[JitDiff X64] [tannergooding] JIT: Remove transparent scalar/vector conversi ...

[MihuBot]

Job completed in 21 minutes 57 seconds (remote runner delay: 1 minute 6 seconds).
dotnet/runtime#130444
Using arguments: -nuget
Main commit: dotnet/runtime@7ce50b9
PR commit: tannergooding/runtime@e75b094

Diffs

Diffs

Found 139 files with textual diffs.

Summary of Code Size diffs:
(Lower is better)

Total bytes of base: 395597373
Total bytes of diff: 395589945
Total bytes of delta: -7428 (-0.00 % of base)
Total relative delta: -67.79
    diff is an improvement.
    relative diff is an improvement.


Top file improvements (bytes):
       -4439 : System.Private.CoreLib.dasm (-0.06 % of base)
       -1078 : System.Numerics.Tensors.dasm (-0.09 % of base)
        -959 : SixLabors.ImageSharp.dasm (-0.04 % of base)
        -264 : SixLabors.ImageSharp.Drawing.dasm (-0.08 % of base)
        -157 : BouncyCastle.Cryptography.dasm (-0.00 % of base)
        -110 : SixLabors.Fonts.dasm (-0.01 % of base)
         -76 : ClosedXML.dasm (-0.00 % of base)
         -64 : SharpCompress.dasm (-0.00 % of base)
         -34 : BepuPhysics.dasm (-0.00 % of base)
         -24 : CommunityToolkit.HighPerformance.dasm (-0.01 % of base)
         -24 : MathNet.Numerics.dasm (-0.00 % of base)
         -24 : System.IO.Hashing.dasm (-0.06 % of base)
         -24 : Silk.NET.Maths.dasm (-0.00 % of base)
         -20 : Elastic.Apm.dasm (-0.00 % of base)
         -16 : System.Formats.Tar.dasm (-0.02 % of base)
         -16 : System.Linq.dasm (-0.00 % of base)
         -12 : System.Formats.Cbor.dasm (-0.03 % of base)
         -12 : System.Memory.dasm (-0.00 % of base)
         -12 : Magick.NET.Core.dasm (-0.01 % of base)
         -12 : MongoDB.Bson.dasm (-0.00 % of base)
          -8 : System.Runtime.Numerics.dasm (-0.00 % of base)
          -8 : ClosedXML.Parser.dasm (-0.00 % of base)
          -4 : ExcelNumberFormat.dasm (-0.01 % of base)
          -4 : Nest.dasm (-0.00 % of base)
          -4 : System.Configuration.ConfigurationManager.dasm (-0.00 % of base)
          -4 : NuGet.Packaging.dasm (-0.00 % of base)
          -4 : App.Metrics.Core.dasm (-0.00 % of base)
          -4 : SkiaSharp.dasm (-0.00 % of base)
          -4 : App.Metrics.Formatters.Json.dasm (-0.01 % of base)
          -4 : App.Metrics.Abstractions.dasm (-0.00 % of base)
          -3 : MessagePack.dasm (-0.00 % of base)

31 total files with Code Size differences (31 improved, 0 regressed), 729 unchanged.

Top method regressions (bytes):
           4 (0.31 % of base) : SixLabors.Fonts.dasm - SixLabors.Fonts.FontGlyphMetrics:RenderDecorationsTo(SixLabors.Fonts.Rendering.IGlyphRenderer,System.Numerics.Vector2,int,System.Numerics.Matrix3x2,float,SixLabors.Fonts.TextOptions):this (FullOpts)
           1 (0.14 % of base) : System.Private.CoreLib.dasm - System.Text.Ascii:WidenAsciiToUtf16(ptr,ptr,nuint):nuint (FullOpts)

Top method improvements (bytes):
         -62 (-1.86 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives:CosineSimilarityHalfCore(System.ReadOnlySpan`1[System.Half],System.ReadOnlySpan`1[System.Half]):System.Half (FullOpts)
         -53 (-7.37 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]] (FullOpts)
         -53 (-7.46 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -49 (-7.45 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -49 (-7.50 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],byte):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -49 (-7.45 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -49 (-7.28 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[byte]:op_Division(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -49 (-7.50 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[byte],byte):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -49 (-7.45 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -41 (-6.45 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[byte]:op_Division(System.Runtime.Intrinsics.Vector512`1[byte],byte):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -39 (-0.93 % of base) : BouncyCastle.Cryptography.dasm - Org.BouncyCastle.Crypto.Digests.Blake2b_X86:Compress(System.Span`1[ulong],System.ReadOnlySpan`1[ulong],ulong,ulong,ulong,System.ReadOnlySpan`1[byte]) (FullOpts)
         -38 (-0.93 % of base) : BouncyCastle.Cryptography.dasm - Org.BouncyCastle.Crypto.Digests.Blake2bDigest:Compress(System.ReadOnlySpan`1[byte]):this (FullOpts)
         -36 (-0.56 % of base) : BouncyCastle.Cryptography.dasm - Org.BouncyCastle.Crypto.Digests.Blake2b_X86:Perform12Rounds(System.ReadOnlySpan`1[byte],byref,byref,byref,byref) (FullOpts)
         -32 (-4.73 % of base) : SixLabors.ImageSharp.Drawing.dasm - SixLabors.ImageSharp.Drawing.ArcLineSegment:.ctor(SixLabors.ImageSharp.PointF,SixLabors.ImageSharp.PointF,SixLabors.ImageSharp.SizeF,float,bool,bool):this (FullOpts)
         -30 (-3.46 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives:CosineSimilarityCore[double](System.ReadOnlySpan`1[double],System.ReadOnlySpan`1[double]):double (FullOpts)
         -28 (-4.42 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:CreateHarmonicSequence[byte](byte,byte):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -26 (-1.86 % of base) : SixLabors.ImageSharp.Drawing.dasm - SixLabors.ImageSharp.Drawing.ArcLineSegment:.ctor(SixLabors.ImageSharp.PointF,SixLabors.ImageSharp.SizeF,float,float,float):this (FullOpts)
         -24 (-7.41 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -24 (-6.65 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]] (FullOpts)
         -24 (-6.78 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -24 (-7.41 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],byte):System.Numerics.Vector`1[byte] (FullOpts)
         -24 (-7.41 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte]):System.Numerics.Vector`1[byte] (FullOpts)
         -24 (-7.41 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[byte],byte):System.Numerics.Vector`1[byte] (FullOpts)
         -24 (-7.41 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte]):System.Numerics.Vector`1[byte] (FullOpts)
         -24 (-7.41 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Divide[byte](System.Runtime.Intrinsics.Vector256`1[byte],byte):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -24 (-7.41 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Divide[byte](System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -24 (-7.41 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[byte]:op_Division(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -24 (-7.41 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.Divide(System.Runtime.Intrinsics.Vector256`1[byte],byte):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -24 (-7.41 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.Divide(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -21 (-7.12 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:MinMaxInteger[ushort,System.MemoryExtensions+MaxCalc`1[ushort]](System.ReadOnlySpan`1[ushort]):ushort (FullOpts)
         -21 (-7.12 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:MinMaxInteger[ushort,System.MemoryExtensions+MinCalc`1[ushort]](System.ReadOnlySpan`1[ushort]):ushort (FullOpts)
         -20 (-2.79 % of base) : SixLabors.ImageSharp.Drawing.dasm - SixLabors.ImageSharp.Drawing.EllipsePolygon:CreateSegment(System.Numerics.Vector2,SixLabors.ImageSharp.SizeF):SixLabors.ImageSharp.Drawing.CubicBezierLineSegment (FullOpts)
         -19 (-4.81 % of base) : SixLabors.ImageSharp.Drawing.dasm - SixLabors.ImageSharp.Drawing.ArcLineSegment:EllipticArcFromEndParams(SixLabors.ImageSharp.PointF,SixLabors.ImageSharp.PointF,SixLabors.ImageSharp.SizeF,float,bool,bool):SixLabors.ImageSharp.PointF[] (FullOpts)
         -19 (-0.98 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Formats.Png.PngEncoderCore:ApplyOptimalFilteredScanline(byref,byref):this (FullOpts)
         -19 (-6.44 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:MinMaxInteger[byte,System.MemoryExtensions+MaxCalc`1[byte]](System.ReadOnlySpan`1[byte]):byte (FullOpts)
         -19 (-6.44 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:MinMaxInteger[byte,System.MemoryExtensions+MinCalc`1[byte]](System.ReadOnlySpan`1[byte]):byte (FullOpts)
         -18 (-8.61 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives:Finalize[double](System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double],System.Runtime.Intrinsics.Vector512`1[double]):double (FullOpts)
         -16 (-2.61 % of base) : CommunityToolkit.HighPerformance.dasm - CommunityToolkit.HighPerformance.Helpers.Internals.SpanHelper:CountSimd[short](byref,nint,short):nint (FullOpts)
         -16 (-0.15 % of base) : SixLabors.Fonts.dasm - SixLabors.Fonts.Tables.Cff.CffEvaluationEngine:Parse(System.ReadOnlySpan`1[byte]):this (FullOpts)
         -16 (-0.54 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Formats.Webp.Lossy.QuantEnc:PickBestIntra4(SixLabors.ImageSharp.Formats.Webp.Lossy.Vp8EncIterator,byref,SixLabors.ImageSharp.Formats.Webp.Lossy.Vp8SegmentInfo[],SixLabors.ImageSharp.Formats.Webp.Lossy.Vp8EncProba,int):bool (FullOpts)
         -16 (-0.59 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Formats.Webp.Lossy.QuantEnc:RefineUsingDistortion(SixLabors.ImageSharp.Formats.Webp.Lossy.Vp8EncIterator,SixLabors.ImageSharp.Formats.Webp.Lossy.Vp8SegmentInfo[],SixLabors.ImageSharp.Formats.Webp.Lossy.Vp8ModeScore,bool,bool,int) (FullOpts)
         -16 (-0.47 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Processing.Processors.Transforms.RotateProcessor:.ctor(float,SixLabors.ImageSharp.Processing.Processors.Transforms.IResampler,SixLabors.ImageSharp.Size):this (FullOpts)
         -16 (-0.47 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Processing.Processors.Transforms.RotateProcessor:.ctor(float,SixLabors.ImageSharp.Size):this (FullOpts)
         -16 (-0.49 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Processing.Processors.Transforms.SkewProcessor:.ctor(float,float,SixLabors.ImageSharp.Processing.Processors.Transforms.IResampler,SixLabors.ImageSharp.Size):this (FullOpts)
         -16 (-0.49 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Processing.Processors.Transforms.SkewProcessor:.ctor(float,float,SixLabors.ImageSharp.Size):this (FullOpts)
         -16 (-0.46 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Processing.RotateExtensions:Rotate(SixLabors.ImageSharp.Processing.IImageProcessingContext,float,SixLabors.ImageSharp.Processing.Processors.Transforms.IResampler):SixLabors.ImageSharp.Processing.IImageProcessingContext (FullOpts)
         -16 (-0.49 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Processing.SkewExtensions:Skew(SixLabors.ImageSharp.Processing.IImageProcessingContext,float,float,SixLabors.ImageSharp.Processing.Processors.Transforms.IResampler):SixLabors.ImageSharp.Processing.IImageProcessingContext (FullOpts)
         -16 (-6.32 % of base) : System.Formats.Tar.dasm - System.Formats.Tar.TarHeader:Checksum(System.ReadOnlySpan`1[byte]):int (FullOpts)
         -16 (-3.50 % of base) : System.IO.Hashing.dasm - System.IO.Hashing.Adler32:UpdateVector512(uint,System.ReadOnlySpan`1[byte]):uint (FullOpts)
         -16 (-2.63 % of base) : System.Linq.dasm - System.Linq.Enumerable:Average(System.Collections.Generic.IEnumerable`1[int]):double (FullOpts)
         -16 (-3.30 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):System.Runtime.Intrinsics.Vector512`1[short] (FullOpts)
         -16 (-3.17 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]] (FullOpts)
         -16 (-3.23 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):System.Runtime.Intrinsics.Vector512`1[short] (FullOpts)
         -16 (-4.72 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:CreateHarmonicSequence[byte](byte,byte):System.Numerics.Vector`1[byte] (FullOpts)
         -16 (-4.72 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:CreateHarmonicSequence[byte](byte,byte):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -16 (-5.28 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[byte]:op_Division(System.Runtime.Intrinsics.Vector256`1[byte],byte):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -16 (-3.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:Divide[short](System.Runtime.Intrinsics.Vector512`1[short],short):System.Runtime.Intrinsics.Vector512`1[short] (FullOpts)
         -16 (-3.30 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:Divide[short](System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):System.Runtime.Intrinsics.Vector512`1[short] (FullOpts)
         -16 (-3.23 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[short]:op_Division(System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):System.Runtime.Intrinsics.Vector512`1[short] (FullOpts)
         -16 (-3.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[short],short):System.Runtime.Intrinsics.Vector512`1[short] (FullOpts)
         -16 (-3.30 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):System.Runtime.Intrinsics.Vector512`1[short] (FullOpts)
         -14 (-5.15 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.ColorProfiles.Icc.Calculators.ClutCalculator:Interpolate1d(ptr,ptr):this (FullOpts)
         -13 (-0.16 % of base) : BepuPhysics.dasm - BepuPhysics.CollisionDetection.CollisionTasks.BoxConvexHullTester:Test(byref,byref,byref,byref,byref,byref,int,byref) (FullOpts)
         -13 (-4.38 % of base) : SixLabors.Fonts.dasm - SixLabors.Fonts.Tables.General.Colr.ColrTable:BuildSkew(float,float,bool,float,float):System.Numerics.Matrix3x2 (FullOpts)
         -12 (-1.93 % of base) : BepuPhysics.dasm - BepuPhysics.CollisionDetection.MeshReduction+TestTriangle:.ctor(byref,int):this (FullOpts)
         -12 (-0.76 % of base) : BouncyCastle.Cryptography.dasm - Org.BouncyCastle.Crypto.Engines.ChaCha7539Engine:ImplProcessBlocks2_X86_Avx2(int,uint[],System.ReadOnlySpan`1[byte],System.Span`1[byte]) (FullOpts)
         -12 (-0.56 % of base) : BouncyCastle.Cryptography.dasm - Org.BouncyCastle.Crypto.Engines.ChaCha7539Engine:ProcessBlocks2(System.ReadOnlySpan`1[byte],System.Span`1[byte]):this (FullOpts)
         -12 (-0.17 % of base) : SixLabors.Fonts.dasm - SixLabors.Fonts.Tables.General.Colr.ColrGlyphSourceBase:FlattenPaint(SixLabors.Fonts.Tables.General.Colr.Paint,System.Numerics.Matrix3x2,int,SixLabors.Fonts.Tables.General.CpalTable,SixLabors.Fonts.Tables.General.Colr.ColrTable,SixLabors.Fonts.Tables.AdvancedTypographic.Variations.GlyphVariationProcessor,System.Collections.Generic.List`1[SixLabors.Fonts.Rendering.Paint]) (FullOpts)
         -12 (-1.08 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.ColorProfiles.Icc.Calculators.ClutCalculator:Interpolate4d(ptr,ptr):this (FullOpts)
         -12 (-2.04 % of base) : SixLabors.ImageSharp.Drawing.dasm - SixLabors.ImageSharp.Drawing.Processing.Backends.DefaultRasterizer+StrokeLinearizer`1[System.__Canon]:EmitPointStrokeContour(SixLabors.ImageSharp.PointF,bool):this (FullOpts)
         -12 (-4.78 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Formats.Png.Filters.PaethFilter:PaethPredictor(System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte]):System.Numerics.Vector`1[byte] (FullOpts)
         -12 (-11.32 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Numerics:Accumulate(byref,System.Numerics.Vector`1[byte]) (FullOpts)
         -12 (-2.48 % of base) : System.Private.CoreLib.dasm - System.Double:<RootN>g__NegativeN|242_1(double,int):double (FullOpts)
         -12 (-2.53 % of base) : System.Private.CoreLib.dasm - System.Double:<RootN>g__PositiveN|242_0(double,int):double (FullOpts)
         -12 (-10.91 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives:Finalize[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):double (FullOpts)
         -12 (-10.34 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+WidenByteToSingleOperator:Invoke(System.Runtime.Intrinsics.Vector256`1[byte]):System.ValueTuple`4[System.Runtime.Intrinsics.Vector256`1[float],System.Runtime.Intrinsics.Vector256`1[float],System.Runtime.Intrinsics.Vector256`1[float],System.Runtime.Intrinsics.Vector256`1[float]] (FullOpts)
         -12 (-8.70 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+WidenByteToSingleOperator:Invoke(System.Runtime.Intrinsics.Vector512`1[byte]):System.ValueTuple`4[System.Runtime.Intrinsics.Vector512`1[float],System.Runtime.Intrinsics.Vector512`1[float],System.Runtime.Intrinsics.Vector512`1[float],System.Runtime.Intrinsics.Vector512`1[float]] (FullOpts)
         -12 (-13.04 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+WidenByteToUInt32Operator:Invoke(System.Runtime.Intrinsics.Vector256`1[byte]):System.ValueTuple`4[System.Runtime.Intrinsics.Vector256`1[uint],System.Runtime.Intrinsics.Vector256`1[uint],System.Runtime.Intrinsics.Vector256`1[uint],System.Runtime.Intrinsics.Vector256`1[uint]] (FullOpts)
         -12 (-10.53 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+WidenByteToUInt32Operator:Invoke(System.Runtime.Intrinsics.Vector512`1[byte]):System.ValueTuple`4[System.Runtime.Intrinsics.Vector512`1[uint],System.Runtime.Intrinsics.Vector512`1[uint],System.Runtime.Intrinsics.Vector512`1[uint],System.Runtime.Intrinsics.Vector512`1[uint]] (FullOpts)
         -12 (-10.62 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:MultiplyAddEstimate[byte](System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
         -12 (-14.46 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:MultiplyAddEstimate[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
         -12 (-14.12 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:MultiplyAddEstimate[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
         -12 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:MultiplyAddEstimate[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
         -12 (-7.74 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:MultiplyAddEstimate[byte](System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
         -12 (-10.26 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:MultiplyAddEstimate[int](System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
         -12 (-10.08 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:MultiplyAddEstimate[long](System.Runtime.Intrinsics.Vector512`1[long],System.Runtime.Intrinsics.Vector512`1[long],System.Runtime.Intrinsics.Vector512`1[long]):System.Runtime.Intrinsics.Vector512`1[long] (FullOpts)
         -12 (-10.43 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:MultiplyAddEstimate[short](System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short],System.Runtime.Intrinsics.Vector512`1[short]):System.Runtime.Intrinsics.Vector512`1[short] (FullOpts)
         -12 (-2.54 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[short]:op_Division(System.Runtime.Intrinsics.Vector512`1[short],short):System.Runtime.Intrinsics.Vector512`1[short] (FullOpts)
         -12 (-3.08 % of base) : System.Private.CoreLib.dasm - System.Single:<RootN>g__NegativeN|242_1(float,int):float (FullOpts)
         -12 (-3.16 % of base) : System.Private.CoreLib.dasm - System.Single:<RootN>g__PositiveN|242_0(float,int):float (FullOpts)
         -11 (-2.33 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.ColorProfiles.Icc.Calculators.ClutCalculator:Interpolate2d(ptr,ptr):this (FullOpts)
         -10 (-1.73 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Formats.Jpeg.Components.JpegColorConverterBase+YCbCrScalar:ConvertToRgbInPlace(byref,float,float) (FullOpts)
         -10 (-6.85 % of base) : SixLabors.ImageSharp.dasm - SixLabors.ImageSharp.Matrix3x2Extensions:CreateSkewDegrees(float,float):System.Numerics.Matrix3x2 (FullOpts)
         -10 (-7.46 % of base) : System.Private.CoreLib.dasm - System.Numerics.Matrix3x2:CreateSkew(float,float):System.Numerics.Matrix3x2 (FullOpts)
          -9 (-1.32 % of base) : BepuPhysics.dasm - BepuPhysics.Trees.Tree:PartitionSubtreesWorker(long,ptr,int,BepuUtilities.IThreadDispatcher) (FullOpts)
          -9 (-0.70 % of base) : SixLabors.ImageSharp.Drawing.dasm - SixLabors.ImageSharp.Drawing.Processing.Backends.DefaultRasterizer+StrokeLinearizer`1[System.__Canon]:BuildContourSegments(System.ReadOnlySpan`1[SixLabors.ImageSharp.PointF],bool,System.Span`1[SixLabors.ImageSharp.Drawing.Processing.Backends.DefaultRasterizer+StrokeLinearizer`1+StrokeContourSegment[System.__Canon]],byref,byref):int:this (FullOpts)
          -8 (-2.47 % of base) : ClosedXML.dasm - ClosedXML.Excel.CalcEngine.Functions.XLMath:Round(double,double):double (FullOpts)
          -8 (-3.38 % of base) : ClosedXML.dasm - ClosedXML.Excel.XLHelper:NoCToPixels(double,ClosedXML.Excel.IXLFont,ClosedXML.Excel.XLWorkbook):int (FullOpts)
          -8 (-2.11 % of base) : ClosedXML.Parser.dasm - ClosedXML.Parser.NameUtils:IsSheetNameValid(System.ReadOnlySpan`1[char]):bool (FullOpts)
          -8 (-1.79 % of base) : CommunityToolkit.HighPerformance.dasm - CommunityToolkit.HighPerformance.Helpers.Internals.SpanHelper:CountSimd[double](byref,nint,double):nint (FullOpts)

