[JitDiff X64] [tannergooding] Improve the handling of SIMD comparisons

[MihuBot]

Job completed in 14 minutes.
dotnet/runtime#104944

Diffs

Diffs

Found 277 files with textual diffs.

Summary of Code Size diffs:
(Lower is better)

Total bytes of base: 39198197
Total bytes of diff: 39195568
Total bytes of delta: -2629 (-0.01 % of base)
Total relative delta: -19.78
    diff is an improvement.
    relative diff is an improvement.


Top file improvements (bytes):
       -2316 : System.Private.CoreLib.dasm (-0.03 % of base)
        -101 : System.Memory.dasm (-0.03 % of base)
         -31 : System.Collections.Immutable.dasm (-0.00 % of base)
         -30 : System.Text.Json.dasm (-0.00 % of base)
         -26 : System.Collections.dasm (-0.01 % of base)
         -25 : System.Collections.Concurrent.dasm (-0.01 % of base)
         -15 : System.Composition.TypedParts.dasm (-0.03 % of base)
         -15 : System.Linq.Expressions.dasm (-0.00 % of base)
         -15 : System.ComponentModel.Composition.dasm (-0.00 % of base)
         -15 : System.Data.Common.dasm (-0.00 % of base)
         -10 : Microsoft.CSharp.dasm (-0.00 % of base)
          -5 : System.Linq.dasm (-0.00 % of base)
          -5 : System.Reflection.Context.dasm (-0.01 % of base)
          -5 : System.Numerics.Tensors.dasm (-0.00 % of base)
          -5 : System.Linq.Queryable.dasm (-0.00 % of base)
          -5 : System.Linq.Parallel.dasm (-0.00 % of base)
          -5 : System.ComponentModel.TypeConverter.dasm (-0.00 % of base)

17 total files with Code Size differences (17 improved, 0 regressed), 242 unchanged.

Top method improvements (bytes):
        -203 (-10.75 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
        -198 (-10.55 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
        -134 (-10.09 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
        -129 (-9.58 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -95 (-11.31 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOf[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],int):int (FullOpts)
         -62 (-7.87 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:Contains[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],int):ubyte (FullOpts)
         -62 (-7.53 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOf[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],int):int (FullOpts)
         -59 (-6.50 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:SequenceEqual[System.Numerics.Vector`1[float]](byref,byref,int):ubyte (FullOpts)
         -31 (-51.67 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[long]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[long],System.Runtime.Intrinsics.Vector128`1[long]):ubyte (FullOpts)
         -30 (-4.50 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:IndexOfAnyExcept[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]):int (FullOpts)
         -29 (-50.88 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):ubyte (FullOpts)
         -29 (-50.88 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[short]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):ubyte (FullOpts)
         -29 (-50.88 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[ubyte]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):ubyte (FullOpts)
         -26 (-1.00 % of base) : System.Memory.dasm - System.Buffers.SequenceReader`1[System.Numerics.Vector`1[float]]:TryReadTo(byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],ubyte):ubyte:this (FullOpts) (2 methods)
         -24 (-10.08 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4:Equals(System.Numerics.Matrix4x4):ubyte:this (FullOpts)
         -24 (-9.06 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4:Equals(System.Object):ubyte:this (FullOpts)
         -24 (-10.00 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4+Impl:Equals(byref):ubyte:this (FullOpts)
         -24 (-9.16 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4+Impl:Equals(System.Object):ubyte:this (FullOpts)
         -24 (-10.08 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4+Impl:System.IEquatable<System.Numerics.Matrix4x4.Impl>.Equals(System.Numerics.Matrix4x4+Impl):ubyte:this (FullOpts)
         -24 (-9.80 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -24 (-9.84 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -22 (-8.98 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2:Equals(System.Object):ubyte:this (FullOpts)
         -22 (-9.09 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2+Impl:Equals(System.Object):ubyte:this (FullOpts)
         -21 (-87.50 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.AnyWhereAllBitsSet(System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -20 (-4.37 % of base) : System.Memory.dasm - System.Buffers.SequenceReader`1[System.Numerics.Vector`1[float]]:AdvancePastAny(System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):long:this (FullOpts)
         -20 (-0.82 % of base) : System.Memory.dasm - System.Buffers.SequenceReader`1[System.Numerics.Vector`1[float]]:TryReadToSlow(byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int,ubyte):ubyte:this (FullOpts) (2 methods)
         -19 (-9.95 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -18 (-8.26 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2:Equals(System.Numerics.Matrix3x2):ubyte:this (FullOpts)
         -18 (-8.18 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2+Impl:Equals(byref):ubyte:this (FullOpts)
         -18 (-8.26 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2+Impl:System.IEquatable<System.Numerics.Matrix3x2.Impl>.Equals(System.Numerics.Matrix3x2+Impl):ubyte:this (FullOpts)
         -16 (-84.21 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.AnyWhereAllBitsSet(System.Numerics.Vector`1[double]):ubyte (FullOpts)
         -16 (-84.21 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.AnyWhereAllBitsSet(System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -15 (-4.09 % of base) : System.Memory.dasm - System.Buffers.SequenceReader`1[System.Numerics.Vector`1[float]]:AdvancePastAny(System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):long:this (FullOpts)
         -15 (-10.34 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):int (FullOpts)
         -15 (-7.81 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -14 (-3.81 % of base) : System.Private.CoreLib.dasm - System.Collections.Generic.ObjectEqualityComparer`1[System.Numerics.Vector`1[float]]:IndexOf(System.Numerics.Vector`1[float][],System.Numerics.Vector`1[float],int,int):int:this (FullOpts)
         -14 (-3.76 % of base) : System.Private.CoreLib.dasm - System.Collections.Generic.ObjectEqualityComparer`1[System.Numerics.Vector`1[float]]:LastIndexOf(System.Numerics.Vector`1[float][],System.Numerics.Vector`1[float],int,int):int:this (FullOpts)
         -13 (-6.81 % of base) : System.Collections.dasm - System.Collections.Generic.LinkedList`1[System.Numerics.Vector`1[float]]:FindLast(System.Numerics.Vector`1[float]):System.Collections.Generic.LinkedListNode`1[System.Numerics.Vector`1[float]]:this (FullOpts)
         -13 (-4.15 % of base) : System.Private.CoreLib.dasm - System.Collections.Generic.NullableEqualityComparer`1[System.Numerics.Vector`1[float]]:IndexOf(System.Nullable`1[System.Numerics.Vector`1[float]][],System.Nullable`1[System.Numerics.Vector`1[float]],int,int):int:this (FullOpts)
         -13 (-4.13 % of base) : System.Private.CoreLib.dasm - System.Collections.Generic.NullableEqualityComparer`1[System.Numerics.Vector`1[float]]:LastIndexOf(System.Nullable`1[System.Numerics.Vector`1[float]][],System.Nullable`1[System.Numerics.Vector`1[float]],int,int):int:this (FullOpts)
         -13 (-2.06 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]):int (FullOpts)
         -13 (-81.25 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.AnyWhereAllBitsSet(System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanAll[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -12 (-13.64 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanAll[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanAll[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanOrEqualAll[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanAll[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -12 (-13.64 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanAll[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanAll[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanOrEqualAll[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanAll[double](System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanAll[long](System.Runtime.Intrinsics.Vector512`1[long],System.Runtime.Intrinsics.Vector512`1[long]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanOrEqualAll[double](System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanAll[double](System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanAll[long](System.Runtime.Intrinsics.Vector512`1[long],System.Runtime.Intrinsics.Vector512`1[long]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanOrEqualAll[double](System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -10 (-3.44 % of base) : System.Memory.dasm - System.Buffers.SequenceReader`1[System.Numerics.Vector`1[float]]:AdvancePastAny(System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):long:this (FullOpts)
         -10 (-4.78 % of base) : System.Private.CoreLib.dasm - System.Collections.Generic.GenericEqualityComparer`1[System.Numerics.Vector`1[float]]:IndexOf(System.Numerics.Vector`1[float][],System.Numerics.Vector`1[float],int,int):int:this (FullOpts)
         -10 (-4.69 % of base) : System.Private.CoreLib.dasm - System.Collections.Generic.GenericEqualityComparer`1[System.Numerics.Vector`1[float]]:LastIndexOf(System.Numerics.Vector`1[float][],System.Numerics.Vector`1[float],int,int):int:this (FullOpts)
         -10 (-4.61 % of base) : System.Data.Common.dasm - System.Data.DataRowComparer:CompareEquatableArray[System.Numerics.Vector`1[float]](System.Numerics.Vector`1[float][],System.Numerics.Vector`1[float][]):ubyte (FullOpts)
         -10 (-7.14 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:ContainsAnyExcept[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):ubyte (FullOpts)
         -10 (-7.14 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:ContainsAnyExcept[System.Numerics.Vector`1[float]](System.Span`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):ubyte (FullOpts)
         -10 (-7.41 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:IndexOfAnyExcept[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):int (FullOpts)
         -10 (-7.41 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:IndexOfAnyExcept[System.Numerics.Vector`1[float]](System.Span`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):int (FullOpts)
         -10 (-7.41 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](System.Span`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):int (FullOpts)
         -10 (-11.63 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanAll[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):ubyte (FullOpts)
         -10 (-11.63 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanAll[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):ubyte (FullOpts)
         -10 (-9.80 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanAll[int](System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):ubyte (FullOpts)
         -10 (-9.80 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanAll[short](System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):ubyte (FullOpts)
         -10 (-9.80 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanAll[int](System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):ubyte (FullOpts)
         -10 (-9.80 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanAll[short](System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):ubyte (FullOpts)
         -10 (-7.25 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -10 (-7.30 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
          -9 (-3.53 % of base) : System.Collections.Immutable.dasm - System.Collections.Frozen.ValueTypeDefaultComparerFrozenDictionary`2[System.Numerics.Vector`1[float],System.Nullable`1[int]]:GetValueRefOrNullRefCore(System.Numerics.Vector`1[float]):byref:this (FullOpts)
          -6 (-10.53 % of base) : System.Private.CoreLib.dasm - System.Numerics.Plane:Equals(System.Numerics.Plane):ubyte:this (FullOpts)
          -6 (-6.98 % of base) : System.Private.CoreLib.dasm - System.Numerics.Plane:Equals(System.Object):ubyte:this (FullOpts)
          -6 (-10.53 % of base) : System.Private.CoreLib.dasm - System.Numerics.Quaternion:Equals(System.Numerics.Quaternion):ubyte:this (FullOpts)
          -6 (-6.98 % of base) : System.Private.CoreLib.dasm - System.Numerics.Quaternion:Equals(System.Object):ubyte:this (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.GreaterThanAll(System.Numerics.Vector`1[double],System.Numerics.Vector`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.GreaterThanOrEqualAll(System.Numerics.Vector`1[double],System.Numerics.Vector`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.LessThanAll(System.Numerics.Vector`1[double],System.Numerics.Vector`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.LessThanOrEqualAll(System.Numerics.Vector`1[double],System.Numerics.Vector`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.GreaterThanAll(System.Numerics.Vector`1[long],System.Numerics.Vector`1[long]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.LessThanAll(System.Numerics.Vector`1[long],System.Numerics.Vector`1[long]):ubyte (FullOpts)
          -6 (-9.38 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector2:Equals(System.Numerics.Vector2):ubyte:this (FullOpts)
          -6 (-6.12 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector2:Equals(System.Object):ubyte:this (FullOpts)
          -6 (-7.32 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector3:Equals(System.Numerics.Vector3):ubyte:this (FullOpts)
          -6 (-5.36 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector3:Equals(System.Object):ubyte:this (FullOpts)
          -6 (-10.53 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector4:Equals(System.Numerics.Vector4):ubyte:this (FullOpts)
          -6 (-6.98 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector4:Equals(System.Object):ubyte:this (FullOpts)
          -6 (-6.98 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:Equals(System.Object):ubyte:this (FullOpts)
          -6 (-9.68 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:Equals(System.Runtime.Intrinsics.Vector128`1[double]):ubyte:this (FullOpts)
          -6 (-10.00 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.GreaterThanOrEqualAll(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.LessThanOrEqualAll(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
          -6 (-17.65 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):ubyte (FullOpts)
          -6 (-17.65 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector128`1[long],System.Runtime.Intrinsics.Vector128`1[long]):ubyte (FullOpts)

