[JitDiff X64] xtqqczze/dotnet-runtime/SliceLongerSpanToMatchShorterLength

[MihuBot]

Job completed in 16 minutes 30 seconds (remote runner delay: 29 seconds).
https://github.com/xtqqczze/dotnet-runtime/tree/SliceLongerSpanToMatchShorterLength

Diffs

Found 82 files with textual diffs.

Summary of Code Size diffs:
(Lower is better)

Total bytes of base: 46024855
Total bytes of diff: 46024016
Total bytes of delta: -839 (-0.00 % of base)
Total relative delta: -3.29
    diff is an improvement.
    relative diff is an improvement.


Top file improvements (bytes):
        -839 : System.Private.CoreLib.dasm (-0.01 % of base)

1 total files with Code Size differences (1 improved, 0 regressed), 259 unchanged.

Top method improvements (bytes):
        -143 (-42.31 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon]):int (FullOpts)
        -101 (-26.58 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon],System.Collections.Generic.IEqualityComparer`1[System.__Canon]):int (FullOpts)
         -67 (-18.31 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]):int (FullOpts)
         -66 (-38.37 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.Nullable`1[int]](System.ReadOnlySpan`1[System.Nullable`1[int]],System.ReadOnlySpan`1[System.Nullable`1[int]]):int (FullOpts)
         -62 (-35.43 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]):int (FullOpts)
         -58 (-17.68 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[double](System.ReadOnlySpan`1[double],System.ReadOnlySpan`1[double],System.Collections.Generic.IEqualityComparer`1[double]):int (FullOpts)
         -56 (-17.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[short](System.ReadOnlySpan`1[short],System.ReadOnlySpan`1[short],System.Collections.Generic.IEqualityComparer`1[short]):int (FullOpts)
         -55 (-17.08 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[byte](System.ReadOnlySpan`1[byte],System.ReadOnlySpan`1[byte],System.Collections.Generic.IEqualityComparer`1[byte]):int (FullOpts)
         -54 (-16.88 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[int](System.ReadOnlySpan`1[int],System.ReadOnlySpan`1[int],System.Collections.Generic.IEqualityComparer`1[int]):int (FullOpts)
         -54 (-16.88 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[long](System.ReadOnlySpan`1[long],System.ReadOnlySpan`1[long],System.Collections.Generic.IEqualityComparer`1[long]):int (FullOpts)
         -54 (-16.88 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.Nullable`1[int]](System.ReadOnlySpan`1[System.Nullable`1[int]],System.ReadOnlySpan`1[System.Nullable`1[int]],System.Collections.Generic.IEqualityComparer`1[System.Nullable`1[int]]):int (FullOpts)
         -53 (-39.55 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[double](System.ReadOnlySpan`1[double],System.ReadOnlySpan`1[double]):int (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[byte](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[double](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[int](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[long](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[short](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[System.__Canon](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[System.Nullable`1[int]](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[System.Numerics.Vector`1[float]](byref,byref) (FullOpts)

Top method improvements (percentages):
        -143 (-42.31 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon]):int (FullOpts)
         -53 (-39.55 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[double](System.ReadOnlySpan`1[double],System.ReadOnlySpan`1[double]):int (FullOpts)
         -66 (-38.37 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.Nullable`1[int]](System.ReadOnlySpan`1[System.Nullable`1[int]],System.ReadOnlySpan`1[System.Nullable`1[int]]):int (FullOpts)
         -62 (-35.43 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]):int (FullOpts)
        -101 (-26.58 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon],System.Collections.Generic.IEqualityComparer`1[System.__Canon]):int (FullOpts)
         -67 (-18.31 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]):int (FullOpts)
         -58 (-17.68 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[double](System.ReadOnlySpan`1[double],System.ReadOnlySpan`1[double],System.Collections.Generic.IEqualityComparer`1[double]):int (FullOpts)
         -56 (-17.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[short](System.ReadOnlySpan`1[short],System.ReadOnlySpan`1[short],System.Collections.Generic.IEqualityComparer`1[short]):int (FullOpts)
         -55 (-17.08 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[byte](System.ReadOnlySpan`1[byte],System.ReadOnlySpan`1[byte],System.Collections.Generic.IEqualityComparer`1[byte]):int (FullOpts)
         -54 (-16.88 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[int](System.ReadOnlySpan`1[int],System.ReadOnlySpan`1[int],System.Collections.Generic.IEqualityComparer`1[int]):int (FullOpts)
         -54 (-16.88 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[long](System.ReadOnlySpan`1[long],System.ReadOnlySpan`1[long],System.Collections.Generic.IEqualityComparer`1[long]):int (FullOpts)
         -54 (-16.88 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:CommonPrefixLength[System.Nullable`1[int]](System.ReadOnlySpan`1[System.Nullable`1[int]],System.ReadOnlySpan`1[System.Nullable`1[int]],System.Collections.Generic.IEqualityComparer`1[System.Nullable`1[int]]):int (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[byte](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[double](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[int](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[long](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[short](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[System.__Canon](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[System.Nullable`1[int]](byref,byref) (FullOpts)
          -2 (-3.28 % of base) : System.Private.CoreLib.dasm - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[System.Numerics.Vector`1[float]](byref,byref) (FullOpts)

