Removing the legacy helper intrinsics and adding tests for their replacements (#20994)

* Removing helper intrinsics from the x86 APIs in S.P.Corelib

* Removing JIT support for the removed x86 helper intrinsics

* Removing the x86 HardwareIntrinsics tests for the removed helper APIs

* Fixing up existing usages to no longer use the removed x86 helper intrinsics

* Skip CoreFX tests dependent on the removed x86 helper intrinsics

* Adding a GenerateTests.csx and templates for the new shared helper intrinsics

* Generating the new shared helper intrinsics from their templates

* Disabling some tests for arm and arm64 that are failing due to an assert

1 files changed, 0 insertions, 18 deletions

diff --git a/src/jit/hwintrinsiclistxarch.h b/src/jit/hwintrinsiclistxarch.h
index 4052e4bc69..28678984e3 100644
--- a/src/jit/hwintrinsiclistxarch.h
+++ b/src/jit/hwintrinsiclistxarch.h
@@ -71,7 +71,6 @@ HARDWARE_INTRINSIC(SSE_CompareUnordered,                            "CompareUnor
 HARDWARE_INTRINSIC(SSE_CompareUnorderedScalar,                      "CompareUnorderedScalar",                       SSE,           3,              16,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cmpss,          INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_CopyUpperBits)
 HARDWARE_INTRINSIC(SSE_ConvertToInt32,                              "ConvertToInt32",                               SSE,          -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cvtss2si,       INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE_ConvertToInt64,                              "ConvertToInt64",                               SSE,          -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cvtss2si,       INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_NoRMWSemantics)
-HARDWARE_INTRINSIC(SSE_ConvertToSingle,                             "ConvertToSingle",                              SSE,          -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movss,          INS_invalid},           HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_BaseTypeFromFirstArg|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE_ConvertScalarToVector128Single,              "ConvertScalarToVector128Single",               SSE,          -1,              16,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cvtsi2ss,       INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_SecondArgMaybe64Bit|HW_Flag_BaseTypeFromFirstArg|HW_Flag_CopyUpperBits)
 HARDWARE_INTRINSIC(SSE_ConvertToInt32WithTruncation,                "ConvertToInt32WithTruncation",                 SSE,          -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cvttss2si,      INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE_ConvertToInt64WithTruncation,                "ConvertToInt64WithTruncation",                 SSE,          -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cvttss2si,      INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_64BitOnly|HW_Flag_NoRMWSemantics)
@@ -101,12 +100,9 @@ HARDWARE_INTRINSIC(SSE_Reciprocal,                                  "Reciprocal"
 HARDWARE_INTRINSIC(SSE_ReciprocalScalar,                            "ReciprocalScalar",                             SSE,          -1,              16,          -1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_rcpss,          INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_CopyUpperBits)
 HARDWARE_INTRINSIC(SSE_ReciprocalSqrt,                              "ReciprocalSqrt",                               SSE,          -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_rsqrtps,        INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE_ReciprocalSqrtScalar,                        "ReciprocalSqrtScalar",                         SSE,          -1,              16,          -1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_rsqrtss,        INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_CopyUpperBits)
-HARDWARE_INTRINSIC(SSE_SetScalarVector128,                          "SetScalarVector128",                           SSE,          -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movss,          INS_invalid},           HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_MultiIns|HW_Flag_NoRMWSemantics)
-HARDWARE_INTRINSIC(SSE_SetZeroVector128,                            "SetZeroVector128",                             SSE,          -1,              16,           0,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_xorps,          INS_invalid},           HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE_Shuffle,                                     "Shuffle",                                      SSE,          -1,              16,           3,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_shufps,         INS_invalid},           HW_Category_IMM,                    HW_Flag_FullRangeIMM)
 HARDWARE_INTRINSIC(SSE_Sqrt,                                        "Sqrt",                                         SSE,          -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_sqrtps,         INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE_SqrtScalar,                                  "SqrtScalar",                                   SSE,          -1,              16,          -1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_sqrtss,         INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_CopyUpperBits)
