[MihaZupan] JIT: Optimize const ShiftRightLogical for byte values on XArch #88

MihuBot · 2023-07-06T21:35:05Z

Build completed in 50 minutes.
dotnet/runtime#86841

CoreLib diffs

Found 2 files with textual diffs.

Summary of Code Size diffs:
(Lower is better)

Total bytes of base: 6511504
Total bytes of diff: 6508978
Total bytes of delta: -2526 (-0.04 % of base)
Total relative delta: -4.94
    diff is an improvement.
    relative diff is an improvement.


Top file improvements (bytes):
       -2526 : System.Private.CoreLib.dasm (-0.039% of base)

1 total files with Code Size differences (1 improved, 0 regressed), 0 unchanged.

Top method improvements (bytes):
        -632 (-88.889% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[byte],int):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
        -628 (-88.826% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
        -628 (-88.826% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[ubyte]:op_UnsignedRightShift(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
        -207 (-72.125% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftRightLogical(System.Runtime.Intrinsics.Vector256`1[byte],int):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
        -203 (-71.731% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftRightLogical(System.Runtime.Intrinsics.Vector256`1[ubyte],int):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
        -203 (-71.731% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[ubyte]:op_UnsignedRightShift(System.Runtime.Intrinsics.Vector256`1[ubyte],int):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
         -14 (-1.317% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IndexOfAnyVectorized(byref,byref,int,System.ReadOnlySpan`1[ushort]):int (FullOpts)
          -4 (-3.008% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IsCharBitSet(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):System.Runtime.Intrinsics.Vector128`1[ubyte] (FullOpts)
          -4 (-2.941% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IsCharBitSetAvx2(System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte]):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
          -3 (-4.918% of base) : System.Private.CoreLib.dasm - System.Buffers.IndexOfAnyAsciiSearcher:IndexOfAnyLookupCore(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):System.Runtime.Intrinsics.Vector128`1[ubyte] (FullOpts)

Top method improvements (percentages):
        -632 (-88.889% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[byte],int):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
        -628 (-88.826% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
        -628 (-88.826% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[ubyte]:op_UnsignedRightShift(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
        -207 (-72.125% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftRightLogical(System.Runtime.Intrinsics.Vector256`1[byte],int):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
        -203 (-71.731% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftRightLogical(System.Runtime.Intrinsics.Vector256`1[ubyte],int):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
        -203 (-71.731% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[ubyte]:op_UnsignedRightShift(System.Runtime.Intrinsics.Vector256`1[ubyte],int):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
          -3 (-4.918% of base) : System.Private.CoreLib.dasm - System.Buffers.IndexOfAnyAsciiSearcher:IndexOfAnyLookupCore(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):System.Runtime.Intrinsics.Vector128`1[ubyte] (FullOpts)
          -4 (-3.008% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IsCharBitSet(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):System.Runtime.Intrinsics.Vector128`1[ubyte] (FullOpts)
          -4 (-2.941% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IsCharBitSetAvx2(System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte]):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
         -14 (-1.317% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IndexOfAnyVectorized(byref,byref,int,System.ReadOnlySpan`1[ushort]):int (FullOpts)

10 total methods with Code Size differences (10 improved, 0 regressed), 52366 unchanged.

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

Frameworks diffs

Diffs

Found 265 files with textual diffs.

Summary of Code Size diffs:
(Lower is better)

Total bytes of base: 37913835
Total bytes of diff: 37913533
Total bytes of delta: -302 (-0.00 % of base)
Total relative delta: -0.91
    diff is an improvement.
    relative diff is an improvement.


Top file regressions (bytes):
        2224 : System.Security.Cryptography.dasm (0.209% of base)

Top file improvements (bytes):
       -2526 : System.Private.CoreLib.dasm (-0.039% of base)

2 total files with Code Size differences (1 improved, 1 regressed), 253 unchanged.

Top method regressions (bytes):
          58 (6.270% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.SP800108HmacCounterKdfImplementationManaged:DeriveBytesOneShot(System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName,System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[ushort],System.Span`1[ubyte]) (FullOpts)
          52 (2.683% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream+<CopyToAsyncInternal>d__56:MoveNext():this (FullOpts)
          49 (1.577% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream+<ReadAsyncCore>d__44:MoveNext():this (FullOpts)
          49 (15.457% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.DSA:HashSpanToArray(System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName):ubyte[]:this (FullOpts)
          49 (15.409% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDsa:HashSpanToArray(System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName):ubyte[]:this (FullOpts)
          49 (7.538% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixPkcs12Reader:ExtractPrivateKeys(System.ReadOnlySpan`1[ushort],System.Security.Cryptography.Asn1.Pkcs12.SafeBagAsn[],int,System.Security.Cryptography.AsymmetricAlgorithm[],System.Security.Cryptography.X509Certificates.UnixPkcs12Reader+RentedSubjectPublicKeyInfo[]):this (FullOpts)
          47 (10.330% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.CertificateRequest:NormalizeSerialNumber(System.ReadOnlySpan`1[ubyte]):System.ArraySegment`1[ubyte] (FullOpts)
          46 (8.156% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDsa:SignDataCore(System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName,int):ubyte[]:this (FullOpts)
          46 (8.679% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDsa:SignHashCore(System.ReadOnlySpan`1[ubyte],int):ubyte[]:this (FullOpts)
          46 (14.603% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RandomNumberGenerator:GetBytes(System.Span`1[ubyte]):this (FullOpts)
          46 (14.887% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RandomNumberGenerator:GetNonZeroBytes(System.Span`1[ubyte]):this (FullOpts)
          44 (3.873% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.HashAlgorithm+<ComputeHashAsyncCore>d__16:MoveNext():this (FullOpts)
          44 (5.263% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.UniversalCryptoDecryptor:UncheckedTransformFinalBlock(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte]):int:this (FullOpts)
          42 (8.714% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDsa:TryHashData(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],System.Security.Cryptography.HashAlgorithmName,byref):bool:this (FullOpts)
          42 (8.537% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryHashData(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],System.Security.Cryptography.HashAlgorithmName,byref):bool:this (FullOpts)
          41 (3.475% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.CertificateRequest:LoadSigningRequestPem(System.ReadOnlySpan`1[ushort],System.Security.Cryptography.HashAlgorithmName,int,System.Security.Cryptography.RSASignaturePadding):System.Security.Cryptography.X509Certificates.CertificateRequest (FullOpts)
          38 (1.151% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream+<WriteAsyncCore>d__53:MoveNext():this (FullOpts)
          33 (3.837% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.Rfc2898DeriveBytes:Pbkdf2Core(System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],int,System.Security.Cryptography.HashAlgorithmName) (FullOpts)
          32 (4.432% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.CertificateRevocationListBuilder:LoadPem(System.ReadOnlySpan`1[ushort],byref):System.Security.Cryptography.X509Certificates.CertificateRevocationListBuilder (FullOpts)
          32 (7.407% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.ManagedX509ExtensionProcessor:ComputeCapiSha1OfPublicKey(System.Security.Cryptography.X509Certificates.PublicKey):ubyte[]:this (FullOpts)
          31 (8.179% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream:Write(System.ReadOnlySpan`1[ubyte]):this (FullOpts)
          30 (6.993% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.SymmetricAlgorithm:DecryptCbc(System.ReadOnlySpan`1[ubyte],System.ReadOnlySpan`1[ubyte],int):ubyte[]:this (FullOpts)
          28 (6.009% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixExportProvider:EncodeKeys(System.Formats.Asn1.AsnWriter,System.Security.Cryptography.Asn1.Pkcs12.SafeBagAsn[],int):System.ArraySegment`1[ubyte] (FullOpts)
          26 (15.758% of base) : System.Security.Cryptography.dasm - System.Formats.Asn1.AsnWriterExtensions:RentAndEncode(System.Formats.Asn1.AsnWriter):System.ArraySegment`1[ubyte] (FullOpts)
          26 (4.452% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[double,System.Nullable`1[int]](double,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[double,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.538% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[int,System.Nullable`1[int]](int,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[int,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.538% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[long,System.Nullable`1[int]](long,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[long,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.530% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[short,System.Nullable`1[int]](short,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[short,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.569% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[System.__Canon,System.Nullable`1[int]](System.__Canon,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[System.__Canon,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.522% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[System.Nullable`1[int],System.Nullable`1[int]](System.Nullable`1[int],System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[System.Nullable`1[int],System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.399% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[System.Numerics.Vector`1[float],System.Nullable`1[int]](System.Numerics.Vector`1[float],System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[System.Numerics.Vector`1[float],System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.530% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[ubyte,System.Nullable`1[int]](ubyte,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[ubyte,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.569% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[double](double,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[double],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.610% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[int](int,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[int],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.610% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[long](long,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[long],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.602% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[short](short,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[short],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.635% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[System.__Canon](System.__Canon,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[System.__Canon],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.635% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[System.Nullable`1[int]](System.Nullable`1[int],System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.483% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[System.Numerics.Vector`1[float]](System.Numerics.Vector`1[float],System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[System.Numerics.Vector`1[float]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.602% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[ubyte](ubyte,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[ubyte],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.635% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSAOpenSsl:TryDecrypt(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],System.Security.Cryptography.RSAEncryptionPadding,byref):bool:this (FullOpts)
          26 (1.399% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.UniversalCryptoOneShot:OneShotDecrypt(System.Security.Cryptography.ILiteSymmetricCipher,int,System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],byref):bool (FullOpts)
          26 (1.852% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixExportProvider:EncodeAuthSafe(System.Formats.Asn1.AsnWriter,System.ReadOnlyMemory`1[ubyte],System.ReadOnlyMemory`1[ubyte],bool,System.String,System.String,System.Span`1[ubyte],System.Span`1[ubyte]):System.ArraySegment`1[ubyte] (FullOpts)
          26 (4.538% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.X500DistinguishedNameBuilder:Build():System.Security.Cryptography.X509Certificates.X500DistinguishedName:this (FullOpts)
          25 (10.373% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.HashAlgorithm:ComputeHash(System.IO.Stream):ubyte[]:this (FullOpts)
          25 (4.026% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.UniversalCryptoDecryptor:UncheckedTransformFinalBlock(ubyte[],int,int):ubyte[]:this (FullOpts)
          23 (3.680% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[double](System.ReadOnlySpan`1[ubyte],double,System.Security.Cryptography.RSA+TryFunc`1[double],bool):ubyte[]:this (FullOpts)
          23 (3.686% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[int](System.ReadOnlySpan`1[ubyte],int,System.Security.Cryptography.RSA+TryFunc`1[int],bool):ubyte[]:this (FullOpts)
          23 (3.686% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[long](System.ReadOnlySpan`1[ubyte],long,System.Security.Cryptography.RSA+TryFunc`1[long],bool):ubyte[]:this (FullOpts)
          23 (3.674% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[short](System.ReadOnlySpan`1[ubyte],short,System.Security.Cryptography.RSA+TryFunc`1[short],bool):ubyte[]:this (FullOpts)
          23 (3.710% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[System.__Canon](System.ReadOnlySpan`1[ubyte],System.__Canon,System.Security.Cryptography.RSA+TryFunc`1[System.__Canon],bool):ubyte[]:this (FullOpts)
          23 (3.668% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[System.Nullable`1[int]](System.ReadOnlySpan`1[ubyte],System.Nullable`1[int],System.Security.Cryptography.RSA+TryFunc`1[System.Nullable`1[int]],bool):ubyte[]:this (FullOpts)
          23 (3.651% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[ubyte],System.Numerics.Vector`1[float],System.Security.Cryptography.RSA+TryFunc`1[System.Numerics.Vector`1[float]],bool):ubyte[]:this (FullOpts)
          23 (3.674% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[ubyte](System.ReadOnlySpan`1[ubyte],ubyte,System.Security.Cryptography.RSA+TryFunc`1[ubyte],bool):ubyte[]:this (FullOpts)
          23 (2.205% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixExportProvider:EncodeCerts(System.Formats.Asn1.AsnWriter,System.Security.Cryptography.Asn1.Pkcs12.CertBagAsn[],System.Security.Cryptography.Asn1.AttributeAsn[],int,System.Span`1[ubyte],System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref,byref,byref):System.ArraySegment`1[ubyte] (FullOpts)
          22 (1.424% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.Asn1.Pkcs12.PfxAsn:DecryptContentInfo(System.Security.Cryptography.Asn1.Pkcs7.ContentInfoAsn,byref):System.ArraySegment`1[ubyte] (FullOpts)
          22 (0.692% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDiffieHellmanOpenSsl:DeriveSecretAgreement(System.Security.Cryptography.ECDiffieHellmanPublicKey,System.Security.Cryptography.IncrementalHash):ubyte[]:this (FullOpts)
          22 (2.072% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.HKDF:Expand(System.Security.Cryptography.HashAlgorithmName,int,System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],System.ReadOnlySpan`1[ubyte]) (FullOpts)
          22 (5.432% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.OpenSslCipherLite:Transform(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte]):int:this (FullOpts)
          22 (3.846% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.OpenSslCipherLite:TransformFinal(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte]):int:this (FullOpts)
          22 (1.220% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.Pkcs.Pkcs12Kdf:Derive(System.ReadOnlySpan`1[ushort],System.Security.Cryptography.HashAlgorithmName,int,ubyte,System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte]) (FullOpts)
          22 (5.598% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryExportSubjectPublicKeyInfo(System.Span`1[ubyte],byref):bool:this (FullOpts)
          22 (4.545% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:VerifyData(System.ReadOnlySpan`1[ubyte],System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName,System.Security.Cryptography.RSASignaturePadding):bool:this (FullOpts)
          22 (5.898% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:WritePkcs8PrivateKey():System.Formats.Asn1.AsnWriter:this (FullOpts)
          22 (4.418% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSAOpenSsl:Decrypt(ubyte[],System.Security.Cryptography.RSAEncryptionPadding):ubyte[]:this (FullOpts)
          22 (1.649% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.OpenSslX509ChainProcessor:FindChainViaAia(byref):Interop+Crypto+X509VerifyStatusCode:this (FullOpts)
          22 (2.839% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixPkcs12Reader:DecryptSafeContents(System.ReadOnlySpan`1[ushort],byref) (FullOpts)
          22 (2.249% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.X509Certificate2:CreateFromPem(System.ReadOnlySpan`1[ushort]):System.Security.Cryptography.X509Certificates.X509Certificate2 (FullOpts)
          21 (5.932% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream:CopyTo(System.IO.Stream,int):this (FullOpts)
          21 (13.462% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixPkcs12Reader:GrowIfNeeded[ubyte](byref,int) (FullOpts)
          20 (10.695% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.HashAlgorithm:HashCore(System.ReadOnlySpan`1[ubyte]):this (FullOpts)
          19 (1.551% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportPem(System.ReadOnlySpan`1[ushort],System.Security.Cryptography.PemKeyHelpers+FindImportActionFunc) (FullOpts)
          16 (2.367% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream:<WriteAsyncCore>g__TransformBlock|53_0(System.Security.Cryptography.ICryptoTransform,System.ReadOnlyMemory`1[ubyte],ubyte[],int):int (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[double](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[double],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[double]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[int](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[int],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[int]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[long](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[long],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[long]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[short](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[short],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[short]) (FullOpts)
           8 (0.881% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[System.__Canon](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[System.__Canon],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[System.__Canon]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[System.Nullable`1[int]](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[System.Nullable`1[int]]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[System.Numerics.Vector`1[float]]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[ubyte](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[ubyte]) (FullOpts)

