[JitDiff X64] [alexcovington] Vector int divide short byte

[MihuBot]

Job completed in 15 minutes 14 seconds (remote runner delay: 51 seconds).
dotnet/runtime#117996

Diffs

Diffs

Found 85 files with textual diffs.

Summary of Code Size diffs:
(Lower is better)

Total bytes of base: 41693573
Total bytes of diff: 41680808
Total bytes of delta: -12765 (-0.03 % of base)
Total relative delta: Infinity
    diff is an improvement.
    relative diff is a regression.


Top file regressions (bytes):
          59 : System.Net.Sockets.dasm (0.02 % of base)

Top file improvements (bytes):
       -7282 : System.Private.CoreLib.dasm (-0.10 % of base)
       -5542 : System.Numerics.Tensors.dasm (-0.51 % of base)

3 total files with Code Size differences (2 improved, 1 regressed), 257 unchanged.

Top method regressions (bytes):
         248 (295.24 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],byte):System.Numerics.Vector`1[byte] (FullOpts)
         248 (295.24 % 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)
         240 (260.87 % 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)
         240 (260.87 % 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)
         154 (183.33 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
         154 (183.33 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
         144 (153.19 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
         144 (153.19 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
          59 (Infinity of base) : System.Net.Sockets.dasm - System.Net.Sockets.SocketAsyncEngine+<>c:<.ctor>b__16_0(System.Object):this (FullOpts)

Top method improvements (bytes):
        -950 (-65.52 % 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)
        -948 (-65.07 % 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)
        -910 (-65.05 % 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)
        -910 (-65.05 % 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)
        -910 (-65.05 % 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)
        -899 (-64.26 % 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)
        -558 (-45.33 % 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)
        -558 (-45.33 % 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)
        -558 (-45.33 % 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)
        -414 (-62.92 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -412 (-62.14 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]] (FullOpts)
        -388 (-61.98 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -388 (-61.98 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Divide[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -388 (-61.98 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_Division(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -388 (-61.98 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.Divide(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -341 (-41.84 % 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)
        -331 (-40.61 % 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)
        -331 (-40.61 % 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)
        -262 (-25.27 % 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)
        -260 (-24.90 % 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)
        -235 (-25.74 % 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)
        -235 (-25.74 % 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)
        -235 (-25.74 % 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)
        -220 (-24.10 % 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)
        -170 (-34.55 % 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)
        -160 (-32.52 % 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)
        -160 (-32.52 % 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)
        -145 (-51.79 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]] (FullOpts)
        -142 (-52.59 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
        -134 (-54.92 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
        -134 (-54.92 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[short](System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
        -134 (-54.92 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
        -109 (-32.83 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_Division(System.Runtime.Intrinsics.Vector256`1[short],short):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -100 (-21.65 % 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)
         -98 (-20.99 % 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)
         -94 (-28.31 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Divide[short](System.Runtime.Intrinsics.Vector256`1[short],short):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
         -94 (-28.31 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.Divide(System.Runtime.Intrinsics.Vector256`1[short],short):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
         -79 (-32.92 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[byte](System.Runtime.Intrinsics.Vector128`1[byte],byte):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
         -79 (-32.92 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[byte],byte):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
         -77 (-18.83 % 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)
         -77 (-18.83 % 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)
         -77 (-18.83 % 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)
         -77 (-18.83 % 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)
         -46 (-28.75 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[short](System.Runtime.Intrinsics.Vector128`1[short],short):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
         -46 (-28.75 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[short],short):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
         -11 (-4.66 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
         -11 (-4.31 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]] (FullOpts)
         -11 (-4.47 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
         -11 (-4.66 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:Divide[int](System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
         -11 (-4.66 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
         -10 (-5.99 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
         -10 (-5.99 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[byte](System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
         -10 (-5.99 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
          -9 (-4.27 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]] (FullOpts)
          -7 (-3.08 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:Divide[int](System.Runtime.Intrinsics.Vector512`1[int],int):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
          -7 (-3.08 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[int],int):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
          -6 (-2.99 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
          -3 (-3.06 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-2.68 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]] (FullOpts)
          -3 (-2.86 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-3.06 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[int](System.Runtime.Intrinsics.Vector128`1[int],int):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-3.06 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[int](System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-3.06 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[int],int):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-3.06 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)

Top method regressions (percentages):
          59 (Infinity of base) : System.Net.Sockets.dasm - System.Net.Sockets.SocketAsyncEngine+<>c:<.ctor>b__16_0(System.Object):this (FullOpts)
         248 (295.24 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],byte):System.Numerics.Vector`1[byte] (FullOpts)
         248 (295.24 % 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)
         240 (260.87 % 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)
         240 (260.87 % 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)
         154 (183.33 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
         154 (183.33 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
         144 (153.19 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
         144 (153.19 % of base) : System.Private.CoreLib.dasm - System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)

Top method improvements (percentages):
        -950 (-65.52 % 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)
        -948 (-65.07 % 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)
        -910 (-65.05 % 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)
        -910 (-65.05 % 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)
        -910 (-65.05 % 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)
        -899 (-64.26 % 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)
        -414 (-62.92 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -412 (-62.14 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]] (FullOpts)
        -388 (-61.98 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -388 (-61.98 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Divide[short](System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -388 (-61.98 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_Division(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -388 (-61.98 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.Divide(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -134 (-54.92 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
        -134 (-54.92 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[short](System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
        -134 (-54.92 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
        -142 (-52.59 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
        -145 (-51.79 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[short],System.Runtime.Intrinsics.Vector128`1[short]] (FullOpts)
        -558 (-45.33 % 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)
        -558 (-45.33 % 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)
        -558 (-45.33 % 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)
        -341 (-41.84 % 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)
        -331 (-40.61 % 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)
        -331 (-40.61 % 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)
        -170 (-34.55 % 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)
         -79 (-32.92 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[byte](System.Runtime.Intrinsics.Vector128`1[byte],byte):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
         -79 (-32.92 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[byte],byte):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
        -109 (-32.83 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:op_Division(System.Runtime.Intrinsics.Vector256`1[short],short):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -160 (-32.52 % 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)
        -160 (-32.52 % 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)
         -46 (-28.75 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[short](System.Runtime.Intrinsics.Vector128`1[short],short):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
         -46 (-28.75 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[short],short):System.Runtime.Intrinsics.Vector128`1[short] (FullOpts)
         -94 (-28.31 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:Divide[short](System.Runtime.Intrinsics.Vector256`1[short],short):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
         -94 (-28.31 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector256<T>,T>.Divide(System.Runtime.Intrinsics.Vector256`1[short],short):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
        -235 (-25.74 % 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)
        -235 (-25.74 % 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)
        -235 (-25.74 % 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)
        -262 (-25.27 % 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)
        -260 (-24.90 % 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)
        -220 (-24.10 % 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)
        -100 (-21.65 % 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)
         -98 (-20.99 % 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)
         -77 (-18.83 % 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)
         -77 (-18.83 % 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)
         -77 (-18.83 % 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)
         -77 (-18.83 % 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)
         -10 (-5.99 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
         -10 (-5.99 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[byte](System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
         -10 (-5.99 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[byte]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
         -11 (-4.66 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
         -11 (-4.66 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:Divide[int](System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
         -11 (-4.66 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
         -11 (-4.47 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
         -11 (-4.31 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector512`1[int],System.Runtime.Intrinsics.Vector512`1[int]] (FullOpts)
          -9 (-4.27 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]] (FullOpts)
          -7 (-3.08 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:Divide[int](System.Runtime.Intrinsics.Vector512`1[int],int):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
          -7 (-3.08 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector512<T>,T>.Divide(System.Runtime.Intrinsics.Vector512`1[int],int):System.Runtime.Intrinsics.Vector512`1[int] (FullOpts)
          -3 (-3.06 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivideOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-3.06 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[int](System.Runtime.Intrinsics.Vector128`1[int],int):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-3.06 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128:Divide[int](System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-3.06 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[int],int):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-3.06 % of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector128`1[int]:System.Runtime.Intrinsics.ISimdVector<System.Runtime.Intrinsics.Vector128<T>,T>.Divide(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -6 (-2.99 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[byte]:Invoke(System.Runtime.Intrinsics.Vector128`1[byte],System.Runtime.Intrinsics.Vector128`1[byte]):System.Runtime.Intrinsics.Vector128`1[byte] (FullOpts)
          -3 (-2.86 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.Runtime.Intrinsics.Vector128`1[int] (FullOpts)
          -3 (-2.68 % of base) : System.Numerics.Tensors.dasm - System.Numerics.Tensors.TensorPrimitives+DivRemOperator`1[int]:Invoke(System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]):System.ValueTuple`2[System.Runtime.Intrinsics.Vector128`1[int],System.Runtime.Intrinsics.Vector128`1[int]] (FullOpts)

73 total methods with Code Size differences (64 improved, 9 regressed), 250497 unchanged.

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

Artifacts:

• build-clr-checked-main.zip (88 MB)
• build-artifacts-main.zip (681 MB)
• build-clr-checked-pr.zip (88 MB)
• build-artifacts-pr.zip (682 MB)
• jit-diffs-pr.zip (138 MB)
• jit-diffs-main.zip (138 MB)
• diff-frameworks.txt (40 KB)
• ShortDiffsRegressions.md (52 KB)
• ShortDiffsImprovements.md (51 KB)
• LongDiffsImprovements.md (553 KB)

[MihuBot]

Top method regressions

248 (295.24 % of base) - System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],byte):System.Numerics.Vector`1[byte]

 ; Assembly listing for method System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],byte):System.Numerics.Vector`1[byte] (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 2 single block inlinees; 2 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T03] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T05] (  1,  1   )  simd32  ->  [rbp+0x10]  single-def <System.Numerics.Vector`1[byte]>
-;  V02 arg1         [V02,T04] (  3,  3   )   ubyte  ->  rsi         single-def
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T07] (  2,  2   )  simd32  ->  mm0         single-def <System.Numerics.Vector`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    ] (  2,  9   )  simd32  ->  [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Numerics.Vector`1[byte]>
-;  V05 tmp2         [V05,T00] (  5, 33   )     int  ->  rcx         "Inline stloc first use temp"
-;  V06 tmp3         [V06    ] (  2, 18   )  simd32  ->  [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[byte]>
-;* V07 tmp4         [V07    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V08 tmp5         [V08    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V09 tmp6         [V09    ] (  0,  0   )   ubyte  ->  zero-ref    "Inlining Arg"
-;  V10 cse0         [V10,T02] (  2,  9   )     int  ->  rsi         hoist "CSE #01: aggressive"
-;  V11 cse1         [V11,T01] (  3, 24   )    long  ->   r8         "CSE #02: aggressive"
+;  V04 tmp1         [V04,T02] (  3,  6   )  simd32  ->  mm3         "fgMakeTemp is creating a new local variable"
+;  V05 tmp2         [V05,T03] (  3,  6   )  simd64  ->  mm1         "fgMakeTemp is creating a new local variable"
+;  V06 tmp3         [V06,T04] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
+;  V07 tmp4         [V07,T05] (  3,  6   )  simd64  ->  mm0         "fgMakeTemp is creating a new local variable"
+;  V08 tmp5         [V08,T06] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
 ;
-; Lcl frame size = 80
+; Lcl frame size = 8
 
 G_M10982_IG01:
-       push     rbp
-       sub      rsp, 80
-       lea      rbp, [rsp+0x50]
-						;; size=10 bbWeight=1 PerfScore 1.75
+       push     rax
+       vmovups  ymm0, ymmword ptr [rsp+0x10]
+						;; size=7 bbWeight=1 PerfScore 5.00
 G_M10982_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+0x10]
-       vmovups  ymmword ptr [rbp-0x50], ymm0
-       xor      ecx, ecx
-       movzx    rsi, sil
-       align    [6 bytes for IG03]
-						;; size=22 bbWeight=1 PerfScore 5.75
-G_M10982_IG03:
-       lea      rax, [rbp-0x50]
-       movsxd   r8, ecx
-       movzx    rax, byte  ptr [rax+r8]
-       xor      edx, edx
-       div      edx:eax, esi
-       lea      rdx, [rbp-0x30]
-       mov      byte  ptr [rdx+r8], al
-       inc      ecx
-       cmp      ecx, 32
-       jl       SHORT G_M10982_IG03
-						;; size=31 bbWeight=8 PerfScore 248.00
-G_M10982_IG04:
-       vmovups  ymm0, ymmword ptr [rbp-0x30]
+       vmovaps  ymm1, ymm0
+       vpmovzxbd zmm1, zmm1
+       vmovaps  zmm2, zmm1
+       vpbroadcastb ymm3, esi
+       vmovaps  ymm4, ymm3
+       vpmovzxbd zmm4, zmm4
+       vmovaps  zmm5, zmm4
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      G_M10982_IG04
+       vcvtudq2pd zmm6, zmm2
+       vcvtudq2pd zmm7, zmm5
+       vdivpd   zmm2, zmm6, zmm7
+       vcvttpd2udq zmm2, zmm2
+       vextracti32x8 ymm1, zmm1, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M10982_IG04
+       vcvtudq2pd zmm5, zmm1
+       vcvtudq2pd zmm6, zmm4
+       vdivpd   zmm1, zmm5, zmm6
+       vcvttpd2udq zmm1, zmm1
+       vinserti32x8 zmm1, zmm2, ymm1, 1
+       vpmovdb  zmm1, zmm1
+       vextracti128 xmm0, ymm0
+       vpmovzxbd zmm0, zmm0
+       vmovaps  zmm2, zmm0
+       vextracti128 xmm3, ymm3
+       vpmovzxbd zmm3, zmm3
+       vmovaps  zmm4, zmm3
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      SHORT G_M10982_IG04
+       vcvtudq2pd zmm5, zmm2
+       vcvtudq2pd zmm6, zmm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2udq zmm2, zmm2
+       vextracti32x8 ymm0, zmm0, 1
+       vextracti32x8 ymm3, zmm3, 1
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm3
+       vptest   ymm4, ymm4
+       jne      SHORT G_M10982_IG04
+       vcvtudq2pd zmm4, zmm0
+       vcvtudq2pd zmm5, zmm3
+       vdivpd   zmm0, zmm4, zmm5
+       vcvttpd2udq zmm0, zmm0
+       vinserti32x8 zmm0, zmm2, ymm0, 1
+       vpmovdb  zmm0, zmm0
+       vinserti128 ymm0, ymm1, xmm0
        vmovups  ymmword ptr [rdi], ymm0
        mov      rax, rdi
-						;; size=12 bbWeight=1 PerfScore 6.25
-G_M10982_IG05:
+						;; size=305 bbWeight=1 PerfScore 157.08
+G_M10982_IG03:
        vzeroupper 
-       add      rsp, 80
-       pop      rbp
+       add      rsp, 8
        ret      
-						;; size=9 bbWeight=1 PerfScore 2.75
+						;; size=8 bbWeight=1 PerfScore 2.25
+G_M10982_IG04:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M10982_IG05:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
 