Top method regressions (percentages):
           4 (0.31 % of base) : SixLabors.Fonts.dasm - SixLabors.Fonts.FontGlyphMetrics:RenderDecorationsTo(SixLabors.Fonts.Rendering.IGlyphRenderer,System.Numerics.Vector2,int,System.Numerics.Matrix3x2,float,SixLabors.Fonts.TextOptions):this (FullOpts)
           1 (0.14 % of base) : System.Private.CoreLib.dasm - System.Text.Ascii:WidenAsciiToUtf16(ptr,ptr,nuint):nuint (FullOpts)

Top method improvements (percentages):
          -8 (-17.39 % of base) : System.Runtime.Numerics.dasm - System.Numerics.Complex`1[double]:MultiplyAddEstimate(System.Numerics.Complex`1[double],System.Numerics.Complex`1[double],System.Numerics.Complex`1[double]):System.Numerics.Complex`1[double] (FullOpts)
          -4 (-16.00 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[double](double):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-14.81 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+MultiplyOperator`1[double]:Invoke(System.Runtime.Intrinsics.Vector512`1[double]):double (FullOpts)
          -4 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[byte](byte):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -4 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[byte](System.Runtime.Intrinsics.Vector128`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -4 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[double](System.Runtime.Intrinsics.Vector128`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -4 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[int](int):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -4 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[int](System.Runtime.Intrinsics.Vector128`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -4 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[long](long):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -4 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[long](System.Runtime.Intrinsics.Vector128`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -4 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[short](short):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -4 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Create[short](System.Runtime.Intrinsics.Vector128`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
         -12 (-14.81 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:MultiplyAddEstimate[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
         -12 (-14.46 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:MultiplyAddEstimate[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-14.29 % of base) : System.Private.CoreLib.dasm - System.Buffers.IndexOfAnyAsciiSearcher+AnyByteState:.ctor(System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte],System.Buffers.BitVector256):this (FullOpts)
         -12 (-14.12 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:MultiplyAddEstimate[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Equals[byte](System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Equals[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Equals[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThan[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThan[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThan[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThan[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[byte]:op_Addition(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[byte]:op_BitwiseAnd(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[byte]:op_BitwiseOr(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[byte]:op_ExclusiveOr(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[byte]:op_Subtraction(System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:op_Addition(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:op_BitwiseAnd(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:op_BitwiseOr(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:op_Division(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:op_ExclusiveOr(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:op_Multiply(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[double]:op_Subtraction(System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[int]:op_Addition(System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[int]:op_BitwiseAnd(System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[int]:op_BitwiseOr(System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[int]:op_ExclusiveOr(System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[int]:op_Subtraction(System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[long]:op_Addition(System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[long]:op_BitwiseAnd(System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[long]:op_BitwiseOr(System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[long]:op_ExclusiveOr(System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[long]:op_Subtraction(System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_Addition(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_BitwiseAnd(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_BitwiseOr(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_ExclusiveOr(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_Multiply(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-14.04 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_Subtraction(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-13.79 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+AddOperator`1[long]:Invoke(System.Runtime.Intrinsics.Vector512`1[long]):long (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:ConcatLowerLower[byte](System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte]):System.Numerics.Vector`1[byte] (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:ConcatLowerLower[double](System.Numerics.Vector`1[double],System.Numerics.Vector`1[double]):System.Numerics.Vector`1[double] (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:ConcatLowerLower[int](System.Numerics.Vector`1[int],System.Numerics.Vector`1[int]):System.Numerics.Vector`1[int] (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:ConcatLowerLower[long](System.Numerics.Vector`1[long],System.Numerics.Vector`1[long]):System.Numerics.Vector`1[long] (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:ConcatLowerLower[short](System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ConcatLowerLower[byte](System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ConcatLowerLower[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ConcatLowerLower[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ConcatLowerLower[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -4 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ConcatLowerLower[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-13.79 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[long]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Sum(System.Runtime.Intrinsics.Vector512`1[long]):long (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Equals[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Equals[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThan[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThan[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:GreaterThanOrEqual[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThan[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThan[long](System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:LessThanOrEqual[double](System.Runtime.Intrinsics.Vector256`1[double],System.Runtime.Intrinsics.Vector256`1[double]):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftLeft(System.Runtime.Intrinsics.Vector256`1[uint],System.Runtime.Intrinsics.Vector256`1[uint]):System.Runtime.Intrinsics.Vector256`1[uint] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftLeft(System.Runtime.Intrinsics.Vector256`1[ulong],System.Runtime.Intrinsics.Vector256`1[ulong]):System.Runtime.Intrinsics.Vector256`1[ulong] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:UnzipEven[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:UnzipOdd[int](System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-13.56 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[int]:op_Multiply(System.Runtime.Intrinsics.Vector256`1[int],System.Runtime.Intrinsics.Vector256`1[int]):System.Runtime.Intrinsics.Vector256`1[int] (FullOpts)
          -8 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:AddSaturate[byte](System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -8 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:AddSaturate[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:SubtractSaturate[byte](System.Runtime.Intrinsics.Vector256`1[byte],System.Runtime.Intrinsics.Vector256`1[byte]):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
          -8 (-13.33 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:SubtractSaturate[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
          -8 (-13.11 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[long]:op_Multiply(System.Runtime.Intrinsics.Vector256`1[long],System.Runtime.Intrinsics.Vector256`1[long]):System.Runtime.Intrinsics.Vector256`1[long] (FullOpts)
         -12 (-13.04 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+WidenByteToUInt32Operator:Invoke(System.Runtime.Intrinsics.Vector256`1[byte]):System.ValueTuple`4[System.Runtime.Intrinsics.Vector256`1[uint],System.Runtime.Intrinsics.Vector256`1[uint],System.Runtime.Intrinsics.Vector256`1[uint],System.Runtime.Intrinsics.Vector256`1[uint]] (FullOpts)
          -8 (-12.31 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+IndexOfMaxOperator`1[long]:Aggregate(System.Runtime.Intrinsics.Vector512`1[long]):long (FullOpts)
          -8 (-12.31 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+IndexOfMinOperator`1[long]:Aggregate(System.Runtime.Intrinsics.Vector512`1[long]):long (FullOpts)
          -8 (-12.31 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+MaxNumberOperator`1[long]:Invoke(System.Runtime.Intrinsics.Vector512`1[long]):long (FullOpts)
          -8 (-12.31 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+MaxOperator`1[long]:Invoke(System.Runtime.Intrinsics.Vector512`1[long]):long (FullOpts)
          -8 (-12.31 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+MinNumberOperator`1[long]:Invoke(System.Runtime.Intrinsics.Vector512`1[long]):long (FullOpts)
          -8 (-12.31 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+MinOperator`1[long]:Invoke(System.Runtime.Intrinsics.Vector512`1[long]):long (FullOpts)
          -8 (-12.31 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+MultiplyOperator`1[long]:Invoke(System.Runtime.Intrinsics.Vector512`1[long]):long (FullOpts)
          -8 (-12.12 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+AddOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector512`1[int]):int (FullOpts)
          -4 (-12.12 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:CreateAlternatingSequence[double](double,double):System.Runtime.Intrinsics.Vector256`1[double] (FullOpts)
          -4 (-12.12 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ExtractMostSignificantBits[byte](System.Runtime.Intrinsics.Vector256`1[byte]):uint (FullOpts)
          -4 (-12.12 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ExtractMostSignificantBits[double](System.Runtime.Intrinsics.Vector256`1[double]):uint (FullOpts)
          -4 (-12.12 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ExtractMostSignificantBits[int](System.Runtime.Intrinsics.Vector256`1[int]):uint (FullOpts)
          -4 (-12.12 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ExtractMostSignificantBits[long](System.Runtime.Intrinsics.Vector256`1[long]):uint (FullOpts)
          -8 (-12.12 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Sum(System.Runtime.Intrinsics.Vector512`1[int]):int (FullOpts)
          -4 (-11.76 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+AddOperator`1[double]:Invoke(System.Runtime.Intrinsics.Vector256`1[double]):double (FullOpts)
          -4 (-11.76 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+MultiplyOperator`1[double]:Invoke(System.Runtime.Intrinsics.Vector256`1[double]):double (FullOpts)
          -4 (-11.76 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RoundAwayFromZeroOperator`1[double]:Invoke(double):double (FullOpts)
          -4 (-11.76 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[double]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Sum(System.Numerics.Vector`1[double]):double (FullOpts)

1067 total methods with Code Size differences (1065 improved, 2 regressed), 2113162 unchanged.

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

Artifacts:

• PackageList.json (200 KB)
• diff-frameworks.txt (50 KB)
• ShortDiffsRegressions.md (57 KB)
• ShortDiffsImprovements.md (54 KB)
• LongDiffsImprovements.md (547 KB)
• jit-diffs-pr.7z (381 MB)
• jit-diffs-main.7z (381 MB)

[MihuBot]

Top method regressions

4 (0.31 % of base) - SixLabors.Fonts.FontGlyphMetrics:RenderDecorationsTo(SixLabors.Fonts.Rendering.IGlyphRenderer,System.Numerics.Vector2,int,System.Numerics.Matrix3x2,float,SixLabors.Fonts.TextOptions):this

 ; Assembly listing for method SixLabors.Fonts.FontGlyphMetrics:RenderDecorationsTo(SixLabors.Fonts.Rendering.IGlyphRenderer,System.Numerics.Vector2,int,System.Numerics.Matrix3x2,float,SixLabors.Fonts.TextOptions):this (FullOpts)
 ; Emitting BLENDED_CODE for x64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; partially interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 23 single block inlinees; 4 inlinees without PGO data
 ; Final local variable assignments
 ;
 ;  V00 this         [V00,T01] ( 12,  8   )     ref  ->  rbx         this class-hnd single-def <SixLabors.Fonts.FontGlyphMetrics>
 ;  V01 arg1         [V01,T09] (  3,  3   )     ref  ->  rsi         class-hnd single-def <SixLabors.Fonts.Rendering.IGlyphRenderer>
 ;  V02 arg2         [V02,T21] (  3,  3   )   simd8  ->  mm0         single-def <System.Numerics.Vector2>
 ;  V03 arg3         [V03,T10] (  3,  3   )     int  ->  rdx         single-def
 ;  V04 arg4         [V04,T20] (  1,  1   )  struct (24) [rbp+0x10]  do-not-enreg[S] single-def <System.Numerics.Matrix3x2>
 ;  V05 arg5         [V05,T22] (  3,  3   )   float  ->  mm1         single-def
 ;  V06 arg6         [V06,T08] (  4,  3.50)     ref  ->  rcx         class-hnd single-def <SixLabors.Fonts.TextOptions>
 ;  V07 loc0         [V07    ] ( 27, 19   )  struct (88) [rbp-0x80]  do-not-enreg[XSF] must-init addr-exposed ld-addr-op <SixLabors.Fonts.FontGlyphMetrics+<>c__DisplayClass70_0>
 ;* V08 loc1         [V08    ] (  0,  0   )     ref  ->  zero-ref    class-hnd single-def <SixLabors.Fonts.FontMetrics>
 ;  V09 loc2         [V09,T14] (  3,  2   )   ubyte  ->  r12         single-def
 ;  V10 loc3         [V10,T26] (  3,  1.50)   float  ->  [rbp-0x84]  spill-single-def
 ;  V11 loc4         [V11,T27] (  3,  1.50)   float  ->  [rbp-0x88]  spill-single-def
 ;  V12 loc5         [V12,T15] (  2,  2   )   ubyte  ->  rdi        
 ;* V13 loc6         [V13    ] (  0,  0   )     int  ->  zero-ref   
 ;# V14 OutArgs      [V14    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
 ;  V15 tmp1         [V15,T06] (  3,  6   )     int  ->  r15         "dup spill"
 ;* V16 tmp2         [V16    ] (  0,  0   )     int  ->  zero-ref   
 ;* V17 tmp3         [V17    ] (  0,  0   )     int  ->  zero-ref    single-def
 ;  V18 tmp4         [V18,T00] ( 28, 14   )     ref  ->  r14        
 ;* V19 tmp5         [V19    ] (  0,  0   )   simd8  ->  zero-ref    ld-addr-op "NewObj constructor temp" <System.Numerics.Vector2>
 ;  V20 tmp6         [V20,T02] (  4,  8   )     int  ->  r13         "impAppendStmt"
 ;* V21 tmp7         [V21    ] (  0,  0   )     int  ->  zero-ref   
 ;* V22 tmp8         [V22    ] (  0,  0   )     int  ->  zero-ref   
 ;* V23 tmp9         [V23    ] (  0,  0   )   float  ->  zero-ref    "non-inline candidate call"
 ;* V24 tmp10        [V24    ] (  0,  0   )     int  ->  zero-ref    "non-inline candidate call"
 ;* V25 tmp11        [V25    ] (  0,  0   )     int  ->  zero-ref    single-def
 ;* V26 tmp12        [V26    ] (  0,  0   )     ref  ->  zero-ref    single-def
 ;* V27 tmp13        [V27    ] (  0,  0   )     int  ->  zero-ref    single-def
 ;  V28 tmp14        [V28,T32] (  2,  1   )   float  ->  [rbp-0x8C]  spill-single-def
 ;* V29 tmp15        [V29    ] (  0,  0   )     int  ->  zero-ref    single-def
 ;* V30 tmp16        [V30    ] (  0,  0   )     ref  ->  zero-ref    single-def
 ;* V31 tmp17        [V31    ] (  0,  0   )     int  ->  zero-ref    single-def
 ;* V32 tmp18        [V32    ] (  0,  0   )   float  ->  zero-ref    single-def
 ;  V33 tmp19        [V33,T28] (  3,  1.50)   float  ->  mm1        
 ;* V34 tmp20        [V34    ] (  0,  0   )     int  ->  zero-ref    single-def
 ;* V35 tmp21        [V35    ] (  0,  0   )     ref  ->  zero-ref    single-def
 ;* V36 tmp22        [V36    ] (  0,  0   )     int  ->  zero-ref    single-def
 ;  V37 tmp23        [V37,T33] (  2,  1   )   float  ->  [rbp-0x90]  spill-single-def
 ;* V38 tmp24        [V38    ] (  0,  0   )     int  ->  zero-ref   
 ;* V39 tmp25        [V39    ] (  0,  0   )     ref  ->  zero-ref   
 ;* V40 tmp26        [V40    ] (  0,  0   )     int  ->  zero-ref   
 ;* V41 tmp27        [V41    ] (  0,  0   )   float  ->  zero-ref   
 ;  V42 tmp28        [V42,T16] (  3,  1.50)     int  ->  rax        
 ;* V43 tmp29        [V43    ] (  0,  0   )   simd8  ->  zero-ref    "non-inline candidate call"
 ;* V44 tmp30        [V44    ] (  0,  0   )   float  ->  zero-ref    "non-inline candidate call"
 ;* V45 tmp31        [V45    ] (  0,  0   )   simd8  ->  zero-ref    ld-addr-op "NewObj constructor temp" <System.Numerics.Vector2>
 ;* V46 tmp32        [V46    ] (  0,  0   )   float  ->  zero-ref    "non-inline candidate call"
 ;* V47 tmp33        [V47    ] (  0,  0   )   byref  ->  zero-ref   
 ;* V48 tmp34        [V48    ] (  0,  0   )   float  ->  zero-ref   
 ;* V49 tmp35        [V49    ] (  0,  0   )   byref  ->  zero-ref   
 ;  V50 tmp36        [V50,T34] (  2,  1   )   float  ->  [rbp-0x94]  spill-single-def
 ;  V51 tmp37        [V51,T17] (  3,  1.50)     int  ->  r15        
 ;* V52 tmp38        [V52    ] (  0,  0   )   simd8  ->  zero-ref    ld-addr-op "NewObj constructor temp" <System.Numerics.Vector2>
 ;* V53 tmp39        [V53    ] (  0,  0   )   simd8  ->  zero-ref    "non-inline candidate call"
 ;* V54 tmp40        [V54    ] (  0,  0   )   float  ->  zero-ref    "non-inline candidate call"
 ;* V55 tmp41        [V55    ] (  0,  0   )   simd8  ->  zero-ref    ld-addr-op "NewObj constructor temp" <System.Numerics.Vector2>
 ;* V56 tmp42        [V56    ] (  0,  0   )   float  ->  zero-ref    "non-inline candidate call"
 ;* V57 tmp43        [V57    ] (  0,  0   )   byref  ->  zero-ref   
 ;* V58 tmp44        [V58    ] (  0,  0   )   float  ->  zero-ref   
 ;* V59 tmp45        [V59    ] (  0,  0   )   byref  ->  zero-ref   
 ;  V60 tmp46        [V60,T35] (  2,  1   )   float  ->  [rbp-0x98]  spill-single-def
 ;  V61 tmp47        [V61,T18] (  3,  1.50)     int  ->  rax        
 ;* V62 tmp48        [V62    ] (  0,  0   )   simd8  ->  zero-ref    ld-addr-op "NewObj constructor temp" <System.Numerics.Vector2>
 ;* V63 tmp49        [V63    ] (  0,  0   )   float  ->  zero-ref    "Inlining Arg"
 ;* V64 tmp50        [V64    ] (  0,  0   )   simd8  ->  zero-ref    ld-addr-op "Inline ldloca(s) first use temp" <System.Numerics.Vector2>
 ;* V65 tmp51        [V65    ] (  0,  0   )   float  ->  zero-ref    "Inlining Arg"
 ;* V66 tmp52        [V66    ] (  0,  0   )   simd8  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector2>
 ;* V67 tmp53        [V67    ] (  0,  0   )   float  ->  zero-ref    "Inlining Arg"
 ;* V68 tmp54        [V68    ] (  0,  0   )   float  ->  zero-ref    "Inlining Arg"
 ;* V69 tmp55        [V69    ] (  0,  0   )   float  ->  zero-ref    "Inlining Arg"
 ;* V70 tmp56        [V70    ] (  0,  0   )   simd8  ->  zero-ref    "Inlining Arg" <System.Numerics.Vector2>
 ;* V71 tmp57        [V71    ] (  0,  0   )   float  ->  zero-ref    "Inlining Arg"
 ;* V72 tmp58        [V72    ] (  0,  0   )   float  ->  zero-ref    "Inlining Arg"
 ;  V73 tmp59        [V73,T05] (  6,  6   )   short  ->  rax         "Inlining Arg"
 ;* V74 tmp60        [V74    ] (  0,  0   )     ref  ->  zero-ref    class-hnd "Inlining Arg" <SixLabors.Fonts.FontGlyphMetrics>
 ;* V75 tmp61        [V75    ] (  0,  0   )   float  ->  zero-ref    "Inlining Arg"
 ;  V76 tmp62        [V76,T11] (  4,  4   )  struct (24) [rbp-0xB0]  do-not-enreg[DAS] defined-via-address "dup spill" <System.ValueTuple`3[System.Numerics.Vector2,System.Numerics.Vector2,float]>
 ;  V77 tmp63        [V77,T36] (  2,  1   )   simd8  ->  mm0         single-def "Inline stloc first use temp" <System.Numerics.Vector2>
 ;  V78 tmp64        [V78,T37] (  2,  1   )   simd8  ->  mm1         single-def "Inline stloc first use temp" <System.Numerics.Vector2>
 ;  V79 tmp65        [V79,T29] (  3,  1.50)   float  ->  mm2         single-def "Inline stloc first use temp"
 ;* V80 tmp66        [V80    ] (  0,  0   )     ref  ->  zero-ref    class-hnd "Inlining Arg" <SixLabors.Fonts.FontGlyphMetrics>
 ;  V81 tmp67        [V81,T12] (  4,  4   )  struct (24) [rbp-0xC8]  do-not-enreg[DAS] defined-via-address "dup spill" <System.ValueTuple`3[System.Numerics.Vector2,System.Numerics.Vector2,float]>
 ;  V82 tmp68        [V82,T38] (  2,  1   )   simd8  ->  mm0         single-def "Inline stloc first use temp" <System.Numerics.Vector2>
 ;  V83 tmp69        [V83,T39] (  2,  1   )   simd8  ->  mm1         single-def "Inline stloc first use temp" <System.Numerics.Vector2>
 ;  V84 tmp70        [V84,T30] (  3,  1.50)   float  ->  mm2         single-def "Inline stloc first use temp"
 ;* V85 tmp71        [V85    ] (  0,  0   )   float  ->  zero-ref    "Inlining Arg"
 ;  V86 tmp72        [V86,T13] (  4,  4   )  struct (24) [rbp-0xE0]  do-not-enreg[DAS] defined-via-address "dup spill" <System.ValueTuple`3[System.Numerics.Vector2,System.Numerics.Vector2,float]>
 ;  V87 tmp73        [V87,T40] (  2,  1   )   simd8  ->  mm0         single-def "Inline stloc first use temp" <System.Numerics.Vector2>
 ;  V88 tmp74        [V88,T41] (  2,  1   )   simd8  ->  mm1         single-def "Inline stloc first use temp" <System.Numerics.Vector2>
 ;  V89 tmp75        [V89,T31] (  3,  1.50)   float  ->  mm2         single-def "Inline stloc first use temp"
 ;  V90 tmp76        [V90,T24] (  2,  2   )   float  ->  [rbp-0xE4]  spill-single-def "argument with side effect"
 ;  V91 tmp77        [V91,T25] (  2,  2   )   float  ->  mm1         "argument with side effect"
 ;  V92 cse0         [V92,T07] ( 11,  5.50)    long  ->  r13         multi-def "CSE #03: aggressive"
 ;  V93 cse1         [V93,T04] ( 13,  6.50)    long  ->  [rbp-0xF0]  multi-def "CSE #10: aggressive"
 ;  V94 cse2         [V94,T23] (  3,  2.50)   simd8  ->  mm0         "CSE #01: moderate"
 ;  V95 cse3         [V95,T19] (  3,  1.50)     int  ->  rdi         "CSE #05: conservative"
 ;  V96 cse4         [V96,T03] ( 14,  7   )    long  ->  r15         multi-def "CSE #02: aggressive"
-;  TEMP_02                                  simd16  ->  [rbp-0x100]
-;  TEMP_01                                  simd16  ->  [rbp-0x110]
+;  TEMP_01                                   float  ->  [rbp-0xF4]
+;  TEMP_02                                  simd16  ->  [rbp-0x104]
 ;
 ; Lcl frame size = 232
 