Top method improvements (bytes):
        -632 (-88.889% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[byte],int):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
        -628 (-88.826% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
        -628 (-88.826% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[ubyte]:op_UnsignedRightShift(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
        -207 (-72.125% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftRightLogical(System.Runtime.Intrinsics.Vector256`1[byte],int):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
        -203 (-71.731% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftRightLogical(System.Runtime.Intrinsics.Vector256`1[ubyte],int):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
        -203 (-71.731% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[ubyte]:op_UnsignedRightShift(System.Runtime.Intrinsics.Vector256`1[ubyte],int):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
         -14 (-1.317% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IndexOfAnyVectorized(byref,byref,int,System.ReadOnlySpan`1[ushort]):int (FullOpts)
          -4 (-3.008% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IsCharBitSet(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):System.Runtime.Intrinsics.Vector128`1[ubyte] (FullOpts)
          -4 (-2.941% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IsCharBitSetAvx2(System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte]):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
          -3 (-4.918% of base) : System.Private.CoreLib.dasm - System.Buffers.IndexOfAnyAsciiSearcher:IndexOfAnyLookupCore(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):System.Runtime.Intrinsics.Vector128`1[ubyte] (FullOpts)

Top method regressions (percentages):
          26 (15.758% of base) : System.Security.Cryptography.dasm - System.Formats.Asn1.AsnWriterExtensions:RentAndEncode(System.Formats.Asn1.AsnWriter):System.ArraySegment`1[ubyte] (FullOpts)
          49 (15.457% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.DSA:HashSpanToArray(System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName):ubyte[]:this (FullOpts)
          49 (15.409% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDsa:HashSpanToArray(System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName):ubyte[]:this (FullOpts)
          46 (14.887% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RandomNumberGenerator:GetNonZeroBytes(System.Span`1[ubyte]):this (FullOpts)
          46 (14.603% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RandomNumberGenerator:GetBytes(System.Span`1[ubyte]):this (FullOpts)
          21 (13.462% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixPkcs12Reader:GrowIfNeeded[ubyte](byref,int) (FullOpts)
          20 (10.695% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.HashAlgorithm:HashCore(System.ReadOnlySpan`1[ubyte]):this (FullOpts)
          25 (10.373% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.HashAlgorithm:ComputeHash(System.IO.Stream):ubyte[]:this (FullOpts)
          47 (10.330% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.CertificateRequest:NormalizeSerialNumber(System.ReadOnlySpan`1[ubyte]):System.ArraySegment`1[ubyte] (FullOpts)
          42 (8.714% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDsa:TryHashData(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],System.Security.Cryptography.HashAlgorithmName,byref):bool:this (FullOpts)
          46 (8.679% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDsa:SignHashCore(System.ReadOnlySpan`1[ubyte],int):ubyte[]:this (FullOpts)
          42 (8.537% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryHashData(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],System.Security.Cryptography.HashAlgorithmName,byref):bool:this (FullOpts)
          31 (8.179% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream:Write(System.ReadOnlySpan`1[ubyte]):this (FullOpts)
          46 (8.156% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDsa:SignDataCore(System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName,int):ubyte[]:this (FullOpts)
          49 (7.538% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixPkcs12Reader:ExtractPrivateKeys(System.ReadOnlySpan`1[ushort],System.Security.Cryptography.Asn1.Pkcs12.SafeBagAsn[],int,System.Security.Cryptography.AsymmetricAlgorithm[],System.Security.Cryptography.X509Certificates.UnixPkcs12Reader+RentedSubjectPublicKeyInfo[]):this (FullOpts)
          32 (7.407% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.ManagedX509ExtensionProcessor:ComputeCapiSha1OfPublicKey(System.Security.Cryptography.X509Certificates.PublicKey):ubyte[]:this (FullOpts)
          30 (6.993% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.SymmetricAlgorithm:DecryptCbc(System.ReadOnlySpan`1[ubyte],System.ReadOnlySpan`1[ubyte],int):ubyte[]:this (FullOpts)
          58 (6.270% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.SP800108HmacCounterKdfImplementationManaged:DeriveBytesOneShot(System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName,System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[ushort],System.Span`1[ubyte]) (FullOpts)
          28 (6.009% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixExportProvider:EncodeKeys(System.Formats.Asn1.AsnWriter,System.Security.Cryptography.Asn1.Pkcs12.SafeBagAsn[],int):System.ArraySegment`1[ubyte] (FullOpts)
          21 (5.932% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream:CopyTo(System.IO.Stream,int):this (FullOpts)
          22 (5.898% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:WritePkcs8PrivateKey():System.Formats.Asn1.AsnWriter:this (FullOpts)
          22 (5.598% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryExportSubjectPublicKeyInfo(System.Span`1[ubyte],byref):bool:this (FullOpts)
          22 (5.432% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.OpenSslCipherLite:Transform(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte]):int:this (FullOpts)
          44 (5.263% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.UniversalCryptoDecryptor:UncheckedTransformFinalBlock(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte]):int:this (FullOpts)
          26 (4.635% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[System.__Canon](System.__Canon,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[System.__Canon],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.635% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[System.Nullable`1[int]](System.Nullable`1[int],System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.635% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSAOpenSsl:TryDecrypt(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],System.Security.Cryptography.RSAEncryptionPadding,byref):bool:this (FullOpts)
          26 (4.610% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[int](int,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[int],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.610% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[long](long,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[long],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.602% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[short](short,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[short],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.602% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[ubyte](ubyte,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[ubyte],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.569% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[System.__Canon,System.Nullable`1[int]](System.__Canon,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[System.__Canon,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.569% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[double](double,System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[double],System.Span`1[ushort],byref):bool (FullOpts)
          22 (4.545% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:VerifyData(System.ReadOnlySpan`1[ubyte],System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.HashAlgorithmName,System.Security.Cryptography.RSASignaturePadding):bool:this (FullOpts)
          26 (4.538% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[int,System.Nullable`1[int]](int,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[int,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.538% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[long,System.Nullable`1[int]](long,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[long,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.538% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.X500DistinguishedNameBuilder:Build():System.Security.Cryptography.X509Certificates.X500DistinguishedName:this (FullOpts)
          26 (4.530% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[short,System.Nullable`1[int]](short,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[short,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.530% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[ubyte,System.Nullable`1[int]](ubyte,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[ubyte,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.522% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[System.Nullable`1[int],System.Nullable`1[int]](System.Nullable`1[int],System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[System.Nullable`1[int],System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.483% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToPem[System.Numerics.Vector`1[float]](System.Numerics.Vector`1[float],System.String,System.Security.Cryptography.PemKeyHelpers+TryExportKeyAction`1[System.Numerics.Vector`1[float]],System.Span`1[ushort],byref):bool (FullOpts)
          26 (4.452% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[double,System.Nullable`1[int]](double,System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[double,System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          32 (4.432% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.CertificateRevocationListBuilder:LoadPem(System.ReadOnlySpan`1[ushort],byref):System.Security.Cryptography.X509Certificates.CertificateRevocationListBuilder (FullOpts)
          22 (4.418% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSAOpenSsl:Decrypt(ubyte[],System.Security.Cryptography.RSAEncryptionPadding):ubyte[]:this (FullOpts)
          26 (4.399% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:TryExportToEncryptedPem[System.Numerics.Vector`1[float],System.Nullable`1[int]](System.Numerics.Vector`1[float],System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PbeParameters,System.Security.Cryptography.PemKeyHelpers+TryExportEncryptedKeyAction`2[System.Numerics.Vector`1[float],System.Nullable`1[int]],System.Span`1[ushort],byref):bool (FullOpts)
          25 (4.026% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.UniversalCryptoDecryptor:UncheckedTransformFinalBlock(ubyte[],int,int):ubyte[]:this (FullOpts)
          44 (3.873% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.HashAlgorithm+<ComputeHashAsyncCore>d__16:MoveNext():this (FullOpts)
          22 (3.846% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.OpenSslCipherLite:TransformFinal(System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte]):int:this (FullOpts)
          33 (3.837% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.Rfc2898DeriveBytes:Pbkdf2Core(System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],int,System.Security.Cryptography.HashAlgorithmName) (FullOpts)
          23 (3.710% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[System.__Canon](System.ReadOnlySpan`1[ubyte],System.__Canon,System.Security.Cryptography.RSA+TryFunc`1[System.__Canon],bool):ubyte[]:this (FullOpts)
          23 (3.686% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[int](System.ReadOnlySpan`1[ubyte],int,System.Security.Cryptography.RSA+TryFunc`1[int],bool):ubyte[]:this (FullOpts)
          23 (3.686% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[long](System.ReadOnlySpan`1[ubyte],long,System.Security.Cryptography.RSA+TryFunc`1[long],bool):ubyte[]:this (FullOpts)
          23 (3.680% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[double](System.ReadOnlySpan`1[ubyte],double,System.Security.Cryptography.RSA+TryFunc`1[double],bool):ubyte[]:this (FullOpts)
          23 (3.674% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[short](System.ReadOnlySpan`1[ubyte],short,System.Security.Cryptography.RSA+TryFunc`1[short],bool):ubyte[]:this (FullOpts)
          23 (3.674% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[ubyte](System.ReadOnlySpan`1[ubyte],ubyte,System.Security.Cryptography.RSA+TryFunc`1[ubyte],bool):ubyte[]:this (FullOpts)
          23 (3.668% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[System.Nullable`1[int]](System.ReadOnlySpan`1[ubyte],System.Nullable`1[int],System.Security.Cryptography.RSA+TryFunc`1[System.Nullable`1[int]],bool):ubyte[]:this (FullOpts)
          23 (3.651% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.RSA:TryWithKeyBuffer[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[ubyte],System.Numerics.Vector`1[float],System.Security.Cryptography.RSA+TryFunc`1[System.Numerics.Vector`1[float]],bool):ubyte[]:this (FullOpts)
          41 (3.475% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.CertificateRequest:LoadSigningRequestPem(System.ReadOnlySpan`1[ushort],System.Security.Cryptography.HashAlgorithmName,int,System.Security.Cryptography.RSASignaturePadding):System.Security.Cryptography.X509Certificates.CertificateRequest (FullOpts)
          22 (2.839% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixPkcs12Reader:DecryptSafeContents(System.ReadOnlySpan`1[ushort],byref) (FullOpts)
          52 (2.683% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream+<CopyToAsyncInternal>d__56:MoveNext():this (FullOpts)
          16 (2.367% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream:<WriteAsyncCore>g__TransformBlock|53_0(System.Security.Cryptography.ICryptoTransform,System.ReadOnlyMemory`1[ubyte],ubyte[],int):int (FullOpts)
          22 (2.249% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.X509Certificate2:CreateFromPem(System.ReadOnlySpan`1[ushort]):System.Security.Cryptography.X509Certificates.X509Certificate2 (FullOpts)
          23 (2.205% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixExportProvider:EncodeCerts(System.Formats.Asn1.AsnWriter,System.Security.Cryptography.Asn1.Pkcs12.CertBagAsn[],System.Security.Cryptography.Asn1.AttributeAsn[],int,System.Span`1[ubyte],System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref,byref,byref):System.ArraySegment`1[ubyte] (FullOpts)
          22 (2.072% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.HKDF:Expand(System.Security.Cryptography.HashAlgorithmName,int,System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],System.ReadOnlySpan`1[ubyte]) (FullOpts)
          26 (1.852% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.UnixExportProvider:EncodeAuthSafe(System.Formats.Asn1.AsnWriter,System.ReadOnlyMemory`1[ubyte],System.ReadOnlyMemory`1[ubyte],bool,System.String,System.String,System.Span`1[ubyte],System.Span`1[ubyte]):System.ArraySegment`1[ubyte] (FullOpts)
          22 (1.649% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.X509Certificates.OpenSslX509ChainProcessor:FindChainViaAia(byref):Interop+Crypto+X509VerifyStatusCode:this (FullOpts)
          49 (1.577% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream+<ReadAsyncCore>d__44:MoveNext():this (FullOpts)
          19 (1.551% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportPem(System.ReadOnlySpan`1[ushort],System.Security.Cryptography.PemKeyHelpers+FindImportActionFunc) (FullOpts)
          22 (1.424% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.Asn1.Pkcs12.PfxAsn:DecryptContentInfo(System.Security.Cryptography.Asn1.Pkcs7.ContentInfoAsn,byref):System.ArraySegment`1[ubyte] (FullOpts)
          26 (1.399% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.UniversalCryptoOneShot:OneShotDecrypt(System.Security.Cryptography.ILiteSymmetricCipher,int,System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte],byref):bool (FullOpts)
          22 (1.220% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.Pkcs.Pkcs12Kdf:Derive(System.ReadOnlySpan`1[ushort],System.Security.Cryptography.HashAlgorithmName,int,ubyte,System.ReadOnlySpan`1[ubyte],System.Span`1[ubyte]) (FullOpts)
          38 (1.151% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.CryptoStream+<WriteAsyncCore>d__53:MoveNext():this (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[double](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[double],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[double]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[int](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[int],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[int]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[long](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[long],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[long]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[short](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[short],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[short]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[System.Nullable`1[int]](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[System.Nullable`1[int]],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[System.Nullable`1[int]]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[System.Numerics.Vector`1[float]]) (FullOpts)
           8 (0.882% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[ubyte](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[ubyte],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[ubyte]) (FullOpts)
           8 (0.881% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.PemKeyHelpers:ImportEncryptedPem[System.__Canon](System.ReadOnlySpan`1[ushort],System.ReadOnlySpan`1[System.__Canon],System.Security.Cryptography.PemKeyHelpers+ImportEncryptedKeyAction`1[System.__Canon]) (FullOpts)
          22 (0.692% of base) : System.Security.Cryptography.dasm - System.Security.Cryptography.ECDiffieHellmanOpenSsl:DeriveSecretAgreement(System.Security.Cryptography.ECDiffieHellmanPublicKey,System.Security.Cryptography.IncrementalHash):ubyte[]:this (FullOpts)

Top method improvements (percentages):
        -632 (-88.889% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[byte],int):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
        -628 (-88.826% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
        -628 (-88.826% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector512`1[ubyte]:op_UnsignedRightShift(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
        -207 (-72.125% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftRightLogical(System.Runtime.Intrinsics.Vector256`1[byte],int):System.Runtime.Intrinsics.Vector256`1[byte] (FullOpts)
        -203 (-71.731% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256:ShiftRightLogical(System.Runtime.Intrinsics.Vector256`1[ubyte],int):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
        -203 (-71.731% of base) : System.Private.CoreLib.dasm - System.Runtime.Intrinsics.Vector256`1[ubyte]:op_UnsignedRightShift(System.Runtime.Intrinsics.Vector256`1[ubyte],int):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
          -3 (-4.918% of base) : System.Private.CoreLib.dasm - System.Buffers.IndexOfAnyAsciiSearcher:IndexOfAnyLookupCore(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):System.Runtime.Intrinsics.Vector128`1[ubyte] (FullOpts)
          -4 (-3.008% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IsCharBitSet(System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte],System.Runtime.Intrinsics.Vector128`1[ubyte]):System.Runtime.Intrinsics.Vector128`1[ubyte] (FullOpts)
          -4 (-2.941% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IsCharBitSetAvx2(System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte],System.Runtime.Intrinsics.Vector256`1[ubyte]):System.Runtime.Intrinsics.Vector256`1[ubyte] (FullOpts)
         -14 (-1.317% of base) : System.Private.CoreLib.dasm - System.Buffers.ProbabilisticMap:IndexOfAnyVectorized(byref,byref,int,System.ReadOnlySpan`1[ushort]):int (FullOpts)

91 total methods with Code Size differences (10 improved, 81 regressed), 232852 unchanged.

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

Artifacts:

The text was updated successfully, but these errors were encountered:

MihuBot · 2023-07-06T22:25:28Z

Top method improvements

-632 (-88.889% of base) - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[byte],int):System.Runtime.Intrinsics.Vector512`1[byte]