20 total methods with Code Size differences (20 improved, 0 regressed), 282901 unchanged.

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

Artifacts:

• build-clr-checked-main.zip (87 MB)
• build-artifacts-main.zip (678 MB)
• build-clr-checked-pr.zip (87 MB)
• build-artifacts-pr.zip (678 MB)
• jit-diffs-pr.zip (154 MB)
• jit-diffs-main.zip (154 MB)
• diff-frameworks.txt (9 KB)
• ShortDiffsImprovements.md (58 KB)
• LongDiffsImprovements.md (175 KB)

[MihuBot]

Top method improvements

-143 (-42.31 % of base) - System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon]):int

 ; Assembly listing for method System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon]):int (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; partially interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 6 single block inlinees; 4 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 TypeCtx      [V00,T08] (  7,  3.65)    long  ->  r12         single-def
+;  V00 TypeCtx      [V00,T08] (  5,  3.60)    long  ->  rdi         single-def
 ;* V01 arg0         [V01    ] (  0,  0   )  struct (16) zero-ref    multireg-arg ld-addr-op single-def <System.ReadOnlySpan`1[System.__Canon]>
 ;* V02 arg1         [V02    ] (  0,  0   )  struct (16) zero-ref    multireg-arg ld-addr-op single-def <System.ReadOnlySpan`1[System.__Canon]>
 ;* V03 loc0         [V03    ] (  0,  0   )    long  ->  zero-ref   
 ;* V04 loc1         [V04    ] (  0,  0   )    long  ->  zero-ref   
-;  V05 loc2         [V05,T01] ( 12, 17.58)     int  ->  [rbp-0x34] 
+;  V05 loc2         [V05,T01] (  6, 17.34)     int  ->  r13        
 ;# V06 OutArgs      [V06    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
 ;* V07 tmp1         [V07    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V08 tmp2         [V08    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V09 tmp3         [V09    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V10 tmp4         [V10    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V11 tmp5         [V11    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V12 tmp6         [V12    ] (  0,  0   )   byref  ->  zero-ref    "impAppendStmt"
 ;* V13 tmp7         [V13    ] (  0,  0   )    long  ->  zero-ref    "Inline return value spill temp"
 ;* V14 tmp8         [V14    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V15 tmp9         [V15    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V16 tmp10        [V16    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "Inlining Arg" <System.ReadOnlySpan`1[System.__Canon]>
 ;* V17 tmp11        [V17    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "Inlining Arg" <System.ReadOnlySpan`1[System.__Canon]>
 ;* V18 tmp12        [V18    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V19 tmp13        [V19    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V20 tmp14        [V20    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V21 tmp15        [V21    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
 ;* V22 tmp16        [V22    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[System.__Canon]>
 ;* V23 tmp17        [V23    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V24 tmp18        [V24    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
 ;* V25 tmp19        [V25    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
 ;* V26 tmp20        [V26    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[System.__Canon]>
 ;* V27 tmp21        [V27    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V28 tmp22        [V28    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
