i16> @llvm.aarch64.neon.sqrshrun.v4i16(<4 x i32> [[TMP0]], i32 16)
// CHECK: [[TMP1:%.*]] = extractelement <4 x i16> [[VQRSHRUNS_N_S32]], i64 0
// CHECK: ret i16 [[TMP1]]
int16_t test_vqrshruns_n_s32(int32_t a) {
return (int16_t)vqrshruns_n_s32(a, 16);
uint16_t test_vqrshruns_n_s32(int32_t a) {
return (uint16_t)vqrshruns_n_s32(a, 16);
}

// CHECK-LABEL: @test_vqrshrund_n_s64(
// CHECK: [[VQRSHRUND_N_S64:%.*]] = call i32 @llvm.aarch64.neon.sqrshrun.i32(i64 %a, i32 32)
// CHECK: ret i32 [[VQRSHRUND_N_S64]]
int32_t test_vqrshrund_n_s64(int64_t a) {
return (int32_t)vqrshrund_n_s64(a, 32);
uint32_t test_vqrshrund_n_s64(int64_t a) {
return (uint32_t)vqrshrund_n_s64(a, 32);
}

// CHECK-LABEL: @test_vcvts_n_f32_s32(
Expand Down