 ; Assembly listing for method System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[byte],int):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
 ; Emitting BLENDED_CODE for X64 with AVX - Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 48 single block inlinees; 27 inlinees without PGO data
+; 0 inlinees with PGO data; 4 single block inlinees; 1 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T17] (  5,  5   )   byref  ->  rdi         single-def
+;  V00 RetBuf       [V00,T00] (  5,  5   )   byref  ->  rdi         single-def
 ;* V01 arg0         [V01    ] (  0,  0   )  struct (64) zero-ref    single-def
-;  V02 arg1         [V02,T18] (  3,  3   )     int  ->  rsi         single-def
+;  V02 arg1         [V02,T02] (  3,  3   )     int  ->  rsi         single-def
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+00H]   do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
-;  V04 tmp1         [V04,T33] (  2,  4   )  simd32  ->  mm0         "impAppendStmt"
-;  V05 tmp2         [V05,T34] (  2,  4   )  simd32  ->  mm1         "spilled call-like call argument"
-;  V06 tmp3         [V06,T27] (  3,  6   )  simd32  ->  [rbp-30H]   do-not-enreg[SF] "Inlining Arg"
-;  V07 tmp4         [V07,T35] (  2,  4   )  simd16  ->  mm0         "impAppendStmt"
-;* V08 tmp5         [V08    ] (  0,  0   )  simd16  ->  zero-ref    "spilled call-like call argument"
-;  V09 tmp6         [V09,T28] (  3,  6   )  simd16  ->  [rbp-40H]   do-not-enreg[SF] "Inlining Arg"
-;* V10 tmp7         [V10    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt"
-;* V11 tmp8         [V11    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument"
-;* V12 tmp9         [V12    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V13 tmp10        [V13    ] (  2,  5   )  struct ( 8) [rbp-48H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V14 tmp11        [V14,T01] (  6, 21   )     int  ->  rax         "Inline stloc first use temp"
-;  V15 tmp12        [V15    ] (  2, 10   )  struct ( 8) [rbp-50H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V16 tmp13        [V16    ] (  0,  0   )    byte  ->  zero-ref    "Inline stloc first use temp"
-;* V17 tmp14        [V17    ] (  0,  0   )    byte  ->  zero-ref    "Inline return value spill temp"
-;* V18 tmp15        [V18    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V19 tmp16        [V19,T09] (  2,  8   )    byte  ->  rcx         "Inline return value spill temp"
-;* V20 tmp17        [V20    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;* V21 tmp18        [V21    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V22 tmp19        [V22    ] (  2,  5   )  struct ( 8) [rbp-58H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V23 tmp20        [V23,T02] (  6, 21   )     int  ->  rcx         "Inline stloc first use temp"
-;  V24 tmp21        [V24    ] (  2, 10   )  struct ( 8) [rbp-60H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V25 tmp22        [V25    ] (  0,  0   )    byte  ->  zero-ref    "Inline stloc first use temp"
-;* V26 tmp23        [V26    ] (  0,  0   )    byte  ->  zero-ref    "Inline return value spill temp"
-;* V27 tmp24        [V27    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V28 tmp25        [V28,T10] (  2,  8   )    byte  ->  rdx         "Inline return value spill temp"
-;* V29 tmp26        [V29    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V30 tmp27        [V30,T37] (  3,  3   )  simd16  ->  [rbp-70H]   do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp"
-;  V31 tmp28        [V31,T29] (  3,  6   )  simd16  ->  [rbp-80H]   do-not-enreg[SF] "Inlining Arg"
-;* V32 tmp29        [V32    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt"
-;* V33 tmp30        [V33    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument"
-;* V34 tmp31        [V34    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V35 tmp32        [V35    ] (  2,  5   )  struct ( 8) [rbp-88H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V36 tmp33        [V36,T03] (  6, 21   )     int  ->  rax         "Inline stloc first use temp"
-;  V37 tmp34        [V37    ] (  2, 10   )  struct ( 8) [rbp-90H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V38 tmp35        [V38    ] (  0,  0   )    byte  ->  zero-ref    "Inline stloc first use temp"
-;* V39 tmp36        [V39    ] (  0,  0   )    byte  ->  zero-ref    "Inline return value spill temp"
-;* V40 tmp37        [V40    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V41 tmp38        [V41,T11] (  2,  8   )    byte  ->  rcx         "Inline return value spill temp"
-;* V42 tmp39        [V42    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;* V43 tmp40        [V43    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V44 tmp41        [V44    ] (  2,  5   )  struct ( 8) [rbp-98H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V45 tmp42        [V45,T04] (  6, 21   )     int  ->  rcx         "Inline stloc first use temp"
-;  V46 tmp43        [V46    ] (  2, 10   )  struct ( 8) [rbp-A0H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V47 tmp44        [V47    ] (  0,  0   )    byte  ->  zero-ref    "Inline stloc first use temp"
-;* V48 tmp45        [V48    ] (  0,  0   )    byte  ->  zero-ref    "Inline return value spill temp"
-;* V49 tmp46        [V49    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V50 tmp47        [V50,T12] (  2,  8   )    byte  ->  rdx         "Inline return value spill temp"
-;* V51 tmp48        [V51    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V52 tmp49        [V52,T38] (  3,  3   )  simd16  ->  [rbp-B0H]   do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp"
-;* V53 tmp50        [V53    ] (  0,  0   )  simd32  ->  zero-ref    "Inline return value spill temp"
-;* V54 tmp51        [V54    ] (  0,  0   )  simd32  ->  zero-ref    "Inline stloc first use temp"
-;  V55 tmp52        [V55,T30] (  3,  6   )  simd32  ->  [rbp-D0H]   do-not-enreg[SF] "Inlining Arg"
-;  V56 tmp53        [V56,T36] (  2,  4   )  simd16  ->  mm1         "impAppendStmt"
-;* V57 tmp54        [V57    ] (  0,  0   )  simd16  ->  zero-ref    "spilled call-like call argument"
-;  V58 tmp55        [V58,T31] (  3,  6   )  simd16  ->  [rbp-E0H]   do-not-enreg[SF] "Inlining Arg"
-;* V59 tmp56        [V59    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt"
-;* V60 tmp57        [V60    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument"
-;* V61 tmp58        [V61    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V62 tmp59        [V62    ] (  2,  5   )  struct ( 8) [rbp-E8H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V63 tmp60        [V63,T05] (  6, 21   )     int  ->  rax         "Inline stloc first use temp"
-;  V64 tmp61        [V64    ] (  2, 10   )  struct ( 8) [rbp-F0H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V65 tmp62        [V65    ] (  0,  0   )    byte  ->  zero-ref    "Inline stloc first use temp"
-;* V66 tmp63        [V66    ] (  0,  0   )    byte  ->  zero-ref    "Inline return value spill temp"
-;* V67 tmp64        [V67    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V68 tmp65        [V68,T13] (  2,  8   )    byte  ->  rcx         "Inline return value spill temp"
-;* V69 tmp66        [V69    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;* V70 tmp67        [V70    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V71 tmp68        [V71    ] (  2,  5   )  struct ( 8) [rbp-F8H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V72 tmp69        [V72,T06] (  6, 21   )     int  ->  rcx         "Inline stloc first use temp"
-;  V73 tmp70        [V73    ] (  2, 10   )  struct ( 8) [rbp-100H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V74 tmp71        [V74    ] (  0,  0   )    byte  ->  zero-ref    "Inline stloc first use temp"
-;* V75 tmp72        [V75    ] (  0,  0   )    byte  ->  zero-ref    "Inline return value spill temp"
-;* V76 tmp73        [V76    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V77 tmp74        [V77,T14] (  2,  8   )    byte  ->  rdx         "Inline return value spill temp"
-;* V78 tmp75        [V78    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V79 tmp76        [V79,T39] (  3,  3   )  simd16  ->  [rbp-110H]   do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp"