Top method improvements (percentages):
         -21 (-87.50 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.AnyWhereAllBitsSet(System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -16 (-84.21 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.AnyWhereAllBitsSet(System.Numerics.Vector`1[double]):ubyte (FullOpts)
         -16 (-84.21 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.AnyWhereAllBitsSet(System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -13 (-81.25 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.AnyWhereAllBitsSet(System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
         -31 (-51.67 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[long]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[long],System.Runtime.Intrinsics.Vector128`1[long]):ubyte (FullOpts)
         -29 (-50.88 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):ubyte (FullOpts)
         -29 (-50.88 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[short]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):ubyte (FullOpts)
         -29 (-50.88 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[ubyte]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):ubyte (FullOpts)
          -6 (-17.65 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):ubyte (FullOpts)
          -6 (-17.65 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.GreaterThanOrEqualAll(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.LessThanOrEqualAll(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector128`1[long],System.Runtime.Intrinsics.Vector128`1[long]):ubyte (FullOpts)
          -6 (-17.14 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector128`1[long],System.Runtime.Intrinsics.Vector128`1[long]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.GreaterThanAll(System.Numerics.Vector`1[double],System.Numerics.Vector`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.GreaterThanOrEqualAll(System.Numerics.Vector`1[double],System.Numerics.Vector`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.LessThanAll(System.Numerics.Vector`1[double],System.Numerics.Vector`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.LessThanOrEqualAll(System.Numerics.Vector`1[double],System.Numerics.Vector`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.GreaterThanAll(System.Numerics.Vector`1[long],System.Numerics.Vector`1[long]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.LessThanAll(System.Numerics.Vector`1[long],System.Numerics.Vector`1[long]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.GreaterThanOrEqualAll(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.LessThanOrEqualAll(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):ubyte (FullOpts)
          -6 (-15.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):ubyte (FullOpts)
          -5 (-15.15 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):ubyte (FullOpts)
          -5 (-15.15 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):ubyte (FullOpts)
          -5 (-13.89 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.GreaterThanAll(System.Numerics.Vector`1[int],System.Numerics.Vector`1[int]):ubyte (FullOpts)
          -5 (-13.89 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.LessThanAll(System.Numerics.Vector`1[int],System.Numerics.Vector`1[int]):ubyte (FullOpts)
          -5 (-13.89 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.GreaterThanAll(System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):ubyte (FullOpts)
          -5 (-13.89 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.LessThanAll(System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):ubyte (FullOpts)
          -5 (-13.89 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):ubyte (FullOpts)
          -5 (-13.89 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):ubyte (FullOpts)
          -5 (-13.89 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.GreaterThanAll(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):ubyte (FullOpts)
          -5 (-13.89 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.LessThanAll(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):ubyte (FullOpts)
         -12 (-13.64 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanAll[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):ubyte (FullOpts)
         -12 (-13.64 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanAll[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanAll[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanAll[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanOrEqualAll[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanAll[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanAll[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):ubyte (FullOpts)
         -12 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanOrEqualAll[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):ubyte (FullOpts)
         -10 (-11.63 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanAll[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):ubyte (FullOpts)
         -10 (-11.63 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanAll[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanAll[double](System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanAll[long](System.Runtime.Intrinsics.Vector512`1[long],System.Runtime.Intrinsics.Vector512`1[long]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanOrEqualAll[double](System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanAll[double](System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanAll[long](System.Runtime.Intrinsics.Vector512`1[long],System.Runtime.Intrinsics.Vector512`1[long]):ubyte (FullOpts)
         -12 (-11.32 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanOrEqualAll[double](System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double]):ubyte (FullOpts)
         -95 (-11.31 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOf[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],int):int (FullOpts)
        -203 (-10.75 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
        -198 (-10.55 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
          -6 (-10.53 % of base) : System.Private.CoreLib.dasm - System.Numerics.Plane:Equals(System.Numerics.Plane):ubyte:this (FullOpts)
          -6 (-10.53 % of base) : System.Private.CoreLib.dasm - System.Numerics.Quaternion:Equals(System.Numerics.Quaternion):ubyte:this (FullOpts)
          -6 (-10.53 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector4:Equals(System.Numerics.Vector4):ubyte:this (FullOpts)
         -15 (-10.34 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):int (FullOpts)
        -134 (-10.09 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -24 (-10.08 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4:Equals(System.Numerics.Matrix4x4):ubyte:this (FullOpts)
         -24 (-10.08 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4+Impl:System.IEquatable<System.Numerics.Matrix4x4.Impl>.Equals(System.Numerics.Matrix4x4+Impl):ubyte:this (FullOpts)
         -24 (-10.00 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4+Impl:Equals(byref):ubyte:this (FullOpts)
          -6 (-10.00 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:EqualsFloatingPoint(System.Runtime.Intrinsics.Vector128`1[double],System.Runtime.Intrinsics.Vector128`1[double]):ubyte (FullOpts)
         -19 (-9.95 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -24 (-9.84 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -10 (-9.80 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanAll[int](System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):ubyte (FullOpts)
         -10 (-9.80 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:GreaterThanAll[short](System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):ubyte (FullOpts)
         -10 (-9.80 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanAll[int](System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):ubyte (FullOpts)
         -10 (-9.80 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:LessThanAll[short](System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):ubyte (FullOpts)
         -24 (-9.80 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
          -6 (-9.68 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[double]:Equals(System.Runtime.Intrinsics.Vector128`1[double]):ubyte:this (FullOpts)
        -129 (-9.58 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
          -6 (-9.38 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector2:Equals(System.Numerics.Vector2):ubyte:this (FullOpts)
         -24 (-9.16 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4+Impl:Equals(System.Object):ubyte:this (FullOpts)
         -22 (-9.09 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2+Impl:Equals(System.Object):ubyte:this (FullOpts)
         -24 (-9.06 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix4x4:Equals(System.Object):ubyte:this (FullOpts)
         -22 (-8.98 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2:Equals(System.Object):ubyte:this (FullOpts)
          -5 (-8.33 % of base) : System.Private.CoreLib.dasm - System.ValueTuple`1[System.Numerics.Vector`1[float]]:Equals(System.ValueTuple`1[System.Numerics.Vector`1[float]]):ubyte:this (FullOpts)
         -18 (-8.26 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2:Equals(System.Numerics.Matrix3x2):ubyte:this (FullOpts)
         -18 (-8.26 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2+Impl:System.IEquatable<System.Numerics.Matrix3x2.Impl>.Equals(System.Numerics.Matrix3x2+Impl):ubyte:this (FullOpts)
         -18 (-8.18 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2+Impl:Equals(byref):ubyte:this (FullOpts)
          -5 (-8.06 % of base) : System.Private.CoreLib.dasm - System.Collections.Generic.GenericEqualityComparer`1[System.Numerics.Vector`1[float]]:Equals(System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):ubyte:this (FullOpts)
          -5 (-8.06 % of base) : System.Private.CoreLib.dasm - System.Collections.Generic.ObjectEqualityComparer`1[System.Numerics.Vector`1[float]]:Equals(System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):ubyte:this (FullOpts)
         -62 (-7.87 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:Contains[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],int):ubyte (FullOpts)
          -5 (-7.81 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:Equals(System.Numerics.Vector`1[double]):ubyte:this (FullOpts)
          -5 (-7.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:Equals(System.Runtime.Intrinsics.Vector256`1[double]):ubyte:this (FullOpts)
         -15 (-7.81 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -62 (-7.53 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOf[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],int):int (FullOpts)
         -10 (-7.41 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:IndexOfAnyExcept[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):int (FullOpts)
         -10 (-7.41 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:IndexOfAnyExcept[System.Numerics.Vector`1[float]](System.Span`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):int (FullOpts)
         -10 (-7.41 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](System.Span`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):int (FullOpts)
          -6 (-7.32 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector3:Equals(System.Numerics.Vector3):ubyte:this (FullOpts)
         -10 (-7.30 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:LastIndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -10 (-7.25 % of base) : System.Private.CoreLib.dasm - System.SpanHelpers:IndexOfAnyExcept[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
         -10 (-7.14 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:ContainsAnyExcept[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):ubyte (FullOpts)
         -10 (-7.14 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:ContainsAnyExcept[System.Numerics.Vector`1[float]](System.Span`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):ubyte (FullOpts)
          -5 (-7.14 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:StartsWith[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Numerics.Vector`1[float]):ubyte (FullOpts)