-HARDWARE_INTRINSIC(SSE_StaticCast,                                  "StaticCast",                                   SSE,          -1,              16,           1,     {INS_movaps,            INS_movaps,         INS_movaps,         INS_movaps,         INS_movaps,         INS_movaps,         INS_movaps,         INS_movaps,         INS_movaps,         INS_movaps},            HW_Category_Helper,                 HW_Flag_NoCodeGen|HW_Flag_TwoTypeGeneric)
 HARDWARE_INTRINSIC(SSE_Store,                                       "Store",                                        SSE,          -1,              16,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movups,         INS_invalid},           HW_Category_MemoryStore,            HW_Flag_NoContainment|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE_StoreAligned,                                "StoreAligned",                                 SSE,          -1,              16,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movaps,         INS_invalid},           HW_Category_MemoryStore,            HW_Flag_NoContainment|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE_StoreAlignedNonTemporal,                     "StoreAlignedNonTemporal",                      SSE,          -1,              16,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movntps,        INS_invalid},           HW_Category_MemoryStore,            HW_Flag_NoContainment|HW_Flag_NoRMWSemantics)
@@ -168,7 +164,6 @@ HARDWARE_INTRINSIC(SSE2_CompareOrdered,                             "CompareOrde
 HARDWARE_INTRINSIC(SSE2_CompareOrderedScalar,                       "CompareOrderedScalar",                         SSE2,          7,              16,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cmpsd},             HW_Category_SIMDScalar,             HW_Flag_CopyUpperBits)
 HARDWARE_INTRINSIC(SSE2_CompareUnordered,                           "CompareUnordered",                             SSE2,          3,              16,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cmppd},             HW_Category_SimpleSIMD,             HW_Flag_NoFlag)
 HARDWARE_INTRINSIC(SSE2_CompareUnorderedScalar,                     "CompareUnorderedScalar",                       SSE2,          3,              16,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cmpsd},             HW_Category_SIMDScalar,             HW_Flag_CopyUpperBits)
-HARDWARE_INTRINSIC(SSE2_ConvertToDouble,                            "ConvertToDouble",                              SSE2,         -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movsdsse2},         HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_BaseTypeFromFirstArg|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE2_ConvertToInt32,                             "ConvertToInt32",                               SSE2,         -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_mov_xmm2i,      INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cvtsd2si},          HW_Category_SIMDScalar,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_SpecialCodeGen|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE2_ConvertToInt32WithTruncation,               "ConvertToInt32WithTruncation",                 SSE2,         -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cvttsd2si},         HW_Category_SIMDScalar,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_SpecialCodeGen|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(SSE2_ConvertToInt64,                             "ConvertToInt64",                               SSE2,         -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_mov_xmm2i,      INS_invalid,        INS_invalid,        INS_cvtsd2si},          HW_Category_SIMDScalar,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_SpecialCodeGen|HW_Flag_NoRMWSemantics)
@@ -211,8 +206,6 @@ HARDWARE_INTRINSIC(SSE2_MultiplyScalar,                             "MultiplySca
 HARDWARE_INTRINSIC(SSE2_Or,                                         "Or",                                           SSE2,         -1,              16,           2,     {INS_por,               INS_por,            INS_por,            INS_por,            INS_por,            INS_por,            INS_por,            INS_por,            INS_invalid,        INS_orpd},              HW_Category_SimpleSIMD,             HW_Flag_Commutative)
 HARDWARE_INTRINSIC(SSE2_PackSignedSaturate,                         "PackSignedSaturate",                           SSE2,         -1,              16,           2,     {INS_packsswb,          INS_invalid,        INS_packssdw,       INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoFlag)
 HARDWARE_INTRINSIC(SSE2_PackUnsignedSaturate,                       "PackUnsignedSaturate",                         SSE2,         -1,              16,           2,     {INS_invalid,           INS_packuswb,       INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoFlag)
-HARDWARE_INTRINSIC(SSE2_SetScalarVector128,                         "SetScalarVector128",                           SSE2,         -1,              16,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movsdsse2},         HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_MultiIns|HW_Flag_NoRMWSemantics)