 ;* V29 tmp23        [V29    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
-;  V30 tmp24        [V30,T05] (  5,  6   )   byref  ->  r15         "field V01._reference (fldOffset=0x0)" P-INDEP
-;  V31 tmp25        [V31,T04] ( 10,  9.50)     int  ->  rbx         "field V01._length (fldOffset=0x8)" P-INDEP
-;  V32 tmp26        [V32,T06] (  5,  6   )   byref  ->  r14         "field V02._reference (fldOffset=0x0)" P-INDEP
-;  V33 tmp27        [V33,T07] (  7,  4.04)     int  ->  r13         "field V02._length (fldOffset=0x8)" P-INDEP
+;  V30 tmp24        [V30,T05] (  4,  6.96)   byref  ->  r15         "field V01._reference (fldOffset=0x0)" P-INDEP
+;  V31 tmp25        [V31,T04] (  7,  8.96)     int  ->  rbx         "field V01._length (fldOffset=0x8)" P-INDEP
+;  V32 tmp26        [V32,T06] (  4,  5.96)   byref  ->  r14         "field V02._reference (fldOffset=0x0)" P-INDEP
+;  V33 tmp27        [V33,T07] (  6,  5.50)     int  ->   r8         "field V02._length (fldOffset=0x8)" P-INDEP
 ;* V34 tmp28        [V34    ] (  0,  0   )   byref  ->  zero-ref    "field V16._reference (fldOffset=0x0)" P-INDEP
 ;* V35 tmp29        [V35    ] (  0,  0   )     int  ->  zero-ref    "field V16._length (fldOffset=0x8)" P-INDEP
 ;* V36 tmp30        [V36    ] (  0,  0   )   byref  ->  zero-ref    "field V17._reference (fldOffset=0x0)" P-INDEP
 ;* V37 tmp31        [V37    ] (  0,  0   )     int  ->  zero-ref    "field V17._length (fldOffset=0x8)" P-INDEP
-;  V38 tmp32        [V38,T12] (  2,  1   )   byref  ->  r14         single-def "field V22._reference (fldOffset=0x0)" P-INDEP
+;  V38 tmp32        [V38,T13] (  2,  1   )   byref  ->  r14         single-def "field V22._reference (fldOffset=0x0)" P-INDEP
 ;* V39 tmp33        [V39    ] (  0,  0   )     int  ->  zero-ref    "field V22._length (fldOffset=0x8)" P-INDEP
-;  V40 tmp34        [V40,T13] (  2,  1   )   byref  ->  r15         single-def "field V26._reference (fldOffset=0x0)" P-INDEP
+;  V40 tmp34        [V40,T12] (  2,  2   )   byref  ->  r15         single-def "field V26._reference (fldOffset=0x0)" P-INDEP
 ;* V41 tmp35        [V41    ] (  0,  0   )     int  ->  zero-ref    "field V26._length (fldOffset=0x8)" P-INDEP
-;  V42 tmp36        [V42,T00] (  6, 24   )     ref  ->  rdi         "argument with side effect"
-;  V43 tmp37        [V43,T02] (  4, 16   )     ref  ->  rsi         "argument with side effect"
-;  V44 cse0         [V44,T09] (  4,  4.54)    long  ->  registers   hoist multi-def "CSE #01: moderate"
+;  V42 tmp36        [V42,T00] (  3, 23.76)     ref  ->  rdi         "argument with side effect"
+;  V43 tmp37        [V43,T02] (  2, 15.84)     ref  ->  rsi         "argument with side effect"
+;  V44 cse0         [V44,T09] (  2,  4.46)    long  ->  r12         hoist "CSE #01: moderate"
 ;  V45 cse1         [V45,T03] (  3, 11.88)    long  ->  rdx         "CSE #02: aggressive"
-;  V46 rat0         [V46,T11] (  3,  2   )    long  ->  r13         "runtime lookup"
-;  V47 rat1         [V47,T10] (  3,  2.80)    long  ->  r13         "fgMakeTemp is creating a new local variable"
-;  V48 rat2         [V48,T15] (  3,  0.16)    long  ->  rcx         "runtime lookup"
-;  V49 rat3         [V49,T14] (  3,  0.22)    long  ->  rcx         "fgMakeTemp is creating a new local variable"
+;  V46 rat0         [V46,T11] (  3,  2   )    long  ->  r12         "runtime lookup"
+;  V47 rat1         [V47,T10] (  3,  2.80)    long  ->  r12         "fgMakeTemp is creating a new local variable"
 ;
-; Lcl frame size = 24
+; Lcl frame size = 8
 