 G_M36385_IG01:
        push     rbp
        push     r15
        push     r14
        push     r13
        push     r12
        push     rbx
        sub      rsp, 232
        lea      rbp, [rsp+0x110]
        vxorps   xmm8, xmm8, xmm8
        vmovdqu32 zmmword ptr [rbp-0x80], zmm8
        vmovdqa  xmmword ptr [rbp-0x40], xmm8
        xor      eax, eax
        mov      qword ptr [rbp-0x30], rax
        mov      rbx, rdi
 						;; size=51 bbWeight=1 PerfScore 11.58
 G_M36385_IG02:
        mov      dword ptr [rbp-0x70], edx
        mov      gword ptr [rbp-0x80], rbx
        vmovss   dword ptr [rbp-0x6C], xmm1
        vmovsd   qword ptr [rbp-0x4C], xmm0
        vmovdqu  xmm0, xmmword ptr [rbp+0x10]
        vmovdqu  xmmword ptr [rbp-0x44], xmm0
        mov      rdi, qword ptr [rbp+0x20]
        mov      qword ptr [rbp-0x34], rdi
        mov      gword ptr [rbp-0x78], rsi
        cmp      dword ptr [rcx+0x74], 1
        sete     r15b
        movzx    r15, r15b
        test     r15d, r15d
        je       SHORT G_M36385_IG04
 						;; size=56 bbWeight=1 PerfScore 13.00
 G_M36385_IG03:
        mov      r14, gword ptr [rbx+0x08]
        jmp      SHORT G_M36385_IG05
 						;; size=6 bbWeight=0.50 PerfScore 2.00
 G_M36385_IG04:
        mov      rdi, gword ptr [rcx+0x08]
        mov      rax, 0xD1FFAB1E      ; code for SixLabors.Fonts.Font:get_FontMetrics():SixLabors.Fonts.FontMetrics:this
        cmp      dword ptr [rdi], edi
        call     [rax]SixLabors.Fonts.Font:get_FontMetrics():SixLabors.Fonts.FontMetrics:this
        mov      r14, rax
 						;; size=21 bbWeight=0.50 PerfScore 3.75
 G_M36385_IG05:
        vmovsd   xmm0, qword ptr [rbx+0x50]
        vmovsd   qword ptr [rbp-0x64], xmm0
        test     r15d, r15d
        jne      G_M36385_IG12
 						;; size=19 bbWeight=1 PerfScore 5.25
 G_M36385_IG06:
        mov      rdi, r14
        mov      r15, qword ptr [r14]
        mov      rax, qword ptr [r15+0x40]
        call     [rax+0x28]SixLabors.Fonts.FontMetrics:get_UnitsPerEm():ushort:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vmulss   xmm0, xmm0, dword ptr [reloc @RWD00]
        vbroadcastss xmm0, xmm0
        vmovsd   qword ptr [rbp-0x5C], xmm0
        vxorps   xmm0, xmm0, xmm0
        vmovsd   qword ptr [rbp-0x54], xmm0
        mov      edi, dword ptr [rbx+0x24]
        test     dil, 1
        jne      G_M36385_IG09
        test     dil, 2
        je       G_M36385_IG13
        movzx    rdi, word  ptr [rbx+0x38]
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, edi
        vmovss   dword ptr [rbp-0x88], xmm0
        vmovsd   xmm1, qword ptr [rbp-0x5C]
-       vmovups  xmmword ptr [rbp-0x100], xmm1
+       vmovups  xmmword ptr [rbp-0x104], xmm1
        mov      rdi, r14
        mov      r13, qword ptr [r15+0x48]
        call     [r13+0x28]SixLabors.Fonts.FontMetrics:get_SuperscriptXSize():short:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vdivss   xmm0, xmm0, dword ptr [rbp-0x88]
-       vmovups  xmmword ptr [rbp-0x110], xmm0
+       vmovss   dword ptr [rbp-0xF4], xmm0
        mov      rdi, r14
        call     [r13+0x30]SixLabors.Fonts.FontMetrics:get_SuperscriptYSize():short:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vdivss   xmm0, xmm0, dword ptr [rbp-0x88]
-       vmovups  xmm1, xmmword ptr [rbp-0x110]
+       vmovss   xmm1, dword ptr [rbp-0xF4]
        vinsertps xmm0, xmm1, xmm0, 28
-       vmovups  xmm1, xmmword ptr [rbp-0x100]
+       vmovups  xmm1, xmmword ptr [rbp-0x104]
        vdivps   xmm0, xmm1, xmm0
        vmovsd   qword ptr [rbp-0x5C], xmm0
        mov      rdi, r14
        call     [r13+0x38]SixLabors.Fonts.FontMetrics:get_SuperscriptXOffset():short:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vmovss   dword ptr [rbp-0x94], xmm0
        mov      rdi, r14
        mov      r12, qword ptr [r15+0x50]
        call     [r12]SixLabors.Fonts.FontMetrics:get_SuperscriptYOffset():short:this
        test     eax, eax
        jge      SHORT G_M36385_IG07
        mov      rdi, r14
        call     [r12]SixLabors.Fonts.FontMetrics:get_SuperscriptYOffset():short:this
        mov      r15d, eax
        neg      r15d
        jmp      SHORT G_M36385_IG08
-						;; size=238 bbWeight=0.50 PerfScore 60.88
+						;; size=240 bbWeight=0.50 PerfScore 61.38
 G_M36385_IG07:
        mov      rdi, r14
        call     [r12]SixLabors.Fonts.FontMetrics:get_SuperscriptYOffset():short:this
        mov      r15d, eax
 						;; size=10 bbWeight=0.50 PerfScore 1.75
 G_M36385_IG08:
-       vmovss   xmm0, dword ptr [rbp-0x94]
-       vxorps   xmm1, xmm1, xmm1
-       vcvtsi2ss xmm1, xmm1, r15d
-       vinsertps xmm0, xmm0, xmm1, 28
+       vxorps   xmm0, xmm0, xmm0
+       vcvtsi2ss xmm0, xmm0, r15d
+       vmovss   xmm1, dword ptr [rbp-0x94]
+       vinsertps xmm0, xmm1, xmm0, 28
        vmovsd   qword ptr [rbp-0x54], xmm0
        jmp      G_M36385_IG13
 						;; size=32 bbWeight=0.50 PerfScore 6.17
 G_M36385_IG09:
        movzx    rdi, word  ptr [rbx+0x38]
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, edi
        vmovss   dword ptr [rbp-0x84], xmm0
        vmovsd   xmm1, qword ptr [rbp-0x5C]
-       vmovups  xmmword ptr [rbp-0x100], xmm1
+       vmovups  xmmword ptr [rbp-0x104], xmm1
        mov      rdi, r14
        mov      r13, qword ptr [r15+0x48]
        call     [r13+0x08]SixLabors.Fonts.FontMetrics:get_SubscriptXSize():short:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vdivss   xmm0, xmm0, dword ptr [rbp-0x84]
-       vmovups  xmmword ptr [rbp-0x110], xmm0
+       vmovss   dword ptr [rbp-0xF4], xmm0
        mov      rdi, r14
        call     [r13+0x10]SixLabors.Fonts.FontMetrics:get_SubscriptYSize():short:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vdivss   xmm0, xmm0, dword ptr [rbp-0x84]
-       vmovups  xmm1, xmmword ptr [rbp-0x110]
+       vmovss   xmm1, dword ptr [rbp-0xF4]
        vinsertps xmm0, xmm1, xmm0, 28
-       vmovups  xmm1, xmmword ptr [rbp-0x100]
+       vmovups  xmm1, xmmword ptr [rbp-0x104]
        vdivps   xmm0, xmm1, xmm0
        vmovsd   qword ptr [rbp-0x5C], xmm0
        mov      rdi, r14
        call     [r13+0x18]SixLabors.Fonts.FontMetrics:get_SubscriptXOffset():short:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vmovss   dword ptr [rbp-0x98], xmm0
        mov      rdi, r14
        call     [r13+0x20]SixLabors.Fonts.FontMetrics:get_SubscriptYOffset():short:this
        test     eax, eax
        jge      SHORT G_M36385_IG10
        mov      rdi, r14
        call     [r13+0x20]SixLabors.Fonts.FontMetrics:get_SubscriptYOffset():short:this
        jmp      SHORT G_M36385_IG11
-						;; size=157 bbWeight=0.50 PerfScore 46.42
+						;; size=159 bbWeight=0.50 PerfScore 46.92
 G_M36385_IG10:
        mov      rdi, r14
        call     [r13+0x20]SixLabors.Fonts.FontMetrics:get_SubscriptYOffset():short:this
        neg      eax
 						;; size=9 bbWeight=0.50 PerfScore 1.75
 G_M36385_IG11:
-       vmovss   xmm0, dword ptr [rbp-0x98]
-       vxorps   xmm1, xmm1, xmm1
-       vcvtsi2ss xmm1, xmm1, eax
-       vinsertps xmm0, xmm0, xmm1, 28
+       vxorps   xmm0, xmm0, xmm0
+       vcvtsi2ss xmm0, xmm0, eax
+       vmovss   xmm1, dword ptr [rbp-0x98]
+       vinsertps xmm0, xmm1, xmm0, 28
        vmovsd   qword ptr [rbp-0x54], xmm0
        jmp      SHORT G_M36385_IG13
 						;; size=28 bbWeight=0.50 PerfScore 6.17
 G_M36385_IG12:
        vmovsd   qword ptr [rbp-0x5C], xmm0
        vmovsd   xmm0, qword ptr [rbx+0x58]
        vmovsd   qword ptr [rbp-0x54], xmm0
 						;; size=15 bbWeight=0.50 PerfScore 2.50
 G_M36385_IG13:
        mov      edi, dword ptr [rbp-0x70]
        dec      edi
        cmp      edi, 1
        setbe    dil
        movzx    rdi, dil
        mov      byte  ptr [rbp-0x68], dil
        mov      rdi, gword ptr [rbp-0x78]
        mov      r11, 0xD1FFAB1E      ; code for SixLabors.Fonts.Rendering.IGlyphRenderer:EnabledDecorations():int:this
        call     [r11]SixLabors.Fonts.Rendering.IGlyphRenderer:EnabledDecorations():int:this
        mov      r13d, eax
        cmp      dword ptr [rbp-0x70], 1
        sete     r12b
        movzx    r12, r12b
        test     r13b, 1
        je       G_M36385_IG19
 						;; size=62 bbWeight=1 PerfScore 10.75
 G_M36385_IG14:
        mov      rdi, r14
        mov      r15, qword ptr [r14]
        mov      rax, qword ptr [r15+0x50]
        mov      r15, rax
        call     [r15+0x20]SixLabors.Fonts.FontMetrics:get_UnderlineThickness():short:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vmovss   dword ptr [rbp-0x90], xmm0
        test     r12d, r12d
        je       SHORT G_M36385_IG16
        mov      rdi, r14
        call     [r15+0x18]SixLabors.Fonts.FontMetrics:get_UnderlinePosition():short:this
        test     eax, eax
        jge      SHORT G_M36385_IG15
        neg      eax
        cwde     
        test     eax, eax
        jl       G_M36385_IG29
 						;; size=59 bbWeight=0.50 PerfScore 11.17
 G_M36385_IG15:
        jmp      SHORT G_M36385_IG17
 						;; size=2 bbWeight=0.50 PerfScore 1.00
 G_M36385_IG16:
        mov      rdi, r14
        call     [r15+0x18]SixLabors.Fonts.FontMetrics:get_UnderlinePosition():short:this
 						;; size=7 bbWeight=0.50 PerfScore 1.62
 G_M36385_IG17:
        vxorps   xmm1, xmm1, xmm1
        vcvtsi2ss xmm1, xmm1, eax
        lea      rsi, [rbp-0xB0]
        lea      rcx, [rbp-0x80]
        mov      rdi, rbx
        vmovss   xmm0, dword ptr [rbp-0x90]
        mov      edx, 1
        mov      rax, 0xD1FFAB1E      ; code for SixLabors.Fonts.FontGlyphMetrics:<RenderDecorationsTo>g__GetEnds|70_0(int,float,float,byref):System.ValueTuple`3[System.Numerics.Vector2,System.Numerics.Vector2,float]:this
        call     [rax]SixLabors.Fonts.FontGlyphMetrics:<RenderDecorationsTo>g__GetEnds|70_0(int,float,float,byref):System.ValueTuple`3[System.Numerics.Vector2,System.Numerics.Vector2,float]:this
        vmovsd   xmm0, qword ptr [rbp-0xAC]
        vmovsd   xmm1, qword ptr [rbp-0xA4]
        vmovss   xmm2, dword ptr [rbp-0xB0]
        vxorps   xmm3, xmm3, xmm3
        vucomiss xmm2, xmm3
        jp       SHORT G_M36385_IG18
        je       SHORT G_M36385_IG19
 						;; size=81 bbWeight=0.50 PerfScore 11.71
 G_M36385_IG18:
        mov      rdi, gword ptr [rbp-0x78]
        mov      r11, 0xD1FFAB1E      ; code for SixLabors.Fonts.Rendering.IGlyphRenderer:SetDecoration(int,System.Numerics.Vector2,System.Numerics.Vector2,float):this
        mov      esi, 1
        call     [r11]SixLabors.Fonts.Rendering.IGlyphRenderer:SetDecoration(int,System.Numerics.Vector2,System.Numerics.Vector2,float):this
 						;; size=22 bbWeight=0.50 PerfScore 2.25
 G_M36385_IG19:
        test     r13b, 2
        je       G_M36385_IG24
 						;; size=10 bbWeight=1 PerfScore 1.25
 G_M36385_IG20:
        mov      rdi, r14
        mov      r15, qword ptr [r14]
        mov      rax, qword ptr [r15+0x50]
        mov      qword ptr [rbp-0xF0], rax
        call     [rax+0x08]SixLabors.Fonts.FontMetrics:get_StrikeoutSize():short:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vmovss   dword ptr [rbp-0x8C], xmm0
        test     r12d, r12d
        je       SHORT G_M36385_IG21
        mov      rdi, r14
        mov      rax, qword ptr [r15+0x40]
        call     [rax+0x28]SixLabors.Fonts.FontMetrics:get_UnitsPerEm():ushort:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vmulss   xmm1, xmm0, dword ptr [reloc @RWD04]
        jmp      SHORT G_M36385_IG22
 						;; size=68 bbWeight=0.50 PerfScore 17.71
 G_M36385_IG21:
        mov      rdi, r14
        mov      r12, qword ptr [rbp-0xF0]
        call     [r12+0x10]SixLabors.Fonts.FontMetrics:get_StrikeoutPosition():short:this
        vxorps   xmm1, xmm1, xmm1
        vcvtsi2ss xmm1, xmm1, eax
 						;; size=23 bbWeight=0.50 PerfScore 5.29
 G_M36385_IG22:
        lea      rcx, [rbp-0x80]
        lea      rsi, [rbp-0xC8]
        mov      rdi, rbx
        vmovss   xmm0, dword ptr [rbp-0x8C]
        mov      edx, 2
        mov      rax, 0xD1FFAB1E      ; code for SixLabors.Fonts.FontGlyphMetrics:<RenderDecorationsTo>g__GetEnds|70_0(int,float,float,byref):System.ValueTuple`3[System.Numerics.Vector2,System.Numerics.Vector2,float]:this
        call     [rax]SixLabors.Fonts.FontGlyphMetrics:<RenderDecorationsTo>g__GetEnds|70_0(int,float,float,byref):System.ValueTuple`3[System.Numerics.Vector2,System.Numerics.Vector2,float]:this
        vmovsd   xmm0, qword ptr [rbp-0xC4]
        vmovsd   xmm1, qword ptr [rbp-0xBC]
        vmovss   xmm2, dword ptr [rbp-0xC8]
        vxorps   xmm3, xmm3, xmm3
        vucomiss xmm2, xmm3
        jp       SHORT G_M36385_IG23
        je       SHORT G_M36385_IG24
 						;; size=73 bbWeight=0.50 PerfScore 8.54
 G_M36385_IG23:
        mov      rdi, gword ptr [rbp-0x78]
        mov      r11, 0xD1FFAB1E      ; code for SixLabors.Fonts.Rendering.IGlyphRenderer:SetDecoration(int,System.Numerics.Vector2,System.Numerics.Vector2,float):this
        mov      esi, 2
        call     [r11]SixLabors.Fonts.Rendering.IGlyphRenderer:SetDecoration(int,System.Numerics.Vector2,System.Numerics.Vector2,float):this
 						;; size=22 bbWeight=0.50 PerfScore 2.25
 G_M36385_IG24:
        test     r13b, 4
        je       G_M36385_IG27
 						;; size=10 bbWeight=1 PerfScore 1.25
 G_M36385_IG25:
        mov      rdi, r14
        mov      r15, qword ptr [r14]
        mov      r12, qword ptr [r15+0x50]
        call     [r12+0x20]SixLabors.Fonts.FontMetrics:get_UnderlineThickness():short:this
        vxorps   xmm0, xmm0, xmm0
        vcvtsi2ss xmm0, xmm0, eax
        vmovss   dword ptr [rbp-0xE4], xmm0
        mov      rdi, r14
        mov      rax, qword ptr [r15+0x40]
        call     [rax+0x28]SixLabors.Fonts.FontMetrics:get_UnitsPerEm():ushort:this
        mov      r13d, eax
        mov      rdi, r14
        mov      rax, qword ptr [r15+0x50]
        call     [rax+0x18]SixLabors.Fonts.FontMetrics:get_UnderlinePosition():short:this
        sub      r13d, eax
        vxorps   xmm1, xmm1, xmm1
        vcvtsi2ss xmm1, xmm1, r13d
        vmovss   xmm0, dword ptr [rbp-0xE4]
        lea      rcx, [rbp-0x80]
        lea      rsi, [rbp-0xE0]
        mov      rdi, rbx
        mov      edx, 4
        mov      rax, 0xD1FFAB1E      ; code for SixLabors.Fonts.FontGlyphMetrics:<RenderDecorationsTo>g__GetEnds|70_0(int,float,float,byref):System.ValueTuple`3[System.Numerics.Vector2,System.Numerics.Vector2,float]:this
        call     [rax]SixLabors.Fonts.FontGlyphMetrics:<RenderDecorationsTo>g__GetEnds|70_0(int,float,float,byref):System.ValueTuple`3[System.Numerics.Vector2,System.Numerics.Vector2,float]:this
        vmovsd   xmm0, qword ptr [rbp-0xDC]
        vmovsd   xmm1, qword ptr [rbp-0xD4]
        vmovss   xmm2, dword ptr [rbp-0xE0]
        vxorps   xmm3, xmm3, xmm3
        vucomiss xmm2, xmm3
        jp       SHORT G_M36385_IG26
        je       SHORT G_M36385_IG27
 						;; size=138 bbWeight=0.50 PerfScore 24.50
 G_M36385_IG26:
        mov      rdi, gword ptr [rbp-0x78]
        mov      r11, 0xD1FFAB1E      ; code for SixLabors.Fonts.Rendering.IGlyphRenderer:SetDecoration(int,System.Numerics.Vector2,System.Numerics.Vector2,float):this
        mov      esi, 4
        call     [r11]SixLabors.Fonts.Rendering.IGlyphRenderer:SetDecoration(int,System.Numerics.Vector2,System.Numerics.Vector2,float):this
 						;; size=22 bbWeight=0.50 PerfScore 2.25
 G_M36385_IG27:
        nop      
 						;; size=1 bbWeight=1 PerfScore 0.25
 G_M36385_IG28:
        add      rsp, 232
        pop      rbx
        pop      r12
        pop      r13
        pop      r14
        pop      r15
        pop      rbp
        ret      
 						;; size=18 bbWeight=1 PerfScore 4.25
 G_M36385_IG29:
        mov      rax, 0xD1FFAB1E      ; code for System.Math:ThrowNegateTwosCompOverflow()
        call     [rax]System.Math:ThrowNegateTwosCompOverflow()
        int3     
 						;; size=13 bbWeight=0 PerfScore 0.00
 RWD00  	dd	42900000h		;        72
 RWD04  	dd	3F000000h		;       0.5
 
