Skip to content

[mono] Intrinsify multiple LoadVector API's #98077

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
fanyang-mono merged 12 commits into from
Feb 12, 2024
Merged

[mono] Intrinsify multiple LoadVector API's #98077

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
b532aaa
Intrinsify LoadVector*
fanyang-mono Feb 7, 2024
c7ce20a
Fix the support for v128
fanyang-mono Feb 7, 2024
905f33b
Add logic to handle tuple3 and tuple4
fanyang-mono Feb 7, 2024
4b011ab
Correct intrinsics in the comment
fanyang-mono Feb 7, 2024
2bbe476
Use ld1
fanyang-mono Feb 8, 2024
7edc0aa
Enable tests for mono
fanyang-mono Feb 8, 2024
b543e0e
Intrinsify LoadVector*x*AndUnzip
fanyang-mono Feb 8, 2024
1e43ecf
Uncomment for LoadVector128x*AndUnzip
fanyang-mono Feb 8, 2024
c77dc71
Uncomment for LoadVector128x*AndUnzip 2
fanyang-mono Feb 8, 2024
4c637b7
Intrinsify LoadAndReplicateToVector*x*
fanyang-mono Feb 8, 2024
0018853
Merge remote-tracking branch 'origin/main' into intrinsify_loadVector
fanyang-mono Feb 9, 2024
b707469
Update code after merge with main branch
fanyang-mono Feb 9, 2024
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
16 changes: 0 additions & 16 deletions .../System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/AdvSimd.PlatformNotSupported.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1722,9 +1722,6 @@ internal Arm64() { }
/// </summary>
public static unsafe Vector128<ulong> LoadAndReplicateToVector128(ulong* address) { throw new PlatformNotSupportedException(); }

#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081

/// <summary>
/// A64: LD2R { Vn.16B, Vn+1.16B }, [Xn]
/// </summary>
Expand Down Expand Up @@ -1874,7 +1871,6 @@ internal Arm64() { }
/// A64: LD4R { Vn.2D, Vn+1.2D, Vn+2.2D, Vn+3.2D }, [Xn]
/// </summary>
public static unsafe (Vector128<double> Value1, Vector128<double> Value2, Vector128<double> Value3, Vector128<double> Value4) LoadAndReplicateToVector128x4(double* address) { throw new PlatformNotSupportedException(); }
#endif

/// <summary>
/// A64: LDP Dt1, Dt2, [Xn]
Expand Down Expand Up @@ -2106,9 +2102,6 @@ internal Arm64() { }
/// </summary>
public static unsafe (Vector128<ulong> Value1, Vector128<ulong> Value2) LoadPairVector128NonTemporal(ulong* address) { throw new PlatformNotSupportedException(); }

#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081

/// <summary>
/// A64: LD2 { Vn.16B, Vn+1.16B }, [Xn]
/// </summary>
Expand Down Expand Up @@ -2408,7 +2401,6 @@ internal Arm64() { }
/// A64: LD1 { Vn.2D, Vn+1.2D, Vn+2.2D, Vn+3.2D }, [Xn]
/// </summary>
public static unsafe (Vector128<double> Value1, Vector128<double> Value2, Vector128<double> Value3, Vector128<double> Value4) LoadVector128x4(double* address) { throw new PlatformNotSupportedException(); }
#endif

/// <summary>
/// float64x2_t vmaxq_f64 (float64x2_t a, float64x2_t b)
Expand Down Expand Up @@ -9383,9 +9375,6 @@ internal Arm64() { }
/// </summary>
public static unsafe Vector128<uint> LoadAndReplicateToVector128(uint* address) { throw new PlatformNotSupportedException(); }

#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081

/// <summary>
/// A64: LD2R { Vn.8B, Vn+1.8B }, [Xn]
/// </summary>
Expand Down Expand Up @@ -9490,7 +9479,6 @@ internal Arm64() { }
/// A64: LD4R { Vn.2S, Vn+1.2S, Vn+2.2S, Vn+3.2S }, [Xn]
/// </summary>
public static unsafe (Vector64<float> Value1, Vector64<float> Value2, Vector64<float> Value3, Vector64<float> Value4) LoadAndReplicateToVector64x4(float* address) { throw new PlatformNotSupportedException(); }
#endif

/// <summary>
/// uint8x8_t vld1_u8 (uint8_t const * ptr)
Expand Down Expand Up @@ -9632,9 +9620,6 @@ internal Arm64() { }
/// </summary>
public static unsafe Vector128<ulong> LoadVector128(ulong* address) { throw new PlatformNotSupportedException(); }