199 total methods with Code Size differences (199 improved, 0 regressed), 230442 unchanged.

--------------------------------------------------------------------------------

Artifacts:

• build-artifacts-main.zip (653 MB)
• build-clr-checked-main.zip (87 MB)
• build-artifacts-pr.zip (654 MB)
• build-clr-checked-pr.zip (87 MB)
• diff-frameworks.txt (47 KB)
• jit-diffs-frameworks.zip (259 MB)

[xtqqczze]

@MihaZupan Ah, didn't expect this to trigger from dotnet/runtime#104944 (comment).

[MihuBot]

Top method improvements

-203 (-10.75 % of base) - System.SpanHelpers:IndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int

 ; Assembly listing for method System.SpanHelpers:IndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
 ; Emitting BLENDED_CODE for X64 with AVX512 - Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; fully interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 0 single block inlinees; 39 inlinees without PGO data
 ; Final local variable assignments
 ;
 ;  V00 arg0         [V00,T01] ( 15, 40   )   byref  ->  rdi         single-def
 ;  V01 arg1         [V01,T09] ( 19, 40   )  simd32  ->  mm2         ld-addr-op single-def <System.Numerics.Vector`1[float]>
 ;  V02 arg2         [V02,T05] ( 19, 55   )  simd32  ->  mm0         ld-addr-op single-def <System.Numerics.Vector`1[float]>
 ;  V03 arg3         [V03,T06] ( 19, 55   )  simd32  ->  mm1         ld-addr-op single-def <System.Numerics.Vector`1[float]>
 ;  V04 arg4         [V04,T02] (  7, 12   )     int  ->  rsi         single-def
 ;  V05 loc0         [V05,T04] ( 78,228   )  simd32  ->  mm4         ld-addr-op <System.Numerics.Vector`1[float]>
 ;  V06 loc1         [V06,T00] ( 32, 69   )     int  ->  rax        
 ;* V07 loc2         [V07    ] (  0,  0   )  simd32  ->  zero-ref    ld-addr-op <System.Numerics.Vector`1[float]>
 ;# V08 OutArgs      [V08    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
 ;* V09 tmp1         [V09    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V10 tmp2         [V10    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V11 tmp3         [V11    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V12 tmp4         [V12    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V13 tmp5         [V13    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V14 tmp6         [V14    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V15 tmp7         [V15    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V16 tmp8         [V16    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V17 tmp9         [V17    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V18 tmp10        [V18    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V19 tmp11        [V19    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V20 tmp12        [V20    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V21 tmp13        [V21    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V22 tmp14        [V22    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V23 tmp15        [V23    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V24 tmp16        [V24    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V25 tmp17        [V25    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V26 tmp18        [V26    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V27 tmp19        [V27    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V28 tmp20        [V28    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V29 tmp21        [V29    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V30 tmp22        [V30    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V31 tmp23        [V31    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V32 tmp24        [V32    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V33 tmp25        [V33    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V34 tmp26        [V34    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V35 tmp27        [V35    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V36 tmp28        [V36    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V37 tmp29        [V37    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V38 tmp30        [V38    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V39 tmp31        [V39    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V40 tmp32        [V40    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V41 tmp33        [V41    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V42 tmp34        [V42    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V43 tmp35        [V43    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V44 tmp36        [V44    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V45 tmp37        [V45    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V46 tmp38        [V46    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V47 tmp39        [V47    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V48 tmp40        [V48    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V49 tmp41        [V49    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V50 tmp42        [V50    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V51 tmp43        [V51    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V52 tmp44        [V52    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V53 tmp45        [V53    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V54 tmp46        [V54    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V55 tmp47        [V55    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V56 tmp48        [V56    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V57 tmp49        [V57    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V58 tmp50        [V58    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V59 tmp51        [V59    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V60 tmp52        [V60    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V61 tmp53        [V61    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V62 tmp54        [V62    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V63 tmp55        [V63    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V64 tmp56        [V64    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V65 tmp57        [V65    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V66 tmp58        [V66    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V67 tmp59        [V67    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V68 tmp60        [V68    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V69 tmp61        [V69    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V70 tmp62        [V70    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V71 tmp63        [V71    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V72 tmp64        [V72    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V73 tmp65        [V73    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V74 tmp66        [V74    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V75 tmp67        [V75    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V76 tmp68        [V76    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V77 tmp69        [V77    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V78 tmp70        [V78    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V79 tmp71        [V79    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V80 tmp72        [V80    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V81 tmp73        [V81    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V82 tmp74        [V82    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V83 tmp75        [V83    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V84 tmp76        [V84    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V85 tmp77        [V85    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V86 tmp78        [V86    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;  V87 tmp79        [V87,T03] (  9,  9   )     int  ->  rax         "Single return block return value"
 ;  V88 cse0         [V88,T10] ( 16, 39   )  simd32  ->  mm3         hoist multi-def "CSE #01: moderate"
 ;  V89 cse1         [V89,T07] ( 16, 46.50)  simd32  ->  mm6         multi-def "CSE #03: moderate"
 ;  V90 cse2         [V90,T08] ( 16, 46.50)  simd32  ->  mm7         multi-def "CSE #05: moderate"
 ;  V91 cse3         [V91,T11] (  4, 16   )  simd32  ->  mm5         "CSE #02: moderate"
 ;  V92 cse4         [V92,T12] (  4, 16   )  simd32  ->  mm5         "CSE #04: moderate"
 ;  V93 cse5         [V93,T13] (  4, 16   )  simd32  ->  mm5         "CSE #06: moderate"
 ;  V94 cse6         [V94,T14] (  4, 16   )  simd32  ->  mm5         "CSE #07: moderate"
 ;  V95 cse7         [V95,T15] (  4, 16   )  simd32  ->  mm5         "CSE #08: moderate"
 ;  V96 cse8         [V96,T16] (  4, 16   )  simd32  ->  mm5         "CSE #09: moderate"
 ;  V97 cse9         [V97,T17] (  4, 16   )  simd32  ->  mm5         "CSE #10: moderate"
 ;  V98 cse10        [V98,T18] (  4, 16   )  simd32  ->  mm5         "CSE #11: moderate"
 ;  V99 cse11        [V99,T19] (  4, 16   )  simd32  ->  mm5         "CSE #16: moderate"
 ;  V100 cse12       [V100,T20] (  4,  2   )  simd32  ->  mm5         "CSE #12: conservative"
 ;  V101 cse13       [V101,T21] (  4,  2   )  simd32  ->  mm5         "CSE #13: conservative"
 ;  V102 cse14       [V102,T22] (  4,  2   )  simd32  ->  mm5         "CSE #14: conservative"
 ;  V103 cse15       [V103,T23] (  4,  2   )  simd32  ->  mm5         "CSE #15: conservative"
 ;
 ; Lcl frame size = 0
 