 
-; Total bytes of code 1273, prolog size 48, PerfScore 267.25, instruction count 296, allocated bytes for code 1273 (MethodHash=0ce071de) for method SixLabors.Fonts.FontGlyphMetrics:RenderDecorationsTo(SixLabors.Fonts.Rendering.IGlyphRenderer,System.Numerics.Vector2,int,System.Numerics.Matrix3x2,float,SixLabors.Fonts.TextOptions):this (FullOpts)
+; Total bytes of code 1277, prolog size 48, PerfScore 268.25, instruction count 296, allocated bytes for code 1277 (MethodHash=0ce071de) for method SixLabors.Fonts.FontGlyphMetrics:RenderDecorationsTo(SixLabors.Fonts.Rendering.IGlyphRenderer,System.Numerics.Vector2,int,System.Numerics.Matrix3x2,float,SixLabors.Fonts.TextOptions):this (FullOpts)
 ; ============================================================

1 (0.14 % of base) - System.Text.Ascii:WidenAsciiToUtf16(ptr,ptr,nuint):nuint

 ; Assembly listing for method System.Text.Ascii:WidenAsciiToUtf16(ptr,ptr,nuint):nuint (FullOpts)
 ; Emitting BLENDED_CODE for x64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; fully interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 98 single block inlinees; 16 inlinees without PGO data
 ; Final local variable assignments
 ;
 ;  V00 arg0         [V00,T02] ( 12, 21   )    long  ->  rdi         single-def
 ;  V01 arg1         [V01,T03] ( 19, 17.50)    long  ->  rsi         single-def
 ;  V02 arg2         [V02,T08] (  9,  6.50)    long  ->  rdx         single-def
 ;  V03 loc0         [V03,T00] ( 43, 94.50)    long  ->  rax         ld-addr-op
 ;  V04 loc1         [V04,T13] (  5,  3.50)    long  ->  rdx        
 ;  V05 loc2         [V05,T01] ( 17, 33   )     int  ->   r8        
 ;  V06 loc3         [V06,T12] (  2,  4.50)    long  ->  rcx        
 ;# V07 OutArgs      [V07    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
 ;  V08 tmp1         [V08,T04] (  9, 18.50)    long  ->   r8         "Inline stloc first use temp"
 ;  V09 tmp2         [V09,T09] (  3,  5.50)    long  ->  rcx         "Inline stloc first use temp"
 ;  V10 tmp3         [V10,T14] (  8, 18   )  simd64  ->  mm0         "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;* V11 tmp4         [V11    ] (  0,  0   )  struct (128) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;* V12 tmp5         [V12    ] (  0,  0   )  simd64  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;* V13 tmp6         [V13    ] (  0,  0   )    long  ->  zero-ref    "impAppendStmt"
 ;* V14 tmp7         [V14    ] (  0,  0   )  struct (128) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;* V15 tmp8         [V15    ] (  0,  0   )    long  ->  zero-ref    "impAppendStmt"
 ;* V16 tmp9         [V16    ] (  0,  0   )    long  ->  zero-ref    "Inline stloc first use temp"
 ;* V17 tmp10        [V17    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V18 tmp11        [V18    ] (  0,  0   )  simd64  ->  zero-ref    ld-addr-op "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;* V19 tmp12        [V19    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V20 tmp13        [V20    ] (  0,  0   )  struct (128) zero-ref    "Inline return value spill temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;* V21 tmp14        [V21    ] (  0,  0   )  struct (128) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;* V22 tmp15        [V22    ] (  0,  0   )  simd64  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;* V23 tmp16        [V23    ] (  0,  0   )  simd64  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;* V24 tmp17        [V24    ] (  0,  0   )  struct (128) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;* V25 tmp18        [V25    ] (  0,  0   )  struct (128) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;  V26 tmp19        [V26,T26] (  2,  2   )  simd64  ->  mm2         "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;  V27 tmp20        [V27,T27] (  2,  2   )  simd64  ->  mm0         "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;* V28 tmp21        [V28    ] (  0,  0   )  simd64  ->  zero-ref    "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;* V29 tmp22        [V29    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V30 tmp23        [V30    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V31 tmp24        [V31    ] (  0,  0   )  simd64  ->  zero-ref    ld-addr-op "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;* V32 tmp25        [V32    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V33 tmp26        [V33    ] (  0,  0   )  struct (128) zero-ref    "Inline return value spill temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;* V34 tmp27        [V34    ] (  0,  0   )  struct (128) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;* V35 tmp28        [V35    ] (  0,  0   )  simd64  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;* V36 tmp29        [V36    ] (  0,  0   )  simd64  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;* V37 tmp30        [V37    ] (  0,  0   )  struct (128) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;* V38 tmp31        [V38    ] (  0,  0   )  struct (128) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[ushort],System.Runtime.Intrinsics.Vector512`1[ushort]]>
 ;  V39 tmp32        [V39,T17] (  2, 16   )  simd64  ->  mm2         "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;  V40 tmp33        [V40,T18] (  2, 16   )  simd64  ->  mm0         "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;* V41 tmp34        [V41    ] (  0,  0   )  simd64  ->  zero-ref    "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
 ;* V42 tmp35        [V42    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;  V43 tmp36        [V43,T05] (  9, 18.50)    long  ->   r8         "Inline stloc first use temp"
 ;  V44 tmp37        [V44,T10] (  3,  5.50)    long  ->  rcx         "Inline stloc first use temp"
 ;  V45 tmp38        [V45,T15] (  8, 18   )  simd32  ->  mm0         "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[byte]>
 ;* V46 tmp39        [V46    ] (  0,  0   )  struct (64) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;* V47 tmp40        [V47    ] (  0,  0   )  simd32  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;* V48 tmp41        [V48    ] (  0,  0   )    long  ->  zero-ref    "impAppendStmt"
 ;* V49 tmp42        [V49    ] (  0,  0   )  struct (64) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;* V50 tmp43        [V50    ] (  0,  0   )    long  ->  zero-ref    "impAppendStmt"
 ;* V51 tmp44        [V51    ] (  0,  0   )    long  ->  zero-ref    "Inline stloc first use temp"
 ;* V52 tmp45        [V52    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V53 tmp46        [V53    ] (  0,  0   )  simd32  ->  zero-ref    ld-addr-op "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[byte]>
 ;* V54 tmp47        [V54    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V55 tmp48        [V55    ] (  0,  0   )  struct (64) zero-ref    "Inline return value spill temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;* V56 tmp49        [V56    ] (  0,  0   )  struct (64) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;* V57 tmp50        [V57    ] (  0,  0   )  simd32  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;* V58 tmp51        [V58    ] (  0,  0   )  simd32  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;* V59 tmp52        [V59    ] (  0,  0   )  struct (64) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;* V60 tmp53        [V60    ] (  0,  0   )  struct (64) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;  V61 tmp54        [V61,T28] (  2,  2   )  simd32  ->  mm2         "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;  V62 tmp55        [V62,T29] (  2,  2   )  simd32  ->  mm0         "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;* V63 tmp56        [V63    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;* V64 tmp57        [V64    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V65 tmp58        [V65    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V66 tmp59        [V66    ] (  0,  0   )  simd32  ->  zero-ref    ld-addr-op "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[byte]>
 ;* V67 tmp60        [V67    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V68 tmp61        [V68    ] (  0,  0   )  struct (64) zero-ref    "Inline return value spill temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;* V69 tmp62        [V69    ] (  0,  0   )  struct (64) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;* V70 tmp63        [V70    ] (  0,  0   )  simd32  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;* V71 tmp64        [V71    ] (  0,  0   )  simd32  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;* V72 tmp65        [V72    ] (  0,  0   )  struct (64) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;* V73 tmp66        [V73    ] (  0,  0   )  struct (64) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[ushort],System.Runtime.Intrinsics.Vector256`1[ushort]]>
 ;  V74 tmp67        [V74,T19] (  2, 16   )  simd32  ->  mm2         "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;  V75 tmp68        [V75,T20] (  2, 16   )  simd32  ->  mm0         "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;* V76 tmp69        [V76    ] (  0,  0   )  simd32  ->  zero-ref    "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
 ;* V77 tmp70        [V77    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;  V78 tmp71        [V78,T06] (  9, 18.50)    long  ->   r8         "Inline stloc first use temp"
 ;  V79 tmp72        [V79,T11] (  3,  5.50)    long  ->  rcx         "Inline stloc first use temp"
 ;  V80 tmp73        [V80,T16] (  8, 18   )  simd16  ->  mm0         "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[byte]>
 ;* V81 tmp74        [V81    ] (  0,  0   )  struct (32) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;* V82 tmp75        [V82    ] (  0,  0   )  simd16  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;* V83 tmp76        [V83    ] (  0,  0   )    long  ->  zero-ref    "impAppendStmt"
 ;* V84 tmp77        [V84    ] (  0,  0   )  struct (32) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;* V85 tmp78        [V85    ] (  0,  0   )    long  ->  zero-ref    "impAppendStmt"
 ;* V86 tmp79        [V86    ] (  0,  0   )    long  ->  zero-ref    "Inline stloc first use temp"
 ;* V87 tmp80        [V87    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V88 tmp81        [V88    ] (  0,  0   )  simd16  ->  zero-ref    ld-addr-op "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[byte]>
 ;* V89 tmp82        [V89    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V90 tmp83        [V90    ] (  0,  0   )  struct (32) zero-ref    "Inline return value spill temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;* V91 tmp84        [V91    ] (  0,  0   )  struct (32) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;* V92 tmp85        [V92    ] (  0,  0   )  simd16  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;* V93 tmp86        [V93    ] (  0,  0   )  simd16  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;* V94 tmp87        [V94    ] (  0,  0   )  struct (32) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;* V95 tmp88        [V95    ] (  0,  0   )  struct (32) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;  V96 tmp89        [V96,T30] (  2,  2   )  simd16  ->  mm2         "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;  V97 tmp90        [V97,T31] (  2,  2   )  simd16  ->  mm0         "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;* V98 tmp91        [V98    ] (  0,  0   )  simd16  ->  zero-ref    "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;* V99 tmp92        [V99    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V100 tmp93       [V100    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V101 tmp94       [V101    ] (  0,  0   )  simd16  ->  zero-ref    ld-addr-op "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[byte]>
 ;* V102 tmp95       [V102    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V103 tmp96       [V103    ] (  0,  0   )  struct (32) zero-ref    "Inline return value spill temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;* V104 tmp97       [V104    ] (  0,  0   )  struct (32) zero-ref    "dup spill" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;* V105 tmp98       [V105    ] (  0,  0   )  simd16  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;* V106 tmp99       [V106    ] (  0,  0   )  simd16  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;* V107 tmp100      [V107    ] (  0,  0   )  struct (32) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;* V108 tmp101      [V108    ] (  0,  0   )  struct (32) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[ushort],System.Runtime.Intrinsics.Vector128`1[ushort]]>
 ;  V109 tmp102      [V109,T21] (  2, 16   )  simd16  ->  mm2         "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;  V110 tmp103      [V110,T22] (  2, 16   )  simd16  ->  mm0         "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;* V111 tmp104      [V111    ] (  0,  0   )  simd16  ->  zero-ref    "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
 ;* V112 tmp105      [V112    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V113 tmp106      [V113    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
 ;* V114 tmp107      [V114    ] (  0,  0   )  simd16  ->  zero-ref    "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ulong]>
 ;  V115 tmp108      [V115,T07] (  2, 16   )   byref  ->   r9         "Inlining Arg"
 ;* V116 tmp109      [V116    ] (  0,  0   )  simd64  ->  zero-ref    "field V11.Item1 (fldOffset=0x0)" P-INDEP
 ;* V117 tmp110      [V117    ] (  0,  0   )  simd64  ->  zero-ref    "field V11.Item2 (fldOffset=0x40)" P-INDEP
 ;* V118 tmp111      [V118    ] (  0,  0   )  simd64  ->  zero-ref    "field V14.Item1 (fldOffset=0x0)" P-INDEP
 ;* V119 tmp112      [V119    ] (  0,  0   )  simd64  ->  zero-ref    "field V14.Item2 (fldOffset=0x40)" P-INDEP
 ;* V120 tmp113      [V120    ] (  0,  0   )  simd64  ->  zero-ref    "field V20.Item1 (fldOffset=0x0)" P-INDEP
 ;* V121 tmp114      [V121    ] (  0,  0   )  simd64  ->  zero-ref    "field V20.Item2 (fldOffset=0x40)" P-INDEP
 ;* V122 tmp115      [V122    ] (  0,  0   )  simd64  ->  zero-ref    "field V21.Item1 (fldOffset=0x0)" P-INDEP
 ;* V123 tmp116      [V123    ] (  0,  0   )  simd64  ->  zero-ref    "field V21.Item2 (fldOffset=0x40)" P-INDEP
 ;* V124 tmp117      [V124    ] (  0,  0   )  simd64  ->  zero-ref    "field V24.Item1 (fldOffset=0x0)" P-INDEP
 ;* V125 tmp118      [V125    ] (  0,  0   )  simd64  ->  zero-ref    "field V24.Item2 (fldOffset=0x40)" P-INDEP
 ;* V126 tmp119      [V126    ] (  0,  0   )  simd64  ->  zero-ref    "field V25.Item1 (fldOffset=0x0)" P-INDEP
 ;* V127 tmp120      [V127    ] (  0,  0   )  simd64  ->  zero-ref    "field V25.Item2 (fldOffset=0x40)" P-INDEP
 ;* V128 tmp121      [V128    ] (  0,  0   )  simd64  ->  zero-ref    "field V33.Item1 (fldOffset=0x0)" P-INDEP
 ;* V129 tmp122      [V129    ] (  0,  0   )  simd64  ->  zero-ref    "field V33.Item2 (fldOffset=0x40)" P-INDEP
 ;* V130 tmp123      [V130    ] (  0,  0   )  simd64  ->  zero-ref    "field V34.Item1 (fldOffset=0x0)" P-INDEP
 ;* V131 tmp124      [V131    ] (  0,  0   )  simd64  ->  zero-ref    "field V34.Item2 (fldOffset=0x40)" P-INDEP
 ;* V132 tmp125      [V132    ] (  0,  0   )  simd64  ->  zero-ref    "field V37.Item1 (fldOffset=0x0)" P-INDEP
 ;* V133 tmp126      [V133    ] (  0,  0   )  simd64  ->  zero-ref    "field V37.Item2 (fldOffset=0x40)" P-INDEP
 ;* V134 tmp127      [V134    ] (  0,  0   )  simd64  ->  zero-ref    "field V38.Item1 (fldOffset=0x0)" P-INDEP
 ;* V135 tmp128      [V135    ] (  0,  0   )  simd64  ->  zero-ref    "field V38.Item2 (fldOffset=0x40)" P-INDEP
 ;* V136 tmp129      [V136    ] (  0,  0   )  simd32  ->  zero-ref    "field V46.Item1 (fldOffset=0x0)" P-INDEP
 ;* V137 tmp130      [V137    ] (  0,  0   )  simd32  ->  zero-ref    "field V46.Item2 (fldOffset=0x20)" P-INDEP
 ;* V138 tmp131      [V138    ] (  0,  0   )  simd32  ->  zero-ref    "field V49.Item1 (fldOffset=0x0)" P-INDEP
 ;* V139 tmp132      [V139    ] (  0,  0   )  simd32  ->  zero-ref    "field V49.Item2 (fldOffset=0x20)" P-INDEP
 ;* V140 tmp133      [V140    ] (  0,  0   )  simd32  ->  zero-ref    "field V55.Item1 (fldOffset=0x0)" P-INDEP
 ;* V141 tmp134      [V141    ] (  0,  0   )  simd32  ->  zero-ref    "field V55.Item2 (fldOffset=0x20)" P-INDEP
 ;* V142 tmp135      [V142    ] (  0,  0   )  simd32  ->  zero-ref    "field V56.Item1 (fldOffset=0x0)" P-INDEP
 ;* V143 tmp136      [V143    ] (  0,  0   )  simd32  ->  zero-ref    "field V56.Item2 (fldOffset=0x20)" P-INDEP
 ;* V144 tmp137      [V144    ] (  0,  0   )  simd32  ->  zero-ref    "field V59.Item1 (fldOffset=0x0)" P-INDEP
 ;* V145 tmp138      [V145    ] (  0,  0   )  simd32  ->  zero-ref    "field V59.Item2 (fldOffset=0x20)" P-INDEP
 ;* V146 tmp139      [V146    ] (  0,  0   )  simd32  ->  zero-ref    "field V60.Item1 (fldOffset=0x0)" P-INDEP
 ;* V147 tmp140      [V147    ] (  0,  0   )  simd32  ->  zero-ref    "field V60.Item2 (fldOffset=0x20)" P-INDEP
 ;* V148 tmp141      [V148    ] (  0,  0   )  simd32  ->  zero-ref    "field V68.Item1 (fldOffset=0x0)" P-INDEP
 ;* V149 tmp142      [V149    ] (  0,  0   )  simd32  ->  zero-ref    "field V68.Item2 (fldOffset=0x20)" P-INDEP
 ;* V150 tmp143      [V150    ] (  0,  0   )  simd32  ->  zero-ref    "field V69.Item1 (fldOffset=0x0)" P-INDEP
 ;* V151 tmp144      [V151    ] (  0,  0   )  simd32  ->  zero-ref    "field V69.Item2 (fldOffset=0x20)" P-INDEP
 ;* V152 tmp145      [V152    ] (  0,  0   )  simd32  ->  zero-ref    "field V72.Item1 (fldOffset=0x0)" P-INDEP
 ;* V153 tmp146      [V153    ] (  0,  0   )  simd32  ->  zero-ref    "field V72.Item2 (fldOffset=0x20)" P-INDEP
 ;* V154 tmp147      [V154    ] (  0,  0   )  simd32  ->  zero-ref    "field V73.Item1 (fldOffset=0x0)" P-INDEP
 ;* V155 tmp148      [V155    ] (  0,  0   )  simd32  ->  zero-ref    "field V73.Item2 (fldOffset=0x20)" P-INDEP
 ;* V156 tmp149      [V156    ] (  0,  0   )  simd16  ->  zero-ref    "field V81.Item1 (fldOffset=0x0)" P-INDEP
 ;* V157 tmp150      [V157    ] (  0,  0   )  simd16  ->  zero-ref    "field V81.Item2 (fldOffset=0x10)" P-INDEP
 ;* V158 tmp151      [V158    ] (  0,  0   )  simd16  ->  zero-ref    "field V84.Item1 (fldOffset=0x0)" P-INDEP
 ;* V159 tmp152      [V159    ] (  0,  0   )  simd16  ->  zero-ref    "field V84.Item2 (fldOffset=0x10)" P-INDEP
 ;* V160 tmp153      [V160    ] (  0,  0   )  simd16  ->  zero-ref    "field V90.Item1 (fldOffset=0x0)" P-INDEP
 ;* V161 tmp154      [V161    ] (  0,  0   )  simd16  ->  zero-ref    "field V90.Item2 (fldOffset=0x10)" P-INDEP
 ;* V162 tmp155      [V162    ] (  0,  0   )  simd16  ->  zero-ref    "field V91.Item1 (fldOffset=0x0)" P-INDEP
 ;* V163 tmp156      [V163    ] (  0,  0   )  simd16  ->  zero-ref    "field V91.Item2 (fldOffset=0x10)" P-INDEP
 ;* V164 tmp157      [V164    ] (  0,  0   )  simd16  ->  zero-ref    "field V94.Item1 (fldOffset=0x0)" P-INDEP
 ;* V165 tmp158      [V165    ] (  0,  0   )  simd16  ->  zero-ref    "field V94.Item2 (fldOffset=0x10)" P-INDEP
 ;* V166 tmp159      [V166    ] (  0,  0   )  simd16  ->  zero-ref    "field V95.Item1 (fldOffset=0x0)" P-INDEP
 ;* V167 tmp160      [V167    ] (  0,  0   )  simd16  ->  zero-ref    "field V95.Item2 (fldOffset=0x10)" P-INDEP
 ;* V168 tmp161      [V168    ] (  0,  0   )  simd16  ->  zero-ref    "field V103.Item1 (fldOffset=0x0)" P-INDEP
 ;* V169 tmp162      [V169    ] (  0,  0   )  simd16  ->  zero-ref    "field V103.Item2 (fldOffset=0x10)" P-INDEP
 ;* V170 tmp163      [V170    ] (  0,  0   )  simd16  ->  zero-ref    "field V104.Item1 (fldOffset=0x0)" P-INDEP
 ;* V171 tmp164      [V171    ] (  0,  0   )  simd16  ->  zero-ref    "field V104.Item2 (fldOffset=0x10)" P-INDEP
 ;* V172 tmp165      [V172    ] (  0,  0   )  simd16  ->  zero-ref    "field V107.Item1 (fldOffset=0x0)" P-INDEP
 ;* V173 tmp166      [V173    ] (  0,  0   )  simd16  ->  zero-ref    "field V107.Item2 (fldOffset=0x10)" P-INDEP
 ;* V174 tmp167      [V174    ] (  0,  0   )  simd16  ->  zero-ref    "field V108.Item1 (fldOffset=0x0)" P-INDEP
 ;* V175 tmp168      [V175    ] (  0,  0   )  simd16  ->  zero-ref    "field V108.Item2 (fldOffset=0x10)" P-INDEP
 ;  V176 cse0        [V176,T23] (  3,  5   )  simd64  ->  mm1         "CSE #01: moderate"
 ;  V177 cse1        [V177,T24] (  3,  5   )  simd32  ->  mm1         "CSE #02: moderate"
 ;  V178 cse2        [V178,T25] (  3,  5   )  simd16  ->  mm1         "CSE #03: moderate"
 ;
 ; Lcl frame size = 0
 