-HARDWARE_INTRINSIC(SSE2_SetZeroVector128,                           "SetZeroVector128",                             SSE2,         -1,              16,           0,     {INS_pxor,              INS_pxor,           INS_pxor,           INS_pxor,           INS_pxor,           INS_pxor,           INS_pxor,           INS_pxor,           INS_xorps,          INS_xorpd},             HW_Category_Helper,                 HW_Flag_OneTypeGeneric|HW_Flag_NoContainment)
 HARDWARE_INTRINSIC(SSE2_SumAbsoluteDifferences,                     "SumAbsoluteDifferences",                       SSE2,         -1,              16,           2,     {INS_invalid,           INS_invalid,         INS_invalid,       INS_psadbw,         INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoFlag)
 HARDWARE_INTRINSIC(SSE2_ShiftLeftLogical,                           "ShiftLeftLogical",                             SSE2,         -1,              16,           2,     {INS_invalid,           INS_invalid,        INS_psllw,          INS_psllw,          INS_pslld,          INS_pslld,          INS_psllq,          INS_psllq,          INS_invalid,        INS_invalid},           HW_Category_IMM,                    HW_Flag_MaybeIMM|HW_Flag_NoJmpTableIMM|HW_Flag_FullRangeIMM)
 HARDWARE_INTRINSIC(SSE2_ShiftLeftLogical128BitLane,                 "ShiftLeftLogical128BitLane",                   SSE2,         -1,              16,           2,     {INS_pslldq,            INS_pslldq,         INS_pslldq,         INS_pslldq,         INS_pslldq,         INS_pslldq,         INS_pslldq,         INS_pslldq,         INS_invalid,        INS_invalid},           HW_Category_IMM,                    HW_Flag_FullRangeIMM)
@@ -341,7 +334,6 @@ HARDWARE_INTRINSIC(AVX_BroadcastScalarToVector256,                  "BroadcastSc
 HARDWARE_INTRINSIC(AVX_BroadcastVector128ToVector256,               "BroadcastVector128ToVector256",                AVX,          -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_vbroadcastf128, INS_vbroadcastf128},    HW_Category_MemoryLoad,             HW_Flag_NoContainment)
 HARDWARE_INTRINSIC(AVX_Compare,                                     "Compare",                                      AVX,          -1,              32,           3,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cmpps,          INS_cmppd},             HW_Category_IMM,                    HW_Flag_NoFlag)
 HARDWARE_INTRINSIC(AVX_CompareScalar,                               "CompareScalar",                                AVX,          -1,              16,           3,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cmpss,          INS_cmpsd},             HW_Category_IMM,                    HW_Flag_CopyUpperBits)
-HARDWARE_INTRINSIC(AVX_ConvertToSingle,                             "ConvertToSingle",                              AVX,          -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movss,          INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_ConvertToVector128Int32,                     "ConvertToVector128Int32",                      AVX,          -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_cvtpd2dq,       INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_ConvertToVector128Single,                    "ConvertToVector128Single",                     AVX,          -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_cvtpd2ps,       INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_ConvertToVector256Int32,                     "ConvertToVector256Int32",                      AVX,          -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_cvtps2dq,       INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
@@ -353,14 +345,10 @@ HARDWARE_INTRINSIC(AVX_Divide,                                      "Divide",
 HARDWARE_INTRINSIC(AVX_DotProduct,                                  "DotProduct",                                   AVX,          -1,              32,           3,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_dpps,           INS_invalid},           HW_Category_IMM,                    HW_Flag_FullRangeIMM)
 HARDWARE_INTRINSIC(AVX_DuplicateEvenIndexed,                        "DuplicateEvenIndexed",                         AVX,          -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movsldup,       INS_movddup},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_DuplicateOddIndexed,                         "DuplicateOddIndexed",                          AVX,          -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movshdup,       INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
-HARDWARE_INTRINSIC(AVX_Extract,                                     "Extract",                                      AVX,          -1,              32,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_IMM,                    HW_Flag_BaseTypeFromFirstArg|HW_Flag_FullRangeIMM|HW_Flag_NoCodeGen)
-HARDWARE_INTRINSIC(AVX_ExtendToVector256,                           "ExtendToVector256",                            AVX,          -1,              32,           1,     {INS_movdqa,            INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movaps,         INS_movapd},            HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_OneTypeGeneric|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_ExtractVector128,                            "ExtractVector128",                             AVX,          -1,              32,          -1,     {INS_vextractf128,      INS_vextractf128,   INS_vextractf128,   INS_vextractf128,   INS_vextractf128,   INS_vextractf128,   INS_vextractf128,   INS_vextractf128,   INS_vextractf128,   INS_vextractf128},      HW_Category_IMM,                    HW_Flag_MaybeMemoryStore|HW_Flag_SpecialImport|HW_Flag_SpecialCodeGen|HW_Flag_FullRangeIMM)