-;  V80 tmp77        [V80,T32] (  3,  6   )  simd16  ->  [rbp-120H]   do-not-enreg[SF] "Inlining Arg"
-;* V81 tmp78        [V81    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt"
-;* V82 tmp79        [V82    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument"
-;* V83 tmp80        [V83    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V84 tmp81        [V84    ] (  2,  5   )  struct ( 8) [rbp-128H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V85 tmp82        [V85,T07] (  6, 21   )     int  ->  rax         "Inline stloc first use temp"
-;  V86 tmp83        [V86    ] (  2, 10   )  struct ( 8) [rbp-130H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V87 tmp84        [V87    ] (  0,  0   )    byte  ->  zero-ref    "Inline stloc first use temp"
-;* V88 tmp85        [V88    ] (  0,  0   )    byte  ->  zero-ref    "Inline return value spill temp"
-;* V89 tmp86        [V89    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V90 tmp87        [V90,T15] (  2,  8   )    byte  ->  rcx         "Inline return value spill temp"
-;* V91 tmp88        [V91    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;* V92 tmp89        [V92    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V93 tmp90        [V93    ] (  2,  5   )  struct ( 8) [rbp-138H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V94 tmp91        [V94,T08] (  6, 21   )     int  ->  rcx         "Inline stloc first use temp"
-;  V95 tmp92        [V95    ] (  2, 10   )  struct ( 8) [rbp-140H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V96 tmp93        [V96    ] (  0,  0   )    byte  ->  zero-ref    "Inline stloc first use temp"
-;* V97 tmp94        [V97    ] (  0,  0   )    byte  ->  zero-ref    "Inline return value spill temp"
-;* V98 tmp95        [V98    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V99 tmp96        [V99,T16] (  2,  8   )    byte  ->  rdx         "Inline return value spill temp"
-;* V100 tmp97       [V100    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V101 tmp98       [V101,T40] (  3,  3   )  simd16  ->  [rbp-150H]   do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp"
-;* V102 tmp99       [V102    ] (  0,  0   )  simd32  ->  zero-ref    "Inline return value spill temp"
-;* V103 tmp100      [V103    ] (  0,  0   )  simd32  ->  zero-ref    "Inline stloc first use temp"
-;* V104 tmp101      [V104    ] (  0,  0   )  struct (64) zero-ref    ld-addr-op "Inline ldloca(s) first use temp"
-;  V105 tmp102      [V105,T43] (  1,  1   )  simd32  ->  [rbp+10H]   single-def "field V01._lower (fldOffset=0x0)" P-INDEP
-;  V106 tmp103      [V106,T44] (  1,  1   )  simd32  ->  [rbp+30H]   single-def "field V01._upper (fldOffset=0x20)" P-INDEP
-;  V107 tmp104      [V107,T19] (  2,  2   )    long  ->  rax         "field V10._00 (fldOffset=0x0)" P-INDEP
-;  V108 tmp105      [V108,T20] (  2,  2   )    long  ->  rcx         "field V11._00 (fldOffset=0x0)" P-INDEP
-;* V109 tmp106      [V109    ] (  0,  0   )    long  ->  zero-ref    "field V12._00 (fldOffset=0x0)" P-INDEP
-;  V110 tmp107      [V110    ] (  2,  5   )    long  ->  [rbp-48H]   do-not-enreg[X] addr-exposed "field V13._00 (fldOffset=0x0)" P-DEP
-;  V111 tmp108      [V111    ] (  2,  9   )    long  ->  [rbp-50H]   do-not-enreg[X] addr-exposed "field V15._00 (fldOffset=0x0)" P-DEP
-;* V112 tmp109      [V112    ] (  0,  0   )    long  ->  zero-ref    "field V21._00 (fldOffset=0x0)" P-INDEP
-;  V113 tmp110      [V113    ] (  2,  5   )    long  ->  [rbp-58H]   do-not-enreg[X] addr-exposed "field V22._00 (fldOffset=0x0)" P-DEP
-;  V114 tmp111      [V114    ] (  2,  9   )    long  ->  [rbp-60H]   do-not-enreg[X] addr-exposed "field V24._00 (fldOffset=0x0)" P-DEP
-;  V115 tmp112      [V115,T21] (  2,  2   )    long  ->  rax         "field V32._00 (fldOffset=0x0)" P-INDEP
-;  V116 tmp113      [V116,T22] (  2,  2   )    long  ->  rcx         "field V33._00 (fldOffset=0x0)" P-INDEP
-;* V117 tmp114      [V117    ] (  0,  0   )    long  ->  zero-ref    "field V34._00 (fldOffset=0x0)" P-INDEP
-;  V118 tmp115      [V118    ] (  2,  5   )    long  ->  [rbp-88H]   do-not-enreg[X] addr-exposed "field V35._00 (fldOffset=0x0)" P-DEP
-;  V119 tmp116      [V119    ] (  2,  9   )    long  ->  [rbp-90H]   do-not-enreg[X] addr-exposed "field V37._00 (fldOffset=0x0)" P-DEP
-;* V120 tmp117      [V120    ] (  0,  0   )    long  ->  zero-ref    "field V43._00 (fldOffset=0x0)" P-INDEP
-;  V121 tmp118      [V121    ] (  2,  5   )    long  ->  [rbp-98H]   do-not-enreg[X] addr-exposed "field V44._00 (fldOffset=0x0)" P-DEP
-;  V122 tmp119      [V122    ] (  2,  9   )    long  ->  [rbp-A0H]   do-not-enreg[X] addr-exposed "field V46._00 (fldOffset=0x0)" P-DEP
-;  V123 tmp120      [V123,T23] (  2,  2   )    long  ->  rax         "field V59._00 (fldOffset=0x0)" P-INDEP
-;  V124 tmp121      [V124,T24] (  2,  2   )    long  ->  rcx         "field V60._00 (fldOffset=0x0)" P-INDEP
-;* V125 tmp122      [V125    ] (  0,  0   )    long  ->  zero-ref    "field V61._00 (fldOffset=0x0)" P-INDEP
-;  V126 tmp123      [V126    ] (  2,  5   )    long  ->  [rbp-E8H]   do-not-enreg[X] addr-exposed "field V62._00 (fldOffset=0x0)" P-DEP
-;  V127 tmp124      [V127    ] (  2,  9   )    long  ->  [rbp-F0H]   do-not-enreg[X] addr-exposed "field V64._00 (fldOffset=0x0)" P-DEP
-;* V128 tmp125      [V128    ] (  0,  0   )    long  ->  zero-ref    "field V70._00 (fldOffset=0x0)" P-INDEP
-;  V129 tmp126      [V129    ] (  2,  5   )    long  ->  [rbp-F8H]   do-not-enreg[X] addr-exposed "field V71._00 (fldOffset=0x0)" P-DEP
-;  V130 tmp127      [V130    ] (  2,  9   )    long  ->  [rbp-100H]   do-not-enreg[X] addr-exposed "field V73._00 (fldOffset=0x0)" P-DEP
-;  V131 tmp128      [V131,T25] (  2,  2   )    long  ->  rax         "field V81._00 (fldOffset=0x0)" P-INDEP
-;  V132 tmp129      [V132,T26] (  2,  2   )    long  ->  rcx         "field V82._00 (fldOffset=0x0)" P-INDEP
-;* V133 tmp130      [V133    ] (  0,  0   )    long  ->  zero-ref    "field V83._00 (fldOffset=0x0)" P-INDEP
-;  V134 tmp131      [V134    ] (  2,  5   )    long  ->  [rbp-128H]   do-not-enreg[X] addr-exposed "field V84._00 (fldOffset=0x0)" P-DEP
-;  V135 tmp132      [V135    ] (  2,  9   )    long  ->  [rbp-130H]   do-not-enreg[X] addr-exposed "field V86._00 (fldOffset=0x0)" P-DEP
-;* V136 tmp133      [V136    ] (  0,  0   )    long  ->  zero-ref    "field V92._00 (fldOffset=0x0)" P-INDEP
-;  V137 tmp134      [V137    ] (  2,  5   )    long  ->  [rbp-138H]   do-not-enreg[X] addr-exposed "field V93._00 (fldOffset=0x0)" P-DEP
-;  V138 tmp135      [V138    ] (  2,  9   )    long  ->  [rbp-140H]   do-not-enreg[X] addr-exposed "field V95._00 (fldOffset=0x0)" P-DEP
-;  V139 tmp136      [V139,T41] (  2,  2   )  simd32  ->  mm0         "field V104._lower (fldOffset=0x0)" P-INDEP
-;  V140 tmp137      [V140,T42] (  2,  2   )  simd32  ->  mm1         "field V104._upper (fldOffset=0x20)" P-INDEP
-;  V141 cse0        [V141,T00] (  9, 33   )     int  ->  rsi         "CSE - aggressive"
+;  V04 tmp1         [V04,T01] (  3,  6   )     int  ->  rax         "fgMakeTemp is creating a new local variable"
+;  V05 tmp2         [V05,T03] (  2,  4   )     int  ->  rsi         "fgMakeTemp is creating a new local variable"
+;  V06 tmp3         [V06,T05] (  2,  4   )  simd32  ->  mm0         "Inlining Arg"
+;  V07 tmp4         [V07,T06] (  2,  4   )  simd32  ->  mm1         "Inlining Arg"
+;* V08 tmp5         [V08    ] (  0,  0   )  struct (64) zero-ref    ld-addr-op "Inline ldloca(s) first use temp"
+;  V09 tmp6         [V09,T10] (  1,  1   )  simd32  ->  [rsp+08H]   single-def "field V01._lower (fldOffset=0x0)" P-INDEP
+;  V10 tmp7         [V10,T11] (  1,  1   )  simd32  ->  [rsp+28H]   single-def "field V01._upper (fldOffset=0x20)" P-INDEP
+;  V11 tmp8         [V11,T08] (  2,  2   )  simd32  ->  mm0         "field V08._lower (fldOffset=0x0)" P-INDEP
+;  V12 tmp9         [V12,T09] (  2,  2   )  simd32  ->  mm1         "field V08._upper (fldOffset=0x20)" P-INDEP
+;  V13 cse0         [V13,T07] (  3,  3   )  simd32  ->  mm1         "CSE - aggressive"
+;  V14 cse1         [V14,T04] (  3,  3   )     int  ->  rsi         "CSE - aggressive"
 ;
-; Lcl frame size = 336
+; Lcl frame size = 0
 