 G_M35753_IG01:
        push     rbp
        mov      rbp, rsp
 						;; size=4 bbWeight=1 PerfScore 1.25
 G_M35753_IG02:
        xor      eax, eax
        cmp      rdx, 16
        jb       G_M35753_IG15
 						;; size=12 bbWeight=1 PerfScore 1.50
 G_M35753_IG03:
        cmp      rdx, 64
        jae      G_M35753_IG11
        cmp      rdx, 32
        jae      G_M35753_IG07
        lea      rcx, [rdx-0x10]
        vmovups  xmm0, xmmword ptr [rdi]
        vbroadcastss xmm1, dword ptr [reloc @RWD00]
        vptest   xmm1, xmm0
        jne      G_M35753_IG15
        vpmovzxbw xmm2, xmm0
        vpsrldq  xmm0, xmm0, 8
        vpmovzxbw xmm0, xmm0
        vmovups  xmmword ptr [rsi], xmm2
        vmovups  xmmword ptr [rsi+0x10], xmm0
        lea      r8, [rsi+0x20]
        test     r8b, 1
        je       SHORT G_M35753_IG04
        mov      eax, 16
        jmp      SHORT G_M35753_IG05
        align    [1 bytes for IG06]
 						;; size=90 bbWeight=0.50 PerfScore 10.00
 G_M35753_IG04:
        and      r8, -16
        mov      rax, r8
        sub      rax, rsi
        shr      rax, 1
 						;; size=13 bbWeight=0.50 PerfScore 0.62
 G_M35753_IG05:
        cmp      rax, rcx
        ja       G_M35753_IG15
 						;; size=9 bbWeight=1 PerfScore 1.25
 G_M35753_IG06:
        vmovups  xmm0, xmmword ptr [rdi+rax]
        vptest   xmm1, xmm0
        jne      G_M35753_IG15
        vpmovzxbw xmm2, xmm0
        vpsrldq  xmm0, xmm0, 8
        vpmovzxbw xmm0, xmm0
        vmovups  xmmword ptr [r8], xmm2
        vmovups  xmmword ptr [r8+0x10], xmm0
        add      rax, 16
        add      r8, 32
        cmp      rax, rcx
        jbe      SHORT G_M35753_IG06
        jmp      G_M35753_IG15
 						;; size=60 bbWeight=4 PerfScore 59.00
 G_M35753_IG07:
        lea      rcx, [rdx-0x20]
        vmovups  ymm0, ymmword ptr [rdi]
        vbroadcastss ymm1, dword ptr [reloc @RWD00]
        vptest   ymm1, ymm0
        jne      G_M35753_IG15
-       vmovaps  xmm2, xmm0
-       vpmovzxbw ymm2, xmm2
+       vpmovzxbw ymm2, xmm0
        vextracti128 xmm0, ymm0
        vpmovzxbw ymm0, xmm0
        vmovups  ymmword ptr [rsi], ymm2
        vmovups  ymmword ptr [rsi+0x20], ymm0
        lea      r8, [rsi+0x40]
        test     r8b, 1
        je       SHORT G_M35753_IG08
        mov      eax, 32
        jmp      SHORT G_M35753_IG09
-       align    [0 bytes for IG10]
-						;; size=74 bbWeight=0.50 PerfScore 13.38
+       align    [8 bytes for IG10]
+						;; size=78 bbWeight=0.50 PerfScore 13.25
 G_M35753_IG08:
        and      r8, -32
        mov      rax, r8
        sub      rax, rsi
        shr      rax, 1
 						;; size=13 bbWeight=0.50 PerfScore 0.62
 G_M35753_IG09:
        cmp      rax, rcx
        ja       G_M35753_IG15
 						;; size=9 bbWeight=1 PerfScore 1.25
 G_M35753_IG10:
        vmovups  ymm0, ymmword ptr [rdi+rax]
        vptest   ymm1, ymm0
        jne      G_M35753_IG15
-       vmovaps  xmm2, xmm0
-       vpmovzxbw ymm2, xmm2
+       vpmovzxbw ymm2, xmm0
        vextracti128 xmm0, ymm0
        vpmovzxbw ymm0, xmm0
        vmovups  ymmword ptr [r8], ymm2
        vmovups  ymmword ptr [r8+0x20], ymm0
        add      rax, 32
        add      r8, 64
        cmp      rax, rcx
        jbe      SHORT G_M35753_IG10
        jmp      G_M35753_IG15
-						;; size=65 bbWeight=4 PerfScore 84.00
+						;; size=61 bbWeight=4 PerfScore 83.00
 G_M35753_IG11:
        lea      rcx, [rdx-0x40]
        vmovups  zmm0, zmmword ptr [rdi]
        vbroadcastss zmm1, dword ptr [reloc @RWD00]
        vptestmd k1, zmm0, zmm1
        kortestw k1, k1
+		  ;; NOP compensation instructions of 2 bytes.
        jne      G_M35753_IG15
-       vmovaps  ymm2, ymm0
-       vpmovzxbw zmm2, ymm2
+       vpmovzxbw zmm2, ymm0
        vextracti32x8 ymm0, zmm0, 1
        vpmovzxbw zmm0, ymm0
        vmovups  zmmword ptr [rsi], zmm2
        vmovups  zmmword ptr [rsi+0x40], zmm0
        lea      r8, [rsi+0x80]
        test     r8b, 1
        je       SHORT G_M35753_IG12
        mov      eax, 64
        jmp      SHORT G_M35753_IG13
        align    [0 bytes for IG14]
-						;; size=92 bbWeight=0.50 PerfScore 14.88
+						;; size=90 bbWeight=0.50 PerfScore 14.75
 G_M35753_IG12:
        and      r8, -64
        mov      rax, r8
        sub      rax, rsi
        shr      rax, 1
 						;; size=13 bbWeight=0.50 PerfScore 0.62
 G_M35753_IG13:
        cmp      rax, rcx
        ja       SHORT G_M35753_IG15
 						;; size=5 bbWeight=1 PerfScore 1.25
 G_M35753_IG14:
        vmovups  zmm0, zmmword ptr [rdi+rax]
        vptestmd k1, zmm0, zmm1
        kortestw k1, k1
+		  ;; NOP compensation instructions of 2 bytes.
        jne      SHORT G_M35753_IG15
-       vmovaps  ymm2, ymm0
-       vpmovzxbw zmm2, ymm2
+       vpmovzxbw zmm2, ymm0
        vextracti32x8 ymm0, zmm0, 1
        vpmovzxbw zmm0, ymm0
        vmovups  zmmword ptr [r8], zmm2
        vmovups  zmmword ptr [r8+0x40], zmm0
        add      rax, 64
        add      r8, 128
        cmp      rax, rcx
        jbe      SHORT G_M35753_IG14
-						;; size=71 bbWeight=4 PerfScore 84.00
+						;; size=69 bbWeight=4 PerfScore 83.00
 G_M35753_IG15:
        sub      rdx, rax
        cmp      rdx, 4
        jb       SHORT G_M35753_IG21
-						;; size=9 bbWeight=1 PerfScore 1.50
+		  ;; NOP compensation instructions of 4 bytes.
+						;; size=13 bbWeight=1 PerfScore 1.50
 G_M35753_IG16:
        lea      rcx, [rax+rdx-0x04]
        mov      r8d, dword ptr [rdi+rax]
        test     r8d, 0xD1FFAB1E
        jne      SHORT G_M35753_IG18
        align    [0 bytes for IG17]
 						;; size=18 bbWeight=0.50 PerfScore 2.12
 G_M35753_IG17:
        lea      r9, [rsi+2*rax]
        vmovd    xmm0, r8d
        vpmovzxbw xmm0, xmm0
        vmovq    qword ptr [r9], xmm0
        add      rax, 4
        cmp      rax, rcx
        ja       SHORT G_M35753_IG21
        mov      r8d, dword ptr [rdi+rax]
        test     r8d, 0xD1FFAB1E
        je       SHORT G_M35753_IG17
 						;; size=41 bbWeight=4 PerfScore 45.00
 G_M35753_IG18:
        movzx    rcx, r8b
        test     cl, 128
        jne      SHORT G_M35753_IG20
-       align    [0 bytes for IG19]
-						;; size=9 bbWeight=0.50 PerfScore 0.75
+       align    [1 bytes for IG19]
+						;; size=10 bbWeight=0.50 PerfScore 0.88
 G_M35753_IG19:
        movzx    rcx, r8b
        mov      word  ptr [rsi+2*rax], cx
        inc      rax
        shr      r8d, 8
        movzx    rcx, r8b
        test     cl, 128
        je       SHORT G_M35753_IG19
 						;; size=24 bbWeight=4 PerfScore 14.00
 G_M35753_IG20:
        vzeroupper 
        pop      rbp
        ret      
 						;; size=5 bbWeight=1 PerfScore 2.50
 G_M35753_IG21:
        test     dl, 2
        je       SHORT G_M35753_IG22
        movzx    r8, word  ptr [rdi+rax]
        test     r8d, 0xD1FFAB1E
        jne      SHORT G_M35753_IG18
        movzx    rcx, r8b
        mov      word  ptr [rsi+2*rax], cx
        shr      r8d, 8
        mov      word  ptr [rsi+2*rax+0x02], r8w
        add      rax, 2
 						;; size=41 bbWeight=0.50 PerfScore 3.75
 G_M35753_IG22:
        test     dl, 1
        je       SHORT G_M35753_IG20
        movzx    r8, byte  ptr [rdi+rax]
        test     r8b, 128
        jne      SHORT G_M35753_IG20
        mov      word  ptr [rsi+2*rax], r8w
        inc      rax
        jmp      SHORT G_M35753_IG20
 						;; size=26 bbWeight=0.50 PerfScore 3.88
 RWD00  	dd	80808080h		; -1.1801e-38
 