 G_M13892_IG01:
        push     rbp
        mov      rbp, rsp
        vmovups  ymm2, ymmword ptr [rbp+0x10]
        vmovups  ymm0, ymmword ptr [rbp+0x30]
        vmovups  ymm1, ymmword ptr [rbp+0x50]
 						;; size=19 bbWeight=1 PerfScore 13.25
 G_M13892_IG02:
        xor      eax, eax
        cmp      esi, 8
        jl       G_M13892_IG19
 						;; size=11 bbWeight=1 PerfScore 1.50
 G_M13892_IG03:
        vcmpps   ymm3, ymm2, ymm2, 0
        align    [0 bytes for IG04]
 						;; size=5 bbWeight=0.25 PerfScore 0.75
 G_M13892_IG04:
        movsxd   rcx, eax
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm6, ymm5, ymm3, 17
        vcmpps   ymm7, ymm4, ymm2, 0
        vorps    ymm6, ymm6, ymm7
        vpcmpeqd ymm7, ymm7, ymm7
-       vpcmpeqd k1, ymm7, ymm6
-       kortestb k1, k1
-       jb       G_M13892_IG27
+       vptest   ymm6, ymm7
+       jb       G_M13892_IG26
        vcmpps   ymm6, ymm0, ymm0, 0
        vpternlogd ymm7, ymm5, ymm6, 17
        vcmpps   ymm8, ymm4, ymm0, 0
        vorps    ymm7, ymm7, ymm8
        vpcmpeqd ymm8, ymm8, ymm8
-       vpcmpeqd k1, ymm8, ymm7
-       kortestb k1, k1
-       jb       G_M13892_IG27
+       vptest   ymm7, ymm8
+       jb       G_M13892_IG26
        vcmpps   ymm7, ymm1, ymm1, 0
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
        vpcmpeqd ymm5, ymm5, ymm5
-       vpcmpeqd k1, ymm5, ymm4
-       kortestb k1, k1
-       jb       G_M13892_IG27
+       vptest   ymm4, ymm5
+       jb       G_M13892_IG26
        lea      ecx, [rax+0x01]
        movsxd   rcx, ecx
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        je       SHORT G_M13892_IG06
-						;; size=271 bbWeight=4 PerfScore 267.00
+						;; size=241 bbWeight=4 PerfScore 351.00
 G_M13892_IG05:
        inc      eax
-       jmp      G_M13892_IG27
-       align    [0 bytes for IG24]
+       jmp      G_M13892_IG26
+       align    [0 bytes for IG23]
 						;; size=7 bbWeight=0.50 PerfScore 1.12
 G_M13892_IG06:
        lea      ecx, [rax+0x02]
        movsxd   rcx, ecx
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        je       SHORT G_M13892_IG08
-						;; size=134 bbWeight=4 PerfScore 126.00
+						;; size=119 bbWeight=4 PerfScore 168.00
 G_M13892_IG07:
        add      eax, 2
-       jmp      G_M13892_IG27
+       jmp      G_M13892_IG26
 						;; size=8 bbWeight=0.50 PerfScore 1.12
 G_M13892_IG08:
        lea      ecx, [rax+0x03]
        movsxd   rcx, ecx
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        je       SHORT G_M13892_IG10
-						;; size=134 bbWeight=4 PerfScore 126.00
+						;; size=119 bbWeight=4 PerfScore 168.00
 G_M13892_IG09:
        add      eax, 3
-       jmp      G_M13892_IG27
+       jmp      G_M13892_IG26
 						;; size=8 bbWeight=0.50 PerfScore 1.12
 G_M13892_IG10:
        lea      ecx, [rax+0x04]
        movsxd   rcx, ecx
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        je       SHORT G_M13892_IG12
-						;; size=134 bbWeight=4 PerfScore 126.00
+						;; size=119 bbWeight=4 PerfScore 168.00
 G_M13892_IG11:
        add      eax, 4
-       jmp      G_M13892_IG27
+       jmp      G_M13892_IG26
 						;; size=8 bbWeight=0.50 PerfScore 1.12
 G_M13892_IG12:
        lea      ecx, [rax+0x05]
        movsxd   rcx, ecx
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        je       SHORT G_M13892_IG14
-						;; size=134 bbWeight=4 PerfScore 126.00
+						;; size=119 bbWeight=4 PerfScore 168.00
 G_M13892_IG13:
        add      eax, 5
-       jmp      G_M13892_IG27
+       jmp      G_M13892_IG26
 						;; size=8 bbWeight=0.50 PerfScore 1.12
 G_M13892_IG14:
        lea      ecx, [rax+0x06]
        movsxd   rcx, ecx
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        je       SHORT G_M13892_IG16
-						;; size=134 bbWeight=4 PerfScore 126.00
+						;; size=119 bbWeight=4 PerfScore 168.00
 G_M13892_IG15:
        add      eax, 6
-       jmp      G_M13892_IG27
+       jmp      G_M13892_IG26
 						;; size=8 bbWeight=0.50 PerfScore 1.12
 G_M13892_IG16:
        lea      ecx, [rax+0x07]
        movsxd   rcx, ecx
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        vpternlogd ymm6, ymm5, ymm6, 17
        vcmpps   ymm8, ymm4, ymm0, 0
        vorps    ymm6, ymm6, ymm8
-       vpcmpeqd k1, ymm9, ymm6
-       kortestb k1, k1
+       vptest   ymm6, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        vpternlogd ymm7, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm7, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     dl
        movzx    rdx, dl
        or       ecx, edx
        je       SHORT G_M13892_IG18
-						;; size=129 bbWeight=4 PerfScore 124.00
+						;; size=114 bbWeight=4 PerfScore 166.00
 G_M13892_IG17:
        add      eax, 7
-       jmp      G_M13892_IG27
+       jmp      G_M13892_IG26
 						;; size=8 bbWeight=0.50 PerfScore 1.12
 G_M13892_IG18:
        add      eax, 8
        mov      ecx, esi
        sub      ecx, eax
        cmp      ecx, 8
        jge      G_M13892_IG04
 						;; size=16 bbWeight=4 PerfScore 8.00
 G_M13892_IG19:
        mov      ecx, esi
        sub      ecx, eax
        cmp      ecx, 4