 HARDWARE_INTRINSIC(AVX_Floor,                                       "Floor",                                        AVX,           9,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_roundps,        INS_roundpd},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
-HARDWARE_INTRINSIC(AVX_GetLowerHalf,                                "GetLowerHalf",                                 AVX,          -1,              32,           1,     {INS_movdqa,            INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movaps,         INS_movapd},            HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_OneTypeGeneric|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_HorizontalAdd,                               "HorizontalAdd",                                AVX,          -1,              32,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_haddps,         INS_haddpd},            HW_Category_SimpleSIMD,             HW_Flag_NoFlag)
 HARDWARE_INTRINSIC(AVX_HorizontalSubtract,                          "HorizontalSubtract",                           AVX,          -1,              32,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_hsubps,         INS_hsubpd},            HW_Category_SimpleSIMD,             HW_Flag_NoFlag)
-HARDWARE_INTRINSIC(AVX_Insert,                                      "Insert",                                       AVX,          -1,              32,           3,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_IMM,                    HW_Flag_FullRangeIMM|HW_Flag_NoCodeGen|HW_Flag_SecondArgMaybe64Bit)
 HARDWARE_INTRINSIC(AVX_InsertVector128,                             "InsertVector128",                              AVX,          -1,              32,           3,     {INS_vinsertf128,       INS_vinsertf128,    INS_vinsertf128,    INS_vinsertf128,    INS_vinsertf128,    INS_vinsertf128,    INS_vinsertf128,    INS_vinsertf128,    INS_vinsertf128,    INS_vinsertf128},       HW_Category_IMM,                    HW_Flag_MaybeMemoryLoad|HW_Flag_FullRangeIMM|HW_Flag_SpecialCodeGen)
 HARDWARE_INTRINSIC(AVX_LoadAlignedVector256,                        "LoadAlignedVector256",                         AVX,          -1,              32,           1,     {INS_movdqa,            INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movaps,         INS_movapd},            HW_Category_MemoryLoad,             HW_Flag_NoContainment|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_LoadDquVector256,                            "LoadDquVector256",                             AVX,          -1,              32,           1,     {INS_lddqu,             INS_lddqu,          INS_lddqu,          INS_lddqu,          INS_lddqu,          INS_lddqu,          INS_lddqu,          INS_lddqu,          INS_invalid,        INS_invalid},           HW_Category_MemoryLoad,             HW_Flag_NoContainment|HW_Flag_NoRMWSemantics)
@@ -382,13 +370,8 @@ HARDWARE_INTRINSIC(AVX_RoundToNearestInteger,                       "RoundToNear
 HARDWARE_INTRINSIC(AVX_RoundToNegativeInfinity,                     "RoundToNegativeInfinity",                      AVX,           9,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_roundps,        INS_roundpd},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_RoundToPositiveInfinity,                     "RoundToPositiveInfinity",                      AVX,          10,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_roundps,        INS_roundpd},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_RoundToZero,                                 "RoundToZero",                                  AVX,          11,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_roundps,        INS_roundpd},           HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
-HARDWARE_INTRINSIC(AVX_SetVector256,                                "SetVector256",                                 AVX,          -1,              32,          -1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_Helper,                 HW_Flag_NoCodeGen|HW_Flag_SecondArgMaybe64Bit)
-HARDWARE_INTRINSIC(AVX_SetHighLow,                                  "SetHighLow",                                   AVX,          -1,              32,           2,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_Helper,                 HW_Flag_NoCodeGen|HW_Flag_OneTypeGeneric)
-HARDWARE_INTRINSIC(AVX_SetAllVector256,                             "SetAllVector256",                              AVX,          -1,              32,           1,     {INS_vpbroadcastb,      INS_vpbroadcastb,   INS_vpbroadcastw,   INS_vpbroadcastw,   INS_vpbroadcastd,   INS_vpbroadcastd,   INS_vpbroadcastq,   INS_vpbroadcastq,   INS_vbroadcastss,   INS_vbroadcastsd},      HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_MultiIns|HW_Flag_SpecialImport|HW_Flag_OneTypeGeneric)