#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081

/// <summary>
/// A64: LD2 { Vn.8B, Vn+1.8B }, [Xn]
/// </summary>
Expand Down Expand Up @@ -9844,7 +9829,6 @@ internal Arm64() { }
/// A64: LD1 { Vn.2S, Vn+1.2S, Vn+2.2S, Vn+3.2S }, [Xn]
/// </summary>
public static unsafe (Vector64<float> Value1, Vector64<float> Value2, Vector64<float> Value3, Vector64<float> Value4) LoadVector64x4(float* address) { throw new PlatformNotSupportedException(); }
#endif

/// <summary>
/// uint8x8_t vmax_u8 (uint8x8_t a, uint8x8_t b)
Expand Down
16 changes: 0 additions & 16 deletions src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/AdvSimd.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1719,9 +1719,6 @@ internal Arm64() { }
/// </summary>
public static unsafe Vector128<ulong> LoadAndReplicateToVector128(ulong* address) => LoadAndReplicateToVector128(address);

#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081

/// <summary>
/// A64: LD2R { Vn.16B, Vn+1.16B }, [Xn]
/// </summary>
Expand Down Expand Up @@ -1871,7 +1868,6 @@ internal Arm64() { }
/// A64: LD4R { Vn.2D, Vn+1.2D, Vn+2.2D, Vn+3.2D }, [Xn]
/// </summary>
public static unsafe (Vector128<double> Value1, Vector128<double> Value2, Vector128<double> Value3, Vector128<double> Value4) LoadAndReplicateToVector128x4(double* address) => LoadAndReplicateToVector128x4(address);
#endif

/// <summary>
/// A64: LDP Dt1, Dt2, [Xn]
Expand Down Expand Up @@ -2103,9 +2099,6 @@ internal Arm64() { }
/// </summary>
public static unsafe (Vector128<ulong> Value1, Vector128<ulong> Value2) LoadPairVector128NonTemporal(ulong* address) => LoadPairVector128NonTemporal(address);

#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081

/// <summary>
/// A64: LD2 { Vn.16B, Vn+1.16B }, [Xn]
/// </summary>
Expand Down Expand Up @@ -2405,7 +2398,6 @@ internal Arm64() { }
/// A64: LD1 { Vn.2D, Vn+1.2D, Vn+2.2D, Vn+3.2D }, [Xn]
/// </summary>
public static unsafe (Vector128<double> Value1, Vector128<double> Value2, Vector128<double> Value3, Vector128<double> Value4) LoadVector128x4(double* address) => LoadVector128x4(address);
#endif

/// <summary>
/// float64x2_t vmaxq_f64 (float64x2_t a, float64x2_t b)
Expand Down Expand Up @@ -9379,9 +9371,6 @@ internal Arm64() { }
/// </summary>
public static unsafe Vector128<uint> LoadAndReplicateToVector128(uint* address) => LoadAndReplicateToVector128(address);

#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081

/// <summary>
/// A64: LD2R { Vn.8B, Vn+1.8B }, [Xn]
/// </summary>
Expand Down Expand Up @@ -9486,7 +9475,6 @@ internal Arm64() { }
/// A64: LD4R { Vn.2S, Vn+1.2S, Vn+2.2S, Vn+3.2S }, [Xn]
/// </summary>
public static unsafe (Vector64<float> Value1, Vector64<float> Value2, Vector64<float> Value3, Vector64<float> Value4) LoadAndReplicateToVector64x4(float* address) => LoadAndReplicateToVector64x4(address);
#endif

/// <summary>
/// uint8x8_t vld1_u8 (uint8_t const * ptr)
Expand Down Expand Up @@ -9628,9 +9616,6 @@ internal Arm64() { }
/// </summary>
public static unsafe Vector128<ulong> LoadVector128(ulong* address) => LoadVector128(address);

#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081

/// <summary>
/// A64: LD2 { Vn.8B, Vn+1.8B }, [Xn]
/// </summary>
Expand Down Expand Up @@ -9840,7 +9825,6 @@ internal Arm64() { }
/// A64: LD1 { Vn.2S, Vn+1.2S, Vn+2.2S, Vn+3.2S }, [Xn]
/// </summary>
public static unsafe (Vector64<float> Value1, Vector64<float> Value2, Vector64<float> Value3, Vector64<float> Value4) LoadVector64x4(float* address) => LoadVector64x4(address);
#endif