 
-; Total bytes of code 703, prolog size 4, PerfScore 347.12, instruction count 169, allocated bytes for code 711 (MethodHash=7f1b7456) for method System.Text.Ascii:WidenAsciiToUtf16(ptr,ptr,nuint):nuint (FullOpts)
+; Total bytes of code 704, prolog size 4, PerfScore 345.00, instruction count 165, allocated bytes for code 704 (MethodHash=7f1b7456) for method System.Text.Ascii:WidenAsciiToUtf16(ptr,ptr,nuint):nuint (FullOpts)
 ; ============================================================

[MihuBot]

Top method improvements

-53 (-7.37 % of base) - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]]

 ; Assembly listing for method System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]] (FullOpts)
 ; Emitting BLENDED_CODE for x64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rsp based frame
 ; partially interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 1 single block inlinees; 0 inlinees without PGO data
 ; Final local variable assignments
 ;
 ;  V00 RetBuf       [V00,T00] (  5,  5   )    long  ->  rdi         single-def
 ;  V01 arg0         [V01,T16] (  3,  3   )  simd64  ->  mm1         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;  V02 arg1         [V02,T13] (  4,  4   )  simd64  ->  mm0         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;  V03 loc0         [V03,T14] (  4,  4   )  simd64  ->  mm2         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;# V04 OutArgs      [V04    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
 ;  V05 tmp1         [V05,T01] (  3,  6   )  simd32  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V06 tmp2         [V06,T02] (  3,  6   )  simd32  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V06 tmp2         [V06,T02] (  3,  6   )  simd32  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V07 tmp3         [V07,T03] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V08 tmp4         [V08,T04] (  3,  6   )  simd64  ->  mm6         "fgMakeTemp is creating a new local variable"
+;  V08 tmp4         [V08,T04] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;  V09 tmp5         [V09,T05] (  3,  6   )  simd64  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V10 tmp6         [V10,T06] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V10 tmp6         [V10,T06] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V11 tmp7         [V11,T07] (  3,  6   )  simd32  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V12 tmp8         [V12,T08] (  3,  6   )  simd32  ->  mm6         "fgMakeTemp is creating a new local variable"
+;  V12 tmp8         [V12,T08] (  3,  6   )  simd32  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;  V13 tmp9         [V13,T09] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
-;  V14 tmp10        [V14,T10] (  3,  6   )  simd64  ->  mm7         "fgMakeTemp is creating a new local variable"
+;  V14 tmp10        [V14,T10] (  3,  6   )  simd64  ->  mm6         "fgMakeTemp is creating a new local variable"
 ;  V15 tmp11        [V15,T11] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V16 tmp12        [V16,T12] (  3,  6   )  simd64  ->  mm6         "fgMakeTemp is creating a new local variable"
+;  V16 tmp12        [V16,T12] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;* V17 tmp13        [V17    ] (  0,  0   )  struct (128) zero-ref    ld-addr-op "NewObj constructor temp" <System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]]>
 ;  V18 tmp14        [V18,T15] (  2,  4   )  simd64  ->  mm0         "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;* V19 tmp15        [V19    ] (  0,  0   )  simd64  ->  zero-ref    single-def "field V17.Item1 (fldOffset=0x0)" P-INDEP
 ;* V20 tmp16        [V20    ] (  0,  0   )  simd64  ->  zero-ref    single-def "field V17.Item2 (fldOffset=0x40)" P-INDEP
 ;
 ; Lcl frame size = 8
 
 G_M58530_IG01:
        push     rax
        vmovups  zmm1, zmmword ptr [rsp+0x10]
        vmovups  zmm0, zmmword ptr [rsp+0x50]
 						;; size=23 bbWeight=1 PerfScore 7.00
 G_M58530_IG02:
        vmovaps  ymm2, ymm1
-       vmovaps  xmm3, xmm2
-       vpmovzxbd zmm3, xmm3
-       vmovaps  ymm4, ymm3
-       vmovaps  ymm5, ymm0
-       vmovaps  xmm6, xmm5
-       vpmovzxbd zmm6, xmm6
-       vmovaps  ymm7, ymm6
-       vxorpd   ymm8, ymm8, ymm8
-       vpcmpeqd ymm8, ymm8, ymm7
-       vptest   ymm8, ymm8
+       vpmovzxbd zmm3, xmm2
+       vmovaps  ymm4, ymm0
+       vpmovzxbd zmm5, xmm4
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
        jne      G_M58530_IG05
-       vcvtudq2pd zmm8, ymm4
-       vcvtudq2pd zmm9, ymm7
-       vdivpd   zmm4, zmm8, zmm9
-       vcvttpd2udq ymm4, zmm4
+       vcvtudq2pd zmm6, ymm3
+       vcvtudq2pd zmm7, ymm5
+       vdivpd   zmm8, zmm6, zmm7
+       vcvttpd2udq ymm8, zmm8
        vextracti32x8 ymm3, zmm3, 1
-       vextracti32x8 ymm6, zmm6, 1
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
+       vextracti32x8 ymm5, zmm5, 1
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
        jne      G_M58530_IG05
-       vcvtudq2pd zmm7, ymm3
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm3, zmm7, zmm8
+       vcvtudq2pd zmm6, ymm3
+       vcvtudq2pd zmm7, ymm5
+       vdivpd   zmm3, zmm6, zmm7
        vcvttpd2udq ymm3, zmm3
-       vinserti32x8 zmm3, zmm4, ymm3, 1
+       vinserti32x8 zmm3, zmm8, ymm3, 1
        vpmovdb  xmm3, zmm3
        vextracti128 xmm2, ymm2
        vpmovzxbd zmm2, xmm2
-       vmovaps  ymm4, ymm2
-       vextracti128 xmm5, ymm5
-       vpmovzxbd zmm5, xmm5
-       vmovaps  ymm6, ymm5
+       vextracti128 xmm4, ymm4
+       vpmovzxbd zmm4, xmm4
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M58530_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm7, zmm5, zmm6
+       vcvttpd2udq ymm7, zmm7
+       vextracti32x8 ymm2, zmm2, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M58530_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2udq ymm2, zmm2
+       vinserti32x8 zmm2, zmm7, ymm2, 1
+       vpmovdb  xmm2, zmm2
+       vinserti128 ymm2, ymm3, xmm2
+       vextracti32x8 ymm3, zmm1, 1
+       vpmovzxbd zmm4, xmm3
+       vextracti32x8 ymm5, zmm0, 1
+       vpmovzxbd zmm6, xmm5
        vxorpd   ymm7, ymm7, ymm7
        vpcmpeqd ymm7, ymm7, ymm6
        vptest   ymm7, ymm7
        jne      G_M58530_IG05
        vcvtudq2pd zmm7, ymm4
        vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm4, zmm7, zmm8
-       vcvttpd2udq ymm4, zmm4
-       vextracti32x8 ymm2, zmm2, 1
-       vextracti32x8 ymm5, zmm5, 1
-       vxorpd   ymm6, ymm6, ymm6
-       vpcmpeqd ymm6, ymm6, ymm5
-       vptest   ymm6, ymm6
-       jne      G_M58530_IG05
-       vcvtudq2pd zmm6, ymm2
-       vcvtudq2pd zmm7, ymm5
-       vdivpd   zmm2, zmm6, zmm7
-       vcvttpd2udq ymm2, zmm2
-       vinserti32x8 zmm2, zmm4, ymm2, 1
-       vpmovdb  xmm2, zmm2
-       vinserti128 ymm2, ymm3, xmm2
-       vextracti32x8 ymm3, zmm1, 1
-       vmovaps  xmm4, xmm3
-       vpmovzxbd zmm4, xmm4
-       vmovaps  ymm5, ymm4
-       vextracti32x8 ymm6, zmm0, 1
-       vmovaps  xmm7, xmm6
-       vpmovzxbd zmm7, xmm7
-       vmovaps  ymm8, ymm7
-       vxorpd   ymm9, ymm9, ymm9
-       vpcmpeqd ymm9, ymm9, ymm8
-       vptest   ymm9, ymm9
-       jne      G_M58530_IG05
-						;; size=364 bbWeight=1 PerfScore 237.17
-G_M58530_IG03:
-       vcvtudq2pd zmm9, ymm5
-       vcvtudq2pd zmm10, ymm8
-       vdivpd   zmm5, zmm9, zmm10
-       vcvttpd2udq ymm5, zmm5
+       vdivpd   zmm9, zmm7, zmm8
+       vcvttpd2udq ymm9, zmm9
        vextracti32x8 ymm4, zmm4, 1
-       vextracti32x8 ymm7, zmm7, 1
-       vxorpd   ymm8, ymm8, ymm8
-       vpcmpeqd ymm8, ymm8, ymm7
-       vptest   ymm8, ymm8
-       jne      G_M58530_IG05
-       vcvtudq2pd zmm8, ymm4
-       vcvtudq2pd zmm9, ymm7
-       vdivpd   zmm4, zmm8, zmm9
-       vcvttpd2udq ymm4, zmm4
-       vinserti32x8 zmm4, zmm5, ymm4, 1
-       vpmovdb  xmm4, zmm4
-       vextracti128 xmm3, ymm3
-       vpmovzxbd zmm3, xmm3
-       vmovaps  ymm5, ymm3
-       vextracti128 xmm6, ymm6
-       vpmovzxbd zmm6, xmm6
-       vmovaps  ymm7, ymm6
-       vxorpd   ymm8, ymm8, ymm8
-       vpcmpeqd ymm8, ymm8, ymm7
-       vptest   ymm8, ymm8
-       jne      G_M58530_IG05
-       vcvtudq2pd zmm8, ymm5
-       vcvtudq2pd zmm9, ymm7
-       vdivpd   zmm5, zmm8, zmm9
-       vcvttpd2udq ymm5, zmm5
-       vextracti32x8 ymm3, zmm3, 1
        vextracti32x8 ymm6, zmm6, 1
        vxorpd   ymm7, ymm7, ymm7
        vpcmpeqd ymm7, ymm7, ymm6
        vptest   ymm7, ymm7
-       jne      SHORT G_M58530_IG05
-       vcvtudq2pd zmm7, ymm3
+						;; size=372 bbWeight=1 PerfScore 284.50
+G_M58530_IG03:
+       jne      G_M58530_IG05
+       vcvtudq2pd zmm7, ymm4
        vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm3, zmm7, zmm8
+       vdivpd   zmm4, zmm7, zmm8
+       vcvttpd2udq ymm4, zmm4
+       vinserti32x8 zmm4, zmm9, ymm4, 1
+       vpmovdb  xmm4, zmm4
+       vextracti128 xmm3, ymm3
+       vpmovzxbd zmm3, xmm3
+       vextracti128 xmm5, ymm5
+       vpmovzxbd zmm5, xmm5
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      G_M58530_IG05
+       vcvtudq2pd zmm6, ymm3
+       vcvtudq2pd zmm7, ymm5
+       vdivpd   zmm8, zmm6, zmm7
+       vcvttpd2udq ymm8, zmm8
+       vextracti32x8 ymm3, zmm3, 1
+       vextracti32x8 ymm5, zmm5, 1
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      SHORT G_M58530_IG05
+       vcvtudq2pd zmm6, ymm3
+       vcvtudq2pd zmm7, ymm5
+       vdivpd   zmm3, zmm6, zmm7
        vcvttpd2udq ymm3, zmm3
-       vinserti32x8 zmm3, zmm5, ymm3, 1
+       vinserti32x8 zmm3, zmm8, ymm3, 1
        vpmovdb  xmm3, zmm3
        vinserti128 ymm3, ymm4, xmm3
        vinserti32x8 zmm2, zmm2, ymm3, 1
        vpmullw  zmm3, zmm2, zmm0
        vpsrlw   zmm4, zmm2, 8
        vpandd   zmm0, zmm0, dword ptr [reloc @RWD32] {1to16}
        vpmullw  zmm0, zmm0, zmm4
        vpternlogd zmm0, zmm3, dword ptr [reloc @RWD36] {1to16}, -8
        vpsubb   zmm0, zmm1, zmm0
        vmovups  zmmword ptr [rdi], zmm2
        vmovups  zmmword ptr [rdi+0x40], zmm0
        mov      rax, rdi
-						;; size=312 bbWeight=1 PerfScore 234.58
+						;; size=251 bbWeight=1 PerfScore 184.25
 G_M58530_IG04:
        vzeroupper 
        add      rsp, 8
        ret      
 						;; size=8 bbWeight=1 PerfScore 2.25
 G_M58530_IG05:
        call     CORINFO_HELP_THROWDIVZERO
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 G_M58530_IG06:
        call     CORINFO_HELP_OVERFLOW
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
 RWD32  	dd	FF00FF00h
 RWD36  	dd	00FF00FFh
 
 
-; Total bytes of code 719, prolog size 1, PerfScore 481.00, instruction count 130, allocated bytes for code 719 (MethodHash=3f721b5d) for method System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]] (FullOpts)
+; Total bytes of code 666, prolog size 1, PerfScore 478.00, instruction count 118, allocated bytes for code 666 (MethodHash=3f721b5d) for method System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]] (FullOpts)
 ; ============================================================

-53 (-7.46 % of base) - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte]

 ; Assembly listing for method System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
 ; Emitting BLENDED_CODE for x64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; partially interruptible
 ; No PGO data
 ; Final local variable assignments
 ;
 ;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
 ;  V01 arg0         [V01,T15] (  3,  3   )  simd64  ->  mm1         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;  V02 arg1         [V02,T14] (  4,  4   )  simd64  ->  mm0         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
 ;  V04 tmp1         [V04,T01] (  3,  6   )  simd32  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V05 tmp2         [V05,T02] (  3,  6   )  simd32  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V05 tmp2         [V05,T02] (  3,  6   )  simd32  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V06 tmp3         [V06,T03] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V07 tmp4         [V07,T04] (  3,  6   )  simd64  ->  mm6         "fgMakeTemp is creating a new local variable"
+;  V07 tmp4         [V07,T04] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;  V08 tmp5         [V08,T05] (  3,  6   )  simd64  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V09 tmp6         [V09,T06] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V09 tmp6         [V09,T06] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V10 tmp7         [V10,T07] (  3,  6   )  simd32  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V11 tmp8         [V11,T08] (  3,  6   )  simd32  ->  mm6         "fgMakeTemp is creating a new local variable"
+;  V11 tmp8         [V11,T08] (  3,  6   )  simd32  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;  V12 tmp9         [V12,T09] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
-;  V13 tmp10        [V13,T10] (  3,  6   )  simd64  ->  mm7         "fgMakeTemp is creating a new local variable"
+;  V13 tmp10        [V13,T10] (  3,  6   )  simd64  ->  mm6         "fgMakeTemp is creating a new local variable"
 ;  V14 tmp11        [V14,T11] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V15 tmp12        [V15,T12] (  3,  6   )  simd64  ->  mm6         "fgMakeTemp is creating a new local variable"
+;  V15 tmp12        [V15,T12] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;  V16 tmp13        [V16,T13] (  3,  6   )  simd64  ->  mm2         "fgMakeTemp is creating a new local variable"
 ;
 ; Lcl frame size = 0
 