-       jl       G_M13892_IG22
+       jl       G_M13892_IG21
        movsxd   rcx, eax
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm3, ymm2, ymm2, 0
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm6, ymm5, ymm3, 17
        vcmpps   ymm7, ymm4, ymm2, 0
        vorps    ymm6, ymm6, ymm7
        vpcmpeqd ymm7, ymm7, ymm7
-       vpcmpeqd k1, ymm7, ymm6
-       kortestb k1, k1
-       jb       G_M13892_IG27
+       vptest   ymm6, ymm7
+       jb       G_M13892_IG26
        vcmpps   ymm6, ymm0, ymm0, 0
        vpternlogd ymm7, ymm5, ymm6, 17
        vcmpps   ymm8, ymm4, ymm0, 0
        vorps    ymm7, ymm7, ymm8
        vpcmpeqd ymm8, ymm8, ymm8
-       vpcmpeqd k1, ymm8, ymm7
-       kortestb k1, k1
-       jb       G_M13892_IG27
+       vptest   ymm7, ymm8
+       jb       G_M13892_IG26
        vcmpps   ymm7, ymm1, ymm1, 0
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
        vpcmpeqd ymm5, ymm5, ymm5
-       vpcmpeqd k1, ymm5, ymm4
-       kortestb k1, k1
-       jb       G_M13892_IG27
+       vptest   ymm4, ymm5
+       jb       G_M13892_IG26
        lea      ecx, [rax+0x01]
        movsxd   rcx, ecx
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        jb       G_M13892_IG05
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        jb       G_M13892_IG05
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
        vpcmpeqd ymm5, ymm5, ymm5
-						;; size=271 bbWeight=0.50 PerfScore 33.63
-G_M13892_IG20:
-       vpcmpeqd k1, ymm5, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm5
        jb       G_M13892_IG05
        lea      ecx, [rax+0x02]
        movsxd   rcx, ecx
+						;; size=263 bbWeight=0.50 PerfScore 45.75
+G_M13892_IG20:
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        jb       G_M13892_IG07
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        jb       G_M13892_IG07
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
        vpcmpeqd ymm5, ymm5, ymm5
-       vpcmpeqd k1, ymm5, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm5
        jb       G_M13892_IG07
        lea      ecx, [rax+0x03]
        movsxd   rcx, ecx
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm3, ymm5, ymm3, 17
        vcmpps   ymm8, ymm4, ymm2, 0
        vorps    ymm3, ymm3, ymm8
        vpcmpeqd ymm8, ymm8, ymm8
-       vpcmpeqd k1, ymm8, ymm3
-       kortestb k1, k1
+       vptest   ymm3, ymm8
        jb       G_M13892_IG09
        vpternlogd ymm6, ymm5, ymm6, 17
        vcmpps   ymm3, ymm4, ymm0, 0
        vorps    ymm3, ymm6, ymm3
        vpcmpeqd ymm6, ymm6, ymm6
-       vpcmpeqd k1, ymm6, ymm3
-       kortestb k1, k1
+       vptest   ymm3, ymm6
        jb       G_M13892_IG09
        vpternlogd ymm7, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm3, ymm7, ymm4
        vpcmpeqd ymm4, ymm4, ymm4
-       vpcmpeqd k1, ymm4, ymm3
-       kortestb k1, k1
-						;; size=272 bbWeight=0.50 PerfScore 30.50
-G_M13892_IG21:
+       vptest   ymm3, ymm4
        jb       G_M13892_IG09
        add      eax, 4
-						;; size=9 bbWeight=0.50 PerfScore 0.62
-G_M13892_IG22:
+						;; size=229 bbWeight=0.50 PerfScore 40.00
+G_M13892_IG21:
        cmp      eax, esi
-       jge      G_M13892_IG25
-						;; size=8 bbWeight=0.50 PerfScore 0.62
-G_M13892_IG23:
+       jge      SHORT G_M13892_IG24
+						;; size=4 bbWeight=0.50 PerfScore 0.62
+G_M13892_IG22:
        vcmpps   ymm3, ymm2, ymm2, 0
 						;; size=5 bbWeight=0.25 PerfScore 0.75
-G_M13892_IG24:
+G_M13892_IG23:
        movsxd   rcx, eax
        shl      rcx, 5
        vmovups  ymm4, ymmword ptr [rdi+rcx]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm6, ymm5, ymm3, 17
        vcmpps   ymm7, ymm4, ymm2, 0
        vorps    ymm6, ymm6, ymm7
        vpcmpeqd ymm7, ymm7, ymm7
-       vpcmpeqd k1, ymm7, ymm6
-       kortestb k1, k1
-       jb       SHORT G_M13892_IG27
+       vptest   ymm6, ymm7
+       jb       SHORT G_M13892_IG26
        vcmpps   ymm6, ymm0, ymm0, 0
        vpternlogd ymm6, ymm5, ymm6, 17
        vcmpps   ymm7, ymm4, ymm0, 0
        vorps    ymm6, ymm6, ymm7
        vpcmpeqd ymm7, ymm7, ymm7
-       vpcmpeqd k1, ymm7, ymm6
-       kortestb k1, k1
-       jb       SHORT G_M13892_IG27
+       vptest   ymm6, ymm7
+       jb       SHORT G_M13892_IG26
        vcmpps   ymm7, ymm1, ymm1, 0
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
        vpcmpeqd ymm5, ymm5, ymm5
-       vpcmpeqd k1, ymm5, ymm4
-       kortestb k1, k1
-       jb       SHORT G_M13892_IG27
+       vptest   ymm4, ymm5
+       jb       SHORT G_M13892_IG26
        inc      eax
        cmp      eax, esi
-       jl       G_M13892_IG24
-						;; size=133 bbWeight=4 PerfScore 147.00
-G_M13892_IG25:
+       jl       SHORT G_M13892_IG23
+						;; size=114 bbWeight=4 PerfScore 189.00
+G_M13892_IG24:
        mov      eax, -1
 						;; size=5 bbWeight=0.50 PerfScore 0.12
-G_M13892_IG26:
+G_M13892_IG25:
        vzeroupper 
        pop      rbp
        ret      
 						;; size=5 bbWeight=0.50 PerfScore 1.25
-G_M13892_IG27:
+G_M13892_IG26:
        vzeroupper 
        pop      rbp
        ret      
 						;; size=5 bbWeight=0.50 PerfScore 1.25
 