-HARDWARE_INTRINSIC(AVX_SetZeroVector256,                            "SetZeroVector256",                             AVX,          -1,              32,           0,     {INS_pxor,              INS_pxor,           INS_pxor,           INS_pxor,           INS_pxor,           INS_pxor,           INS_pxor,           INS_pxor,           INS_xorps,          INS_xorpd},             HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_OneTypeGeneric|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_Shuffle,                                     "Shuffle",                                      AVX,          -1,              32,           3,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_shufps,         INS_shufpd},            HW_Category_IMM,                    HW_Flag_NoRMWSemantics|HW_Flag_FullRangeIMM)
 HARDWARE_INTRINSIC(AVX_Sqrt,                                        "Sqrt",                                         AVX,          -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_sqrtps,         INS_sqrtpd},            HW_Category_SimpleSIMD,             HW_Flag_NoRMWSemantics)
-HARDWARE_INTRINSIC(AVX_StaticCast,                                  "StaticCast",                                   AVX,          -1,              32,           1,     {INS_movdqa,            INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movaps,         INS_movapd},            HW_Category_Helper,                 HW_Flag_NoCodeGen|HW_Flag_TwoTypeGeneric)
 HARDWARE_INTRINSIC(AVX_Store,                                       "Store",                                        AVX,          -1,              32,           2,     {INS_movdqu,            INS_movdqu,         INS_movdqu,         INS_movdqu,         INS_movdqu,         INS_movdqu,         INS_movdqu,         INS_movdqu,         INS_movups,         INS_movupd},            HW_Category_MemoryStore,            HW_Flag_NoContainment|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_StoreAligned,                                "StoreAligned",                                 AVX,          -1,              32,           2,     {INS_movdqa,            INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movdqa,         INS_movaps,         INS_movapd},            HW_Category_MemoryStore,            HW_Flag_NoContainment|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX_StoreAlignedNonTemporal,                     "StoreAlignedNonTemporal",                      AVX,          -1,              32,           2,     {INS_movntdq,           INS_movntdq,        INS_movntdq,        INS_movntdq,        INS_movntdq,        INS_movntdq,        INS_movntdq,        INS_movntdq,        INS_movntps,        INS_movntpd},           HW_Category_MemoryStore,            HW_Flag_NoContainment|HW_Flag_NoRMWSemantics)
@@ -421,7 +404,6 @@ HARDWARE_INTRINSIC(AVX2_BroadcastVector128ToVector256,              "BroadcastVe
 HARDWARE_INTRINSIC(AVX2_CompareEqual,                               "CompareEqual",                                 AVX2,         -1,              32,           2,     {INS_pcmpeqb,           INS_pcmpeqb,        INS_pcmpeqw,        INS_pcmpeqw,        INS_pcmpeqd,        INS_pcmpeqd,        INS_pcmpeqq,        INS_pcmpeqq,        INS_invalid,        INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_Commutative)
 HARDWARE_INTRINSIC(AVX2_CompareGreaterThan,                         "CompareGreaterThan",                           AVX2,         -1,              32,           2,     {INS_pcmpgtb,           INS_invalid,        INS_pcmpgtw,        INS_invalid,        INS_pcmpgtd,        INS_invalid,        INS_pcmpgtq,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_NoFlag)
 HARDWARE_INTRINSIC(AVX2_ExtractVector128,                           "ExtractVector128",                             AVX2,         -1,              32,          -1,     {INS_vextracti128,      INS_vextracti128,   INS_vextracti128,   INS_vextracti128,   INS_vextracti128,   INS_vextracti128,   INS_vextracti128,   INS_vextracti128,   INS_invalid,        INS_invalid},           HW_Category_IMM,                    HW_Flag_MaybeMemoryStore|HW_Flag_SpecialImport|HW_Flag_SpecialCodeGen|HW_Flag_FullRangeIMM)
-HARDWARE_INTRINSIC(AVX2_ConvertToDouble,                            "ConvertToDouble",                              AVX2,         -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_movsdsse2},         HW_Category_Helper,                 HW_Flag_NoContainment|HW_Flag_BaseTypeFromFirstArg|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX2_ConvertToInt32,                             "ConvertToInt32",                               AVX2,         -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_mov_xmm2i,      INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_SpecialCodeGen|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX2_ConvertToUInt32,                            "ConvertToUInt32",                              AVX2,         -1,              32,           1,     {INS_invalid,           INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_mov_xmm2i,      INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_SIMDScalar,             HW_Flag_BaseTypeFromFirstArg|HW_Flag_SpecialCodeGen|HW_Flag_NoRMWSemantics)
 HARDWARE_INTRINSIC(AVX2_ConvertToVector256Int16,                    "ConvertToVector256Int16",                      AVX2,         -1,              32,           1,     {INS_pmovsxbw,          INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid,        INS_invalid},           HW_Category_SimpleSIMD,             HW_Flag_BaseTypeFromFirstArg)