 G_M6629_IG01:
        push     rbp
        mov      rbp, rsp
        vmovups  zmm1, zmmword ptr [rbp+0x10]
        vmovups  zmm0, zmmword ptr [rbp+0x50]
 						;; size=24 bbWeight=1 PerfScore 7.25
 G_M6629_IG02:
        vmovaps  ymm2, ymm1
-       vmovaps  xmm3, xmm2
-       vpmovzxbd zmm3, xmm3
-       vmovaps  ymm4, ymm3
-       vmovaps  ymm5, ymm0
-       vmovaps  xmm6, xmm5
-       vpmovzxbd zmm6, xmm6
-       vmovaps  ymm7, ymm6
-       vxorpd   ymm8, ymm8, ymm8
-       vpcmpeqd ymm8, ymm8, ymm7
-       vptest   ymm8, ymm8
+       vpmovzxbd zmm3, xmm2
+       vmovaps  ymm4, ymm0
+       vpmovzxbd zmm5, xmm4
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
        jne      G_M6629_IG05
-       vcvtudq2pd zmm8, ymm4
-       vcvtudq2pd zmm9, ymm7
-       vdivpd   zmm4, zmm8, zmm9
-       vcvttpd2udq ymm4, zmm4
+       vcvtudq2pd zmm6, ymm3
+       vcvtudq2pd zmm7, ymm5
+       vdivpd   zmm8, zmm6, zmm7
+       vcvttpd2udq ymm8, zmm8
        vextracti32x8 ymm3, zmm3, 1
-       vextracti32x8 ymm6, zmm6, 1
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
+       vextracti32x8 ymm5, zmm5, 1
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
        jne      G_M6629_IG05
-       vcvtudq2pd zmm7, ymm3
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm3, zmm7, zmm8
+       vcvtudq2pd zmm6, ymm3
+       vcvtudq2pd zmm7, ymm5
+       vdivpd   zmm3, zmm6, zmm7
        vcvttpd2udq ymm3, zmm3
-       vinserti32x8 zmm3, zmm4, ymm3, 1
+       vinserti32x8 zmm3, zmm8, ymm3, 1
        vpmovdb  xmm3, zmm3
        vextracti128 xmm2, ymm2
        vpmovzxbd zmm2, xmm2
-       vmovaps  ymm4, ymm2
-       vextracti128 xmm5, ymm5
-       vpmovzxbd zmm5, xmm5
-       vmovaps  ymm6, ymm5
+       vextracti128 xmm4, ymm4
+       vpmovzxbd zmm4, xmm4
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M6629_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm7, zmm5, zmm6
+       vcvttpd2udq ymm7, zmm7
+       vextracti32x8 ymm2, zmm2, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M6629_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2udq ymm2, zmm2
+       vinserti32x8 zmm2, zmm7, ymm2, 1
+       vpmovdb  xmm2, zmm2
+       vinserti128 ymm2, ymm3, xmm2
+       vextracti32x8 ymm3, zmm1, 1
+       vpmovzxbd zmm4, xmm3
+       vextracti32x8 ymm5, zmm0, 1
+       vpmovzxbd zmm6, xmm5
        vxorpd   ymm7, ymm7, ymm7
        vpcmpeqd ymm7, ymm7, ymm6
        vptest   ymm7, ymm7
        jne      G_M6629_IG05
        vcvtudq2pd zmm7, ymm4
        vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm4, zmm7, zmm8
-       vcvttpd2udq ymm4, zmm4
-       vextracti32x8 ymm2, zmm2, 1
-       vextracti32x8 ymm5, zmm5, 1
-       vxorpd   ymm6, ymm6, ymm6
-       vpcmpeqd ymm6, ymm6, ymm5
-       vptest   ymm6, ymm6
-       jne      G_M6629_IG05
-       vcvtudq2pd zmm6, ymm2
-       vcvtudq2pd zmm7, ymm5
-       vdivpd   zmm2, zmm6, zmm7
-       vcvttpd2udq ymm2, zmm2
-       vinserti32x8 zmm2, zmm4, ymm2, 1
-       vpmovdb  xmm2, zmm2
-       vinserti128 ymm2, ymm3, xmm2
-       vextracti32x8 ymm3, zmm1, 1
-       vmovaps  xmm4, xmm3
-       vpmovzxbd zmm4, xmm4
-       vmovaps  ymm5, ymm4
-       vextracti32x8 ymm6, zmm0, 1
-       vmovaps  xmm7, xmm6
-       vpmovzxbd zmm7, xmm7
-       vmovaps  ymm8, ymm7
-       vxorpd   ymm9, ymm9, ymm9
-       vpcmpeqd ymm9, ymm9, ymm8
-       vptest   ymm9, ymm9
-       jne      G_M6629_IG05
-						;; size=364 bbWeight=1 PerfScore 237.17
-G_M6629_IG03:
-       vcvtudq2pd zmm9, ymm5
-       vcvtudq2pd zmm10, ymm8
-       vdivpd   zmm5, zmm9, zmm10
-       vcvttpd2udq ymm5, zmm5
+       vdivpd   zmm9, zmm7, zmm8
+       vcvttpd2udq ymm9, zmm9
        vextracti32x8 ymm4, zmm4, 1
-       vextracti32x8 ymm7, zmm7, 1
-       vxorpd   ymm8, ymm8, ymm8
-       vpcmpeqd ymm8, ymm8, ymm7
-       vptest   ymm8, ymm8
-       jne      G_M6629_IG05
-       vcvtudq2pd zmm8, ymm4
-       vcvtudq2pd zmm9, ymm7
-       vdivpd   zmm4, zmm8, zmm9
-       vcvttpd2udq ymm4, zmm4
-       vinserti32x8 zmm4, zmm5, ymm4, 1
-       vpmovdb  xmm4, zmm4
-       vextracti128 xmm3, ymm3
-       vpmovzxbd zmm3, xmm3
-       vmovaps  ymm5, ymm3
-       vextracti128 xmm6, ymm6
-       vpmovzxbd zmm6, xmm6
-       vmovaps  ymm7, ymm6
-       vxorpd   ymm8, ymm8, ymm8
-       vpcmpeqd ymm8, ymm8, ymm7
-       vptest   ymm8, ymm8
-       jne      G_M6629_IG05
-       vcvtudq2pd zmm8, ymm5
-       vcvtudq2pd zmm9, ymm7
-       vdivpd   zmm5, zmm8, zmm9
-       vcvttpd2udq ymm5, zmm5
-       vextracti32x8 ymm3, zmm3, 1
        vextracti32x8 ymm6, zmm6, 1
        vxorpd   ymm7, ymm7, ymm7
        vpcmpeqd ymm7, ymm7, ymm6
        vptest   ymm7, ymm7
-       jne      SHORT G_M6629_IG05
-       vcvtudq2pd zmm7, ymm3
+						;; size=372 bbWeight=1 PerfScore 284.50
+G_M6629_IG03:
+       jne      G_M6629_IG05
+       vcvtudq2pd zmm7, ymm4
        vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm3, zmm7, zmm8
+       vdivpd   zmm4, zmm7, zmm8
+       vcvttpd2udq ymm4, zmm4
+       vinserti32x8 zmm4, zmm9, ymm4, 1
+       vpmovdb  xmm4, zmm4
+       vextracti128 xmm3, ymm3
+       vpmovzxbd zmm3, xmm3
+       vextracti128 xmm5, ymm5
+       vpmovzxbd zmm5, xmm5
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      G_M6629_IG05
+       vcvtudq2pd zmm6, ymm3
+       vcvtudq2pd zmm7, ymm5
+       vdivpd   zmm8, zmm6, zmm7
+       vcvttpd2udq ymm8, zmm8
+       vextracti32x8 ymm3, zmm3, 1
+       vextracti32x8 ymm5, zmm5, 1
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      SHORT G_M6629_IG05
+       vcvtudq2pd zmm6, ymm3
+       vcvtudq2pd zmm7, ymm5
+       vdivpd   zmm3, zmm6, zmm7
        vcvttpd2udq ymm3, zmm3
-       vinserti32x8 zmm3, zmm5, ymm3, 1
+       vinserti32x8 zmm3, zmm8, ymm3, 1
        vpmovdb  xmm3, zmm3
        vinserti128 ymm3, ymm4, xmm3
        vinserti32x8 zmm2, zmm2, ymm3, 1
        vpmullw  zmm3, zmm2, zmm0
        vpsrlw   zmm2, zmm2, 8
        vpandd   zmm0, zmm0, dword ptr [reloc @RWD32] {1to16}
        vpmullw  zmm0, zmm0, zmm2
        vpternlogd zmm0, zmm3, dword ptr [reloc @RWD36] {1to16}, -8
        vpsubb   zmm0, zmm1, zmm0
        vmovups  zmmword ptr [rdi], zmm0
        mov      rax, rdi
-						;; size=305 bbWeight=1 PerfScore 232.58
+						;; size=244 bbWeight=1 PerfScore 182.25
 G_M6629_IG04:
        vzeroupper 
        pop      rbp
        ret      
 						;; size=5 bbWeight=1 PerfScore 2.50
 G_M6629_IG05:
        call     CORINFO_HELP_THROWDIVZERO
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 G_M6629_IG06:
        call     CORINFO_HELP_OVERFLOW
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
 RWD32  	dd	FF00FF00h
 RWD36  	dd	00FF00FFh
 
 
-; Total bytes of code 710, prolog size 4, PerfScore 479.50, instruction count 130, allocated bytes for code 710 (MethodHash=c340e61a) for method System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
+; Total bytes of code 657, prolog size 4, PerfScore 476.50, instruction count 118, allocated bytes for code 657 (MethodHash=c340e61a) for method System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
 ; ============================================================

-49 (-7.45 % of base) - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte]

 ; Assembly listing for method System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
 ; Emitting BLENDED_CODE for x64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rsp based frame
 ; partially interruptible
 ; No PGO data
 ; Final local variable assignments
 ;
 ;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
 ;  V01 arg0         [V01,T13] (  2,  2   )  simd64  ->  mm0         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;  V02 arg1         [V02,T14] (  2,  2   )  simd64  ->  mm1         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
 ;  V04 tmp1         [V04,T01] (  3,  6   )  simd32  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V05 tmp2         [V05,T02] (  3,  6   )  simd32  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V05 tmp2         [V05,T02] (  3,  6   )  simd32  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V06 tmp3         [V06,T03] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V07 tmp4         [V07,T04] (  3,  6   )  simd64  ->  mm6         "fgMakeTemp is creating a new local variable"
+;  V07 tmp4         [V07,T04] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;  V08 tmp5         [V08,T05] (  3,  6   )  simd64  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V09 tmp6         [V09,T06] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V09 tmp6         [V09,T06] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V10 tmp7         [V10,T07] (  3,  6   )  simd32  ->  mm0         "fgMakeTemp is creating a new local variable"
 ;  V11 tmp8         [V11,T08] (  3,  6   )  simd32  ->  mm1         "fgMakeTemp is creating a new local variable"
 ;  V12 tmp9         [V12,T09] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V13 tmp10        [V13,T10] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V13 tmp10        [V13,T10] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V14 tmp11        [V14,T11] (  3,  6   )  simd64  ->  mm0         "fgMakeTemp is creating a new local variable"
 ;  V15 tmp12        [V15,T12] (  3,  6   )  simd64  ->  mm1         "fgMakeTemp is creating a new local variable"
 ;
 ; Lcl frame size = 8
 
 G_M27641_IG01:
        push     rax
        vmovups  zmm0, zmmword ptr [rsp+0x10]
        vmovups  zmm1, zmmword ptr [rsp+0x50]
 						;; size=23 bbWeight=1 PerfScore 7.00
 G_M27641_IG02:
        vmovaps  ymm2, ymm0
-       vmovaps  xmm3, xmm2
-       vpmovzxbd zmm3, xmm3
-       vmovaps  ymm4, ymm3
-       vmovaps  ymm5, ymm1
-       vmovaps  xmm6, xmm5
-       vpmovzxbd zmm6, xmm6
-       vmovaps  ymm7, ymm6
-       vxorpd   ymm8, ymm8, ymm8
-       vpcmpeqd ymm8, ymm8, ymm7
-       vptest   ymm8, ymm8
-       jne      G_M27641_IG05
-       vcvtudq2pd zmm8, ymm4
-       vcvtudq2pd zmm9, ymm7
-       vdivpd   zmm4, zmm8, zmm9
-       vcvttpd2udq ymm4, zmm4
-       vextracti32x8 ymm3, zmm3, 1
-       vextracti32x8 ymm6, zmm6, 1
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
-       jne      G_M27641_IG05
-       vcvtudq2pd zmm7, ymm3
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm3, zmm7, zmm8
-       vcvttpd2udq ymm3, zmm3
-       vinserti32x8 zmm3, zmm4, ymm3, 1
-       vpmovdb  xmm3, zmm3
-       vextracti128 xmm2, ymm2
-       vpmovzxbd zmm2, xmm2
-       vmovaps  ymm4, ymm2
-       vextracti128 xmm5, ymm5
-       vpmovzxbd zmm5, xmm5
-       vmovaps  ymm6, ymm5
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
-       jne      G_M27641_IG05
-       vcvtudq2pd zmm7, ymm4
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm4, zmm7, zmm8
-       vcvttpd2udq ymm4, zmm4
-       vextracti32x8 ymm2, zmm2, 1
-       vextracti32x8 ymm5, zmm5, 1
+       vpmovzxbd zmm3, xmm2
+       vmovaps  ymm4, ymm1
+       vpmovzxbd zmm5, xmm4
        vxorpd   ymm6, ymm6, ymm6
        vpcmpeqd ymm6, ymm6, ymm5
        vptest   ymm6, ymm6
        jne      G_M27641_IG05
-       vcvtudq2pd zmm6, ymm2
+       vcvtudq2pd zmm6, ymm3
        vcvtudq2pd zmm7, ymm5
-       vdivpd   zmm2, zmm6, zmm7
-       vcvttpd2udq ymm2, zmm2
-       vinserti32x8 zmm2, zmm4, ymm2, 1
-       vpmovdb  xmm2, zmm2
-       vinserti128 ymm2, ymm3, xmm2
-       vextracti32x8 ymm0, zmm0, 1
-       vmovaps  xmm3, xmm0
-       vpmovzxbd zmm3, xmm3
-       vmovaps  ymm4, ymm3
-       vextracti32x8 ymm1, zmm1, 1
-       vmovaps  xmm5, xmm1
-       vpmovzxbd zmm5, xmm5
-       vmovaps  ymm6, ymm5
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
-       jne      G_M27641_IG05
-						;; size=362 bbWeight=1 PerfScore 237.17
-G_M27641_IG03:
-       vcvtudq2pd zmm7, ymm4
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm4, zmm7, zmm8
-       vcvttpd2udq ymm4, zmm4
+       vdivpd   zmm8, zmm6, zmm7
+       vcvttpd2udq ymm8, zmm8
        vextracti32x8 ymm3, zmm3, 1
        vextracti32x8 ymm5, zmm5, 1
        vxorpd   ymm6, ymm6, ymm6
        vpcmpeqd ymm6, ymm6, ymm5
        vptest   ymm6, ymm6
        jne      G_M27641_IG05
        vcvtudq2pd zmm6, ymm3
        vcvtudq2pd zmm7, ymm5
        vdivpd   zmm3, zmm6, zmm7
        vcvttpd2udq ymm3, zmm3
-       vinserti32x8 zmm3, zmm4, ymm3, 1
+       vinserti32x8 zmm3, zmm8, ymm3, 1
+       vpmovdb  xmm3, zmm3
+       vextracti128 xmm2, ymm2
+       vpmovzxbd zmm2, xmm2
+       vextracti128 xmm4, ymm4
+       vpmovzxbd zmm4, xmm4
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M27641_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm7, zmm5, zmm6
+       vcvttpd2udq ymm7, zmm7
+       vextracti32x8 ymm2, zmm2, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M27641_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2udq ymm2, zmm2
+       vinserti32x8 zmm2, zmm7, ymm2, 1
+       vpmovdb  xmm2, zmm2
+       vinserti128 ymm2, ymm3, xmm2
+       vextracti32x8 ymm0, zmm0, 1
+       vpmovzxbd zmm3, xmm0
+       vextracti32x8 ymm1, zmm1, 1
+       vpmovzxbd zmm4, xmm1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M27641_IG05
+       vcvtudq2pd zmm5, ymm3
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm7, zmm5, zmm6
+       vcvttpd2udq ymm7, zmm7
+       vextracti32x8 ymm3, zmm3, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+						;; size=372 bbWeight=1 PerfScore 284.50
+G_M27641_IG03:
+       jne      G_M27641_IG05
+       vcvtudq2pd zmm5, ymm3
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm3, zmm5, zmm6
+       vcvttpd2udq ymm3, zmm3
+       vinserti32x8 zmm3, zmm7, ymm3, 1
        vpmovdb  xmm3, zmm3
        vextracti128 xmm0, ymm0
        vpmovzxbd zmm0, xmm0
-       vmovaps  ymm4, ymm0
        vextracti128 xmm1, ymm1
        vpmovzxbd zmm1, xmm1
-       vmovaps  ymm5, ymm1
-       vxorpd   ymm6, ymm6, ymm6
-       vpcmpeqd ymm6, ymm6, ymm5
-       vptest   ymm6, ymm6
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm1
+       vptest   ymm4, ymm4
        jne      SHORT G_M27641_IG05
-       vcvtudq2pd zmm6, ymm4
-       vcvtudq2pd zmm7, ymm5
-       vdivpd   zmm4, zmm6, zmm7
-       vcvttpd2udq ymm4, zmm4
+       vcvtudq2pd zmm4, ymm0
+       vcvtudq2pd zmm5, ymm1
+       vdivpd   zmm6, zmm4, zmm5
+       vcvttpd2udq ymm6, zmm6
        vextracti32x8 ymm0, zmm0, 1
        vextracti32x8 ymm1, zmm1, 1
-       vxorpd   ymm5, ymm5, ymm5
-       vpcmpeqd ymm5, ymm5, ymm1
-       vptest   ymm5, ymm5
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm1
+       vptest   ymm4, ymm4
        jne      SHORT G_M27641_IG05
-       vcvtudq2pd zmm5, ymm0
-       vcvtudq2pd zmm6, ymm1
-       vdivpd   zmm0, zmm5, zmm6
+       vcvtudq2pd zmm4, ymm0
+       vcvtudq2pd zmm5, ymm1
+       vdivpd   zmm0, zmm4, zmm5
        vcvttpd2udq ymm0, zmm0
-       vinserti32x8 zmm0, zmm4, ymm0, 1
+       vinserti32x8 zmm0, zmm6, ymm0, 1
        vpmovdb  xmm0, zmm0
        vinserti128 ymm0, ymm3, xmm0
        vinserti32x8 zmm0, zmm2, ymm0, 1
        vmovups  zmmword ptr [rdi], zmm0
        mov      rax, rdi
-						;; size=253 bbWeight=1 PerfScore 213.25
+						;; size=194 bbWeight=1 PerfScore 162.92
 G_M27641_IG04:
        vzeroupper 
        add      rsp, 8
        ret      
 						;; size=8 bbWeight=1 PerfScore 2.25
 G_M27641_IG05:
        call     CORINFO_HELP_THROWDIVZERO
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 G_M27641_IG06:
        call     CORINFO_HELP_OVERFLOW
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
 
 
-; Total bytes of code 658, prolog size 1, PerfScore 459.67, instruction count 123, allocated bytes for code 658 (MethodHash=97b19406) for method System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
+; Total bytes of code 609, prolog size 1, PerfScore 456.67, instruction count 111, allocated bytes for code 609 (MethodHash=97b19406) for method System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
 ; ============================================================

-49 (-7.50 % of base) - System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],byte):System.Runtime.Intrinsics.Vector512`1[byte]

 ; Assembly listing for method System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],byte):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
 ; Emitting BLENDED_CODE for x64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rsp based frame
 ; partially interruptible
 ; No PGO data
 ; Final local variable assignments
 ;
 ;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
 ;  V01 arg0         [V01,T15] (  2,  2   )  simd64  ->  mm0         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;  V02 arg1         [V02,T01] (  3,  3   )   ubyte  ->  rsi         single-def
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;  V04 tmp1         [V04,T02] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
+;  V04 tmp1         [V04,T02] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
 ;  V05 tmp2         [V05,T03] (  3,  6   )  simd32  ->  mm1         "fgMakeTemp is creating a new local variable"
-;  V06 tmp3         [V06,T04] (  3,  6   )  simd32  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V06 tmp3         [V06,T04] (  3,  6   )  simd32  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V07 tmp4         [V07,T05] (  3,  6   )  simd64  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V08 tmp5         [V08,T06] (  3,  6   )  simd64  ->  mm6         "fgMakeTemp is creating a new local variable"
+;  V08 tmp5         [V08,T06] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;  V09 tmp6         [V09,T07] (  3,  6   )  simd64  ->  mm1         "fgMakeTemp is creating a new local variable"
-;  V10 tmp7         [V10,T08] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V10 tmp7         [V10,T08] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V11 tmp8         [V11,T09] (  3,  6   )  simd32  ->  mm0         "fgMakeTemp is creating a new local variable"
-;  V12 tmp9         [V12,T10] (  3,  6   )  simd32  ->  mm4         "fgMakeTemp is creating a new local variable"
+;  V12 tmp9         [V12,T10] (  3,  6   )  simd32  ->  mm3         "fgMakeTemp is creating a new local variable"
 ;  V13 tmp10        [V13,T11] (  3,  6   )  simd64  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V14 tmp11        [V14,T12] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V14 tmp11        [V14,T12] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V15 tmp12        [V15,T13] (  3,  6   )  simd64  ->  mm0         "fgMakeTemp is creating a new local variable"
-;  V16 tmp13        [V16,T14] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
+;  V16 tmp13        [V16,T14] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
 ;
 ; Lcl frame size = 8
 