 G_M22707_IG01:
-       push     rbp
-       sub      rsp, 336
        vzeroupper 
-       lea      rbp, [rsp+150H]
-						;; size=19 bbWeight=1 PerfScore 2.75
+						;; size=3 bbWeight=1 PerfScore 1.00
 G_M22707_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+10H]
-       vmovups  ymmword ptr [rbp-30H], ymm0
-       vmovups  xmm0, xmmword ptr [rbp-30H]
-       vmovaps  xmmword ptr [rbp-40H], xmm0
-       mov      rax, qword ptr [rbp-40H]
-       mov      qword ptr [rbp-50H], rax
-       xor      eax, eax
        and      esi, 7
-       align    [0 bytes for IG03]
-						;; size=33 bbWeight=1 PerfScore 11.50
-G_M22707_IG03:
-       lea      rcx, bword ptr [rbp-50H]
-       movsxd   rdx, eax
-       movzx    rcx, byte  ptr [rcx+rdx]
-       shrx     ecx, ecx, esi
-       movsx    rcx, cl
-       lea      rdx, bword ptr [rbp-48H]
-       movsxd   r8, eax
-       mov      byte  ptr [rdx+r8], cl
-       inc      eax
-       cmp      eax, 8
-       jl       SHORT G_M22707_IG03
-						;; size=38 bbWeight=4 PerfScore 27.00
-G_M22707_IG04:
-       mov      rax, qword ptr [rbp-48H]
-       mov      rcx, qword ptr [rbp-38H]
-       mov      qword ptr [rbp-60H], rcx
-       xor      ecx, ecx
-       align    [0 bytes for IG05]
-						;; size=14 bbWeight=1 PerfScore 3.25
-G_M22707_IG05:
-       lea      rdx, bword ptr [rbp-60H]
-       movsxd   r8, ecx
-       movzx    rdx, byte  ptr [rdx+r8]
-       shrx     edx, edx, esi
-       movsx    rdx, dl
-       lea      r8, bword ptr [rbp-58H]
-       movsxd   r9, ecx
-       mov      byte  ptr [r8+r9], dl
-       inc      ecx
-       cmp      ecx, 8
-       jl       SHORT G_M22707_IG05
-						;; size=39 bbWeight=4 PerfScore 27.00
-G_M22707_IG06:
-       mov      rcx, qword ptr [rbp-58H]
-       mov      qword ptr [rbp-70H], rax
-       mov      qword ptr [rbp-68H], rcx
-       vmovaps  xmm0, xmmword ptr [rbp-70H]
-       vmovups  xmm1, xmmword ptr [rbp-20H]
-       vmovaps  xmmword ptr [rbp-80H], xmm1
-       mov      rax, qword ptr [rbp-80H]
-       mov      qword ptr [rbp-90H], rax
-       xor      eax, eax
-       align    [0 bytes for IG07]
-						;; size=40 bbWeight=1 PerfScore 12.25
-G_M22707_IG07:
-       lea      rcx, bword ptr [rbp-90H]
-       movsxd   rdx, eax
-       movzx    rcx, byte  ptr [rcx+rdx]
-       shrx     ecx, ecx, esi
-       movsx    rcx, cl
-       lea      rdx, bword ptr [rbp-88H]
-       movsxd   r8, eax
-       mov      byte  ptr [rdx+r8], cl
-       inc      eax
-       cmp      eax, 8
-       jl       SHORT G_M22707_IG07
-						;; size=44 bbWeight=4 PerfScore 27.00
-G_M22707_IG08:
-       mov      rax, qword ptr [rbp-88H]
-       mov      rcx, qword ptr [rbp-78H]
-       mov      qword ptr [rbp-A0H], rcx
-       xor      ecx, ecx
-       align    [0 bytes for IG09]
-						;; size=20 bbWeight=1 PerfScore 3.25
-G_M22707_IG09:
-       lea      rdx, bword ptr [rbp-A0H]
-       movsxd   r8, ecx
-       movzx    rdx, byte  ptr [rdx+r8]
-       shrx     edx, edx, esi
-       movsx    rdx, dl
-       lea      r8, bword ptr [rbp-98H]
-       movsxd   r9, ecx
-       mov      byte  ptr [r8+r9], dl
-       inc      ecx
-       cmp      ecx, 8
-       jl       SHORT G_M22707_IG09
-						;; size=45 bbWeight=4 PerfScore 27.00
-G_M22707_IG10:
-       mov      rcx, qword ptr [rbp-98H]
-       mov      qword ptr [rbp-B0H], rax
-       mov      qword ptr [rbp-A8H], rcx
-       vinserti128 ymm0, ymm0, xmmword ptr [rbp-B0H], 1
-       vmovups  ymm1, ymmword ptr [rbp+30H]
-       vmovups  ymmword ptr [rbp-D0H], ymm1
-       vmovups  xmm1, xmmword ptr [rbp-D0H]
-       vmovaps  xmmword ptr [rbp-E0H], xmm1
-       mov      rax, qword ptr [rbp-E0H]
-       mov      qword ptr [rbp-F0H], rax
-       xor      eax, eax
-       align    [0 bytes for IG11]
-						;; size=76 bbWeight=1 PerfScore 18.25
-G_M22707_IG11:
-       lea      rcx, bword ptr [rbp-F0H]
-       movsxd   rdx, eax
-       movzx    rcx, byte  ptr [rcx+rdx]
-       shrx     ecx, ecx, esi
-       movsx    rcx, cl
-       lea      rdx, bword ptr [rbp-E8H]
-       movsxd   r8, eax
-       mov      byte  ptr [rdx+r8], cl
-       inc      eax
-       cmp      eax, 8
-       jl       SHORT G_M22707_IG11
-						;; size=44 bbWeight=4 PerfScore 27.00
-G_M22707_IG12:
-       mov      rax, qword ptr [rbp-E8H]
-       mov      rcx, qword ptr [rbp-D8H]
-       mov      qword ptr [rbp-100H], rcx
-       xor      ecx, ecx
-       align    [0 bytes for IG13]
-						;; size=23 bbWeight=1 PerfScore 3.25
-G_M22707_IG13:
-       lea      rdx, bword ptr [rbp-100H]
-       movsxd   r8, ecx
-       movzx    rdx, byte  ptr [rdx+r8]
-       shrx     edx, edx, esi
-       movsx    rdx, dl
-       lea      r8, bword ptr [rbp-F8H]
-       movsxd   r9, ecx
-       mov      byte  ptr [r8+r9], dl
-       inc      ecx
-       cmp      ecx, 8
-       jl       SHORT G_M22707_IG13
-						;; size=45 bbWeight=4 PerfScore 27.00
-G_M22707_IG14:
-       mov      rcx, qword ptr [rbp-F8H]
-       mov      qword ptr [rbp-110H], rax
-       mov      qword ptr [rbp-108H], rcx
-       vmovaps  xmm1, xmmword ptr [rbp-110H]
-       vmovups  xmm2, xmmword ptr [rbp-C0H]
-       vmovaps  xmmword ptr [rbp-120H], xmm2
-       mov      rax, qword ptr [rbp-120H]
-       mov      qword ptr [rbp-130H], rax
-       xor      eax, eax
-       align    [3 bytes for IG15]
-						;; size=64 bbWeight=1 PerfScore 12.50
-G_M22707_IG15:
-       lea      rcx, bword ptr [rbp-130H]
-       movsxd   rdx, eax
-       movzx    rcx, byte  ptr [rcx+rdx]
-       shrx     ecx, ecx, esi
-       movsx    rcx, cl
-       lea      rdx, bword ptr [rbp-128H]
-       movsxd   r8, eax
-       mov      byte  ptr [rdx+r8], cl
-       inc      eax
-       cmp      eax, 8
-       jl       SHORT G_M22707_IG15
-						;; size=44 bbWeight=4 PerfScore 27.00
-G_M22707_IG16:
-       mov      rax, qword ptr [rbp-128H]
-       mov      rcx, qword ptr [rbp-118H]
-       mov      qword ptr [rbp-140H], rcx
-       xor      ecx, ecx
-       align    [0 bytes for IG17]
-						;; size=23 bbWeight=1 PerfScore 3.25
-G_M22707_IG17:
-       lea      rdx, bword ptr [rbp-140H]
-       movsxd   r8, ecx
-       movzx    rdx, byte  ptr [rdx+r8]
-       shrx     edx, edx, esi
-       movsx    rdx, dl
-       lea      r8, bword ptr [rbp-138H]
-       movsxd   r9, ecx
-       mov      byte  ptr [r8+r9], dl
-       inc      ecx
-       cmp      ecx, 8
-       jl       SHORT G_M22707_IG17
-						;; size=45 bbWeight=4 PerfScore 27.00
-G_M22707_IG18:
-       mov      rcx, qword ptr [rbp-138H]
-       mov      qword ptr [rbp-150H], rax
-       mov      qword ptr [rbp-148H], rcx
-       vinserti128 ymm1, ymm1, xmmword ptr [rbp-150H], 1
+       mov      eax, esi
+       vmovd    xmm0, rax
+       vmovups  ymm1, ymmword ptr [rsp+08H]
+       vpsrld   ymm0, ymm1, ymm0
+       mov      ecx, 255
+       shrx     eax, ecx, eax
+       vmovd    xmm1, eax
+       vpbroadcastb ymm1, ymm1
+       vpand    ymm0, ymm0, ymm1
+       vmovd    xmm2, rsi
+       vmovups  ymm3, ymmword ptr [rsp+28H]
+       vpsrld   ymm2, ymm3, ymm2
+       vpand    ymm1, ymm2, ymm1
        vmovups  ymmword ptr [rdi], ymm0
        vmovups  ymmword ptr [rdi+20H], ymm1
        mov      rax, rdi
-						;; size=43 bbWeight=1 PerfScore 11.25
-G_M22707_IG19:
+						;; size=72 bbWeight=1 PerfScore 28.17
+G_M22707_IG03:
        vzeroupper 
-       add      rsp, 336
-       pop      rbp
        ret      
-						;; size=12 bbWeight=1 PerfScore 2.75
+						;; size=4 bbWeight=1 PerfScore 2.00
 