 G_M24901_IG01:
        push     rbp
        push     r15
        push     r14
        push     r13
        push     r12
        push     rbx
-       sub      rsp, 24
-       lea      rbp, [rsp+0x40]
+       push     rax
+       lea      rbp, [rsp+0x30]
        mov      qword ptr [rbp-0x30], rdi
-       mov      r12, rdi
        mov      r15, rsi
        mov      ebx, edx
        mov      r14, rcx
-       mov      r13d, r8d
-						;; size=37 bbWeight=1 PerfScore 9.00
+						;; size=28 bbWeight=1 PerfScore 9.25
 G_M24901_IG02:
-       cmp      r13d, ebx
-       jg       SHORT G_M24901_IG04
+       cmp      r8d, ebx
+       jle      SHORT G_M24901_IG04
 						;; size=5 bbWeight=1 PerfScore 1.25
 G_M24901_IG03:
-       cmp      ebx, r13d
-       jle      SHORT G_M24901_IG05
-       mov      ebx, r13d
-       jmp      SHORT G_M24901_IG05
-						;; size=10 bbWeight=0.50 PerfScore 1.75
-G_M24901_IG04:
-       mov      r13d, ebx
+       mov      r8d, ebx
 						;; size=3 bbWeight=0.50 PerfScore 0.12
+G_M24901_IG04:
+       cmp      r8d, ebx
+       jg       G_M24901_IG13
+       mov      ebx, r8d
+       xor      r13d, r13d
+       test     r8d, r8d
+       jle      SHORT G_M24901_IG11
+						;; size=20 bbWeight=1 PerfScore 3.00
 G_M24901_IG05:
-       xor      eax, eax
-       mov      dword ptr [rbp-0x34], eax
-       test     ebx, ebx
-       jle      SHORT G_M24901_IG08
-						;; size=9 bbWeight=1 PerfScore 2.50
+       mov      rsi, qword ptr [rdi+0x18]
+       mov      r12, qword ptr [rsi+0x20]
+       test     r12, r12
+       je       SHORT G_M24901_IG09
+						;; size=13 bbWeight=0.50 PerfScore 2.62
 G_M24901_IG06:
-       cmp      ebx, r13d
-       jg       SHORT G_M24901_IG11
-       mov      rdi, qword ptr [r12+0x18]
-       mov      r13, qword ptr [rdi+0x20]
-       test     r13, r13
-       je       G_M24901_IG16
-						;; size=23 bbWeight=0.50 PerfScore 3.25
-G_M24901_IG07:
-       mov      rdi, r13
-       mov      rcx, 0xD1FFAB1E      ; code for CORINFO_HELP_GET_GCSTATIC_BASE
-       call     [rcx]CORINFO_HELP_GET_GCSTATIC_BASE
+       mov      rdi, r12
+       mov      rax, 0xD1FFAB1E      ; code for CORINFO_HELP_GET_GCSTATIC_BASE
+       call     [rax]CORINFO_HELP_GET_GCSTATIC_BASE
        mov      rdi, gword ptr [rax]
-       mov      r12d, dword ptr [rbp-0x34]
-       mov      edx, r12d
+       mov      edx, r13d
        mov      rsi, gword ptr [r15+8*rdx]
        mov      rdx, gword ptr [r14+8*rdx]
        mov      rax, qword ptr [rdi]
        mov      rax, qword ptr [rax+0x40]
        call     [rax+0x20]System.Collections.Generic.EqualityComparer`1[System.__Canon]:Equals(System.__Canon,System.__Canon):bool:this
        test     eax, eax
-       je       SHORT G_M24901_IG14
-       inc      r12d
-       mov      dword ptr [rbp-0x34], r12d
-       cmp      r12d, ebx
-       jl       SHORT G_M24901_IG07
-						;; size=59 bbWeight=3.96 PerfScore 85.14
+       jne      SHORT G_M24901_IG10
+						;; size=43 bbWeight=3.96 PerfScore 71.28
+G_M24901_IG07:
+       mov      eax, r13d
+						;; size=3 bbWeight=0.50 PerfScore 0.12
 G_M24901_IG08:
+       add      rsp, 8
+       pop      rbx
+       pop      r12
+       pop      r13
+       pop      r14
+       pop      r15
+       pop      rbp
+       ret      
+						;; size=15 bbWeight=0.50 PerfScore 2.12
+G_M24901_IG09:
+       mov      rsi, 0xD1FFAB1E      ; global ptr
+       mov      rax, 0xD1FFAB1E      ; code for CORINFO_HELP_RUNTIMEHANDLE_METHOD