/// <summary>
/// uint8x8_t vmax_u8 (uint8x8_t a, uint8x8_t b)
Expand Down
12 changes: 0 additions & 12 deletions src/libraries/System.Runtime.Intrinsics/ref/System.Runtime.Intrinsics.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1954,8 +1954,6 @@ internal AdvSimd() { }
public static unsafe System.Runtime.Intrinsics.Vector64<float> LoadAndReplicateToVector64(float* address) { throw null; }
public static unsafe System.Runtime.Intrinsics.Vector64<ushort> LoadAndReplicateToVector64(ushort* address) { throw null; }
public static unsafe System.Runtime.Intrinsics.Vector64<uint> LoadAndReplicateToVector64(uint* address) { throw null; }
#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081
public static unsafe (System.Runtime.Intrinsics.Vector64<byte> Value1, System.Runtime.Intrinsics.Vector64<byte> Value2) LoadAndReplicateToVector64x2(byte* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<sbyte> Value1, System.Runtime.Intrinsics.Vector64<sbyte> Value2) LoadAndReplicateToVector64x2(sbyte* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<short> Value1, System.Runtime.Intrinsics.Vector64<short> Value2) LoadAndReplicateToVector64x2(short* address) { throw null; }
Expand All @@ -1977,7 +1975,6 @@ internal AdvSimd() { }
public static unsafe (System.Runtime.Intrinsics.Vector64<int> Value1, System.Runtime.Intrinsics.Vector64<int> Value2, System.Runtime.Intrinsics.Vector64<int> Value3, System.Runtime.Intrinsics.Vector64<int> Value4) LoadAndReplicateToVector64x4(int* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<uint> Value1, System.Runtime.Intrinsics.Vector64<uint> Value2, System.Runtime.Intrinsics.Vector64<uint> Value3, System.Runtime.Intrinsics.Vector64<uint> Value4) LoadAndReplicateToVector64x4(uint* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<float> Value1, System.Runtime.Intrinsics.Vector64<float> Value2, System.Runtime.Intrinsics.Vector64<float> Value3, System.Runtime.Intrinsics.Vector64<float> Value4) LoadAndReplicateToVector64x4(float* address) { throw null; }
#endif
public static unsafe System.Runtime.Intrinsics.Vector128<byte> LoadVector128(byte* address) { throw null; }
public static unsafe System.Runtime.Intrinsics.Vector128<double> LoadVector128(double* address) { throw null; }
public static unsafe System.Runtime.Intrinsics.Vector128<short> LoadVector128(short* address) { throw null; }
Expand All @@ -1998,8 +1995,6 @@ internal AdvSimd() { }
public static unsafe System.Runtime.Intrinsics.Vector64<ushort> LoadVector64(ushort* address) { throw null; }
public static unsafe System.Runtime.Intrinsics.Vector64<uint> LoadVector64(uint* address) { throw null; }
public static unsafe System.Runtime.Intrinsics.Vector64<ulong> LoadVector64(ulong* address) { throw null; }
#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081
public static unsafe (System.Runtime.Intrinsics.Vector64<byte> Value1, System.Runtime.Intrinsics.Vector64<byte> Value2) LoadVector64x2AndUnzip(byte* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<sbyte> Value1, System.Runtime.Intrinsics.Vector64<sbyte> Value2) LoadVector64x2AndUnzip(sbyte* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<short> Value1, System.Runtime.Intrinsics.Vector64<short> Value2) LoadVector64x2AndUnzip(short* address) { throw null; }
Expand Down Expand Up @@ -2042,7 +2037,6 @@ internal AdvSimd() { }
public static unsafe (System.Runtime.Intrinsics.Vector64<int> Value1, System.Runtime.Intrinsics.Vector64<int> Value2, System.Runtime.Intrinsics.Vector64<int> Value3, System.Runtime.Intrinsics.Vector64<int> Value4) LoadVector64x4(int* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<uint> Value1, System.Runtime.Intrinsics.Vector64<uint> Value2, System.Runtime.Intrinsics.Vector64<uint> Value3, System.Runtime.Intrinsics.Vector64<uint> Value4) LoadVector64x4(uint* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<float> Value1, System.Runtime.Intrinsics.Vector64<float> Value2, System.Runtime.Intrinsics.Vector64<float> Value3, System.Runtime.Intrinsics.Vector64<float> Value4) LoadVector64x4(float* address) { throw null; }
#endif
public static System.Runtime.Intrinsics.Vector128<byte> Max(System.Runtime.Intrinsics.Vector128<byte> left, System.Runtime.Intrinsics.Vector128<byte> right) { throw null; }
public static System.Runtime.Intrinsics.Vector128<short> Max(System.Runtime.Intrinsics.Vector128<short> left, System.Runtime.Intrinsics.Vector128<short> right) { throw null; }
public static System.Runtime.Intrinsics.Vector128<int> Max(System.Runtime.Intrinsics.Vector128<int> left, System.Runtime.Intrinsics.Vector128<int> right) { throw null; }
Expand Down Expand Up @@ -3383,8 +3377,6 @@ internal Arm64() { }
public static unsafe System.Runtime.Intrinsics.Vector128<double> LoadAndReplicateToVector128(double* address) { throw null; }
public static unsafe System.Runtime.Intrinsics.Vector128<long> LoadAndReplicateToVector128(long* address) { throw null; }
public static unsafe System.Runtime.Intrinsics.Vector128<ulong> LoadAndReplicateToVector128(ulong* address) { throw null; }
#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081