 G_M14070_IG01:
        push     rax
        vmovups  zmm0, zmmword ptr [rsp+0x10]
 						;; size=12 bbWeight=1 PerfScore 4.00
 G_M14070_IG02:
        vmovaps  ymm1, ymm0
-       vmovaps  xmm2, xmm1
-       vpmovzxbd zmm2, xmm2
-       vmovaps  ymm3, ymm2
-       vpbroadcastb zmm4, esi
-       vmovaps  ymm5, ymm4
-       vmovaps  xmm6, xmm5
-       vpmovzxbd zmm6, xmm6
-       vmovaps  ymm7, ymm6
-       vxorpd   ymm8, ymm8, ymm8
-       vpcmpeqd ymm8, ymm8, ymm7
-       vptest   ymm8, ymm8
-       jne      G_M14070_IG05
-       vcvtudq2pd zmm8, ymm3
-       vcvtudq2pd zmm9, ymm7
-       vdivpd   zmm3, zmm8, zmm9
-       vcvttpd2udq ymm3, zmm3
-       vextracti32x8 ymm2, zmm2, 1
-       vextracti32x8 ymm6, zmm6, 1
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
-       jne      G_M14070_IG05
-       vcvtudq2pd zmm7, ymm2
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm2, zmm7, zmm8
-       vcvttpd2udq ymm2, zmm2
-       vinserti32x8 zmm2, zmm3, ymm2, 1
-       vpmovdb  xmm2, zmm2
-       vextracti128 xmm1, ymm1
-       vpmovzxbd zmm1, xmm1
-       vmovaps  ymm3, ymm1
-       vextracti128 xmm5, ymm5
-       vpmovzxbd zmm5, xmm5
-       vmovaps  ymm6, ymm5
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
-       jne      G_M14070_IG05
-       vcvtudq2pd zmm7, ymm3
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm3, zmm7, zmm8
-       vcvttpd2udq ymm3, zmm3
-       vextracti32x8 ymm1, zmm1, 1
-       vextracti32x8 ymm5, zmm5, 1
+       vpmovzxbd zmm2, xmm1
+       vpbroadcastb zmm3, esi
+       vmovaps  ymm4, ymm3
+       vpmovzxbd zmm5, xmm4
        vxorpd   ymm6, ymm6, ymm6
        vpcmpeqd ymm6, ymm6, ymm5
        vptest   ymm6, ymm6
        jne      G_M14070_IG05
-       vcvtudq2pd zmm6, ymm1
+       vcvtudq2pd zmm6, ymm2
        vcvtudq2pd zmm7, ymm5
-       vdivpd   zmm1, zmm6, zmm7
-       vcvttpd2udq ymm1, zmm1
-       vinserti32x8 zmm1, zmm3, ymm1, 1
-       vpmovdb  xmm1, zmm1
-       vinserti128 ymm1, ymm2, xmm1
-       vextracti32x8 ymm0, zmm0, 1
-       vmovaps  xmm2, xmm0
-       vpmovzxbd zmm2, xmm2
-       vmovaps  ymm3, ymm2
-       vextracti32x8 ymm4, zmm4, 1
-       vmovaps  xmm5, xmm4
-       vpmovzxbd zmm5, xmm5
-       vmovaps  ymm6, ymm5
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
-						;; size=362 bbWeight=1 PerfScore 240.17
-G_M14070_IG03:
-       jne      G_M14070_IG05
-       vcvtudq2pd zmm7, ymm3
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm3, zmm7, zmm8
-       vcvttpd2udq ymm3, zmm3
+       vdivpd   zmm8, zmm6, zmm7
+       vcvttpd2udq ymm8, zmm8
        vextracti32x8 ymm2, zmm2, 1
        vextracti32x8 ymm5, zmm5, 1
        vxorpd   ymm6, ymm6, ymm6
        vpcmpeqd ymm6, ymm6, ymm5
        vptest   ymm6, ymm6
        jne      G_M14070_IG05
        vcvtudq2pd zmm6, ymm2
        vcvtudq2pd zmm7, ymm5
        vdivpd   zmm2, zmm6, zmm7
        vcvttpd2udq ymm2, zmm2
-       vinserti32x8 zmm2, zmm3, ymm2, 1
+       vinserti32x8 zmm2, zmm8, ymm2, 1
        vpmovdb  xmm2, zmm2
-       vextracti128 xmm0, ymm0
-       vpmovzxbd zmm0, xmm0
-       vmovaps  ymm3, ymm0
+       vextracti128 xmm1, ymm1
+       vpmovzxbd zmm1, xmm1
        vextracti128 xmm4, ymm4
        vpmovzxbd zmm4, xmm4
-       vmovaps  ymm5, ymm4
-       vxorpd   ymm6, ymm6, ymm6
-       vpcmpeqd ymm6, ymm6, ymm5
-       vptest   ymm6, ymm6
-       jne      SHORT G_M14070_IG05
-       vcvtudq2pd zmm6, ymm3
-       vcvtudq2pd zmm7, ymm5
-       vdivpd   zmm3, zmm6, zmm7
-       vcvttpd2udq ymm3, zmm3
-       vextracti32x8 ymm0, zmm0, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M14070_IG05
+       vcvtudq2pd zmm5, ymm1
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm7, zmm5, zmm6
+       vcvttpd2udq ymm7, zmm7
+       vextracti32x8 ymm1, zmm1, 1
        vextracti32x8 ymm4, zmm4, 1
        vxorpd   ymm5, ymm5, ymm5
        vpcmpeqd ymm5, ymm5, ymm4
        vptest   ymm5, ymm5
-       jne      SHORT G_M14070_IG05
-       vcvtudq2pd zmm5, ymm0
+       jne      G_M14070_IG05
+       vcvtudq2pd zmm5, ymm1
        vcvtudq2pd zmm6, ymm4
-       vdivpd   zmm0, zmm5, zmm6
+       vdivpd   zmm1, zmm5, zmm6
+       vcvttpd2udq ymm1, zmm1
+       vinserti32x8 zmm1, zmm7, ymm1, 1
+       vpmovdb  xmm1, zmm1
+       vinserti128 ymm1, ymm2, xmm1
+       vextracti32x8 ymm0, zmm0, 1
+       vpmovzxbd zmm2, xmm0
+       vextracti32x8 ymm3, zmm3, 1
+       vpmovzxbd zmm4, xmm3
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M14070_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm7, zmm5, zmm6
+       vcvttpd2udq ymm7, zmm7
+       vextracti32x8 ymm2, zmm2, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+						;; size=373 bbWeight=1 PerfScore 283.50
+G_M14070_IG03:
+       vptest   ymm5, ymm5
+       jne      G_M14070_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2udq ymm2, zmm2
+       vinserti32x8 zmm2, zmm7, ymm2, 1
+       vpmovdb  xmm2, zmm2
+       vextracti128 xmm0, ymm0
+       vpmovzxbd zmm0, xmm0
+       vextracti128 xmm3, ymm3
+       vpmovzxbd zmm3, xmm3
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm3
+       vptest   ymm4, ymm4
+       jne      SHORT G_M14070_IG05
+       vcvtudq2pd zmm4, ymm0
+       vcvtudq2pd zmm5, ymm3
+       vdivpd   zmm6, zmm4, zmm5
+       vcvttpd2udq ymm6, zmm6
+       vextracti32x8 ymm0, zmm0, 1
+       vextracti32x8 ymm3, zmm3, 1
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm3
+       vptest   ymm4, ymm4
+       jne      SHORT G_M14070_IG05
+       vcvtudq2pd zmm4, ymm0
+       vcvtudq2pd zmm5, ymm3
+       vdivpd   zmm0, zmm4, zmm5
        vcvttpd2udq ymm0, zmm0
-       vinserti32x8 zmm0, zmm3, ymm0, 1
+       vinserti32x8 zmm0, zmm6, ymm0, 1
        vpmovdb  xmm0, zmm0
        vinserti128 ymm0, ymm2, xmm0
        vinserti32x8 zmm0, zmm1, ymm0, 1
        vmovups  zmmword ptr [rdi], zmm0
        mov      rax, rdi
-						;; size=259 bbWeight=1 PerfScore 214.25
+						;; size=199 bbWeight=1 PerfScore 167.92
 G_M14070_IG04:
        vzeroupper 
        add      rsp, 8
        ret      
 						;; size=8 bbWeight=1 PerfScore 2.25
 G_M14070_IG05:
        call     CORINFO_HELP_THROWDIVZERO
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 G_M14070_IG06:
        call     CORINFO_HELP_OVERFLOW
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
 
 
-; Total bytes of code 653, prolog size 1, PerfScore 460.67, instruction count 123, allocated bytes for code 653 (MethodHash=cf00c909) for method System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],byte):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
+; Total bytes of code 604, prolog size 1, PerfScore 457.67, instruction count 111, allocated bytes for code 604 (MethodHash=cf00c909) for method System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],byte):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
 ; ============================================================

-49 (-7.45 % of base) - System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte]

 ; Assembly listing for method System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
 ; Emitting BLENDED_CODE for x64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rsp based frame
 ; partially interruptible
 ; No PGO data
 ; Final local variable assignments
 ;
 ;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
 ;  V01 arg0         [V01,T13] (  2,  2   )  simd64  ->  mm0         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;  V02 arg1         [V02,T14] (  2,  2   )  simd64  ->  mm1         single-def <System.Runtime.Intrinsics.Vector512`1[byte]>
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
 ;  V04 tmp1         [V04,T01] (  3,  6   )  simd32  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V05 tmp2         [V05,T02] (  3,  6   )  simd32  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V05 tmp2         [V05,T02] (  3,  6   )  simd32  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V06 tmp3         [V06,T03] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V07 tmp4         [V07,T04] (  3,  6   )  simd64  ->  mm6         "fgMakeTemp is creating a new local variable"
+;  V07 tmp4         [V07,T04] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;  V08 tmp5         [V08,T05] (  3,  6   )  simd64  ->  mm2         "fgMakeTemp is creating a new local variable"
-;  V09 tmp6         [V09,T06] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V09 tmp6         [V09,T06] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V10 tmp7         [V10,T07] (  3,  6   )  simd32  ->  mm0         "fgMakeTemp is creating a new local variable"
 ;  V11 tmp8         [V11,T08] (  3,  6   )  simd32  ->  mm1         "fgMakeTemp is creating a new local variable"
 ;  V12 tmp9         [V12,T09] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
-;  V13 tmp10        [V13,T10] (  3,  6   )  simd64  ->  mm5         "fgMakeTemp is creating a new local variable"
+;  V13 tmp10        [V13,T10] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
 ;  V14 tmp11        [V14,T11] (  3,  6   )  simd64  ->  mm0         "fgMakeTemp is creating a new local variable"
 ;  V15 tmp12        [V15,T12] (  3,  6   )  simd64  ->  mm1         "fgMakeTemp is creating a new local variable"
 ;
 ; Lcl frame size = 8
 
 G_M1973_IG01:
        push     rax
        vmovups  zmm0, zmmword ptr [rsp+0x10]
        vmovups  zmm1, zmmword ptr [rsp+0x50]
 						;; size=23 bbWeight=1 PerfScore 7.00
 G_M1973_IG02:
        vmovaps  ymm2, ymm0
-       vmovaps  xmm3, xmm2
-       vpmovzxbd zmm3, xmm3
-       vmovaps  ymm4, ymm3
-       vmovaps  ymm5, ymm1
-       vmovaps  xmm6, xmm5
-       vpmovzxbd zmm6, xmm6
-       vmovaps  ymm7, ymm6
-       vxorpd   ymm8, ymm8, ymm8
-       vpcmpeqd ymm8, ymm8, ymm7
-       vptest   ymm8, ymm8
-       jne      G_M1973_IG05
-       vcvtudq2pd zmm8, ymm4
-       vcvtudq2pd zmm9, ymm7
-       vdivpd   zmm4, zmm8, zmm9
-       vcvttpd2udq ymm4, zmm4
-       vextracti32x8 ymm3, zmm3, 1
-       vextracti32x8 ymm6, zmm6, 1
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
-       jne      G_M1973_IG05
-       vcvtudq2pd zmm7, ymm3
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm3, zmm7, zmm8
-       vcvttpd2udq ymm3, zmm3
-       vinserti32x8 zmm3, zmm4, ymm3, 1
-       vpmovdb  xmm3, zmm3
-       vextracti128 xmm2, ymm2
-       vpmovzxbd zmm2, xmm2
-       vmovaps  ymm4, ymm2
-       vextracti128 xmm5, ymm5
-       vpmovzxbd zmm5, xmm5
-       vmovaps  ymm6, ymm5
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
-       jne      G_M1973_IG05
-       vcvtudq2pd zmm7, ymm4
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm4, zmm7, zmm8
-       vcvttpd2udq ymm4, zmm4
-       vextracti32x8 ymm2, zmm2, 1
-       vextracti32x8 ymm5, zmm5, 1
+       vpmovzxbd zmm3, xmm2
+       vmovaps  ymm4, ymm1
+       vpmovzxbd zmm5, xmm4
        vxorpd   ymm6, ymm6, ymm6
        vpcmpeqd ymm6, ymm6, ymm5
        vptest   ymm6, ymm6
        jne      G_M1973_IG05
-       vcvtudq2pd zmm6, ymm2
+       vcvtudq2pd zmm6, ymm3
        vcvtudq2pd zmm7, ymm5
-       vdivpd   zmm2, zmm6, zmm7
-       vcvttpd2udq ymm2, zmm2
-       vinserti32x8 zmm2, zmm4, ymm2, 1
-       vpmovdb  xmm2, zmm2
-       vinserti128 ymm2, ymm3, xmm2
-       vextracti32x8 ymm0, zmm0, 1
-       vmovaps  xmm3, xmm0
-       vpmovzxbd zmm3, xmm3
-       vmovaps  ymm4, ymm3
-       vextracti32x8 ymm1, zmm1, 1
-       vmovaps  xmm5, xmm1
-       vpmovzxbd zmm5, xmm5
-       vmovaps  ymm6, ymm5
-       vxorpd   ymm7, ymm7, ymm7
-       vpcmpeqd ymm7, ymm7, ymm6
-       vptest   ymm7, ymm7
-       jne      G_M1973_IG05
-						;; size=362 bbWeight=1 PerfScore 237.17
-G_M1973_IG03:
-       vcvtudq2pd zmm7, ymm4
-       vcvtudq2pd zmm8, ymm6
-       vdivpd   zmm4, zmm7, zmm8
-       vcvttpd2udq ymm4, zmm4
+       vdivpd   zmm8, zmm6, zmm7
+       vcvttpd2udq ymm8, zmm8
        vextracti32x8 ymm3, zmm3, 1
        vextracti32x8 ymm5, zmm5, 1
        vxorpd   ymm6, ymm6, ymm6
        vpcmpeqd ymm6, ymm6, ymm5
        vptest   ymm6, ymm6
        jne      G_M1973_IG05
        vcvtudq2pd zmm6, ymm3
        vcvtudq2pd zmm7, ymm5
        vdivpd   zmm3, zmm6, zmm7
        vcvttpd2udq ymm3, zmm3
-       vinserti32x8 zmm3, zmm4, ymm3, 1
+       vinserti32x8 zmm3, zmm8, ymm3, 1
+       vpmovdb  xmm3, zmm3
+       vextracti128 xmm2, ymm2
+       vpmovzxbd zmm2, xmm2
+       vextracti128 xmm4, ymm4
+       vpmovzxbd zmm4, xmm4
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M1973_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm7, zmm5, zmm6
+       vcvttpd2udq ymm7, zmm7
+       vextracti32x8 ymm2, zmm2, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M1973_IG05
+       vcvtudq2pd zmm5, ymm2
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2udq ymm2, zmm2
+       vinserti32x8 zmm2, zmm7, ymm2, 1
+       vpmovdb  xmm2, zmm2
+       vinserti128 ymm2, ymm3, xmm2
+       vextracti32x8 ymm0, zmm0, 1
+       vpmovzxbd zmm3, xmm0
+       vextracti32x8 ymm1, zmm1, 1
+       vpmovzxbd zmm4, xmm1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M1973_IG05
+       vcvtudq2pd zmm5, ymm3
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm7, zmm5, zmm6
+       vcvttpd2udq ymm7, zmm7
+       vextracti32x8 ymm3, zmm3, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+						;; size=372 bbWeight=1 PerfScore 284.50
+G_M1973_IG03:
+       jne      G_M1973_IG05
+       vcvtudq2pd zmm5, ymm3
+       vcvtudq2pd zmm6, ymm4
+       vdivpd   zmm3, zmm5, zmm6
+       vcvttpd2udq ymm3, zmm3
+       vinserti32x8 zmm3, zmm7, ymm3, 1
        vpmovdb  xmm3, zmm3
        vextracti128 xmm0, ymm0
        vpmovzxbd zmm0, xmm0
-       vmovaps  ymm4, ymm0
        vextracti128 xmm1, ymm1
        vpmovzxbd zmm1, xmm1
-       vmovaps  ymm5, ymm1
-       vxorpd   ymm6, ymm6, ymm6
-       vpcmpeqd ymm6, ymm6, ymm5
-       vptest   ymm6, ymm6
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm1
+       vptest   ymm4, ymm4
        jne      SHORT G_M1973_IG05
-       vcvtudq2pd zmm6, ymm4
-       vcvtudq2pd zmm7, ymm5
-       vdivpd   zmm4, zmm6, zmm7
-       vcvttpd2udq ymm4, zmm4
+       vcvtudq2pd zmm4, ymm0
+       vcvtudq2pd zmm5, ymm1
+       vdivpd   zmm6, zmm4, zmm5
+       vcvttpd2udq ymm6, zmm6
        vextracti32x8 ymm0, zmm0, 1
        vextracti32x8 ymm1, zmm1, 1
-       vxorpd   ymm5, ymm5, ymm5
-       vpcmpeqd ymm5, ymm5, ymm1
-       vptest   ymm5, ymm5
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm1
+       vptest   ymm4, ymm4
        jne      SHORT G_M1973_IG05
-       vcvtudq2pd zmm5, ymm0
-       vcvtudq2pd zmm6, ymm1
-       vdivpd   zmm0, zmm5, zmm6
+       vcvtudq2pd zmm4, ymm0
+       vcvtudq2pd zmm5, ymm1
+       vdivpd   zmm0, zmm4, zmm5
        vcvttpd2udq ymm0, zmm0
-       vinserti32x8 zmm0, zmm4, ymm0, 1
+       vinserti32x8 zmm0, zmm6, ymm0, 1
        vpmovdb  xmm0, zmm0
        vinserti128 ymm0, ymm3, xmm0
        vinserti32x8 zmm0, zmm2, ymm0, 1
        vmovups  zmmword ptr [rdi], zmm0
        mov      rax, rdi
-						;; size=253 bbWeight=1 PerfScore 213.25
+						;; size=194 bbWeight=1 PerfScore 162.92
 G_M1973_IG04:
        vzeroupper 
        add      rsp, 8
        ret      
 						;; size=8 bbWeight=1 PerfScore 2.25
 G_M1973_IG05:
        call     CORINFO_HELP_THROWDIVZERO
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 G_M1973_IG06:
        call     CORINFO_HELP_OVERFLOW
        int3     
 						;; size=6 bbWeight=0 PerfScore 0.00
 RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
 
 
-; Total bytes of code 658, prolog size 1, PerfScore 459.67, instruction count 123, allocated bytes for code 658 (MethodHash=b004f84a) for method System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
+; Total bytes of code 609, prolog size 1, PerfScore 456.67, instruction count 111, allocated bytes for code 609 (MethodHash=b004f84a) for method System.Runtime.Intrinsics.Vector512:Divide[byte](System.Runtime.Intrinsics.Vector512`1[byte],System.Runtime.Intrinsics.Vector512`1[byte]):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
 ; ============================================================

Note: some changes were skipped as they were too large to fit into a comment.

Larger list of diffs: https://gist.github.com/MihuBot/42263c97df9e88398f50b442085eac2e

[MihuBot]

@tannergooding