-; Total bytes of code 711, prolog size 19, PerfScore 371.35, instruction count 164, allocated bytes for code 711 (MethodHash=eab6a74c) for method System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[byte],int):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)
+; Total bytes of code 79, prolog size 3, PerfScore 39.07, instruction count 20, allocated bytes for code 79 (MethodHash=eab6a74c) for method System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[byte],int):System.Runtime.Intrinsics.Vector512`1[byte] (FullOpts)

-628 (-88.826% of base) - System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte]

 ; Assembly listing for method System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
 ; Emitting BLENDED_CODE for X64 with AVX - Unix
 ; FullOpts code
 ; optimized code
-; rbp based frame
-; fully interruptible
+; rsp based frame
+; partially interruptible
 ; No PGO data
-; 0 inlinees with PGO data; 48 single block inlinees; 27 inlinees without PGO data
+; 0 inlinees with PGO data; 4 single block inlinees; 1 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 RetBuf       [V00,T17] (  5,  5   )   byref  ->  rdi         single-def
+;  V00 RetBuf       [V00,T00] (  5,  5   )   byref  ->  rdi         single-def
 ;* V01 arg0         [V01    ] (  0,  0   )  struct (64) zero-ref    single-def
-;  V02 arg1         [V02,T18] (  3,  3   )     int  ->  rsi         single-def
+;  V02 arg1         [V02,T02] (  3,  3   )     int  ->  rsi         single-def
 ;# V03 OutArgs      [V03    ] (  1,  1   )  struct ( 0) [rsp+00H]   do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
-;  V04 tmp1         [V04,T33] (  2,  4   )  simd32  ->  mm0         "impAppendStmt"
-;  V05 tmp2         [V05,T34] (  2,  4   )  simd32  ->  mm1         "spilled call-like call argument"
-;  V06 tmp3         [V06,T27] (  3,  6   )  simd32  ->  [rbp-30H]   do-not-enreg[SF] "Inlining Arg"
-;  V07 tmp4         [V07,T35] (  2,  4   )  simd16  ->  mm0         "impAppendStmt"
-;* V08 tmp5         [V08    ] (  0,  0   )  simd16  ->  zero-ref    "spilled call-like call argument"
-;  V09 tmp6         [V09,T28] (  3,  6   )  simd16  ->  [rbp-40H]   do-not-enreg[SF] "Inlining Arg"
-;* V10 tmp7         [V10    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt"
-;* V11 tmp8         [V11    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument"
-;* V12 tmp9         [V12    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V13 tmp10        [V13    ] (  2,  5   )  struct ( 8) [rbp-48H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V14 tmp11        [V14,T01] (  6, 21   )     int  ->  rax         "Inline stloc first use temp"
-;  V15 tmp12        [V15    ] (  2, 10   )  struct ( 8) [rbp-50H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V16 tmp13        [V16    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V17 tmp14        [V17    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V18 tmp15        [V18    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V19 tmp16        [V19,T09] (  2,  8   )   ubyte  ->  rcx         "Inline return value spill temp"
-;* V20 tmp17        [V20    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;* V21 tmp18        [V21    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V22 tmp19        [V22    ] (  2,  5   )  struct ( 8) [rbp-58H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V23 tmp20        [V23,T02] (  6, 21   )     int  ->  rcx         "Inline stloc first use temp"
-;  V24 tmp21        [V24    ] (  2, 10   )  struct ( 8) [rbp-60H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V25 tmp22        [V25    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V26 tmp23        [V26    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V27 tmp24        [V27    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V28 tmp25        [V28,T10] (  2,  8   )   ubyte  ->  rdx         "Inline return value spill temp"
-;* V29 tmp26        [V29    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V30 tmp27        [V30,T37] (  3,  3   )  simd16  ->  [rbp-70H]   do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp"
-;  V31 tmp28        [V31,T29] (  3,  6   )  simd16  ->  [rbp-80H]   do-not-enreg[SF] "Inlining Arg"
-;* V32 tmp29        [V32    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt"
-;* V33 tmp30        [V33    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument"
-;* V34 tmp31        [V34    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V35 tmp32        [V35    ] (  2,  5   )  struct ( 8) [rbp-88H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V36 tmp33        [V36,T03] (  6, 21   )     int  ->  rax         "Inline stloc first use temp"
-;  V37 tmp34        [V37    ] (  2, 10   )  struct ( 8) [rbp-90H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V38 tmp35        [V38    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V39 tmp36        [V39    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V40 tmp37        [V40    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V41 tmp38        [V41,T11] (  2,  8   )   ubyte  ->  rcx         "Inline return value spill temp"
-;* V42 tmp39        [V42    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;* V43 tmp40        [V43    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V44 tmp41        [V44    ] (  2,  5   )  struct ( 8) [rbp-98H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V45 tmp42        [V45,T04] (  6, 21   )     int  ->  rcx         "Inline stloc first use temp"
-;  V46 tmp43        [V46    ] (  2, 10   )  struct ( 8) [rbp-A0H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V47 tmp44        [V47    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V48 tmp45        [V48    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V49 tmp46        [V49    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V50 tmp47        [V50,T12] (  2,  8   )   ubyte  ->  rdx         "Inline return value spill temp"
-;* V51 tmp48        [V51    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V52 tmp49        [V52,T38] (  3,  3   )  simd16  ->  [rbp-B0H]   do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp"
-;* V53 tmp50        [V53    ] (  0,  0   )  simd32  ->  zero-ref    "Inline return value spill temp"
-;* V54 tmp51        [V54    ] (  0,  0   )  simd32  ->  zero-ref    "Inline stloc first use temp"
-;  V55 tmp52        [V55,T30] (  3,  6   )  simd32  ->  [rbp-D0H]   do-not-enreg[SF] "Inlining Arg"
-;  V56 tmp53        [V56,T36] (  2,  4   )  simd16  ->  mm1         "impAppendStmt"
-;* V57 tmp54        [V57    ] (  0,  0   )  simd16  ->  zero-ref    "spilled call-like call argument"
-;  V58 tmp55        [V58,T31] (  3,  6   )  simd16  ->  [rbp-E0H]   do-not-enreg[SF] "Inlining Arg"
-;* V59 tmp56        [V59    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt"
-;* V60 tmp57        [V60    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument"
-;* V61 tmp58        [V61    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V62 tmp59        [V62    ] (  2,  5   )  struct ( 8) [rbp-E8H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V63 tmp60        [V63,T05] (  6, 21   )     int  ->  rax         "Inline stloc first use temp"
-;  V64 tmp61        [V64    ] (  2, 10   )  struct ( 8) [rbp-F0H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V65 tmp62        [V65    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V66 tmp63        [V66    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V67 tmp64        [V67    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V68 tmp65        [V68,T13] (  2,  8   )   ubyte  ->  rcx         "Inline return value spill temp"
-;* V69 tmp66        [V69    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;* V70 tmp67        [V70    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V71 tmp68        [V71    ] (  2,  5   )  struct ( 8) [rbp-F8H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V72 tmp69        [V72,T06] (  6, 21   )     int  ->  rcx         "Inline stloc first use temp"
-;  V73 tmp70        [V73    ] (  2, 10   )  struct ( 8) [rbp-100H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V74 tmp71        [V74    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V75 tmp72        [V75    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V76 tmp73        [V76    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V77 tmp74        [V77,T14] (  2,  8   )   ubyte  ->  rdx         "Inline return value spill temp"