+       call     [rax]CORINFO_HELP_RUNTIMEHANDLE_METHOD
+       mov      r12, rax
+       jmp      SHORT G_M24901_IG06
+						;; size=27 bbWeight=0.10 PerfScore 0.58
+G_M24901_IG10:
+       inc      r13d
+       cmp      r13d, ebx
+       jl       SHORT G_M24901_IG06
+						;; size=8 bbWeight=3.96 PerfScore 5.94
+G_M24901_IG11:
        mov      eax, ebx
 						;; size=2 bbWeight=0.50 PerfScore 0.12
-G_M24901_IG09:
-       add      rsp, 24
-       pop      rbx
-       pop      r12
-       pop      r13
-       pop      r14
-       pop      r15
-       pop      rbp
-       ret      
-						;; size=15 bbWeight=0.50 PerfScore 2.12
-G_M24901_IG10:
-       mov      ecx, dword ptr [rbp-0x34]
-       inc      ecx
-       cmp      ecx, ebx
-       mov      dword ptr [rbp-0x34], ecx
-       jge      SHORT G_M24901_IG08
-						;; size=12 bbWeight=0.04 PerfScore 0.14
-G_M24901_IG11:
-       mov      rdi, qword ptr [r12+0x18]
-       mov      rcx, qword ptr [rdi+0x20]
-       test     rcx, rcx
-       je       SHORT G_M24901_IG17
-						;; size=14 bbWeight=0.04 PerfScore 0.21
 G_M24901_IG12:
-       mov      rdi, rcx
-       mov      rcx, 0xD1FFAB1E      ; code for CORINFO_HELP_GET_GCSTATIC_BASE
-       call     [rcx]CORINFO_HELP_GET_GCSTATIC_BASE
-       mov      rdi, gword ptr [rax]
-       mov      eax, dword ptr [rbp-0x34]
-       mov      esi, eax
-       mov      rsi, gword ptr [r15+8*rsi]
-       cmp      eax, r13d
-       jae      SHORT G_M24901_IG18
-       mov      dword ptr [rbp-0x34], eax
-       mov      edx, eax
-       mov      rdx, gword ptr [r14+8*rdx]
-       mov      rcx, qword ptr [rdi]
-       mov      rcx, qword ptr [rcx+0x40]
-       call     [rcx+0x20]System.Collections.Generic.EqualityComparer`1[System.__Canon]:Equals(System.__Canon,System.__Canon):bool:this
-       test     eax, eax
-       jne      SHORT G_M24901_IG10
-						;; size=55 bbWeight=0.04 PerfScore 0.86
-G_M24901_IG13:
-       mov      r12d, dword ptr [rbp-0x34]
-						;; size=4 bbWeight=0.02 PerfScore 0.02
-G_M24901_IG14:
-       mov      eax, r12d
-						;; size=3 bbWeight=0.50 PerfScore 0.12
-G_M24901_IG15:
-       add      rsp, 24
+       add      rsp, 8
        pop      rbx
        pop      r12
        pop      r13
        pop      r14
        pop      r15
        pop      rbp
        ret      
 						;; size=15 bbWeight=0.50 PerfScore 2.12
-G_M24901_IG16:
-       mov      rdi, r12
-       mov      rsi, 0xD1FFAB1E      ; global ptr
-       mov      rcx, 0xD1FFAB1E      ; code for CORINFO_HELP_RUNTIMEHANDLE_METHOD
-       call     [rcx]CORINFO_HELP_RUNTIMEHANDLE_METHOD
-       mov      r13, rax
-       jmp      G_M24901_IG07
-						;; size=33 bbWeight=0.10 PerfScore 0.60
-G_M24901_IG17:
-       mov      rdi, r12
-       mov      rsi, 0xD1FFAB1E      ; global ptr
-       mov      rcx, 0xD1FFAB1E      ; code for CORINFO_HELP_RUNTIMEHANDLE_METHOD
-       call     [rcx]CORINFO_HELP_RUNTIMEHANDLE_METHOD
-       mov      rcx, rax
-       jmp      G_M24901_IG12
-						;; size=33 bbWeight=0.01 PerfScore 0.05
-G_M24901_IG18:
-       call     CORINFO_HELP_RNGCHKFAIL
+G_M24901_IG13:
+       mov      rax, 0xD1FFAB1E      ; code for System.ThrowHelper:ThrowArgumentOutOfRangeException()
+       call     [rax]System.ThrowHelper:ThrowArgumentOutOfRangeException()
        int3     
-						;; size=6 bbWeight=0 PerfScore 0.00
+						;; size=13 bbWeight=0 PerfScore 0.00
 