-; Total bytes of code 1889, prolog size 19, PerfScore 1268.13, instruction count 424, allocated bytes for code 1967 (MethodHash=c175c9bb) for method System.SpanHelpers:IndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
+; Total bytes of code 1686, prolog size 19, PerfScore 1667.13, instruction count 385, allocated bytes for code 1686 (MethodHash=c175c9bb) for method System.SpanHelpers:IndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)

-198 (-10.55 % of base) - System.SpanHelpers:LastIndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int

 ; Assembly listing for method System.SpanHelpers:LastIndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
 ; Emitting BLENDED_CODE for X64 with AVX512 - Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; fully interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 0 single block inlinees; 39 inlinees without PGO data
 ; Final local variable assignments
 ;
 ;  V00 arg0         [V00,T01] ( 15, 38   )   byref  ->  rdi         single-def
 ;  V01 arg1         [V01,T08] ( 19, 41.50)  simd32  ->  mm2         ld-addr-op single-def <System.Numerics.Vector`1[float]>
 ;  V02 arg2         [V02,T04] ( 19, 49   )  simd32  ->  mm0         ld-addr-op single-def <System.Numerics.Vector`1[float]>
 ;  V03 arg3         [V03,T05] ( 19, 49   )  simd32  ->  mm1         ld-addr-op single-def <System.Numerics.Vector`1[float]>
 ;  V04 arg4         [V04,T00] ( 33, 64.50)     int  ->  rsi        
 ;  V05 loc0         [V05,T03] ( 78,216   )  simd32  ->  mm4         ld-addr-op <System.Numerics.Vector`1[float]>
 ;* V06 loc1         [V06    ] (  0,  0   )  simd32  ->  zero-ref    ld-addr-op <System.Numerics.Vector`1[float]>
 ;# V07 OutArgs      [V07    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
 ;* V08 tmp1         [V08    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V09 tmp2         [V09    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V10 tmp3         [V10    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V11 tmp4         [V11    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V12 tmp5         [V12    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V13 tmp6         [V13    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V14 tmp7         [V14    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V15 tmp8         [V15    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V16 tmp9         [V16    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V17 tmp10        [V17    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V18 tmp11        [V18    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V19 tmp12        [V19    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V20 tmp13        [V20    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V21 tmp14        [V21    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V22 tmp15        [V22    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V23 tmp16        [V23    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V24 tmp17        [V24    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V25 tmp18        [V25    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V26 tmp19        [V26    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V27 tmp20        [V27    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V28 tmp21        [V28    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V29 tmp22        [V29    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V30 tmp23        [V30    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V31 tmp24        [V31    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V32 tmp25        [V32    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V33 tmp26        [V33    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V34 tmp27        [V34    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V35 tmp28        [V35    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V36 tmp29        [V36    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V37 tmp30        [V37    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V38 tmp31        [V38    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V39 tmp32        [V39    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V40 tmp33        [V40    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V41 tmp34        [V41    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V42 tmp35        [V42    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V43 tmp36        [V43    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V44 tmp37        [V44    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V45 tmp38        [V45    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V46 tmp39        [V46    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V47 tmp40        [V47    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V48 tmp41        [V48    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V49 tmp42        [V49    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V50 tmp43        [V50    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V51 tmp44        [V51    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V52 tmp45        [V52    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V53 tmp46        [V53    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V54 tmp47        [V54    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V55 tmp48        [V55    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V56 tmp49        [V56    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V57 tmp50        [V57    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V58 tmp51        [V58    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V59 tmp52        [V59    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V60 tmp53        [V60    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V61 tmp54        [V61    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V62 tmp55        [V62    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V63 tmp56        [V63    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V64 tmp57        [V64    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V65 tmp58        [V65    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V66 tmp59        [V66    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V67 tmp60        [V67    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V68 tmp61        [V68    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V69 tmp62        [V69    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V70 tmp63        [V70    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V71 tmp64        [V71    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V72 tmp65        [V72    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V73 tmp66        [V73    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V74 tmp67        [V74    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V75 tmp68        [V75    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V76 tmp69        [V76    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V77 tmp70        [V77    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V78 tmp71        [V78    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V79 tmp72        [V79    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V80 tmp73        [V80    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V81 tmp74        [V81    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V82 tmp75        [V82    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V83 tmp76        [V83    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;* V84 tmp77        [V84    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V85 tmp78        [V85    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector`1[float]>
 ;  V86 tmp79        [V86,T02] (  9,  9   )     int  ->  rax         "Single return block return value"
 ;  V87 cse0         [V87,T09] ( 16, 38.75)  simd32  ->  mm3         hoist multi-def "CSE #01: aggressive"
 ;  V88 cse1         [V88,T06] ( 16, 42.50)  simd32  ->  mm6         multi-def "CSE #03: aggressive"
 ;  V89 cse2         [V89,T07] ( 16, 42.50)  simd32  ->  mm7         multi-def "CSE #05: aggressive"
 ;  V90 cse3         [V90,T10] (  4, 16   )  simd32  ->  mm5         "CSE #02: aggressive"
 ;  V91 cse4         [V91,T11] (  4, 16   )  simd32  ->  mm5         "CSE #04: aggressive"
 ;  V92 cse5         [V92,T12] (  4, 16   )  simd32  ->  mm5         "CSE #06: aggressive"
 ;  V93 cse6         [V93,T13] (  4, 16   )  simd32  ->  mm5         "CSE #07: aggressive"
 ;  V94 cse7         [V94,T14] (  4, 16   )  simd32  ->  mm5         "CSE #08: aggressive"
 ;  V95 cse8         [V95,T15] (  4, 16   )  simd32  ->  mm5         "CSE #09: aggressive"
 ;  V96 cse9         [V96,T16] (  4, 16   )  simd32  ->  mm5         "CSE #10: aggressive"
 ;  V97 cse10        [V97,T17] (  4, 16   )  simd32  ->  mm5         "CSE #11: aggressive"
 ;  V98 cse11        [V98,T18] (  4,  8   )  simd32  ->  mm5         "CSE #16: moderate"
 ;  V99 cse12        [V99,T19] (  4,  2   )  simd32  ->  mm5         "CSE #12: conservative"
 ;  V100 cse13       [V100,T20] (  4,  2   )  simd32  ->  mm5         "CSE #13: conservative"
 ;  V101 cse14       [V101,T21] (  4,  2   )  simd32  ->  mm5         "CSE #14: conservative"
 ;  V102 cse15       [V102,T22] (  4,  2   )  simd32  ->  mm5         "CSE #15: conservative"
 ;
 ; Lcl frame size = 0
 