-; Total bytes of code 84, prolog size 10, PerfScore 264.50, instruction count 25, allocated bytes for code 84 (MethodHash=dae8d519) for method System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],byte):System.Numerics.Vector`1[byte] (FullOpts)
+
+; Total bytes of code 332, prolog size 1, PerfScore 164.33, instruction count 65, allocated bytes for code 332 (MethodHash=dae8d519) for method System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],byte):System.Numerics.Vector`1[byte] (FullOpts)
 ; ============================================================

248 (295.24 % of base) - System.Numerics.Vector`1[byte]:System.Runtime.Intrinsics.ISimdVector,T>.Divide(System.Numerics.Vector`1[byte],byte):System.Numerics.Vector`1[byte]

 ; Assembly listing for method 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)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 2 single block inlinees; 2 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T03] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T05] (  1,  1   )  simd32  ->  [rbp+0x10]  single-def <System.Numerics.Vector`1[byte]>
-;  V02 arg1         [V02,T04] (  3,  3   )   ubyte  ->  rsi         single-def
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T07] (  2,  2   )  simd32  ->  mm0         single-def <System.Numerics.Vector`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    ] (  2,  9   )  simd32  ->  [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Numerics.Vector`1[byte]>
-;  V05 tmp2         [V05,T00] (  5, 33   )     int  ->  rcx         "Inline stloc first use temp"
-;  V06 tmp3         [V06    ] (  2, 18   )  simd32  ->  [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[byte]>
-;* V07 tmp4         [V07    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V08 tmp5         [V08    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V09 tmp6         [V09    ] (  0,  0   )   ubyte  ->  zero-ref    "Inlining Arg"
-;  V10 cse0         [V10,T02] (  2,  9   )     int  ->  rsi         hoist "CSE #01: aggressive"
-;  V11 cse1         [V11,T01] (  3, 24   )    long  ->   r8         "CSE #02: aggressive"
+;  V04 tmp1         [V04,T02] (  3,  6   )  simd32  ->  mm3         "fgMakeTemp is creating a new local variable"
+;  V05 tmp2         [V05,T03] (  3,  6   )  simd64  ->  mm1         "fgMakeTemp is creating a new local variable"
+;  V06 tmp3         [V06,T04] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
+;  V07 tmp4         [V07,T05] (  3,  6   )  simd64  ->  mm0         "fgMakeTemp is creating a new local variable"
+;  V08 tmp5         [V08,T06] (  3,  6   )  simd64  ->  mm3         "fgMakeTemp is creating a new local variable"
 ;
-; Lcl frame size = 80
+; Lcl frame size = 8
 
 G_M48937_IG01:
-       push     rbp
-       sub      rsp, 80
-       lea      rbp, [rsp+0x50]
-						;; size=10 bbWeight=1 PerfScore 1.75
+       push     rax
+       vmovups  ymm0, ymmword ptr [rsp+0x10]
+						;; size=7 bbWeight=1 PerfScore 5.00
 G_M48937_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+0x10]
-       vmovups  ymmword ptr [rbp-0x50], ymm0
-       xor      ecx, ecx
-       movzx    rsi, sil
-       align    [6 bytes for IG03]
-						;; size=22 bbWeight=1 PerfScore 5.75
-G_M48937_IG03:
-       lea      rax, [rbp-0x50]
-       movsxd   r8, ecx
-       movzx    rax, byte  ptr [rax+r8]
-       xor      edx, edx
-       div      edx:eax, esi
-       lea      rdx, [rbp-0x30]
-       mov      byte  ptr [rdx+r8], al
-       inc      ecx
-       cmp      ecx, 32
-       jl       SHORT G_M48937_IG03
-						;; size=31 bbWeight=8 PerfScore 248.00
-G_M48937_IG04:
-       vmovups  ymm0, ymmword ptr [rbp-0x30]
+       vmovaps  ymm1, ymm0
+       vpmovzxbd zmm1, zmm1
+       vmovaps  zmm2, zmm1
+       vpbroadcastb ymm3, esi
+       vmovaps  ymm4, ymm3
+       vpmovzxbd zmm4, zmm4
+       vmovaps  zmm5, zmm4
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      G_M48937_IG04
+       vcvtudq2pd zmm6, zmm2
+       vcvtudq2pd zmm7, zmm5
+       vdivpd   zmm2, zmm6, zmm7
+       vcvttpd2udq zmm2, zmm2
+       vextracti32x8 ymm1, zmm1, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M48937_IG04
+       vcvtudq2pd zmm5, zmm1
+       vcvtudq2pd zmm6, zmm4
+       vdivpd   zmm1, zmm5, zmm6
+       vcvttpd2udq zmm1, zmm1
+       vinserti32x8 zmm1, zmm2, ymm1, 1
+       vpmovdb  zmm1, zmm1
+       vextracti128 xmm0, ymm0
+       vpmovzxbd zmm0, zmm0
+       vmovaps  zmm2, zmm0
+       vextracti128 xmm3, ymm3
+       vpmovzxbd zmm3, zmm3
+       vmovaps  zmm4, zmm3
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      SHORT G_M48937_IG04
+       vcvtudq2pd zmm5, zmm2
+       vcvtudq2pd zmm6, zmm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2udq zmm2, zmm2
+       vextracti32x8 ymm0, zmm0, 1
+       vextracti32x8 ymm3, zmm3, 1
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm3
+       vptest   ymm4, ymm4
+       jne      SHORT G_M48937_IG04
+       vcvtudq2pd zmm4, zmm0
+       vcvtudq2pd zmm5, zmm3
+       vdivpd   zmm0, zmm4, zmm5
+       vcvttpd2udq zmm0, zmm0
+       vinserti32x8 zmm0, zmm2, ymm0, 1
+       vpmovdb  zmm0, zmm0
+       vinserti128 ymm0, ymm1, xmm0
        vmovups  ymmword ptr [rdi], ymm0
        mov      rax, rdi
-						;; size=12 bbWeight=1 PerfScore 6.25
-G_M48937_IG05:
+						;; size=305 bbWeight=1 PerfScore 157.08
+G_M48937_IG03:
        vzeroupper 
-       add      rsp, 80
-       pop      rbp
+       add      rsp, 8
        ret      
-						;; size=9 bbWeight=1 PerfScore 2.75
+						;; size=8 bbWeight=1 PerfScore 2.25
+G_M48937_IG04:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M48937_IG05:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
 
-; Total bytes of code 84, prolog size 10, PerfScore 264.50, instruction count 25, allocated bytes for code 84 (MethodHash=5dde40d6) for method 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)
+
+; Total bytes of code 332, prolog size 1, PerfScore 164.33, instruction count 65, allocated bytes for code 332 (MethodHash=5dde40d6) for method 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)
 ; ============================================================

240 (260.87 % of base) - System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte]):System.Numerics.Vector`1[byte]

 ; Assembly listing for method System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte]):System.Numerics.Vector`1[byte] (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 3 single block inlinees; 2 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T02] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T03] (  1,  1   )  simd32  ->  [rbp+0x10]  single-def <System.Numerics.Vector`1[byte]>
-;  V02 arg1         [V02,T04] (  1,  1   )  simd32  ->  [rbp+0x30]  single-def <System.Numerics.Vector`1[byte]>
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T05] (  2,  2   )  simd32  ->  mm0         single-def <System.Numerics.Vector`1[byte]>
+;  V02 arg1         [V02,T06] (  2,  2   )  simd32  ->  mm1         single-def <System.Numerics.Vector`1[byte]>
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;  V04 tmp1         [V04    ] (  2,  9   )  simd32  ->  [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Numerics.Vector`1[byte]>
-;  V05 tmp2         [V05,T00] (  5, 33   )     int  ->  rcx         "Inline stloc first use temp"
-;  V06 tmp3         [V06    ] (  2, 18   )  simd32  ->  [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[byte]>
-;  V07 tmp4         [V07    ] (  2, 18   )  simd32  ->  [rbp-0x70]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[byte]>
-;* V08 tmp5         [V08    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V09 tmp6         [V09    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V10 tmp7         [V10    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V11 tmp8         [V11    ] (  0,  0   )   ubyte  ->  zero-ref    "Inlining Arg"
-;* V12 tmp9         [V12    ] (  0,  0   )   ubyte  ->  zero-ref    "Inlining Arg"
-;  V13 cse0         [V13,T01] (  4, 32   )    long  ->  rsi         "CSE #01: aggressive"
+;  V04 tmp1         [V04,T01] (  3,  6   )  simd64  ->  mm2         "fgMakeTemp is creating a new local variable"
+;  V05 tmp2         [V05,T02] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
+;  V06 tmp3         [V06,T03] (  3,  6   )  simd64  ->  mm0         "fgMakeTemp is creating a new local variable"
+;  V07 tmp4         [V07,T04] (  3,  6   )  simd64  ->  mm1         "fgMakeTemp is creating a new local variable"
 ;
-; Lcl frame size = 112
+; Lcl frame size = 8
 
 G_M4501_IG01:
-       push     rbp
-       sub      rsp, 112
-       lea      rbp, [rsp+0x70]
-						;; size=10 bbWeight=1 PerfScore 1.75
+       push     rax
+       vmovups  ymm0, ymmword ptr [rsp+0x10]
+       vmovups  ymm1, ymmword ptr [rsp+0x30]
+						;; size=13 bbWeight=1 PerfScore 9.00
 G_M4501_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+0x10]
-       vmovups  ymmword ptr [rbp-0x50], ymm0
-       vmovups  ymm0, ymmword ptr [rbp+0x30]
-       vmovups  ymmword ptr [rbp-0x70], ymm0
-       xor      ecx, ecx
-       align    [0 bytes for IG03]
-						;; size=22 bbWeight=1 PerfScore 10.25
-G_M4501_IG03:
-       lea      rax, [rbp-0x50]
-       movsxd   rsi, ecx
-       movzx    rax, byte  ptr [rax+rsi]
-       lea      rdx, [rbp-0x70]
-       movzx    r8, byte  ptr [rdx+rsi]
-       xor      edx, edx
-       div      edx:eax, r8d
-       lea      rdx, [rbp-0x30]
-       mov      byte  ptr [rdx+rsi], al
-       inc      ecx
-       cmp      ecx, 32
-       jl       SHORT G_M4501_IG03
-						;; size=39 bbWeight=8 PerfScore 268.00
-G_M4501_IG04:
-       vmovups  ymm0, ymmword ptr [rbp-0x30]
+       vmovaps  ymm2, ymm0
+       vpmovzxbd zmm2, zmm2
+       vmovaps  zmm3, zmm2
+       vmovaps  ymm4, ymm1
+       vpmovzxbd zmm4, zmm4
+       vmovaps  zmm5, zmm4
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      G_M4501_IG04
+       vcvtudq2pd zmm6, zmm3
+       vcvtudq2pd zmm7, zmm5
+       vdivpd   zmm3, zmm6, zmm7
+       vcvttpd2udq zmm3, zmm3
+       vextracti32x8 ymm2, zmm2, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M4501_IG04
+       vcvtudq2pd zmm5, zmm2
+       vcvtudq2pd zmm6, zmm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2udq zmm2, zmm2
+       vinserti32x8 zmm2, zmm3, ymm2, 1
+       vpmovdb  zmm2, zmm2
+       vextracti128 xmm0, ymm0
+       vpmovzxbd zmm0, zmm0
+       vmovaps  zmm3, zmm0
+       vextracti128 xmm1, ymm1
+       vpmovzxbd zmm1, zmm1
+       vmovaps  zmm4, zmm1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      SHORT G_M4501_IG04
+       vcvtudq2pd zmm5, zmm3
+       vcvtudq2pd zmm6, zmm4
+       vdivpd   zmm3, zmm5, zmm6
+       vcvttpd2udq zmm3, zmm3
+       vextracti32x8 ymm0, zmm0, 1
+       vextracti32x8 ymm1, zmm1, 1
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm1
+       vptest   ymm4, ymm4
+       jne      SHORT G_M4501_IG04
+       vcvtudq2pd zmm4, zmm0
+       vcvtudq2pd zmm5, zmm1
+       vdivpd   zmm0, zmm4, zmm5
+       vcvttpd2udq zmm0, zmm0
+       vinserti32x8 zmm0, zmm3, ymm0, 1
+       vpmovdb  zmm0, zmm0
+       vinserti128 ymm0, ymm2, xmm0
        vmovups  ymmword ptr [rdi], ymm0
        mov      rax, rdi
-						;; size=12 bbWeight=1 PerfScore 6.25
-G_M4501_IG05:
+						;; size=299 bbWeight=1 PerfScore 155.08
+G_M4501_IG03:
        vzeroupper 
-       add      rsp, 112
-       pop      rbp
+       add      rsp, 8
        ret      
-						;; size=9 bbWeight=1 PerfScore 2.75
+						;; size=8 bbWeight=1 PerfScore 2.25
+G_M4501_IG04:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M4501_IG05:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
 