-; Total bytes of code 338, prolog size 23, PerfScore 109.39, instruction count 107, allocated bytes for code 338 (MethodHash=81ba9eba) for method System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon]):int (FullOpts)
+; Total bytes of code 195, prolog size 20, PerfScore 98.54, instruction count 66, allocated bytes for code 195 (MethodHash=81ba9eba) for method System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon]):int (FullOpts)
 ; ============================================================

-101 (-26.58 % of base) - System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon],System.Collections.Generic.IEqualityComparer`1[System.__Canon]):int

 ; Assembly listing for method System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon],System.Collections.Generic.IEqualityComparer`1[System.__Canon]):int (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; partially interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 3 single block inlinees; 3 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 TypeCtx      [V00,T08] (  9,  4.25)    long  ->  r12         single-def
+;  V00 TypeCtx      [V00,T09] (  7,  4.20)    long  ->  [rbp-0x38]  single-def
 ;* V01 arg0         [V01    ] (  0,  0   )  struct (16) zero-ref    multireg-arg ld-addr-op single-def <System.ReadOnlySpan`1[System.__Canon]>
 ;* V02 arg1         [V02    ] (  0,  0   )  struct (16) zero-ref    multireg-arg ld-addr-op single-def <System.ReadOnlySpan`1[System.__Canon]>
-;  V03 arg2         [V03,T05] (  6,  7.50)     ref  ->  r15         class-hnd <System.Collections.Generic.IEqualityComparer`1[System.__Canon]>
-;  V04 loc0         [V04,T01] ( 12, 17.58)     int  ->  [rbp-0x34] 
+;  V03 arg2         [V03,T05] (  5,  7.46)     ref  ->  r15         class-hnd <System.Collections.Generic.IEqualityComparer`1[System.__Canon]>
+;  V04 loc0         [V04,T01] (  6, 17.34)     int  ->  [rbp-0x3C] 
 ;# V05 OutArgs      [V05    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
 ;* V06 tmp1         [V06    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
-;  V07 tmp2         [V07,T00] (  6, 24   )    long  ->  r11         "spilling helperCall"
+;  V07 tmp2         [V07,T00] (  3, 23.76)    long  ->  r11         "spilling helperCall"
 ;* V08 tmp3         [V08    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V09 tmp4         [V09    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V10 tmp5         [V10    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V11 tmp6         [V11    ] (  0,  0   )    long  ->  zero-ref    "spilling helperCall"
 ;* V12 tmp7         [V12    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
 ;* V13 tmp8         [V13    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[System.__Canon]>
 ;* V14 tmp9         [V14    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V15 tmp10        [V15    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
 ;* V16 tmp11        [V16    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
 ;* V17 tmp12        [V17    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[System.__Canon]>
 ;* V18 tmp13        [V18    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V19 tmp14        [V19    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
 ;* V20 tmp15        [V20    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