 G_M12558_IG01:
        push     rbp
        mov      rbp, rsp
        vmovups  ymm2, ymmword ptr [rbp+0x10]
        vmovups  ymm0, ymmword ptr [rbp+0x30]
        vmovups  ymm1, ymmword ptr [rbp+0x50]
 						;; size=19 bbWeight=1 PerfScore 13.25
 G_M12558_IG02:
        cmp      esi, 8
-       jl       G_M12558_IG22
+       jl       G_M12558_IG21
 						;; size=9 bbWeight=1 PerfScore 1.25
 G_M12558_IG03:
        vcmpps   ymm3, ymm2, ymm2, 0
        align    [0 bytes for IG04]
 						;; size=5 bbWeight=0.25 PerfScore 0.75
 G_M12558_IG04:
        add      esi, -8
        lea      eax, [rsi+0x07]
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm6, ymm5, ymm3, 17
        vcmpps   ymm7, ymm4, ymm2, 0
        vorps    ymm6, ymm6, ymm7
        vpcmpeqd ymm7, ymm7, ymm7
-       vpcmpeqd k1, ymm7, ymm6
-       kortestb k1, k1
-       jb       G_M12558_IG07
+       vptest   ymm6, ymm7
+       jb       G_M12558_IG06
        vcmpps   ymm6, ymm0, ymm0, 0
        vpternlogd ymm7, ymm5, ymm6, 17
        vcmpps   ymm8, ymm4, ymm0, 0
        vorps    ymm7, ymm7, ymm8
        vpcmpeqd ymm8, ymm8, ymm8
-       vpcmpeqd k1, ymm8, ymm7
-       kortestb k1, k1
-       jb       G_M12558_IG07
+       vptest   ymm7, ymm8
+       jb       G_M12558_IG06
        vcmpps   ymm7, ymm1, ymm1, 0
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
        vpcmpeqd ymm5, ymm5, ymm5
-       vpcmpeqd k1, ymm5, ymm4
-       kortestb k1, k1
-       jb       G_M12558_IG07
+       vptest   ymm4, ymm5
+       jb       G_M12558_IG06
        lea      eax, [rsi+0x06]
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     al
        movzx    rax, al
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
-						;; size=273 bbWeight=4 PerfScore 266.00
+       je       SHORT G_M12558_IG07
+						;; size=245 bbWeight=4 PerfScore 354.00
 G_M12558_IG05:
-       je       SHORT G_M12558_IG08
-						;; size=2 bbWeight=4 PerfScore 4.00
-G_M12558_IG06:
        lea      eax, [rsi+0x06]
-       jmp      G_M12558_IG20
-       align    [0 bytes for IG25]
+       jmp      G_M12558_IG19
+       align    [0 bytes for IG23]
 						;; size=8 bbWeight=0.50 PerfScore 1.25
-G_M12558_IG07:
+G_M12558_IG06:
        lea      eax, [rsi+0x07]
-       jmp      G_M12558_IG20
+       jmp      G_M12558_IG19
 						;; size=8 bbWeight=0.50 PerfScore 1.25
-G_M12558_IG08:
+G_M12558_IG07:
        lea      eax, [rsi+0x05]
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     al
        movzx    rax, al
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
-       je       SHORT G_M12558_IG10
-						;; size=133 bbWeight=4 PerfScore 126.00
-G_M12558_IG09:
+       je       SHORT G_M12558_IG09
+						;; size=118 bbWeight=4 PerfScore 168.00
+G_M12558_IG08:
        lea      eax, [rsi+0x05]
-       jmp      G_M12558_IG20
+       jmp      G_M12558_IG19
 						;; size=8 bbWeight=0.50 PerfScore 1.25
-G_M12558_IG10:
+G_M12558_IG09:
        lea      eax, [rsi+0x04]
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     al
        movzx    rax, al
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
-       je       SHORT G_M12558_IG12
-						;; size=133 bbWeight=4 PerfScore 126.00
-G_M12558_IG11:
+       je       SHORT G_M12558_IG11
+						;; size=118 bbWeight=4 PerfScore 168.00
+G_M12558_IG10:
        lea      eax, [rsi+0x04]
-       jmp      G_M12558_IG20
+       jmp      G_M12558_IG19
 						;; size=8 bbWeight=0.50 PerfScore 1.25
-G_M12558_IG12:
+G_M12558_IG11:
        lea      eax, [rsi+0x03]
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     al
        movzx    rax, al
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
-       je       SHORT G_M12558_IG14
-						;; size=133 bbWeight=4 PerfScore 126.00
-G_M12558_IG13:
+       je       SHORT G_M12558_IG13
+						;; size=118 bbWeight=4 PerfScore 168.00
+G_M12558_IG12:
        lea      eax, [rsi+0x03]
-       jmp      G_M12558_IG20
+       jmp      G_M12558_IG19
 						;; size=8 bbWeight=0.50 PerfScore 1.25
-G_M12558_IG14:
+G_M12558_IG13:
        lea      eax, [rsi+0x02]
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     al
        movzx    rax, al
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
-       je       SHORT G_M12558_IG16
-						;; size=133 bbWeight=4 PerfScore 126.00
-G_M12558_IG15:
+       je       SHORT G_M12558_IG15
+						;; size=118 bbWeight=4 PerfScore 168.00
+G_M12558_IG14:
        lea      eax, [rsi+0x02]
-       jmp      G_M12558_IG20
+       jmp      G_M12558_IG19
 						;; size=8 bbWeight=0.50 PerfScore 1.25
-G_M12558_IG16:
+G_M12558_IG15:
        lea      eax, [rsi+0x01]
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     al
        movzx    rax, al
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
-       je       SHORT G_M12558_IG18
-						;; size=133 bbWeight=4 PerfScore 126.00
-G_M12558_IG17:
+       je       SHORT G_M12558_IG17
+						;; size=118 bbWeight=4 PerfScore 168.00
+G_M12558_IG16:
        lea      eax, [rsi+0x01]
-       jmp      G_M12558_IG20
-						;; size=8 bbWeight=0.50 PerfScore 1.25
-G_M12558_IG18:
+       jmp      SHORT G_M12558_IG19
+						;; size=5 bbWeight=0.50 PerfScore 1.25
+G_M12558_IG17:
        movsxd   rax, esi
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
+       vptest   ymm8, ymm9
        setb     al
        movzx    rax, al
        vpternlogd ymm6, ymm5, ymm6, 17
        vcmpps   ymm8, ymm4, ymm0, 0
        vorps    ymm6, ymm6, ymm8
-       vpcmpeqd k1, ymm9, ymm6
-       kortestb k1, k1
+       vptest   ymm6, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
        vpternlogd ymm7, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm7, ymm4
-       vpcmpeqd k1, ymm9, ymm4
-       kortestb k1, k1
+       vptest   ymm4, ymm9
        setb     cl
        movzx    rcx, cl
        or       eax, ecx
-       je       SHORT G_M12558_IG21
-						;; size=126 bbWeight=4 PerfScore 122.00
-G_M12558_IG19:
+       je       SHORT G_M12558_IG20
+						;; size=111 bbWeight=4 PerfScore 164.00
+G_M12558_IG18:
        mov      eax, esi
 						;; size=2 bbWeight=0.50 PerfScore 0.12
-G_M12558_IG20:
+G_M12558_IG19:
        vzeroupper 
        pop      rbp
        ret      
 						;; size=5 bbWeight=0.50 PerfScore 1.25
-G_M12558_IG21:
+G_M12558_IG20:
        cmp      esi, 8
        jge      G_M12558_IG04