-; Total bytes of code 92, prolog size 10, PerfScore 289.00, instruction count 28, allocated bytes for code 92 (MethodHash=2ca6ee6a) for method System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte]):System.Numerics.Vector`1[byte] (FullOpts)
+
+; Total bytes of code 332, prolog size 1, PerfScore 166.33, instruction count 65, allocated bytes for code 332 (MethodHash=2ca6ee6a) for method System.Numerics.Vector:Divide[byte](System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte]):System.Numerics.Vector`1[byte] (FullOpts)
 ; ============================================================

240 (260.87 % of base) - System.Numerics.Vector`1[byte]:System.Runtime.Intrinsics.ISimdVector,T>.Divide(System.Numerics.Vector`1[byte],System.Numerics.Vector`1[byte]):System.Numerics.Vector`1[byte]

 ; Assembly listing for method 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)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 3 single block inlinees; 2 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T02] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T03] (  1,  1   )  simd32  ->  [rbp+0x10]  single-def <System.Numerics.Vector`1[byte]>
-;  V02 arg1         [V02,T04] (  1,  1   )  simd32  ->  [rbp+0x30]  single-def <System.Numerics.Vector`1[byte]>
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T05] (  2,  2   )  simd32  ->  mm0         single-def <System.Numerics.Vector`1[byte]>
+;  V02 arg1         [V02,T06] (  2,  2   )  simd32  ->  mm1         single-def <System.Numerics.Vector`1[byte]>
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;  V04 tmp1         [V04    ] (  2,  9   )  simd32  ->  [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Numerics.Vector`1[byte]>
-;  V05 tmp2         [V05,T00] (  5, 33   )     int  ->  rcx         "Inline stloc first use temp"
-;  V06 tmp3         [V06    ] (  2, 18   )  simd32  ->  [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[byte]>
-;  V07 tmp4         [V07    ] (  2, 18   )  simd32  ->  [rbp-0x70]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[byte]>
-;* V08 tmp5         [V08    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V09 tmp6         [V09    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V10 tmp7         [V10    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V11 tmp8         [V11    ] (  0,  0   )   ubyte  ->  zero-ref    "Inlining Arg"
-;* V12 tmp9         [V12    ] (  0,  0   )   ubyte  ->  zero-ref    "Inlining Arg"
-;  V13 cse0         [V13,T01] (  4, 32   )    long  ->  rsi         "CSE #01: aggressive"
+;  V04 tmp1         [V04,T01] (  3,  6   )  simd64  ->  mm2         "fgMakeTemp is creating a new local variable"
+;  V05 tmp2         [V05,T02] (  3,  6   )  simd64  ->  mm4         "fgMakeTemp is creating a new local variable"
+;  V06 tmp3         [V06,T03] (  3,  6   )  simd64  ->  mm0         "fgMakeTemp is creating a new local variable"
+;  V07 tmp4         [V07,T04] (  3,  6   )  simd64  ->  mm1         "fgMakeTemp is creating a new local variable"
 ;
-; Lcl frame size = 112
+; Lcl frame size = 8
 
 G_M63130_IG01:
-       push     rbp
-       sub      rsp, 112
-       lea      rbp, [rsp+0x70]
-						;; size=10 bbWeight=1 PerfScore 1.75
+       push     rax
+       vmovups  ymm0, ymmword ptr [rsp+0x10]
+       vmovups  ymm1, ymmword ptr [rsp+0x30]
+						;; size=13 bbWeight=1 PerfScore 9.00
 G_M63130_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+0x10]
-       vmovups  ymmword ptr [rbp-0x50], ymm0
-       vmovups  ymm0, ymmword ptr [rbp+0x30]
-       vmovups  ymmword ptr [rbp-0x70], ymm0
-       xor      ecx, ecx
-       align    [0 bytes for IG03]
-						;; size=22 bbWeight=1 PerfScore 10.25
-G_M63130_IG03:
-       lea      rax, [rbp-0x50]
-       movsxd   rsi, ecx
-       movzx    rax, byte  ptr [rax+rsi]
-       lea      rdx, [rbp-0x70]
-       movzx    r8, byte  ptr [rdx+rsi]
-       xor      edx, edx
-       div      edx:eax, r8d
-       lea      rdx, [rbp-0x30]
-       mov      byte  ptr [rdx+rsi], al
-       inc      ecx
-       cmp      ecx, 32
-       jl       SHORT G_M63130_IG03
-						;; size=39 bbWeight=8 PerfScore 268.00
-G_M63130_IG04:
-       vmovups  ymm0, ymmword ptr [rbp-0x30]
+       vmovaps  ymm2, ymm0
+       vpmovzxbd zmm2, zmm2
+       vmovaps  zmm3, zmm2
+       vmovaps  ymm4, ymm1
+       vpmovzxbd zmm4, zmm4
+       vmovaps  zmm5, zmm4
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      G_M63130_IG04
+       vcvtudq2pd zmm6, zmm3
+       vcvtudq2pd zmm7, zmm5
+       vdivpd   zmm3, zmm6, zmm7
+       vcvttpd2udq zmm3, zmm3
+       vextracti32x8 ymm2, zmm2, 1
+       vextracti32x8 ymm4, zmm4, 1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M63130_IG04
+       vcvtudq2pd zmm5, zmm2
+       vcvtudq2pd zmm6, zmm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2udq zmm2, zmm2
+       vinserti32x8 zmm2, zmm3, ymm2, 1
+       vpmovdb  zmm2, zmm2
+       vextracti128 xmm0, ymm0
+       vpmovzxbd zmm0, zmm0
+       vmovaps  zmm3, zmm0
+       vextracti128 xmm1, ymm1
+       vpmovzxbd zmm1, zmm1
+       vmovaps  zmm4, zmm1
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      SHORT G_M63130_IG04
+       vcvtudq2pd zmm5, zmm3
+       vcvtudq2pd zmm6, zmm4
+       vdivpd   zmm3, zmm5, zmm6
+       vcvttpd2udq zmm3, zmm3
+       vextracti32x8 ymm0, zmm0, 1
+       vextracti32x8 ymm1, zmm1, 1
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm1
+       vptest   ymm4, ymm4
+       jne      SHORT G_M63130_IG04
+       vcvtudq2pd zmm4, zmm0
+       vcvtudq2pd zmm5, zmm1
+       vdivpd   zmm0, zmm4, zmm5
+       vcvttpd2udq zmm0, zmm0
+       vinserti32x8 zmm0, zmm3, ymm0, 1
+       vpmovdb  zmm0, zmm0
+       vinserti128 ymm0, ymm2, xmm0
        vmovups  ymmword ptr [rdi], ymm0
        mov      rax, rdi
-						;; size=12 bbWeight=1 PerfScore 6.25
-G_M63130_IG05:
+						;; size=299 bbWeight=1 PerfScore 155.08
+G_M63130_IG03:
        vzeroupper 
-       add      rsp, 112
-       pop      rbp
+       add      rsp, 8
        ret      
-						;; size=9 bbWeight=1 PerfScore 2.75
+						;; size=8 bbWeight=1 PerfScore 2.25
+G_M63130_IG04:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M63130_IG05:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
 
-; Total bytes of code 92, prolog size 10, PerfScore 289.00, instruction count 28, allocated bytes for code 92 (MethodHash=3a140965) for method 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)
+
+; Total bytes of code 332, prolog size 1, PerfScore 166.33, instruction count 65, allocated bytes for code 332 (MethodHash=3a140965) for method 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)
 ; ============================================================

154 (183.33 % of base) - System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short]

 ; Assembly listing for method System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 2 single block inlinees; 2 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T03] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T05] (  1,  1   )  simd32  ->  [rbp+0x10]  single-def <System.Numerics.Vector`1[short]>
-;  V02 arg1         [V02,T04] (  3,  3   )   short  ->  rsi         single-def
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T03] (  2,  2   )  simd32  ->  mm0         single-def <System.Numerics.Vector`1[short]>
+;  V02 arg1         [V02,T01] (  3,  3   )   short  ->  rsi         single-def
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;  V04 tmp1         [V04    ] (  2,  9   )  simd32  ->  [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Numerics.Vector`1[short]>
-;  V05 tmp2         [V05,T00] (  5, 33   )     int  ->  rcx         "Inline stloc first use temp"
-;  V06 tmp3         [V06    ] (  2, 18   )  simd32  ->  [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[short]>
-;* V07 tmp4         [V07    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;* V08 tmp5         [V08    ] (  0,  0   )   short  ->  zero-ref    "Inline return value spill temp"
-;* V09 tmp6         [V09    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V10 cse0         [V10,T02] (  2,  9   )     int  ->  rsi         hoist "CSE #01: aggressive"
-;  V11 cse1         [V11,T01] (  3, 24   )    long  ->   r8         "CSE #02: aggressive"
+;  V04 tmp1         [V04,T02] (  3,  6   )  simd32  ->  mm2         "fgMakeTemp is creating a new local variable"
 ;
-; Lcl frame size = 80
+; Lcl frame size = 8
 
 G_M1062_IG01:
-       push     rbp
-       sub      rsp, 80
-       lea      rbp, [rsp+0x50]
-						;; size=10 bbWeight=1 PerfScore 1.75
+       push     rax
+       vmovups  ymm0, ymmword ptr [rsp+0x10]
+						;; size=7 bbWeight=1 PerfScore 5.00
 G_M1062_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+0x10]
-       vmovups  ymmword ptr [rbp-0x50], ymm0
-       xor      ecx, ecx
-       movsx    rsi, si
-       align    [6 bytes for IG03]
-						;; size=22 bbWeight=1 PerfScore 5.75
-G_M1062_IG03:
-       lea      rax, [rbp-0x50]
-       movsxd   r8, ecx
-       movsx    rax, word  ptr [rax+2*r8]
-       cdq      
-       idiv     edx:eax, esi
-       lea      rdx, [rbp-0x30]
-       mov      word  ptr [rdx+2*r8], ax
-       inc      ecx
-       cmp      ecx, 16
-       jl       SHORT G_M1062_IG03
-						;; size=31 bbWeight=8 PerfScore 266.00
-G_M1062_IG04:
-       vmovups  ymm0, ymmword ptr [rbp-0x30]
+       vmovaps  ymm1, ymm0
+       vpmovsxwd ymm1, ymm1
+       vpbroadcastw ymm2, esi
+       vmovaps  ymm3, ymm2
+       vpmovsxwd ymm3, ymm3
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm3
+       vptest   ymm4, ymm4
+       jne      G_M1062_IG04
+       vpcmpeqd ymm4, ymm1, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm5, ymm3, ymmword ptr [reloc @RWD00]
+       vpand    ymm4, ymm4, ymm5
+       vptest   ymm4, ymm4
+       jne      G_M1062_IG05
+       vcvtdq2pd zmm4, zmm1
+       vcvtdq2pd zmm5, zmm3
+       vdivpd   zmm1, zmm4, zmm5
+       vcvttpd2dq zmm1, zmm1
+       vpmovdw  ymm1, ymm1
+       vextracti128 xmm0, ymm0
+       vpmovsxwd ymm0, ymm0
+       vextracti128 xmm2, ymm2
+       vpmovsxwd ymm2, ymm2
+       vxorpd   ymm3, ymm3, ymm3
+       vpcmpeqd ymm3, ymm3, ymm2
+       vptest   ymm3, ymm3
+       jne      SHORT G_M1062_IG04
+       vpcmpeqd ymm3, ymm0, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm4, ymm2, ymmword ptr [reloc @RWD00]
+       vpand    ymm3, ymm3, ymm4
+       vptest   ymm3, ymm3
+       jne      SHORT G_M1062_IG05
+       vcvtdq2pd zmm3, zmm0
+       vcvtdq2pd zmm4, zmm2
+       vdivpd   zmm0, zmm3, zmm4
+       vcvttpd2dq zmm0, zmm0
+       vpmovdw  ymm0, ymm0
+       vinserti128 ymm0, ymm1, xmm0
        vmovups  ymmword ptr [rdi], ymm0
        mov      rax, rdi
-						;; size=12 bbWeight=1 PerfScore 6.25
-G_M1062_IG05:
+						;; size=211 bbWeight=1 PerfScore 107.08
+G_M1062_IG03:
        vzeroupper 
-       add      rsp, 80
-       pop      rbp
+       add      rsp, 8
        ret      
-						;; size=9 bbWeight=1 PerfScore 2.75
+						;; size=8 bbWeight=1 PerfScore 2.25
+G_M1062_IG04:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M1062_IG05:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
+RWD32  	dq	8000000080000000h, 8000000080000000h, 8000000080000000h, 8000000080000000h
 