-;* V78 tmp75        [V78    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V79 tmp76        [V79,T39] (  3,  3   )  simd16  ->  [rbp-110H]   do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp"
-;  V80 tmp77        [V80,T32] (  3,  6   )  simd16  ->  [rbp-120H]   do-not-enreg[SF] "Inlining Arg"
-;* V81 tmp78        [V81    ] (  0,  0   )  struct ( 8) zero-ref    "impAppendStmt"
-;* V82 tmp79        [V82    ] (  0,  0   )  struct ( 8) zero-ref    "spilled call-like call argument"
-;* V83 tmp80        [V83    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V84 tmp81        [V84    ] (  2,  5   )  struct ( 8) [rbp-128H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V85 tmp82        [V85,T07] (  6, 21   )     int  ->  rax         "Inline stloc first use temp"
-;  V86 tmp83        [V86    ] (  2, 10   )  struct ( 8) [rbp-130H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V87 tmp84        [V87    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V88 tmp85        [V88    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V89 tmp86        [V89    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V90 tmp87        [V90,T15] (  2,  8   )   ubyte  ->  rcx         "Inline return value spill temp"
-;* V91 tmp88        [V91    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;* V92 tmp89        [V92    ] (  0,  0   )  struct ( 8) zero-ref    "Inlining Arg"
-;  V93 tmp90        [V93    ] (  2,  5   )  struct ( 8) [rbp-138H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inline ldloca(s) first use temp"
-;  V94 tmp91        [V94,T08] (  6, 21   )     int  ->  rcx         "Inline stloc first use temp"
-;  V95 tmp92        [V95    ] (  2, 10   )  struct ( 8) [rbp-140H]   do-not-enreg[XS] addr-exposed ld-addr-op "Inlining Arg"
-;* V96 tmp93        [V96    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline stloc first use temp"
-;* V97 tmp94        [V97    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
-;* V98 tmp95        [V98    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V99 tmp96        [V99,T16] (  2,  8   )   ubyte  ->  rdx         "Inline return value spill temp"
-;* V100 tmp97       [V100    ] (  0,  0   )   byref  ->  zero-ref    "Inline stloc first use temp"
-;  V101 tmp98       [V101,T40] (  3,  3   )  simd16  ->  [rbp-150H]   do-not-enreg[SF] ld-addr-op "Inline ldloca(s) first use temp"
-;* V102 tmp99       [V102    ] (  0,  0   )  simd32  ->  zero-ref    "Inline return value spill temp"
-;* V103 tmp100      [V103    ] (  0,  0   )  simd32  ->  zero-ref    "Inline stloc first use temp"
-;* V104 tmp101      [V104    ] (  0,  0   )  struct (64) zero-ref    ld-addr-op "Inline ldloca(s) first use temp"
-;  V105 tmp102      [V105,T43] (  1,  1   )  simd32  ->  [rbp+10H]   single-def "field V01._lower (fldOffset=0x0)" P-INDEP
-;  V106 tmp103      [V106,T44] (  1,  1   )  simd32  ->  [rbp+30H]   single-def "field V01._upper (fldOffset=0x20)" P-INDEP
-;  V107 tmp104      [V107,T19] (  2,  2   )    long  ->  rax         "field V10._00 (fldOffset=0x0)" P-INDEP
-;  V108 tmp105      [V108,T20] (  2,  2   )    long  ->  rcx         "field V11._00 (fldOffset=0x0)" P-INDEP
-;* V109 tmp106      [V109    ] (  0,  0   )    long  ->  zero-ref    "field V12._00 (fldOffset=0x0)" P-INDEP
-;  V110 tmp107      [V110    ] (  2,  5   )    long  ->  [rbp-48H]   do-not-enreg[X] addr-exposed "field V13._00 (fldOffset=0x0)" P-DEP
-;  V111 tmp108      [V111    ] (  2,  9   )    long  ->  [rbp-50H]   do-not-enreg[X] addr-exposed "field V15._00 (fldOffset=0x0)" P-DEP
-;* V112 tmp109      [V112    ] (  0,  0   )    long  ->  zero-ref    "field V21._00 (fldOffset=0x0)" P-INDEP
-;  V113 tmp110      [V113    ] (  2,  5   )    long  ->  [rbp-58H]   do-not-enreg[X] addr-exposed "field V22._00 (fldOffset=0x0)" P-DEP
-;  V114 tmp111      [V114    ] (  2,  9   )    long  ->  [rbp-60H]   do-not-enreg[X] addr-exposed "field V24._00 (fldOffset=0x0)" P-DEP
-;  V115 tmp112      [V115,T21] (  2,  2   )    long  ->  rax         "field V32._00 (fldOffset=0x0)" P-INDEP
-;  V116 tmp113      [V116,T22] (  2,  2   )    long  ->  rcx         "field V33._00 (fldOffset=0x0)" P-INDEP
-;* V117 tmp114      [V117    ] (  0,  0   )    long  ->  zero-ref    "field V34._00 (fldOffset=0x0)" P-INDEP
-;  V118 tmp115      [V118    ] (  2,  5   )    long  ->  [rbp-88H]   do-not-enreg[X] addr-exposed "field V35._00 (fldOffset=0x0)" P-DEP
-;  V119 tmp116      [V119    ] (  2,  9   )    long  ->  [rbp-90H]   do-not-enreg[X] addr-exposed "field V37._00 (fldOffset=0x0)" P-DEP
-;* V120 tmp117      [V120    ] (  0,  0   )    long  ->  zero-ref    "field V43._00 (fldOffset=0x0)" P-INDEP
-;  V121 tmp118      [V121    ] (  2,  5   )    long  ->  [rbp-98H]   do-not-enreg[X] addr-exposed "field V44._00 (fldOffset=0x0)" P-DEP
-;  V122 tmp119      [V122    ] (  2,  9   )    long  ->  [rbp-A0H]   do-not-enreg[X] addr-exposed "field V46._00 (fldOffset=0x0)" P-DEP
-;  V123 tmp120      [V123,T23] (  2,  2   )    long  ->  rax         "field V59._00 (fldOffset=0x0)" P-INDEP
-;  V124 tmp121      [V124,T24] (  2,  2   )    long  ->  rcx         "field V60._00 (fldOffset=0x0)" P-INDEP
-;* V125 tmp122      [V125    ] (  0,  0   )    long  ->  zero-ref    "field V61._00 (fldOffset=0x0)" P-INDEP
-;  V126 tmp123      [V126    ] (  2,  5   )    long  ->  [rbp-E8H]   do-not-enreg[X] addr-exposed "field V62._00 (fldOffset=0x0)" P-DEP
-;  V127 tmp124      [V127    ] (  2,  9   )    long  ->  [rbp-F0H]   do-not-enreg[X] addr-exposed "field V64._00 (fldOffset=0x0)" P-DEP
-;* V128 tmp125      [V128    ] (  0,  0   )    long  ->  zero-ref    "field V70._00 (fldOffset=0x0)" P-INDEP
-;  V129 tmp126      [V129    ] (  2,  5   )    long  ->  [rbp-F8H]   do-not-enreg[X] addr-exposed "field V71._00 (fldOffset=0x0)" P-DEP
-;  V130 tmp127      [V130    ] (  2,  9   )    long  ->  [rbp-100H]   do-not-enreg[X] addr-exposed "field V73._00 (fldOffset=0x0)" P-DEP
-;  V131 tmp128      [V131,T25] (  2,  2   )    long  ->  rax         "field V81._00 (fldOffset=0x0)" P-INDEP
-;  V132 tmp129      [V132,T26] (  2,  2   )    long  ->  rcx         "field V82._00 (fldOffset=0x0)" P-INDEP
-;* V133 tmp130      [V133    ] (  0,  0   )    long  ->  zero-ref    "field V83._00 (fldOffset=0x0)" P-INDEP
-;  V134 tmp131      [V134    ] (  2,  5   )    long  ->  [rbp-128H]   do-not-enreg[X] addr-exposed "field V84._00 (fldOffset=0x0)" P-DEP
-;  V135 tmp132      [V135    ] (  2,  9   )    long  ->  [rbp-130H]   do-not-enreg[X] addr-exposed "field V86._00 (fldOffset=0x0)" P-DEP
-;* V136 tmp133      [V136    ] (  0,  0   )    long  ->  zero-ref    "field V92._00 (fldOffset=0x0)" P-INDEP
-;  V137 tmp134      [V137    ] (  2,  5   )    long  ->  [rbp-138H]   do-not-enreg[X] addr-exposed "field V93._00 (fldOffset=0x0)" P-DEP
-;  V138 tmp135      [V138    ] (  2,  9   )    long  ->  [rbp-140H]   do-not-enreg[X] addr-exposed "field V95._00 (fldOffset=0x0)" P-DEP
-;  V139 tmp136      [V139,T41] (  2,  2   )  simd32  ->  mm0         "field V104._lower (fldOffset=0x0)" P-INDEP
-;  V140 tmp137      [V140,T42] (  2,  2   )  simd32  ->  mm1         "field V104._upper (fldOffset=0x20)" P-INDEP
-;  V141 cse0        [V141,T00] (  9, 33   )     int  ->  rsi         "CSE - aggressive"
+;  V04 tmp1         [V04,T01] (  3,  6   )     int  ->  rax         "fgMakeTemp is creating a new local variable"
+;  V05 tmp2         [V05,T03] (  2,  4   )     int  ->  rsi         "fgMakeTemp is creating a new local variable"
+;  V06 tmp3         [V06,T05] (  2,  4   )  simd32  ->  mm0         "Inlining Arg"
+;  V07 tmp4         [V07,T06] (  2,  4   )  simd32  ->  mm1         "Inlining Arg"
+;* V08 tmp5         [V08    ] (  0,  0   )  struct (64) zero-ref    ld-addr-op "Inline ldloca(s) first use temp"
+;  V09 tmp6         [V09,T10] (  1,  1   )  simd32  ->  [rsp+08H]   single-def "field V01._lower (fldOffset=0x0)" P-INDEP
+;  V10 tmp7         [V10,T11] (  1,  1   )  simd32  ->  [rsp+28H]   single-def "field V01._upper (fldOffset=0x20)" P-INDEP
+;  V11 tmp8         [V11,T08] (  2,  2   )  simd32  ->  mm0         "field V08._lower (fldOffset=0x0)" P-INDEP
+;  V12 tmp9         [V12,T09] (  2,  2   )  simd32  ->  mm1         "field V08._upper (fldOffset=0x20)" P-INDEP
+;  V13 cse0         [V13,T07] (  3,  3   )  simd32  ->  mm1         "CSE - aggressive"
+;  V14 cse1         [V14,T04] (  3,  3   )     int  ->  rsi         "CSE - aggressive"
 ;
-; Lcl frame size = 336
+; Lcl frame size = 0
 