public static unsafe (System.Runtime.Intrinsics.Vector128<byte> Value1, System.Runtime.Intrinsics.Vector128<byte> Value2) LoadAndReplicateToVector128x2(byte* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector128<sbyte> Value1, System.Runtime.Intrinsics.Vector128<sbyte> Value2) LoadAndReplicateToVector128x2(sbyte* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector128<short> Value1, System.Runtime.Intrinsics.Vector128<short> Value2) LoadAndReplicateToVector128x2(short* address) { throw null; }
Expand Down Expand Up @@ -3415,7 +3407,6 @@ internal Arm64() { }
public static unsafe (System.Runtime.Intrinsics.Vector128<ulong> Value1, System.Runtime.Intrinsics.Vector128<ulong> Value2, System.Runtime.Intrinsics.Vector128<ulong> Value3, System.Runtime.Intrinsics.Vector128<ulong> Value4) LoadAndReplicateToVector128x4(ulong* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector128<float> Value1, System.Runtime.Intrinsics.Vector128<float> Value2, System.Runtime.Intrinsics.Vector128<float> Value3, System.Runtime.Intrinsics.Vector128<float> Value4) LoadAndReplicateToVector128x4(float* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector128<double> Value1, System.Runtime.Intrinsics.Vector128<double> Value2, System.Runtime.Intrinsics.Vector128<double> Value3, System.Runtime.Intrinsics.Vector128<double> Value4) LoadAndReplicateToVector128x4(double* address) { throw null; }
#endif
public static unsafe (System.Runtime.Intrinsics.Vector64<int> Value1, System.Runtime.Intrinsics.Vector64<int> Value2) LoadPairScalarVector64(int* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<float> Value1, System.Runtime.Intrinsics.Vector64<float> Value2) LoadPairScalarVector64(float* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<uint> Value1, System.Runtime.Intrinsics.Vector64<uint> Value2) LoadPairScalarVector64(uint* address) { throw null; }
Expand Down Expand Up @@ -3462,8 +3453,6 @@ internal Arm64() { }
public static unsafe (System.Runtime.Intrinsics.Vector64<ushort> Value1, System.Runtime.Intrinsics.Vector64<ushort> Value2) LoadPairVector64NonTemporal(ushort* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<uint> Value1, System.Runtime.Intrinsics.Vector64<uint> Value2) LoadPairVector64NonTemporal(uint* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector64<ulong> Value1, System.Runtime.Intrinsics.Vector64<ulong> Value2) LoadPairVector64NonTemporal(ulong* address) { throw null; }
#if false
// Should be disabled until Mono implements these APIs. See https://github.com/dotnet/runtime/issues/93081
public static unsafe (System.Runtime.Intrinsics.Vector128<byte> Value1, System.Runtime.Intrinsics.Vector128<byte> Value2) LoadVector128x2AndUnzip(byte* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector128<sbyte> Value1, System.Runtime.Intrinsics.Vector128<sbyte> Value2) LoadVector128x2AndUnzip(sbyte* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector128<short> Value1, System.Runtime.Intrinsics.Vector128<short> Value2) LoadVector128x2AndUnzip(short* address) { throw null; }
Expand Down Expand Up @@ -3524,7 +3513,6 @@ internal Arm64() { }
public static unsafe (System.Runtime.Intrinsics.Vector128<ulong> Value1, System.Runtime.Intrinsics.Vector128<ulong> Value2, System.Runtime.Intrinsics.Vector128<ulong> Value3, System.Runtime.Intrinsics.Vector128<ulong> Value4) LoadVector128x4(ulong* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector128<float> Value1, System.Runtime.Intrinsics.Vector128<float> Value2, System.Runtime.Intrinsics.Vector128<float> Value3, System.Runtime.Intrinsics.Vector128<float> Value4) LoadVector128x4(float* address) { throw null; }
public static unsafe (System.Runtime.Intrinsics.Vector128<double> Value1, System.Runtime.Intrinsics.Vector128<double> Value2, System.Runtime.Intrinsics.Vector128<double> Value3, System.Runtime.Intrinsics.Vector128<double> Value4) LoadVector128x4(double* address) { throw null; }
#endif
public static System.Runtime.Intrinsics.Vector128<double> Max(System.Runtime.Intrinsics.Vector128<double> left, System.Runtime.Intrinsics.Vector128<double> right) { throw null; }
public static System.Runtime.Intrinsics.Vector64<byte> MaxAcross(System.Runtime.Intrinsics.Vector128<byte> value) { throw null; }
public static System.Runtime.Intrinsics.Vector64<short> MaxAcross(System.Runtime.Intrinsics.Vector128<short> value) { throw null; }
Expand Down
19 changes: 19 additions & 0 deletions src/mono/mono/mini/llvm-intrinsics.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@
#define WidenAcross INTRIN_kind_widen_across
#define Across INTRIN_kind_across
#define Arm64DotProd INTRIN_kind_arm64_dot_prod
#define AddPointer INTRIN_kind_add_pointer
#if !defined(Generic)
#define Generic
#endif
Expand Down Expand Up @@ -361,6 +362,24 @@ INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_SADDV, aarch64_neon_saddv, Arm64, Across,
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_UADDV, aarch64_neon_uaddv, Arm64, Across, V64 | V128 | I1 | I2 | I4 | I8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_FADDV, aarch64_neon_faddv, Arm64, Across, V64 | V128 | R4 | R8)

INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD1X2_V64, aarch64_neon_ld1x2, Arm64, AddPointer, V64 | I1 | I2 | I4 | R4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD1X3_V64, aarch64_neon_ld1x3, Arm64, AddPointer, V64 | I1 | I2 | I4 | R4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD1X4_V64, aarch64_neon_ld1x4, Arm64, AddPointer, V64 | I1 | I2 | I4 | R4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD1X2_V128, aarch64_neon_ld1x2, Arm64, AddPointer, V128 | I1 | I2 | I4 | I8 | R4 | R8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD1X3_V128, aarch64_neon_ld1x3, Arm64, AddPointer, V128 | I1 | I2 | I4 | I8 | R4 | R8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD1X4_V128, aarch64_neon_ld1x4, Arm64, AddPointer, V128 | I1 | I2 | I4 | I8 | R4 | R8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD2_V64, aarch64_neon_ld2, Arm64, AddPointer, V64 | I1 | I2 | I4 | R4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD3_V64, aarch64_neon_ld3, Arm64, AddPointer, V64 | I1 | I2 | I4 | R4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD4_V64, aarch64_neon_ld4, Arm64, AddPointer, V64 | I1 | I2 | I4 | R4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD2_V128, aarch64_neon_ld2, Arm64, AddPointer, V128 | I1 | I2 | I4 | I8 | R4 | R8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD3_V128, aarch64_neon_ld3, Arm64, AddPointer, V128 | I1 | I2 | I4 | I8 | R4 | R8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD4_V128, aarch64_neon_ld4, Arm64, AddPointer, V128 | I1 | I2 | I4 | I8 | R4 | R8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD2R_V64, aarch64_neon_ld2r, Arm64, AddPointer, V64 | I1 | I2 | I4 | R4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD3R_V64, aarch64_neon_ld3r, Arm64, AddPointer, V64 | I1 | I2 | I4 | R4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD4R_V64, aarch64_neon_ld4r, Arm64, AddPointer, V64 | I1 | I2 | I4 | R4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD2R_V128, aarch64_neon_ld2r, Arm64, AddPointer, V128 | I1 | I2 | I4 | I8 | R4 | R8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD3R_V128, aarch64_neon_ld3r, Arm64, AddPointer, V128 | I1 | I2 | I4 | I8 | R4 | R8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_LD4R_V128, aarch64_neon_ld4r, Arm64, AddPointer, V128 | I1 | I2 | I4 | I8 | R4 | R8)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_SMAXV, aarch64_neon_smaxv, Arm64, Across, V64 | V128 | I1 | I2 | I4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_UMAXV, aarch64_neon_umaxv, Arm64, Across, V64 | V128 | I1 | I2 | I4)
INTRINS_OVR_TAG_KIND(AARCH64_ADV_SIMD_SMINV, aarch64_neon_sminv, Arm64, Across, V64 | V128 | I1 | I2 | I4)
Expand Down
Loading