-; Total bytes of code 84, prolog size 10, PerfScore 282.50, instruction count 25, allocated bytes for code 84 (MethodHash=7880fbd9) for method System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
+
+; Total bytes of code 238, prolog size 1, PerfScore 114.33, instruction count 49, allocated bytes for code 238 (MethodHash=7880fbd9) for method System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
 ; ============================================================

154 (183.33 % of base) - System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector,T>.Divide(System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short]

 ; Assembly listing for method System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 2 single block inlinees; 2 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T03] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T05] (  1,  1   )  simd32  ->  [rbp+0x10]  single-def <System.Numerics.Vector`1[short]>
-;  V02 arg1         [V02,T04] (  3,  3   )   short  ->  rsi         single-def
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T03] (  2,  2   )  simd32  ->  mm0         single-def <System.Numerics.Vector`1[short]>
+;  V02 arg1         [V02,T01] (  3,  3   )   short  ->  rsi         single-def
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;  V04 tmp1         [V04    ] (  2,  9   )  simd32  ->  [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Numerics.Vector`1[short]>
-;  V05 tmp2         [V05,T00] (  5, 33   )     int  ->  rcx         "Inline stloc first use temp"
-;  V06 tmp3         [V06    ] (  2, 18   )  simd32  ->  [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[short]>
-;* V07 tmp4         [V07    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;* V08 tmp5         [V08    ] (  0,  0   )   short  ->  zero-ref    "Inline return value spill temp"
-;* V09 tmp6         [V09    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V10 cse0         [V10,T02] (  2,  9   )     int  ->  rsi         hoist "CSE #01: aggressive"
-;  V11 cse1         [V11,T01] (  3, 24   )    long  ->   r8         "CSE #02: aggressive"
+;  V04 tmp1         [V04,T02] (  3,  6   )  simd32  ->  mm2         "fgMakeTemp is creating a new local variable"
 ;
-; Lcl frame size = 80
+; Lcl frame size = 8
 
 G_M19273_IG01:
-       push     rbp
-       sub      rsp, 80
-       lea      rbp, [rsp+0x50]
-						;; size=10 bbWeight=1 PerfScore 1.75
+       push     rax
+       vmovups  ymm0, ymmword ptr [rsp+0x10]
+						;; size=7 bbWeight=1 PerfScore 5.00
 G_M19273_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+0x10]
-       vmovups  ymmword ptr [rbp-0x50], ymm0
-       xor      ecx, ecx
-       movsx    rsi, si
-       align    [6 bytes for IG03]
-						;; size=22 bbWeight=1 PerfScore 5.75
-G_M19273_IG03:
-       lea      rax, [rbp-0x50]
-       movsxd   r8, ecx
-       movsx    rax, word  ptr [rax+2*r8]
-       cdq      
-       idiv     edx:eax, esi
-       lea      rdx, [rbp-0x30]
-       mov      word  ptr [rdx+2*r8], ax
-       inc      ecx
-       cmp      ecx, 16
-       jl       SHORT G_M19273_IG03
-						;; size=31 bbWeight=8 PerfScore 266.00
-G_M19273_IG04:
-       vmovups  ymm0, ymmword ptr [rbp-0x30]
+       vmovaps  ymm1, ymm0
+       vpmovsxwd ymm1, ymm1
+       vpbroadcastw ymm2, esi
+       vmovaps  ymm3, ymm2
+       vpmovsxwd ymm3, ymm3
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm3
+       vptest   ymm4, ymm4
+       jne      G_M19273_IG04
+       vpcmpeqd ymm4, ymm1, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm5, ymm3, ymmword ptr [reloc @RWD00]
+       vpand    ymm4, ymm4, ymm5
+       vptest   ymm4, ymm4
+       jne      G_M19273_IG05
+       vcvtdq2pd zmm4, zmm1
+       vcvtdq2pd zmm5, zmm3
+       vdivpd   zmm1, zmm4, zmm5
+       vcvttpd2dq zmm1, zmm1
+       vpmovdw  ymm1, ymm1
+       vextracti128 xmm0, ymm0
+       vpmovsxwd ymm0, ymm0
+       vextracti128 xmm2, ymm2
+       vpmovsxwd ymm2, ymm2
+       vxorpd   ymm3, ymm3, ymm3
+       vpcmpeqd ymm3, ymm3, ymm2
+       vptest   ymm3, ymm3
+       jne      SHORT G_M19273_IG04
+       vpcmpeqd ymm3, ymm0, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm4, ymm2, ymmword ptr [reloc @RWD00]
+       vpand    ymm3, ymm3, ymm4
+       vptest   ymm3, ymm3
+       jne      SHORT G_M19273_IG05
+       vcvtdq2pd zmm3, zmm0
+       vcvtdq2pd zmm4, zmm2
+       vdivpd   zmm0, zmm3, zmm4
+       vcvttpd2dq zmm0, zmm0
+       vpmovdw  ymm0, ymm0
+       vinserti128 ymm0, ymm1, xmm0
        vmovups  ymmword ptr [rdi], ymm0
        mov      rax, rdi
-						;; size=12 bbWeight=1 PerfScore 6.25
-G_M19273_IG05:
+						;; size=211 bbWeight=1 PerfScore 107.08
+G_M19273_IG03:
        vzeroupper 
-       add      rsp, 80
-       pop      rbp
+       add      rsp, 8
        ret      
-						;; size=9 bbWeight=1 PerfScore 2.75
+						;; size=8 bbWeight=1 PerfScore 2.25
+G_M19273_IG04:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M19273_IG05:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
+RWD32  	dq	8000000080000000h, 8000000080000000h, 8000000080000000h, 8000000080000000h
 
-; Total bytes of code 84, prolog size 10, PerfScore 282.50, instruction count 25, allocated bytes for code 84 (MethodHash=cafab4b6) for method System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
+
+; Total bytes of code 238, prolog size 1, PerfScore 114.33, instruction count 49, allocated bytes for code 238 (MethodHash=cafab4b6) for method System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],short):System.Numerics.Vector`1[short] (FullOpts)
 ; ============================================================

144 (153.19 % of base) - System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short]

 ; Assembly listing for method System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 3 single block inlinees; 2 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T03] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T04] (  1,  1   )  simd32  ->  [rbp+0x10]  single-def <System.Numerics.Vector`1[short]>
-;  V02 arg1         [V02,T05] (  1,  1   )  simd32  ->  [rbp+0x30]  single-def <System.Numerics.Vector`1[short]>
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T01] (  2,  2   )  simd32  ->  mm0         single-def <System.Numerics.Vector`1[short]>
+;  V02 arg1         [V02,T02] (  2,  2   )  simd32  ->  mm1         single-def <System.Numerics.Vector`1[short]>
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;  V04 tmp1         [V04    ] (  2,  9   )  simd32  ->  [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Numerics.Vector`1[short]>
-;  V05 tmp2         [V05,T00] (  5, 33   )     int  ->  rcx         "Inline stloc first use temp"
-;  V06 tmp3         [V06    ] (  2, 18   )  simd32  ->  [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[short]>
-;  V07 tmp4         [V07    ] (  2, 18   )  simd32  ->  [rbp-0x70]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[short]>
-;* V08 tmp5         [V08    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V09 tmp6         [V09    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V10 tmp7         [V10,T02] (  2, 16   )   short  ->  rax         "Inline return value spill temp"
-;* V11 tmp8         [V11    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V12 tmp9         [V12    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V13 cse0         [V13,T01] (  4, 32   )    long  ->  rsi         "CSE #01: aggressive"
 ;
-; Lcl frame size = 112
+; Lcl frame size = 8
 
 G_M1077_IG01:
-       push     rbp
-       sub      rsp, 112
-       lea      rbp, [rsp+0x70]
-						;; size=10 bbWeight=1 PerfScore 1.75
+       push     rax
+       vmovups  ymm0, ymmword ptr [rsp+0x10]
+       vmovups  ymm1, ymmword ptr [rsp+0x30]
+						;; size=13 bbWeight=1 PerfScore 9.00
 G_M1077_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+0x10]
-       vmovups  ymmword ptr [rbp-0x50], ymm0
-       vmovups  ymm0, ymmword ptr [rbp+0x30]
-       vmovups  ymmword ptr [rbp-0x70], ymm0
-       xor      ecx, ecx
-       align    [0 bytes for IG03]
-						;; size=22 bbWeight=1 PerfScore 10.25
-G_M1077_IG03:
-       lea      rax, [rbp-0x50]
-       movsxd   rsi, ecx
-       movsx    rax, word  ptr [rax+2*rsi]
-       lea      rdx, [rbp-0x70]
-       movsx    r8, word  ptr [rdx+2*rsi]
-       cdq      
-       idiv     edx:eax, r8d
-       cwde     
-       lea      rdx, [rbp-0x30]
-       mov      word  ptr [rdx+2*rsi], ax
-       inc      ecx
-       cmp      ecx, 16
-       jl       SHORT G_M1077_IG03
-						;; size=41 bbWeight=8 PerfScore 304.00
-G_M1077_IG04:
-       vmovups  ymm0, ymmword ptr [rbp-0x30]
+       vmovaps  ymm2, ymm0
+       vpmovsxwd ymm2, ymm2
+       vmovaps  ymm3, ymm1
+       vpmovsxwd ymm3, ymm3
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm3
+       vptest   ymm4, ymm4
+       jne      G_M1077_IG04
+       vpcmpeqd ymm4, ymm2, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm5, ymm3, ymmword ptr [reloc @RWD00]
+       vpand    ymm4, ymm4, ymm5
+       vptest   ymm4, ymm4
+       jne      G_M1077_IG05
+       vcvtdq2pd zmm4, zmm2
+       vcvtdq2pd zmm5, zmm3
+       vdivpd   zmm2, zmm4, zmm5
+       vcvttpd2dq zmm2, zmm2
+       vpmovdw  ymm2, ymm2
+       vextracti128 xmm0, ymm0
+       vpmovsxwd ymm0, ymm0
+       vextracti128 xmm1, ymm1
+       vpmovsxwd ymm1, ymm1
+       vxorpd   ymm3, ymm3, ymm3
+       vpcmpeqd ymm3, ymm3, ymm1
+       vptest   ymm3, ymm3
+       jne      SHORT G_M1077_IG04
+       vpcmpeqd ymm3, ymm0, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm4, ymm1, ymmword ptr [reloc @RWD00]
+       vpand    ymm3, ymm3, ymm4
+       vptest   ymm3, ymm3
+       jne      SHORT G_M1077_IG05
+       vcvtdq2pd zmm3, zmm0
+       vcvtdq2pd zmm4, zmm1
+       vdivpd   zmm0, zmm3, zmm4
+       vcvttpd2dq zmm0, zmm0
+       vpmovdw  ymm0, ymm0
+       vinserti128 ymm0, ymm2, xmm0
        vmovups  ymmword ptr [rdi], ymm0
        mov      rax, rdi
-						;; size=12 bbWeight=1 PerfScore 6.25
-G_M1077_IG05:
+						;; size=205 bbWeight=1 PerfScore 105.08
+G_M1077_IG03:
        vzeroupper 
-       add      rsp, 112
-       pop      rbp
+       add      rsp, 8
        ret      
-						;; size=9 bbWeight=1 PerfScore 2.75
+						;; size=8 bbWeight=1 PerfScore 2.25
+G_M1077_IG04:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M1077_IG05:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
+RWD32  	dq	8000000080000000h, 8000000080000000h, 8000000080000000h, 8000000080000000h
 
-; Total bytes of code 94, prolog size 10, PerfScore 325.00, instruction count 29, allocated bytes for code 94 (MethodHash=9b01fbca) for method System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
+
+; Total bytes of code 238, prolog size 1, PerfScore 116.33, instruction count 49, allocated bytes for code 238 (MethodHash=9b01fbca) for method System.Numerics.Vector:Divide[short](System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
 ; ============================================================

144 (153.19 % of base) - System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector,T>.Divide(System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short]