 						;; size=9 bbWeight=4 PerfScore 5.00
-G_M12558_IG22:
+G_M12558_IG21:
        cmp      esi, 4
-       jl       G_M12558_IG25
+       jl       G_M12558_IG23
        add      esi, -4
        lea      eax, [rsi+0x03]
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm3, ymm2, ymm2, 0
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm6, ymm5, ymm3, 17
        vcmpps   ymm7, ymm4, ymm2, 0
        vorps    ymm6, ymm6, ymm7
        vpcmpeqd ymm7, ymm7, ymm7
-       vpcmpeqd k1, ymm7, ymm6
-       kortestb k1, k1
-       jb       G_M12558_IG13
+       vptest   ymm6, ymm7
+       jb       G_M12558_IG12
        vcmpps   ymm6, ymm0, ymm0, 0
        vpternlogd ymm7, ymm5, ymm6, 17
        vcmpps   ymm8, ymm4, ymm0, 0
        vorps    ymm7, ymm7, ymm8
        vpcmpeqd ymm8, ymm8, ymm8
-       vpcmpeqd k1, ymm8, ymm7
-       kortestb k1, k1
-       jb       G_M12558_IG13
+       vptest   ymm7, ymm8
+       jb       G_M12558_IG12
        vcmpps   ymm7, ymm1, ymm1, 0
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
        vpcmpeqd ymm5, ymm5, ymm5
-       vpcmpeqd k1, ymm5, ymm4
-       kortestb k1, k1
-       jb       G_M12558_IG13
+       vptest   ymm4, ymm5
+       jb       G_M12558_IG12
        lea      eax, [rsi+0x02]
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
-       jb       G_M12558_IG15
+       vptest   ymm8, ymm9
+       jb       G_M12558_IG14
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
-       jb       G_M12558_IG15
+       vptest   ymm8, ymm9
+       jb       G_M12558_IG14
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
-						;; size=267 bbWeight=0.50 PerfScore 33.50
-G_M12558_IG23:
        vpcmpeqd ymm5, ymm5, ymm5
-       vpcmpeqd k1, ymm5, ymm4
-       kortestb k1, k1
-       jb       G_M12558_IG15
+       vptest   ymm4, ymm5
+       jb       G_M12558_IG14
        lea      eax, [rsi+0x01]
+						;; size=260 bbWeight=0.50 PerfScore 45.75
+G_M12558_IG22:
        cdqe     
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm8, ymm5, ymm3, 17
        vcmpps   ymm9, ymm4, ymm2, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
-       jb       G_M12558_IG17
+       vptest   ymm8, ymm9
+       jb       G_M12558_IG16
        vpternlogd ymm8, ymm5, ymm6, 17
        vcmpps   ymm9, ymm4, ymm0, 0
        vorps    ymm8, ymm8, ymm9
        vpcmpeqd ymm9, ymm9, ymm9
-       vpcmpeqd k1, ymm9, ymm8
-       kortestb k1, k1
-       jb       G_M12558_IG17
+       vptest   ymm8, ymm9
+       jb       G_M12558_IG16
        vpternlogd ymm5, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm4, ymm5, ymm4
        vpcmpeqd ymm5, ymm5, ymm5
-       vpcmpeqd k1, ymm5, ymm4
-       kortestb k1, k1
-       jb       G_M12558_IG17
+       vptest   ymm4, ymm5
+       jb       G_M12558_IG16
        movsxd   rax, esi
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm3, ymm5, ymm3, 17
        vcmpps   ymm8, ymm4, ymm2, 0
        vorps    ymm3, ymm3, ymm8
        vpcmpeqd ymm8, ymm8, ymm8
-       vpcmpeqd k1, ymm8, ymm3
-       kortestb k1, k1
-       jb       G_M12558_IG19
+       vptest   ymm3, ymm8
+       jb       G_M12558_IG18
        vpternlogd ymm6, ymm5, ymm6, 17
        vcmpps   ymm3, ymm4, ymm0, 0
        vorps    ymm3, ymm6, ymm3
        vpcmpeqd ymm6, ymm6, ymm6
-       vpcmpeqd k1, ymm6, ymm3
-       kortestb k1, k1
-       jb       G_M12558_IG19
+       vptest   ymm3, ymm6
+       jb       G_M12558_IG18
        vpternlogd ymm7, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm3, ymm7, ymm4
        vpcmpeqd ymm4, ymm4, ymm4
-       vpcmpeqd k1, ymm4, ymm3
-       kortestb k1, k1
-						;; size=272 bbWeight=0.50 PerfScore 30.50
-G_M12558_IG24:
-       jb       G_M12558_IG19
-						;; size=6 bbWeight=0.50 PerfScore 0.50
-G_M12558_IG25:
+       vptest   ymm3, ymm4
+       jb       G_M12558_IG18
+						;; size=225 bbWeight=0.50 PerfScore 39.75
+G_M12558_IG23:
        test     esi, esi
-       jg       SHORT G_M12558_IG28
+       jg       SHORT G_M12558_IG26
 						;; size=4 bbWeight=4 PerfScore 5.00
-G_M12558_IG26:
+G_M12558_IG24:
        mov      eax, -1
 						;; size=5 bbWeight=0.50 PerfScore 0.12
-G_M12558_IG27:
+G_M12558_IG25:
        vzeroupper 
        pop      rbp
        ret      
 						;; size=5 bbWeight=0.50 PerfScore 1.25
-G_M12558_IG28:
+G_M12558_IG26:
        dec      esi
        movsxd   rax, esi
        shl      rax, 5
        vmovups  ymm4, ymmword ptr [rdi+rax]
        vcmpps   ymm3, ymm2, ymm2, 0
        vcmpps   ymm5, ymm4, ymm4, 0
        vpternlogd ymm3, ymm5, ymm3, 17
        vcmpps   ymm6, ymm4, ymm2, 0
        vorps    ymm3, ymm3, ymm6
        vpcmpeqd ymm6, ymm6, ymm6
-       vpcmpeqd k1, ymm6, ymm3
-       kortestb k1, k1
-       jb       G_M12558_IG19
+       vptest   ymm3, ymm6
+       jb       G_M12558_IG18
        vcmpps   ymm6, ymm0, ymm0, 0
        vpternlogd ymm3, ymm5, ymm6, 17
        vcmpps   ymm6, ymm4, ymm0, 0
        vorps    ymm3, ymm3, ymm6
        vpcmpeqd ymm6, ymm6, ymm6
-       vpcmpeqd k1, ymm6, ymm3
-       kortestb k1, k1
-       jb       G_M12558_IG19
+       vptest   ymm3, ymm6
+       jb       G_M12558_IG18
        vcmpps   ymm7, ymm1, ymm1, 0
        vpternlogd ymm3, ymm5, ymm7, 17
        vcmpps   ymm4, ymm4, ymm1, 0
        vorps    ymm3, ymm3, ymm4
        vpcmpeqd ymm4, ymm4, ymm4
-       vpcmpeqd k1, ymm4, ymm3
-       kortestb k1, k1
-       jb       G_M12558_IG19
-       jmp      G_M12558_IG25
-						;; size=147 bbWeight=2 PerfScore 81.00
+       vptest   ymm3, ymm4
+       jb       G_M12558_IG18
+       jmp      G_M12558_IG23
+						;; size=132 bbWeight=2 PerfScore 102.00
 
-; Total bytes of code 1877, prolog size 19, PerfScore 1204.25, instruction count 419, allocated bytes for code 1955 (MethodHash=f075cef1) for method System.SpanHelpers:LastIndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)
+; Total bytes of code 1679, prolog size 19, PerfScore 1582.25, instruction count 380, allocated bytes for code 1679 (MethodHash=f075cef1) for method System.SpanHelpers:LastIndexOfAny[System.Numerics.Vector`1[float]](byref,System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],System.Numerics.Vector`1[float],int):int (FullOpts)

Larger list of diffs: https://gist.github.com/MihuBot/19da0c8a13430beaae661d050a25685a

[MihuBot]

@xtqqczze