 G_M33171_IG01:
-       push     rbp
-       sub      rsp, 336
        vzeroupper 
-       lea      rbp, [rsp+150H]
-						;; size=19 bbWeight=1 PerfScore 2.75
+						;; size=3 bbWeight=1 PerfScore 1.00
 G_M33171_IG02:
-       vmovups  ymm0, ymmword ptr [rbp+10H]
-       vmovups  ymmword ptr [rbp-30H], ymm0
-       vmovups  xmm0, xmmword ptr [rbp-30H]
-       vmovaps  xmmword ptr [rbp-40H], xmm0
-       mov      rax, qword ptr [rbp-40H]
-       mov      qword ptr [rbp-50H], rax
-       xor      eax, eax
        and      esi, 7
-       align    [0 bytes for IG03]
-						;; size=33 bbWeight=1 PerfScore 11.50
-G_M33171_IG03:
-       lea      rcx, bword ptr [rbp-50H]
-       movsxd   rdx, eax
-       movzx    rcx, byte  ptr [rcx+rdx]
-       shrx     ecx, ecx, esi
-       movzx    rcx, cl
-       lea      rdx, bword ptr [rbp-48H]
-       movsxd   r8, eax
-       mov      byte  ptr [rdx+r8], cl
-       inc      eax
-       cmp      eax, 8
-       jl       SHORT G_M33171_IG03
-						;; size=37 bbWeight=4 PerfScore 27.00
-G_M33171_IG04:
-       mov      rax, qword ptr [rbp-48H]
-       mov      rcx, qword ptr [rbp-38H]
-       mov      qword ptr [rbp-60H], rcx
-       xor      ecx, ecx
-       align    [0 bytes for IG05]
-						;; size=14 bbWeight=1 PerfScore 3.25
-G_M33171_IG05:
-       lea      rdx, bword ptr [rbp-60H]
-       movsxd   r8, ecx
-       movzx    rdx, byte  ptr [rdx+r8]
-       shrx     edx, edx, esi
-       movzx    rdx, dl
-       lea      r8, bword ptr [rbp-58H]
-       movsxd   r9, ecx
-       mov      byte  ptr [r8+r9], dl
-       inc      ecx
-       cmp      ecx, 8
-       jl       SHORT G_M33171_IG05
-						;; size=38 bbWeight=4 PerfScore 27.00
-G_M33171_IG06:
-       mov      rcx, qword ptr [rbp-58H]
-       mov      qword ptr [rbp-70H], rax
-       mov      qword ptr [rbp-68H], rcx
-       vmovaps  xmm0, xmmword ptr [rbp-70H]
-       vmovups  xmm1, xmmword ptr [rbp-20H]
-       vmovaps  xmmword ptr [rbp-80H], xmm1
-       mov      rax, qword ptr [rbp-80H]
-       mov      qword ptr [rbp-90H], rax
-       xor      eax, eax
-       align    [0 bytes for IG07]
-						;; size=40 bbWeight=1 PerfScore 12.25
-G_M33171_IG07:
-       lea      rcx, bword ptr [rbp-90H]
-       movsxd   rdx, eax
-       movzx    rcx, byte  ptr [rcx+rdx]
-       shrx     ecx, ecx, esi
-       movzx    rcx, cl
-       lea      rdx, bword ptr [rbp-88H]
-       movsxd   r8, eax
-       mov      byte  ptr [rdx+r8], cl
-       inc      eax
-       cmp      eax, 8
-       jl       SHORT G_M33171_IG07
-						;; size=43 bbWeight=4 PerfScore 27.00
-G_M33171_IG08:
-       mov      rax, qword ptr [rbp-88H]
-       mov      rcx, qword ptr [rbp-78H]
-       mov      qword ptr [rbp-A0H], rcx
-       xor      ecx, ecx
-       align    [0 bytes for IG09]
-						;; size=20 bbWeight=1 PerfScore 3.25
-G_M33171_IG09:
-       lea      rdx, bword ptr [rbp-A0H]
-       movsxd   r8, ecx
-       movzx    rdx, byte  ptr [rdx+r8]
-       shrx     edx, edx, esi
-       movzx    rdx, dl
-       lea      r8, bword ptr [rbp-98H]
-       movsxd   r9, ecx
-       mov      byte  ptr [r8+r9], dl
-       inc      ecx
-       cmp      ecx, 8
-       jl       SHORT G_M33171_IG09
-						;; size=44 bbWeight=4 PerfScore 27.00
-G_M33171_IG10:
-       mov      rcx, qword ptr [rbp-98H]
-       mov      qword ptr [rbp-B0H], rax
-       mov      qword ptr [rbp-A8H], rcx
-       vinserti128 ymm0, ymm0, xmmword ptr [rbp-B0H], 1
-       vmovups  ymm1, ymmword ptr [rbp+30H]
-       vmovups  ymmword ptr [rbp-D0H], ymm1
-       vmovups  xmm1, xmmword ptr [rbp-D0H]
-       vmovaps  xmmword ptr [rbp-E0H], xmm1
-       mov      rax, qword ptr [rbp-E0H]
-       mov      qword ptr [rbp-F0H], rax
-       xor      eax, eax
-       align    [0 bytes for IG11]
-						;; size=76 bbWeight=1 PerfScore 18.25
-G_M33171_IG11:
-       lea      rcx, bword ptr [rbp-F0H]
-       movsxd   rdx, eax
-       movzx    rcx, byte  ptr [rcx+rdx]
-       shrx     ecx, ecx, esi
-       movzx    rcx, cl
-       lea      rdx, bword ptr [rbp-E8H]
-       movsxd   r8, eax
-       mov      byte  ptr [rdx+r8], cl
-       inc      eax
-       cmp      eax, 8
-       jl       SHORT G_M33171_IG11
-						;; size=43 bbWeight=4 PerfScore 27.00
-G_M33171_IG12:
-       mov      rax, qword ptr [rbp-E8H]
-       mov      rcx, qword ptr [rbp-D8H]
-       mov      qword ptr [rbp-100H], rcx
-       xor      ecx, ecx
-       align    [0 bytes for IG13]
-						;; size=23 bbWeight=1 PerfScore 3.25
-G_M33171_IG13:
-       lea      rdx, bword ptr [rbp-100H]
-       movsxd   r8, ecx
-       movzx    rdx, byte  ptr [rdx+r8]
-       shrx     edx, edx, esi
-       movzx    rdx, dl
-       lea      r8, bword ptr [rbp-F8H]
-       movsxd   r9, ecx
-       mov      byte  ptr [r8+r9], dl
-       inc      ecx
-       cmp      ecx, 8
-       jl       SHORT G_M33171_IG13
-						;; size=44 bbWeight=4 PerfScore 27.00
-G_M33171_IG14:
-       mov      rcx, qword ptr [rbp-F8H]
-       mov      qword ptr [rbp-110H], rax
-       mov      qword ptr [rbp-108H], rcx
-       vmovaps  xmm1, xmmword ptr [rbp-110H]
-       vmovups  xmm2, xmmword ptr [rbp-C0H]
-       vmovaps  xmmword ptr [rbp-120H], xmm2
-       mov      rax, qword ptr [rbp-120H]
-       mov      qword ptr [rbp-130H], rax
-       xor      eax, eax
-       align    [0 bytes for IG15]
-						;; size=61 bbWeight=1 PerfScore 12.25
-G_M33171_IG15:
-       lea      rcx, bword ptr [rbp-130H]
-       movsxd   rdx, eax
-       movzx    rcx, byte  ptr [rcx+rdx]
-       shrx     ecx, ecx, esi
-       movzx    rcx, cl
-       lea      rdx, bword ptr [rbp-128H]
-       movsxd   r8, eax
-       mov      byte  ptr [rdx+r8], cl
-       inc      eax
-       cmp      eax, 8
-       jl       SHORT G_M33171_IG15
-						;; size=43 bbWeight=4 PerfScore 27.00
-G_M33171_IG16:
-       mov      rax, qword ptr [rbp-128H]
-       mov      rcx, qword ptr [rbp-118H]
-       mov      qword ptr [rbp-140H], rcx
-       xor      ecx, ecx
-       align    [7 bytes for IG17]
-						;; size=30 bbWeight=1 PerfScore 3.50
-G_M33171_IG17:
-       lea      rdx, bword ptr [rbp-140H]
-       movsxd   r8, ecx
-       movzx    rdx, byte  ptr [rdx+r8]
-       shrx     edx, edx, esi
-       movzx    rdx, dl
-       lea      r8, bword ptr [rbp-138H]
-       movsxd   r9, ecx
-       mov      byte  ptr [r8+r9], dl
-       inc      ecx
-       cmp      ecx, 8
-       jl       SHORT G_M33171_IG17
-						;; size=44 bbWeight=4 PerfScore 27.00
-G_M33171_IG18:
-       mov      rcx, qword ptr [rbp-138H]
-       mov      qword ptr [rbp-150H], rax
-       mov      qword ptr [rbp-148H], rcx
-       vinserti128 ymm1, ymm1, xmmword ptr [rbp-150H], 1
+       mov      eax, esi
+       vmovd    xmm0, rax
+       vmovups  ymm1, ymmword ptr [rsp+08H]
+       vpsrld   ymm0, ymm1, ymm0
+       mov      ecx, 255
+       shrx     eax, ecx, eax
+       vmovd    xmm1, eax
+       vpbroadcastb ymm1, ymm1
+       vpand    ymm0, ymm0, ymm1
+       vmovd    xmm2, rsi
+       vmovups  ymm3, ymmword ptr [rsp+28H]
+       vpsrld   ymm2, ymm3, ymm2
+       vpand    ymm1, ymm2, ymm1
        vmovups  ymmword ptr [rdi], ymm0
        vmovups  ymmword ptr [rdi+20H], ymm1
        mov      rax, rdi
-						;; size=43 bbWeight=1 PerfScore 11.25
-G_M33171_IG19:
+						;; size=72 bbWeight=1 PerfScore 28.17
+G_M33171_IG03:
        vzeroupper 
-       add      rsp, 336
-       pop      rbp
        ret      
-						;; size=12 bbWeight=1 PerfScore 2.75
+						;; size=4 bbWeight=1 PerfScore 2.00
 
-; Total bytes of code 707, prolog size 19, PerfScore 370.95, instruction count 164, allocated bytes for code 707 (MethodHash=ecb57e6c) for method System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)
+; Total bytes of code 79, prolog size 3, PerfScore 39.07, instruction count 20, allocated bytes for code 79 (MethodHash=ecb57e6c) for method System.Runtime.Intrinsics.Vector512:ShiftRightLogical(System.Runtime.Intrinsics.Vector512`1[ubyte],int):System.Runtime.Intrinsics.Vector512`1[ubyte] (FullOpts)

Full list of diffs: https://gist.github.com/MihuBot/678ae8aad2b3f5827a506ad588309da0

MihaZupan closed this as completed Jul 6, 2023

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[MihaZupan] JIT: Optimize const ShiftRightLogical for byte values on XArch #88

[MihaZupan] JIT: Optimize const ShiftRightLogical for byte values on XArch #88

MihuBot commented Jul 6, 2023 •

edited

Loading

MihuBot commented Jul 6, 2023

[MihaZupan] JIT: Optimize const ShiftRightLogical for byte values on XArch #88

[MihaZupan] JIT: Optimize const ShiftRightLogical for byte values on XArch #88

Comments

MihuBot commented Jul 6, 2023 • edited Loading

CoreLib diffs

Frameworks diffs

MihuBot commented Jul 6, 2023

Top method improvements

MihuBot commented Jul 6, 2023 •

edited

Loading