 ; Assembly listing for method System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 3 single block inlinees; 2 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T03] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T04] (  1,  1   )  simd32  ->  [rbp+0x10]  single-def <System.Numerics.Vector`1[short]>
-;  V02 arg1         [V02,T05] (  1,  1   )  simd32  ->  [rbp+0x30]  single-def <System.Numerics.Vector`1[short]>
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T01] (  2,  2   )  simd32  ->  mm0         single-def <System.Numerics.Vector`1[short]>
+;  V02 arg1         [V02,T02] (  2,  2   )  simd32  ->  mm1         single-def <System.Numerics.Vector`1[short]>
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;  V04 tmp1         [V04    ] (  2,  9   )  simd32  ->  [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Numerics.Vector`1[short]>
-;  V05 tmp2         [V05,T00] (  5, 33   )     int  ->  rcx         "Inline stloc first use temp"
-;  V06 tmp3         [V06    ] (  2, 18   )  simd32  ->  [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[short]>
-;  V07 tmp4         [V07    ] (  2, 18   )  simd32  ->  [rbp-0x70]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Numerics.Vector`1[short]>
-;* V08 tmp5         [V08    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V09 tmp6         [V09    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V10 tmp7         [V10,T02] (  2, 16   )   short  ->  rax         "Inline return value spill temp"
-;* V11 tmp8         [V11    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V12 tmp9         [V12    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V13 cse0         [V13,T01] (  4, 32   )    long  ->  rsi         "CSE #01: aggressive"
 ;
-; Lcl frame size = 112
+; Lcl frame size = 8
 
 G_M4570_IG01:
-       push     rbp
-       sub      rsp, 112
-       lea      rbp, [rsp+0x70]
-						;; size=10 bbWeight=1 PerfScore 1.75
+       push     rax
+       vmovups  ymm0, ymmword ptr [rsp+0x10]
+       vmovups  ymm1, ymmword ptr [rsp+0x30]
+						;; size=13 bbWeight=1 PerfScore 9.00
 G_M4570_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+0x10]
-       vmovups  ymmword ptr [rbp-0x50], ymm0
-       vmovups  ymm0, ymmword ptr [rbp+0x30]
-       vmovups  ymmword ptr [rbp-0x70], ymm0
-       xor      ecx, ecx
-       align    [0 bytes for IG03]
-						;; size=22 bbWeight=1 PerfScore 10.25
-G_M4570_IG03:
-       lea      rax, [rbp-0x50]
-       movsxd   rsi, ecx
-       movsx    rax, word  ptr [rax+2*rsi]
-       lea      rdx, [rbp-0x70]
-       movsx    r8, word  ptr [rdx+2*rsi]
-       cdq      
-       idiv     edx:eax, r8d
-       cwde     
-       lea      rdx, [rbp-0x30]
-       mov      word  ptr [rdx+2*rsi], ax
-       inc      ecx
-       cmp      ecx, 16
-       jl       SHORT G_M4570_IG03
-						;; size=41 bbWeight=8 PerfScore 304.00
-G_M4570_IG04:
-       vmovups  ymm0, ymmword ptr [rbp-0x30]
+       vmovaps  ymm2, ymm0
+       vpmovsxwd ymm2, ymm2
+       vmovaps  ymm3, ymm1
+       vpmovsxwd ymm3, ymm3
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm3
+       vptest   ymm4, ymm4
+       jne      G_M4570_IG04
+       vpcmpeqd ymm4, ymm2, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm5, ymm3, ymmword ptr [reloc @RWD00]
+       vpand    ymm4, ymm4, ymm5
+       vptest   ymm4, ymm4
+       jne      G_M4570_IG05
+       vcvtdq2pd zmm4, zmm2
+       vcvtdq2pd zmm5, zmm3
+       vdivpd   zmm2, zmm4, zmm5
+       vcvttpd2dq zmm2, zmm2
+       vpmovdw  ymm2, ymm2
+       vextracti128 xmm0, ymm0
+       vpmovsxwd ymm0, ymm0
+       vextracti128 xmm1, ymm1
+       vpmovsxwd ymm1, ymm1
+       vxorpd   ymm3, ymm3, ymm3
+       vpcmpeqd ymm3, ymm3, ymm1
+       vptest   ymm3, ymm3
+       jne      SHORT G_M4570_IG04
+       vpcmpeqd ymm3, ymm0, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm4, ymm1, ymmword ptr [reloc @RWD00]
+       vpand    ymm3, ymm3, ymm4
+       vptest   ymm3, ymm3
+       jne      SHORT G_M4570_IG05
+       vcvtdq2pd zmm3, zmm0
+       vcvtdq2pd zmm4, zmm1
+       vdivpd   zmm0, zmm3, zmm4
+       vcvttpd2dq zmm0, zmm0
+       vpmovdw  ymm0, ymm0
+       vinserti128 ymm0, ymm2, xmm0
        vmovups  ymmword ptr [rdi], ymm0
        mov      rax, rdi
-						;; size=12 bbWeight=1 PerfScore 6.25
-G_M4570_IG05:
+						;; size=205 bbWeight=1 PerfScore 105.08
+G_M4570_IG03:
        vzeroupper 
-       add      rsp, 112
-       pop      rbp
+       add      rsp, 8
        ret      
-						;; size=9 bbWeight=1 PerfScore 2.75
+						;; size=8 bbWeight=1 PerfScore 2.25
+G_M4570_IG04:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M4570_IG05:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
+RWD32  	dq	8000000080000000h, 8000000080000000h, 8000000080000000h, 8000000080000000h
 
-; Total bytes of code 94, prolog size 10, PerfScore 325.00, instruction count 29, allocated bytes for code 94 (MethodHash=e9ebee25) for method System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
+
+; Total bytes of code 238, prolog size 1, PerfScore 116.33, instruction count 49, allocated bytes for code 238 (MethodHash=e9ebee25) for method System.Numerics.Vector`1[short]:System.Runtime.Intrinsics.ISimdVector<System.Numerics.Vector<T>,T>.Divide(System.Numerics.Vector`1[short],System.Numerics.Vector`1[short]):System.Numerics.Vector`1[short] (FullOpts)
 ; ============================================================

[MihuBot]

Top method improvements

-950 (-65.52 % of base) - 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]

 ; Assembly listing for method 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)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 42 single block inlinees; 27 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T08] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T33] (  3,  3   )  simd64  ->  mm0         single-def <System.Runtime.Intrinsics.Vector512`1[short]>
-;  V02 arg1         [V02,T34] (  3,  3   )  simd64  ->  mm1         single-def <System.Runtime.Intrinsics.Vector512`1[short]>
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T05] (  3,  3   )  simd64  ->  mm0         single-def <System.Runtime.Intrinsics.Vector512`1[short]>
+;  V02 arg1         [V02,T06] (  3,  3   )  simd64  ->  mm1         single-def <System.Runtime.Intrinsics.Vector512`1[short]>
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;* V04 tmp1         [V04    ] (  0,  0   )  simd64  ->  zero-ref    "spilled call-like call argument"
-;  V05 tmp2         [V05,T29] (  2,  4   )  simd32  ->  mm2         "impAppendStmt"
-;  V06 tmp3         [V06,T30] (  2,  4   )  simd32  ->  mm3         "spilled call-like call argument"
-;  V07 tmp4         [V07,T17] (  3,  6   )  simd32  ->  mm2         "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[short]>
-;  V08 tmp5         [V08,T18] (  3,  6   )  simd32  ->  mm3         "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[short]>
-;  V09 tmp6         [V09,T31] (  2,  4   )  simd16  ->  mm4         "impAppendStmt"
-;* V10 tmp7         [V10    ] (  0,  0   )  simd16  ->  zero-ref    "spilled call-like call argument"
-;  V11 tmp8         [V11,T19] (  3,  6   )  simd16  ->  [rbp-0x10]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;  V12 tmp9         [V12,T20] (  3,  6   )  simd16  ->  [rbp-0x20]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;* V13 tmp10        [V13    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V14 tmp11        [V14    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V15 tmp12        [V15    ] (  5,  5   )  struct ( 8) [rbp-0x28]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V16 tmp13        [V16    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V17 tmp14        [V17    ] (  5, 10   )  struct ( 8) [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V18 tmp15        [V18    ] (  5, 10   )  struct ( 8) [rbp-0x38]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V19 tmp16        [V19    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V20 tmp17        [V20    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V21 tmp18        [V21,T00] (  8,  8   )   short  ->  rcx         "Inline return value spill temp"
-;* V22 tmp19        [V22    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V23 tmp20        [V23    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V24 tmp21        [V24    ] (  5,  5   )  struct ( 8) [rbp-0x40]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V25 tmp22        [V25    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V26 tmp23        [V26    ] (  5, 10   )  struct ( 8) [rbp-0x48]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V27 tmp24        [V27    ] (  5, 10   )  struct ( 8) [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V28 tmp25        [V28    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V29 tmp26        [V29    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V30 tmp27        [V30,T01] (  8,  8   )   short  ->  rsi         "Inline return value spill temp"
-;* V31 tmp28        [V31    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V32 tmp29        [V32    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V33 tmp30        [V33,T35] (  3,  3   )  simd16  ->  [rbp-0x60]  do-not-enreg[SF] must-init ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[short]>
-;  V34 tmp31        [V34,T21] (  3,  6   )  simd16  ->  [rbp-0x70]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;  V35 tmp32        [V35,T22] (  3,  6   )  simd16  ->  [rbp-0x80]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;* V36 tmp33        [V36    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V37 tmp34        [V37    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V38 tmp35        [V38    ] (  5,  5   )  struct ( 8) [rbp-0x88]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V39 tmp36        [V39    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V40 tmp37        [V40    ] (  5, 10   )  struct ( 8) [rbp-0x90]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V41 tmp38        [V41    ] (  5, 10   )  struct ( 8) [rbp-0x98]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V42 tmp39        [V42    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V43 tmp40        [V43    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V44 tmp41        [V44,T02] (  8,  8   )   short  ->  rcx         "Inline return value spill temp"
