ARM64-SVE: Add AddSequentialAcross (#104640)

* Add AddSequentialAcross * Skip inactive lanes * Generate mask data * Tweak test validation * Remove CndSel scenarios
dotnet · Nov 19, 2024 · 1673488 · 1673488
1 parent 706640a
commit 1673488
Show file tree

Hide file tree

Showing 6 changed files with 115 additions and 45 deletions.
diff --git a/src/coreclr/jit/hwintrinsiclistarm64sve.h b/src/coreclr/jit/hwintrinsiclistarm64sve.h
@@ -25,6 +25,7 @@ HARDWARE_INTRINSIC(Sve,           AbsoluteDifference,
 HARDWARE_INTRINSIC(Sve,           Add,                                                              -1,     -1,      false, {INS_sve_add,        INS_sve_add,        INS_sve_add,        INS_sve_add,        INS_sve_add,        INS_sve_add,        INS_sve_add,        INS_sve_add,        INS_sve_fadd,       INS_sve_fadd},    HW_Category_SIMD,                  HW_Flag_Scalable|HW_Flag_OptionalEmbeddedMaskedOperation|HW_Flag_HasRMWSemantics|HW_Flag_LowMaskedOperation)
 HARDWARE_INTRINSIC(Sve,           AddAcross,                                                        -1,      1,      true,  {INS_sve_saddv,      INS_sve_uaddv,      INS_sve_saddv,      INS_sve_uaddv,      INS_sve_saddv,      INS_sve_uaddv,      INS_sve_uaddv,      INS_sve_uaddv,      INS_sve_faddv,      INS_sve_faddv},   HW_Category_SIMD,                  HW_Flag_Scalable|HW_Flag_BaseTypeFromFirstArg|HW_Flag_EmbeddedMaskedOperation|HW_Flag_LowMaskedOperation)
 HARDWARE_INTRINSIC(Sve,           AddSaturate,                                                      -1,      2,      true,  {INS_sve_sqadd,      INS_sve_uqadd,      INS_sve_sqadd,      INS_sve_uqadd,      INS_sve_sqadd,      INS_sve_uqadd,      INS_sve_sqadd,      INS_sve_uqadd,      INS_invalid,        INS_invalid},     HW_Category_SIMD,                  HW_Flag_Scalable|HW_Flag_OptionalEmbeddedMaskedOperation|HW_Flag_HasRMWSemantics|HW_Flag_LowMaskedOperation)
+HARDWARE_INTRINSIC(Sve,           AddSequentialAcross,                                              -1,      -1,     false, {INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_sve_fadda,      INS_sve_fadda},   HW_Category_SIMD,                  HW_Flag_Scalable|HW_Flag_EmbeddedMaskedOperation|HW_Flag_LowMaskedOperation|HW_Flag_HasRMWSemantics)
 HARDWARE_INTRINSIC(Sve,           And,                                                              -1,     -1,      false, {INS_sve_and,        INS_sve_and,        INS_sve_and,        INS_sve_and,        INS_sve_and,        INS_sve_and,        INS_sve_and,        INS_sve_and,        INS_invalid,        INS_invalid},     HW_Category_SIMD,                  HW_Flag_Scalable|HW_Flag_OptionalEmbeddedMaskedOperation|HW_Flag_HasRMWSemantics|HW_Flag_LowMaskedOperation)
 HARDWARE_INTRINSIC(Sve,           AndAcross,                                                        -1,     -1,      false, {INS_sve_andv,       INS_sve_andv,       INS_sve_andv,       INS_sve_andv,       INS_sve_andv,       INS_sve_andv,       INS_sve_andv,       INS_sve_andv,       INS_invalid,        INS_invalid},     HW_Category_SIMD,                  HW_Flag_Scalable|HW_Flag_EmbeddedMaskedOperation|HW_Flag_LowMaskedOperation)
 HARDWARE_INTRINSIC(Sve,           BitwiseClear,                                                     -1,     -1,      false, {INS_sve_bic,        INS_sve_bic,        INS_sve_bic,        INS_sve_bic,        INS_sve_bic,        INS_sve_bic,        INS_sve_bic,        INS_sve_bic,        INS_invalid,        INS_invalid},     HW_Category_SIMD,                  HW_Flag_Scalable|HW_Flag_OptionalEmbeddedMaskedOperation|HW_Flag_HasRMWSemantics|HW_Flag_LowMaskedOperation)