-;* V45 tmp42        [V45    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V46 tmp43        [V46    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V47 tmp44        [V47    ] (  5,  5   )  struct ( 8) [rbp-0xA0]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V48 tmp45        [V48    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V49 tmp46        [V49    ] (  5, 10   )  struct ( 8) [rbp-0xA8]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V50 tmp47        [V50    ] (  5, 10   )  struct ( 8) [rbp-0xB0]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V51 tmp48        [V51    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V52 tmp49        [V52    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V53 tmp50        [V53,T03] (  8,  8   )   short  ->  rsi         "Inline return value spill temp"
-;* V54 tmp51        [V54    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V55 tmp52        [V55    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V56 tmp53        [V56,T36] (  3,  3   )  simd16  ->  [rbp-0xC0]  do-not-enreg[SF] must-init ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[short]>
-;* V57 tmp54        [V57    ] (  0,  0   )  simd32  ->  zero-ref    "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[short]>
-;  V58 tmp55        [V58,T23] (  3,  6   )  simd32  ->  mm3         "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[short]>
-;  V59 tmp56        [V59,T24] (  3,  6   )  simd32  ->  mm4         "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[short]>
-;  V60 tmp57        [V60,T32] (  2,  4   )  simd16  ->  mm5         "impAppendStmt"
-;* V61 tmp58        [V61    ] (  0,  0   )  simd16  ->  zero-ref    "spilled call-like call argument"
-;  V62 tmp59        [V62,T25] (  3,  6   )  simd16  ->  [rbp-0xD0]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;  V63 tmp60        [V63,T26] (  3,  6   )  simd16  ->  [rbp-0xE0]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;* V64 tmp61        [V64    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V65 tmp62        [V65    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V66 tmp63        [V66    ] (  5,  5   )  struct ( 8) [rbp-0xE8]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V67 tmp64        [V67    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V68 tmp65        [V68    ] (  5, 10   )  struct ( 8) [rbp-0xF0]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V69 tmp66        [V69    ] (  5, 10   )  struct ( 8) [rbp-0xF8]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V70 tmp67        [V70    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V71 tmp68        [V71    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V72 tmp69        [V72,T04] (  8,  8   )   short  ->  rcx         "Inline return value spill temp"
-;* V73 tmp70        [V73    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V74 tmp71        [V74    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V75 tmp72        [V75    ] (  5,  5   )  struct ( 8) [rbp-0x100]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V76 tmp73        [V76    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V77 tmp74        [V77    ] (  5, 10   )  struct ( 8) [rbp-0x108]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V78 tmp75        [V78    ] (  5, 10   )  struct ( 8) [rbp-0x110]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V79 tmp76        [V79    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V80 tmp77        [V80    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V81 tmp78        [V81,T05] (  8,  8   )   short  ->  rsi         "Inline return value spill temp"
-;* V82 tmp79        [V82    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V83 tmp80        [V83    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V84 tmp81        [V84,T37] (  3,  3   )  simd16  ->  [rbp-0x120]  do-not-enreg[SF] must-init ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[short]>
-;  V85 tmp82        [V85,T27] (  3,  6   )  simd16  ->  [rbp-0x130]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;  V86 tmp83        [V86,T28] (  3,  6   )  simd16  ->  [rbp-0x140]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;* V87 tmp84        [V87    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V88 tmp85        [V88    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V89 tmp86        [V89    ] (  5,  5   )  struct ( 8) [rbp-0x148]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V90 tmp87        [V90    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V91 tmp88        [V91    ] (  5, 10   )  struct ( 8) [rbp-0x150]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V92 tmp89        [V92    ] (  5, 10   )  struct ( 8) [rbp-0x158]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V93 tmp90        [V93    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V94 tmp91        [V94    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V95 tmp92        [V95,T06] (  8,  8   )   short  ->  rcx         "Inline return value spill temp"
-;* V96 tmp93        [V96    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V97 tmp94        [V97    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V98 tmp95        [V98    ] (  5,  5   )  struct ( 8) [rbp-0x160]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V99 tmp96        [V99    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V100 tmp97       [V100    ] (  5, 10   )  struct ( 8) [rbp-0x168]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V101 tmp98       [V101    ] (  5, 10   )  struct ( 8) [rbp-0x170]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V102 tmp99       [V102    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V103 tmp100      [V103    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V104 tmp101      [V104,T07] (  8,  8   )   short  ->  rsi         "Inline return value spill temp"
-;* V105 tmp102      [V105    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V106 tmp103      [V106    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V107 tmp104      [V107,T38] (  3,  3   )  simd16  ->  [rbp-0x180]  do-not-enreg[SF] must-init ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[short]>
-;* V108 tmp105      [V108    ] (  0,  0   )  simd32  ->  zero-ref    "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[short]>
-;* V109 tmp106      [V109    ] (  0,  0   )  simd64  ->  zero-ref    ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector512`1[short]>
-;  V110 tmp107      [V110,T09] (  2,  2   )    long  ->  rcx         single-def "field V13._00 (fldOffset=0x0)" P-INDEP
-;  V111 tmp108      [V111,T10] (  2,  2   )    long  ->  rax         single-def "field V14._00 (fldOffset=0x0)" P-INDEP
-;  V112 tmp109      [V112    ] (  5,  5   )    long  ->  [rbp-0x28]  do-not-enreg[X] addr-exposed "field V15._00 (fldOffset=0x0)" P-DEP
-;  V113 tmp110      [V113    ] (  5,  9   )    long  ->  [rbp-0x30]  do-not-enreg[X] addr-exposed "field V17._00 (fldOffset=0x0)" P-DEP
-;  V114 tmp111      [V114    ] (  5,  9   )    long  ->  [rbp-0x38]  do-not-enreg[X] addr-exposed "field V18._00 (fldOffset=0x0)" P-DEP
-;  V115 tmp112      [V115    ] (  5,  5   )    long  ->  [rbp-0x40]  do-not-enreg[X] addr-exposed "field V24._00 (fldOffset=0x0)" P-DEP
-;  V116 tmp113      [V116    ] (  5,  9   )    long  ->  [rbp-0x48]  do-not-enreg[X] addr-exposed "field V26._00 (fldOffset=0x0)" P-DEP
-;  V117 tmp114      [V117    ] (  5,  9   )    long  ->  [rbp-0x50]  do-not-enreg[X] addr-exposed "field V27._00 (fldOffset=0x0)" P-DEP
-;  V118 tmp115      [V118,T11] (  2,  2   )    long  ->  rcx         single-def "field V36._00 (fldOffset=0x0)" P-INDEP
-;  V119 tmp116      [V119,T12] (  2,  2   )    long  ->  rax         single-def "field V37._00 (fldOffset=0x0)" P-INDEP
-;  V120 tmp117      [V120    ] (  5,  5   )    long  ->  [rbp-0x88]  do-not-enreg[X] addr-exposed "field V38._00 (fldOffset=0x0)" P-DEP
-;  V121 tmp118      [V121    ] (  5,  9   )    long  ->  [rbp-0x90]  do-not-enreg[X] addr-exposed "field V40._00 (fldOffset=0x0)" P-DEP
-;  V122 tmp119      [V122    ] (  5,  9   )    long  ->  [rbp-0x98]  do-not-enreg[X] addr-exposed "field V41._00 (fldOffset=0x0)" P-DEP
-;  V123 tmp120      [V123    ] (  5,  5   )    long  ->  [rbp-0xA0]  do-not-enreg[X] addr-exposed "field V47._00 (fldOffset=0x0)" P-DEP
-;  V124 tmp121      [V124    ] (  5,  9   )    long  ->  [rbp-0xA8]  do-not-enreg[X] addr-exposed "field V49._00 (fldOffset=0x0)" P-DEP
-;  V125 tmp122      [V125    ] (  5,  9   )    long  ->  [rbp-0xB0]  do-not-enreg[X] addr-exposed "field V50._00 (fldOffset=0x0)" P-DEP
-;  V126 tmp123      [V126,T13] (  2,  2   )    long  ->  rcx         single-def "field V64._00 (fldOffset=0x0)" P-INDEP
-;  V127 tmp124      [V127,T14] (  2,  2   )    long  ->  rax         single-def "field V65._00 (fldOffset=0x0)" P-INDEP
-;  V128 tmp125      [V128    ] (  5,  5   )    long  ->  [rbp-0xE8]  do-not-enreg[X] addr-exposed "field V66._00 (fldOffset=0x0)" P-DEP
-;  V129 tmp126      [V129    ] (  5,  9   )    long  ->  [rbp-0xF0]  do-not-enreg[X] addr-exposed "field V68._00 (fldOffset=0x0)" P-DEP
-;  V130 tmp127      [V130    ] (  5,  9   )    long  ->  [rbp-0xF8]  do-not-enreg[X] addr-exposed "field V69._00 (fldOffset=0x0)" P-DEP
-;  V131 tmp128      [V131    ] (  5,  5   )    long  ->  [rbp-0x100]  do-not-enreg[X] addr-exposed "field V75._00 (fldOffset=0x0)" P-DEP
-;  V132 tmp129      [V132    ] (  5,  9   )    long  ->  [rbp-0x108]  do-not-enreg[X] addr-exposed "field V77._00 (fldOffset=0x0)" P-DEP
-;  V133 tmp130      [V133    ] (  5,  9   )    long  ->  [rbp-0x110]  do-not-enreg[X] addr-exposed "field V78._00 (fldOffset=0x0)" P-DEP
-;  V134 tmp131      [V134,T15] (  2,  2   )    long  ->  rcx         single-def "field V87._00 (fldOffset=0x0)" P-INDEP
-;  V135 tmp132      [V135,T16] (  2,  2   )    long  ->  rax         single-def "field V88._00 (fldOffset=0x0)" P-INDEP
-;  V136 tmp133      [V136    ] (  5,  5   )    long  ->  [rbp-0x148]  do-not-enreg[X] addr-exposed "field V89._00 (fldOffset=0x0)" P-DEP
-;  V137 tmp134      [V137    ] (  5,  9   )    long  ->  [rbp-0x150]  do-not-enreg[X] addr-exposed "field V91._00 (fldOffset=0x0)" P-DEP
-;  V138 tmp135      [V138    ] (  5,  9   )    long  ->  [rbp-0x158]  do-not-enreg[X] addr-exposed "field V92._00 (fldOffset=0x0)" P-DEP
-;  V139 tmp136      [V139    ] (  5,  5   )    long  ->  [rbp-0x160]  do-not-enreg[X] addr-exposed "field V98._00 (fldOffset=0x0)" P-DEP
-;  V140 tmp137      [V140    ] (  5,  9   )    long  ->  [rbp-0x168]  do-not-enreg[X] addr-exposed "field V100._00 (fldOffset=0x0)" P-DEP
-;  V141 tmp138      [V141    ] (  5,  9   )    long  ->  [rbp-0x170]  do-not-enreg[X] addr-exposed "field V101._00 (fldOffset=0x0)" P-DEP
+;  V04 tmp1         [V04,T01] (  3,  6   )  simd32  ->  mm2         "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   )  simd32  ->  mm3         "fgMakeTemp is creating a new local variable"
+;  V07 tmp4         [V07,T04] (  3,  6   )  simd32  ->  mm5         "fgMakeTemp is creating a new local variable"
 ;
-; Lcl frame size = 384
+; Lcl frame size = 0
 
 G_M59525_IG01:
        push     rbp
-       sub      rsp, 384
-       lea      rbp, [rsp+0x180]
-       vxorps   xmm8, xmm8, xmm8
-       vmovdqu32 zmmword ptr [rbp-0x180], zmm8
-       vmovdqu32 zmmword ptr [rbp-0x140], zmm8
-       vmovdqu32 zmmword ptr [rbp-0x100], zmm8
-       vmovdqu32 zmmword ptr [rbp-0xC0], zmm8
-       vmovdqu32 zmmword ptr [rbp-0x80], zmm8
-       vmovdqu  ymmword ptr [rbp-0x40], ymm8
+       mov      rbp, rsp
        vmovups  zmm0, zmmword ptr [rbp+0x10]
        vmovups  zmm1, zmmword ptr [rbp+0x50]
-						;; size=81 bbWeight=1 PerfScore 20.08
+						;; size=24 bbWeight=1 PerfScore 7.25
 G_M59525_IG02:
        vmovaps  zmm2, zmm0
-       vmovaps  zmm3, zmm1
-       vmovaps  ymm4, ymm2
-       vmovaps  xmmword ptr [rbp-0x10], xmm4
-       vmovaps  ymm4, ymm3
-       vmovaps  xmmword ptr [rbp-0x20], xmm4
-       mov      rax, qword ptr [rbp-0x10]
-       mov      qword ptr [rbp-0x30], rax
-       mov      rax, qword ptr [rbp-0x20]
-       mov      qword ptr [rbp-0x38], rax
-       movsx    rax, word  ptr [rbp-0x30]
-       movsx    rcx, word  ptr [rbp-0x38]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x28], cx
-       movsx    rax, word  ptr [rbp-0x2E]
-       movsx    rcx, word  ptr [rbp-0x36]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x26], cx
-       movsx    rax, word  ptr [rbp-0x2C]
-       movsx    rcx, word  ptr [rbp-0x34]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x24], cx
-       movsx    rax, word  ptr [rbp-0x2A]
-       movsx    rcx, word  ptr [rbp-0x32]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x22], cx
-       mov      rcx, qword ptr [rbp-0x28]
-       mov      rax, qword ptr [rbp-0x08]
-       mov      qword ptr [rbp-0x48], rax
-       mov      rax, qword ptr [rbp-0x18]
-       mov      qword ptr [rbp-0x50], rax
-       movsx    rax, word  ptr [rbp-0x48]
-       movsx    rsi, word  ptr [rbp-0x50]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x40], si
-       movsx    rax, word  ptr [rbp-0x46]
-       movsx    rsi, word  ptr [rbp-0x4E]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x3E], si
-       movsx    rax, word  ptr [rbp-0x44]
-       movsx    rsi, word  ptr [rbp-0x4C]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x3C], si
-       movsx    rax, word  ptr [rbp-0x42]
-       movsx    rsi, word  ptr [rbp-0x4A]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x3A], si
-       mov      rax, qword ptr [rbp-0x40]
-       mov      qword ptr [rbp-0x60], rcx
-						;; size=242 bbWeight=1 PerfScore 276.00
-G_M59525_IG03:
-       mov      qword ptr [rbp-0x58], rax
-       vmovaps  xmm4, xmmword ptr [rbp-0x60]
-       vextractf128 xmm2, ymm2
-       vmovaps  xmmword ptr [rbp-0x70], xmm2
-       vextractf128 xmm2, ymm3
-       vmovaps  xmmword ptr [rbp-0x80], xmm2
-       mov      rax, qword ptr [rbp-0x70]
-       mov      qword ptr [rbp-0x90], rax
-       mov      rax, qword ptr [rbp-0x80]
-       mov      qword ptr [rbp-0x98], rax
-       movsx    rax, word  ptr [rbp-0x90]
-       movsx    rcx, word  ptr [rbp-0x98]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x88], cx
-       movsx    rax, word  ptr [rbp-0x8E]
-       movsx    rcx, word  ptr [rbp-0x96]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x86], cx
-       movsx    rax, word  ptr [rbp-0x8C]
-       movsx    rcx, word  ptr [rbp-0x94]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x84], cx
-       movsx    rax, word  ptr [rbp-0x8A]
-       movsx    rcx, word  ptr [rbp-0x92]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x82], cx
-       mov      rcx, qword ptr [rbp-0x88]
-       mov      rax, qword ptr [rbp-0x68]
-       mov      qword ptr [rbp-0xA8], rax
-       mov      rax, qword ptr [rbp-0x78]
-       mov      qword ptr [rbp-0xB0], rax
-       movsx    rax, word  ptr [rbp-0xA8]
-       movsx    rsi, word  ptr [rbp-0xB0]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0xA0], si
-       movsx    rax, word  ptr [rbp-0xA6]
-       movsx    rsi, word  ptr [rbp-0xAE]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x9E], si
-       movsx    rax, word  ptr [rbp-0xA4]
-       movsx    rsi, word  ptr [rbp-0xAC]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x9C], si
-       movsx    rax, word  ptr [rbp-0xA2]
-       movsx    rsi, word  ptr [rbp-0xAA]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x9A], si
-       mov      rax, qword ptr [rbp-0xA0]
-       mov      qword ptr [rbp-0xC0], rcx
-						;; size=336 bbWeight=1 PerfScore 283.00
-G_M59525_IG04:
-       mov      qword ptr [rbp-0xB8], rax
-       vinserti32x4 ymm2, ymm4, xmmword ptr [rbp-0xC0]
-       vextractf32x8 ymm3, zmm0, 1
-       vextractf32x8 ymm4, zmm1, 1
-       vmovaps  ymm5, ymm3
-       vmovaps  xmmword ptr [rbp-0xD0], xmm5
+       vmovaps  ymm3, ymm2
+       vpmovsxwd ymm3, ymm3
+       vmovaps  zmm4, zmm1
        vmovaps  ymm5, ymm4
-       vmovaps  xmmword ptr [rbp-0xE0], xmm5
-       mov      rax, qword ptr [rbp-0xD0]
-       mov      qword ptr [rbp-0xF0], rax
-       mov      rax, qword ptr [rbp-0xE0]
-       mov      qword ptr [rbp-0xF8], rax
-       movsx    rax, word  ptr [rbp-0xF0]
-       movsx    rcx, word  ptr [rbp-0xF8]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0xE8], cx
-       movsx    rax, word  ptr [rbp-0xEE]
-       movsx    rcx, word  ptr [rbp-0xF6]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0xE6], cx
-       movsx    rax, word  ptr [rbp-0xEC]
-       movsx    rcx, word  ptr [rbp-0xF4]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0xE4], cx
-       movsx    rax, word  ptr [rbp-0xEA]
-       movsx    rcx, word  ptr [rbp-0xF2]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0xE2], cx
-       mov      rcx, qword ptr [rbp-0xE8]
-       mov      rax, qword ptr [rbp-0xC8]
-       mov      qword ptr [rbp-0x108], rax
-       mov      rax, qword ptr [rbp-0xD8]
-       mov      qword ptr [rbp-0x110], rax
-       movsx    rax, word  ptr [rbp-0x108]
-       movsx    rsi, word  ptr [rbp-0x110]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x100], si
-       movsx    rax, word  ptr [rbp-0x106]
-       movsx    rsi, word  ptr [rbp-0x10E]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0xFE], si
-       movsx    rax, word  ptr [rbp-0x104]
-       movsx    rsi, word  ptr [rbp-0x10C]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0xFC], si
-       movsx    rax, word  ptr [rbp-0x102]
-       movsx    rsi, word  ptr [rbp-0x10A]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0xFA], si
-						;; size=354 bbWeight=1 PerfScore 282.50
-G_M59525_IG05:
-       mov      rax, qword ptr [rbp-0x100]
-       mov      qword ptr [rbp-0x120], rcx
-       mov      qword ptr [rbp-0x118], rax
-       vmovaps  xmm5, xmmword ptr [rbp-0x120]
-       vextractf128 xmm3, ymm3
-       vmovaps  xmmword ptr [rbp-0x130], xmm3
-       vextractf128 xmm3, ymm4
-       vmovaps  xmmword ptr [rbp-0x140], xmm3
-       mov      rax, qword ptr [rbp-0x130]
-       mov      qword ptr [rbp-0x150], rax
-       mov      rax, qword ptr [rbp-0x140]
-       mov      qword ptr [rbp-0x158], rax
-       movsx    rax, word  ptr [rbp-0x150]
-       movsx    rcx, word  ptr [rbp-0x158]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x148], cx
-       movsx    rax, word  ptr [rbp-0x14E]
-       movsx    rcx, word  ptr [rbp-0x156]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x146], cx
-       movsx    rax, word  ptr [rbp-0x14C]
-       movsx    rcx, word  ptr [rbp-0x154]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x144], cx
-       movsx    rax, word  ptr [rbp-0x14A]
-       movsx    rcx, word  ptr [rbp-0x152]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x142], cx
-       mov      rcx, qword ptr [rbp-0x148]
-       mov      rax, qword ptr [rbp-0x128]
-       mov      qword ptr [rbp-0x168], rax
-       mov      rax, qword ptr [rbp-0x138]
-       mov      qword ptr [rbp-0x170], rax
-       movsx    rax, word  ptr [rbp-0x168]
-       movsx    rsi, word  ptr [rbp-0x170]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x160], si
-       movsx    rax, word  ptr [rbp-0x166]
-       movsx    rsi, word  ptr [rbp-0x16E]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x15E], si
-       movsx    rax, word  ptr [rbp-0x164]
-       movsx    rsi, word  ptr [rbp-0x16C]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x15C], si
-       movsx    rax, word  ptr [rbp-0x162]
-       movsx    rsi, word  ptr [rbp-0x16A]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x15A], si
-						;; size=357 bbWeight=1 PerfScore 283.00
-G_M59525_IG06:
-       mov      rax, qword ptr [rbp-0x160]
-       mov      qword ptr [rbp-0x180], rcx
-       mov      qword ptr [rbp-0x178], rax
-       vinserti32x4 ymm3, ymm5, xmmword ptr [rbp-0x180]
-       vxorps   ymm4, ymm4, ymm4
-       vinsertf32x8 zmm2, zmm4, ymm2, 0
-       vinsertf32x8 zmm2, zmm2, ymm3, 1
+       vpmovsxwd ymm5, ymm5
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      G_M59525_IG05
+       vpcmpeqd ymm6, ymm3, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm7, ymm5, ymmword ptr [reloc @RWD00]
+       vpand    ymm6, ymm6, ymm7
+       vptest   ymm6, ymm6
+       jne      G_M59525_IG06
+       vcvtdq2pd zmm6, zmm3
+       vcvtdq2pd zmm7, zmm5
+       vdivpd   zmm3, zmm6, zmm7
+       vcvttpd2dq zmm3, zmm3
+       vpmovdw  ymm3, ymm3
+       vextracti128 xmm2, ymm2
+       vpmovsxwd ymm2, ymm2
+       vextracti128 xmm4, ymm4
+       vpmovsxwd ymm4, ymm4
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      G_M59525_IG05
+       vpcmpeqd ymm5, ymm2, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm6, ymm4, ymmword ptr [reloc @RWD00]
+       vpand    ymm5, ymm5, ymm6
+       vptest   ymm5, ymm5
+       jne      G_M59525_IG06
+       vcvtdq2pd zmm5, zmm2
+       vcvtdq2pd zmm6, zmm4
+       vdivpd   zmm2, zmm5, zmm6
+       vcvttpd2dq zmm2, zmm2
+       vpmovdw  ymm2, ymm2
+       vinserti128 ymm2, ymm3, xmm2
+       vextracti32x8 ymm3, zmm0, 1
+       vmovaps  ymm4, ymm3
+       vpmovsxwd ymm4, ymm4
+       vextracti32x8 ymm5, zmm1, 1
+       vmovaps  ymm6, ymm5
+       vpmovsxwd ymm6, ymm6
+       vxorpd   ymm7, ymm7, ymm7
+       vpcmpeqd ymm7, ymm7, ymm6
+       vptest   ymm7, ymm7
+       jne      G_M59525_IG05
+       vpcmpeqd ymm7, ymm4, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm8, ymm6, ymmword ptr [reloc @RWD00]
+       vpand    ymm7, ymm7, ymm8
+       vptest   ymm7, ymm7
+       jne      G_M59525_IG06
+       vcvtdq2pd zmm7, zmm4
+       vcvtdq2pd zmm8, zmm6
+       vdivpd   zmm4, zmm7, zmm8
+       vcvttpd2dq zmm4, zmm4
+       vpmovdw  ymm4, ymm4
+       vextracti128 xmm3, ymm3
+       vpmovsxwd ymm3, ymm3
+       vextracti128 xmm5, ymm5
+       vpmovsxwd ymm5, ymm5
+						;; size=353 bbWeight=1 PerfScore 164.00
+G_M59525_IG03:
+       vxorpd   ymm6, ymm6, ymm6
+       vpcmpeqd ymm6, ymm6, ymm5
+       vptest   ymm6, ymm6
+       jne      SHORT G_M59525_IG05
+       vpcmpeqd ymm6, ymm3, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm7, ymm5, ymmword ptr [reloc @RWD00]
+       vpand    ymm6, ymm6, ymm7
+       vptest   ymm6, ymm6
+       jne      SHORT G_M59525_IG06
+       vcvtdq2pd zmm6, zmm3
+       vcvtdq2pd zmm7, zmm5
+       vdivpd   zmm3, zmm6, zmm7
+       vcvttpd2dq zmm3, zmm3
+       vpmovdw  ymm3, ymm3
+       vinserti128 ymm3, ymm4, xmm3
+       vinserti32x8 zmm2, zmm2, ymm3, 1
        vpmullw  zmm1, zmm2, zmm1
        vpsubw   zmm0, zmm0, zmm1
        vmovups  zmmword ptr [rdi], zmm0
        mov      rax, rdi
-						;; size=68 bbWeight=1 PerfScore 17.92
-G_M59525_IG07:
+						;; size=106 bbWeight=1 PerfScore 54.75
+G_M59525_IG04:
        vzeroupper 
-       add      rsp, 384
        pop      rbp
        ret      
-						;; size=12 bbWeight=1 PerfScore 2.75
+						;; size=5 bbWeight=1 PerfScore 2.50
+G_M59525_IG05:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M59525_IG06:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
+RWD32  	dq	8000000080000000h, 8000000080000000h, 8000000080000000h, 8000000080000000h
 