diff --git a/...ries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/Sve.PlatformNotSupported.cs b/...ries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/Sve.PlatformNotSupported.cs
@@ -397,6 +397,20 @@ internal Arm64() { }
         /// </summary>
         public static unsafe Vector<ulong> AddSaturate(Vector<ulong> left, Vector<ulong> right) { throw new PlatformNotSupportedException(); }
 
+        ///  AddSequentialAcross : Add reduction (strictly-ordered)
+
+        /// <summary>
+        /// float64_t svadda[_f64](svbool_t pg, float64_t initial, svfloat64_t op)
+        ///   FADDA Dtied, Pg, Dtied, Zop.D
+        /// </summary>
+        public static unsafe Vector<double> AddSequentialAcross(Vector<double> initial, Vector<double> value) { throw new PlatformNotSupportedException(); }
+
+        /// <summary>
+        /// float32_t svadda[_f32](svbool_t pg, float32_t initial, svfloat32_t op)
+        ///   FADDA Stied, Pg, Stied, Zop.S
+        /// </summary>
+        public static unsafe Vector<float> AddSequentialAcross(Vector<float> initial, Vector<float> value) { throw new PlatformNotSupportedException(); }
+
         ///  And : Bitwise AND
 
         /// <summary>

diff --git a/src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/Sve.cs b/src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/Sve.cs
@@ -427,6 +427,20 @@ internal Arm64() { }
         /// </summary>
         public static unsafe Vector<ulong> AddSaturate(Vector<ulong> left, Vector<ulong> right) => AddSaturate(left, right);
 
+        ///  AddSequentialAcross : Add reduction (strictly-ordered)
+
+        /// <summary>
+        /// float64_t svadda[_f64](svbool_t pg, float64_t initial, svfloat64_t op)
+        ///   FADDA Dtied, Pg, Dtied, Zop.D
+        /// </summary>
+        public static unsafe Vector<double> AddSequentialAcross(Vector<double> initial, Vector<double> value) => AddSequentialAcross(initial, value);
+
+        /// <summary>
+        /// float32_t svadda[_f32](svbool_t pg, float32_t initial, svfloat32_t op)
+        ///   FADDA Stied, Pg, Stied, Zop.S
+        /// </summary>
+        public static unsafe Vector<float> AddSequentialAcross(Vector<float> initial, Vector<float> value) => AddSequentialAcross(initial, value);
+
         ///  And : Bitwise AND
 
         /// <summary>

diff --git a/src/libraries/System.Runtime.Intrinsics/ref/System.Runtime.Intrinsics.cs b/src/libraries/System.Runtime.Intrinsics/ref/System.Runtime.Intrinsics.cs
@@ -4373,6 +4373,9 @@ internal Arm64() { }
         public static System.Numerics.Vector<uint> AddSaturate(System.Numerics.Vector<uint> left, System.Numerics.Vector<uint> right) { throw null; }
         public static System.Numerics.Vector<ulong> AddSaturate(System.Numerics.Vector<ulong> left, System.Numerics.Vector<ulong> right) { throw null; }
 
+        public static System.Numerics.Vector<double> AddSequentialAcross(System.Numerics.Vector<double> initial, System.Numerics.Vector<double> value) { throw null; }
+        public static System.Numerics.Vector<float> AddSequentialAcross(System.Numerics.Vector<float> initial, System.Numerics.Vector<float> value) { throw null; }
+
         public static System.Numerics.Vector<byte> And(System.Numerics.Vector<byte> left, System.Numerics.Vector<byte> right) { throw null; }
         public static System.Numerics.Vector<short> And(System.Numerics.Vector<short> left, System.Numerics.Vector<short> right) { throw null; }
         public static System.Numerics.Vector<int> And(System.Numerics.Vector<int> left, System.Numerics.Vector<int> right) { throw null; }