-; Total bytes of code 1450, prolog size 61, PerfScore 1165.25, instruction count 287, allocated bytes for code 1450 (MethodHash=dd35177a) for method 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)
+
+; Total bytes of code 500, prolog size 4, PerfScore 228.50, instruction count 94, allocated bytes for code 500 (MethodHash=dd35177a) for method 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)
 ; ============================================================

-414 (-62.92 % of base) - System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short]

 ; Assembly listing for method System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 19 single block inlinees; 13 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T04] (  4,  4   )    long  ->  rdi         single-def
-;  V01 arg0         [V01,T14] (  3,  3   )  simd32  ->  mm0         single-def <System.Runtime.Intrinsics.Vector256`1[short]>
-;  V02 arg1         [V02,T15] (  3,  3   )  simd32  ->  mm1         single-def <System.Runtime.Intrinsics.Vector256`1[short]>
+;  V00 RetBuf       [V00,T00] (  4,  4   )    long  ->  rdi         single-def
+;  V01 arg0         [V01,T01] (  3,  3   )  simd32  ->  mm0         single-def <System.Runtime.Intrinsics.Vector256`1[short]>
+;  V02 arg1         [V02,T02] (  3,  3   )  simd32  ->  mm1         single-def <System.Runtime.Intrinsics.Vector256`1[short]>
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;* V04 tmp1         [V04    ] (  0,  0   )  simd32  ->  zero-ref    "spilled call-like call argument"
-;  V05 tmp2         [V05,T13] (  2,  4   )  simd16  ->  mm2         "impAppendStmt"
-;* V06 tmp3         [V06    ] (  0,  0   )  simd16  ->  zero-ref    "spilled call-like call argument"
-;  V07 tmp4         [V07,T09] (  3,  6   )  simd16  ->  [rbp-0x10]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;  V08 tmp5         [V08,T10] (  3,  6   )  simd16  ->  [rbp-0x20]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;* V09 tmp6         [V09    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V10 tmp7         [V10    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V11 tmp8         [V11    ] (  5,  5   )  struct ( 8) [rbp-0x28]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V12 tmp9         [V12    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V13 tmp10        [V13    ] (  5, 10   )  struct ( 8) [rbp-0x30]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V14 tmp11        [V14    ] (  5, 10   )  struct ( 8) [rbp-0x38]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V15 tmp12        [V15    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V16 tmp13        [V16    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V17 tmp14        [V17,T00] (  8,  8   )   short  ->  rcx         "Inline return value spill temp"
-;* V18 tmp15        [V18    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V19 tmp16        [V19    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V20 tmp17        [V20    ] (  5,  5   )  struct ( 8) [rbp-0x40]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V21 tmp18        [V21    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V22 tmp19        [V22    ] (  5, 10   )  struct ( 8) [rbp-0x48]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V23 tmp20        [V23    ] (  5, 10   )  struct ( 8) [rbp-0x50]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V24 tmp21        [V24    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V25 tmp22        [V25    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V26 tmp23        [V26,T01] (  8,  8   )   short  ->  rsi         "Inline return value spill temp"
-;* V27 tmp24        [V27    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V28 tmp25        [V28    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V29 tmp26        [V29,T16] (  3,  3   )  simd16  ->  [rbp-0x60]  do-not-enreg[SF] must-init ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[short]>
-;  V30 tmp27        [V30,T11] (  3,  6   )  simd16  ->  [rbp-0x70]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;  V31 tmp28        [V31,T12] (  3,  6   )  simd16  ->  [rbp-0x80]  do-not-enreg[SF] "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[short]>
-;* V32 tmp29        [V32    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V33 tmp30        [V33    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V34 tmp31        [V34    ] (  5,  5   )  struct ( 8) [rbp-0x88]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V35 tmp32        [V35    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V36 tmp33        [V36    ] (  5, 10   )  struct ( 8) [rbp-0x90]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V37 tmp34        [V37    ] (  5, 10   )  struct ( 8) [rbp-0x98]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V38 tmp35        [V38    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V39 tmp36        [V39    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V40 tmp37        [V40,T02] (  8,  8   )   short  ->  rcx         "Inline return value spill temp"
-;* V41 tmp38        [V41    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V42 tmp39        [V42    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V43 tmp40        [V43    ] (  5,  5   )  struct ( 8) [rbp-0xA0]  do-not-enreg[XS] must-init addr-exposed ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V44 tmp41        [V44    ] (  0,  0   )     int  ->  zero-ref    "Inline stloc first use temp"
-;  V45 tmp42        [V45    ] (  5, 10   )  struct ( 8) [rbp-0xA8]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;  V46 tmp43        [V46    ] (  5, 10   )  struct ( 8) [rbp-0xB0]  do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg" <System.Runtime.Intrinsics.Vector64`1[short]>
-;* V47 tmp44        [V47    ] (  0,  0   )     int  ->  zero-ref    "impAppendStmt"
-;* V48 tmp45        [V48    ] (  0,  0   )   short  ->  zero-ref    "Inline stloc first use temp"
-;  V49 tmp46        [V49,T03] (  8,  8   )   short  ->  rsi         "Inline return value spill temp"
-;* V50 tmp47        [V50    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;* V51 tmp48        [V51    ] (  0,  0   )   short  ->  zero-ref    "Inlining Arg"
-;  V52 tmp49        [V52,T17] (  3,  3   )  simd16  ->  [rbp-0xC0]  do-not-enreg[SF] must-init ld-addr-op "Inline ldloca(s) first use temp" <System.Runtime.Intrinsics.Vector128`1[short]>
-;* V53 tmp50        [V53    ] (  0,  0   )  simd32  ->  zero-ref    "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[short]>
-;  V54 tmp51        [V54,T05] (  2,  2   )    long  ->  rcx         single-def "field V09._00 (fldOffset=0x0)" P-INDEP
-;  V55 tmp52        [V55,T06] (  2,  2   )    long  ->  rax         single-def "field V10._00 (fldOffset=0x0)" P-INDEP
-;  V56 tmp53        [V56    ] (  5,  5   )    long  ->  [rbp-0x28]  do-not-enreg[X] addr-exposed "field V11._00 (fldOffset=0x0)" P-DEP
-;  V57 tmp54        [V57    ] (  5,  9   )    long  ->  [rbp-0x30]  do-not-enreg[X] addr-exposed "field V13._00 (fldOffset=0x0)" P-DEP
-;  V58 tmp55        [V58    ] (  5,  9   )    long  ->  [rbp-0x38]  do-not-enreg[X] addr-exposed "field V14._00 (fldOffset=0x0)" P-DEP
-;  V59 tmp56        [V59    ] (  5,  5   )    long  ->  [rbp-0x40]  do-not-enreg[X] addr-exposed "field V20._00 (fldOffset=0x0)" P-DEP
-;  V60 tmp57        [V60    ] (  5,  9   )    long  ->  [rbp-0x48]  do-not-enreg[X] addr-exposed "field V22._00 (fldOffset=0x0)" P-DEP
-;  V61 tmp58        [V61    ] (  5,  9   )    long  ->  [rbp-0x50]  do-not-enreg[X] addr-exposed "field V23._00 (fldOffset=0x0)" P-DEP
-;  V62 tmp59        [V62,T07] (  2,  2   )    long  ->  rcx         single-def "field V32._00 (fldOffset=0x0)" P-INDEP
-;  V63 tmp60        [V63,T08] (  2,  2   )    long  ->  rax         single-def "field V33._00 (fldOffset=0x0)" P-INDEP
-;  V64 tmp61        [V64    ] (  5,  5   )    long  ->  [rbp-0x88]  do-not-enreg[X] addr-exposed "field V34._00 (fldOffset=0x0)" P-DEP
-;  V65 tmp62        [V65    ] (  5,  9   )    long  ->  [rbp-0x90]  do-not-enreg[X] addr-exposed "field V36._00 (fldOffset=0x0)" P-DEP
-;  V66 tmp63        [V66    ] (  5,  9   )    long  ->  [rbp-0x98]  do-not-enreg[X] addr-exposed "field V37._00 (fldOffset=0x0)" P-DEP
-;  V67 tmp64        [V67    ] (  5,  5   )    long  ->  [rbp-0xA0]  do-not-enreg[X] addr-exposed "field V43._00 (fldOffset=0x0)" P-DEP
-;  V68 tmp65        [V68    ] (  5,  9   )    long  ->  [rbp-0xA8]  do-not-enreg[X] addr-exposed "field V45._00 (fldOffset=0x0)" P-DEP
-;  V69 tmp66        [V69    ] (  5,  9   )    long  ->  [rbp-0xB0]  do-not-enreg[X] addr-exposed "field V46._00 (fldOffset=0x0)" P-DEP
 ;
-; Lcl frame size = 192
+; Lcl frame size = 0
 
 G_M38274_IG01:
        push     rbp
-       sub      rsp, 192
-       lea      rbp, [rsp+0xC0]
-       vxorps   xmm8, xmm8, xmm8
-       vmovdqu32 zmmword ptr [rbp-0xC0], zmm8
-       vmovdqu32 zmmword ptr [rbp-0x80], zmm8
-       vmovdqu  ymmword ptr [rbp-0x40], ymm8
+       mov      rbp, rsp
        vmovups  ymm0, ymmword ptr [rbp+0x10]
        vmovups  ymm1, ymmword ptr [rbp+0x30]
-						;; size=50 bbWeight=1 PerfScore 16.08
+						;; size=14 bbWeight=1 PerfScore 9.25
 G_M38274_IG02:
        vmovaps  ymm2, ymm0
-       vmovaps  xmmword ptr [rbp-0x10], xmm2
-       vmovaps  ymm2, ymm1
-       vmovaps  xmmword ptr [rbp-0x20], xmm2
-       mov      rax, qword ptr [rbp-0x10]
-       mov      qword ptr [rbp-0x30], rax
-       mov      rax, qword ptr [rbp-0x20]
-       mov      qword ptr [rbp-0x38], rax
-       movsx    rax, word  ptr [rbp-0x30]
-       movsx    rcx, word  ptr [rbp-0x38]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x28], cx
-       movsx    rax, word  ptr [rbp-0x2E]
-       movsx    rcx, word  ptr [rbp-0x36]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x26], cx
-       movsx    rax, word  ptr [rbp-0x2C]
-       movsx    rcx, word  ptr [rbp-0x34]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x24], cx
-       movsx    rax, word  ptr [rbp-0x2A]
-       movsx    rcx, word  ptr [rbp-0x32]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x22], cx
-       mov      rcx, qword ptr [rbp-0x28]
-       mov      rax, qword ptr [rbp-0x08]
-       mov      qword ptr [rbp-0x48], rax
-       mov      rax, qword ptr [rbp-0x18]
-       mov      qword ptr [rbp-0x50], rax
-       movsx    rax, word  ptr [rbp-0x48]
-       movsx    rsi, word  ptr [rbp-0x50]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x40], si
-       movsx    rax, word  ptr [rbp-0x46]
-       movsx    rsi, word  ptr [rbp-0x4E]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x3E], si
-       movsx    rax, word  ptr [rbp-0x44]
-       movsx    rsi, word  ptr [rbp-0x4C]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x3C], si
-       movsx    rax, word  ptr [rbp-0x42]
-       movsx    rsi, word  ptr [rbp-0x4A]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x3A], si
-       mov      rax, qword ptr [rbp-0x40]
-       mov      qword ptr [rbp-0x60], rcx
-       mov      qword ptr [rbp-0x58], rax
-       vmovaps  xmm2, xmmword ptr [rbp-0x60]
-						;; size=239 bbWeight=1 PerfScore 279.50
-G_M38274_IG03:
-       vextractf128 xmm3, ymm0
-       vmovaps  xmmword ptr [rbp-0x70], xmm3
-       vextractf128 xmm3, ymm1
-       vmovaps  xmmword ptr [rbp-0x80], xmm3
-       mov      rax, qword ptr [rbp-0x70]
-       mov      qword ptr [rbp-0x90], rax
-       mov      rax, qword ptr [rbp-0x80]
-       mov      qword ptr [rbp-0x98], rax
-       movsx    rax, word  ptr [rbp-0x90]
-       movsx    rcx, word  ptr [rbp-0x98]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x88], cx
-       movsx    rax, word  ptr [rbp-0x8E]
-       movsx    rcx, word  ptr [rbp-0x96]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x86], cx
-       movsx    rax, word  ptr [rbp-0x8C]
-       movsx    rcx, word  ptr [rbp-0x94]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x84], cx
-       movsx    rax, word  ptr [rbp-0x8A]
-       movsx    rcx, word  ptr [rbp-0x92]
-       cdq      
-       idiv     edx:eax, ecx
-       movsx    rcx, ax
-       mov      word  ptr [rbp-0x82], cx
-       mov      rcx, qword ptr [rbp-0x88]
-       mov      rax, qword ptr [rbp-0x68]
-       mov      qword ptr [rbp-0xA8], rax
-       mov      rax, qword ptr [rbp-0x78]
-       mov      qword ptr [rbp-0xB0], rax
-       movsx    rax, word  ptr [rbp-0xA8]
-       movsx    rsi, word  ptr [rbp-0xB0]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0xA0], si
-       movsx    rax, word  ptr [rbp-0xA6]
-       movsx    rsi, word  ptr [rbp-0xAE]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x9E], si
-       movsx    rax, word  ptr [rbp-0xA4]
-       movsx    rsi, word  ptr [rbp-0xAC]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x9C], si
-       movsx    rax, word  ptr [rbp-0xA2]
-       movsx    rsi, word  ptr [rbp-0xAA]
-       cdq      
-       idiv     edx:eax, esi
-       movsx    rsi, ax
-       mov      word  ptr [rbp-0x9A], si
-       mov      rax, qword ptr [rbp-0xA0]
-       mov      qword ptr [rbp-0xC0], rcx
-       mov      qword ptr [rbp-0xB8], rax
-       vinserti32x4 ymm2, ymm2, xmmword ptr [rbp-0xC0]
-						;; size=342 bbWeight=1 PerfScore 284.00
-G_M38274_IG04:
+       vpmovsxwd ymm2, ymm2
+       vmovaps  ymm3, ymm1
+       vpmovsxwd ymm3, ymm3
+       vxorpd   ymm4, ymm4, ymm4
+       vpcmpeqd ymm4, ymm4, ymm3
+       vptest   ymm4, ymm4
+       jne      G_M38274_IG04
+       vpcmpeqd ymm4, ymm2, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm5, ymm3, ymmword ptr [reloc @RWD00]
+       vpand    ymm4, ymm4, ymm5
+       vptest   ymm4, ymm4
+       jne      G_M38274_IG05
+       vcvtdq2pd zmm4, zmm2
+       vcvtdq2pd zmm5, zmm3
+       vdivpd   zmm2, zmm4, zmm5
+       vcvttpd2dq zmm2, zmm2
+       vpmovdw  ymm2, ymm2
+       vextracti128 xmm3, ymm0
+       vpmovsxwd ymm3, ymm3
+       vextracti128 xmm4, ymm1
+       vpmovsxwd ymm4, ymm4
+       vxorpd   ymm5, ymm5, ymm5
+       vpcmpeqd ymm5, ymm5, ymm4
+       vptest   ymm5, ymm5
+       jne      SHORT G_M38274_IG04
+       vpcmpeqd ymm5, ymm3, ymmword ptr [reloc @RWD32]
+       vpcmpeqd ymm6, ymm4, ymmword ptr [reloc @RWD00]
+       vpand    ymm5, ymm5, ymm6
+       vptest   ymm5, ymm5
+       jne      SHORT G_M38274_IG05
+       vcvtdq2pd zmm5, zmm3
+       vcvtdq2pd zmm6, zmm4
+       vdivpd   zmm3, zmm5, zmm6
+       vcvttpd2dq zmm3, zmm3
+       vpmovdw  ymm3, ymm3
+       vinserti128 ymm2, ymm2, xmm3
        vpmullw  ymm1, ymm2, ymm1
        vpsubw   ymm0, ymm0, ymm1
        vmovups  ymmword ptr [rdi], ymm0
        mov      rax, rdi
-						;; size=15 bbWeight=1 PerfScore 6.58
-G_M38274_IG05:
+						;; size=213 bbWeight=1 PerfScore 109.42
+G_M38274_IG03:
        vzeroupper 
-       add      rsp, 192
        pop      rbp
        ret      
-						;; size=12 bbWeight=1 PerfScore 2.75
+						;; size=5 bbWeight=1 PerfScore 2.50
+G_M38274_IG04:
+       call     CORINFO_HELP_THROWDIVZERO
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+G_M38274_IG05:
+       call     CORINFO_HELP_OVERFLOW
+       int3     
+						;; size=6 bbWeight=0 PerfScore 0.00
+RWD00  	dq	FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh, FFFFFFFFFFFFFFFFh
+RWD32  	dq	8000000080000000h, 8000000080000000h, 8000000080000000h, 8000000080000000h
 
-; Total bytes of code 658, prolog size 40, PerfScore 588.92, instruction count 147, allocated bytes for code 658 (MethodHash=b5526a7d) for method System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
+
+; Total bytes of code 244, prolog size 4, PerfScore 121.17, instruction count 52, allocated bytes for code 244 (MethodHash=b5526a7d) for method System.Numerics.Tensors.TensorPrimitives+RemainderOperator`1[short]:Invoke(System.Runtime.Intrinsics.Vector256`1[short],System.Runtime.Intrinsics.Vector256`1[short]):System.Runtime.Intrinsics.Vector256`1[short] (FullOpts)
 ; ============================================================

Larger list of diffs: https://gist.github.com/MihuBot/060916a7b108d920036e3505c797b83b

[MihuBot]

@EgorBo