-;  V21 tmp16        [V21,T06] (  5,  6   )   byref  ->  r14         "field V01._reference (fldOffset=0x0)" P-INDEP
-;  V22 tmp17        [V22,T04] ( 10,  9.50)     int  ->  rbx         "field V01._length (fldOffset=0x8)" P-INDEP
-;  V23 tmp18        [V23,T07] (  5,  6   )   byref  ->  r13         "field V02._reference (fldOffset=0x0)" P-INDEP
-;  V24 tmp19        [V24,T09] (  7,  4.04)     int  ->  [rbp-0x38]  "field V02._length (fldOffset=0x8)" P-INDEP
-;  V25 tmp20        [V25,T15] (  2,  1   )   byref  ->  r13         single-def "field V13._reference (fldOffset=0x0)" P-INDEP
+;  V21 tmp16        [V21,T06] (  4,  6.96)   byref  ->  r14         "field V01._reference (fldOffset=0x0)" P-INDEP
+;  V22 tmp17        [V22,T04] (  7,  8.96)     int  ->  rbx         "field V01._length (fldOffset=0x8)" P-INDEP
+;  V23 tmp18        [V23,T07] (  4,  5.96)   byref  ->  r13         "field V02._reference (fldOffset=0x0)" P-INDEP
+;  V24 tmp19        [V24,T08] (  6,  5.50)     int  ->  r12         "field V02._length (fldOffset=0x8)" P-INDEP
+;  V25 tmp20        [V25,T16] (  2,  1   )   byref  ->  r13         single-def "field V13._reference (fldOffset=0x0)" P-INDEP
 ;* V26 tmp21        [V26    ] (  0,  0   )     int  ->  zero-ref    "field V13._length (fldOffset=0x8)" P-INDEP
-;  V27 tmp22        [V27,T16] (  2,  1   )   byref  ->  r14         single-def "field V17._reference (fldOffset=0x0)" P-INDEP
+;  V27 tmp22        [V27,T15] (  2,  2   )   byref  ->  r14         single-def "field V17._reference (fldOffset=0x0)" P-INDEP
 ;* V28 tmp23        [V28    ] (  0,  0   )     int  ->  zero-ref    "field V17._length (fldOffset=0x8)" P-INDEP
-;  V29 tmp24        [V29,T02] (  4, 16   )     ref  ->  rsi         "argument with side effect"
-;  V30 cse0         [V30,T10] (  4,  4.54)    long  ->  registers   hoist multi-def "CSE #01: moderate"
+;  V29 tmp24        [V29,T02] (  2, 15.84)     ref  ->  rsi         "argument with side effect"
+;  V30 cse0         [V30,T10] (  2,  4.46)    long  ->  r12         hoist "CSE #01: moderate"
 ;  V31 cse1         [V31,T03] (  3, 11.88)    long  ->  rdx         "CSE #02: aggressive"
 ;  V32 rat0         [V32,T13] (  3,  2   )    long  ->  rdi         "runtime lookup"
 ;  V33 rat1         [V33,T11] (  3,  2.80)    long  ->  rdi         "fgMakeTemp is creating a new local variable"
 ;  V34 rat2         [V34,T14] (  3,  2   )    long  ->  r12         "runtime lookup"
-;  V35 rat3         [V35,T12] (  3,  2.80)    long  ->  rax         "fgMakeTemp is creating a new local variable"
-;  V36 rat4         [V36,T18] (  3,  0.16)    long  ->  rdx         "runtime lookup"
-;  V37 rat5         [V37,T17] (  3,  0.22)    long  ->  rdx         "fgMakeTemp is creating a new local variable"
+;  V35 rat3         [V35,T12] (  3,  2.80)    long  ->  r12         "fgMakeTemp is creating a new local variable"
 ;
 ; Lcl frame size = 24
 
 G_M28531_IG01:
        push     rbp
        push     r15
        push     r14
        push     r13
        push     r12
        push     rbx
        sub      rsp, 24
        lea      rbp, [rsp+0x40]
        mov      qword ptr [rbp-0x30], rdi
-       mov      r12, rdi
+       mov      rax, rdi
        mov      r14, rsi
        mov      ebx, edx
        mov      r13, rcx
-       mov      eax, r8d
+       mov      r12d, r8d
        mov      r15, r9
 						;; size=40 bbWeight=1 PerfScore 9.25
 G_M28531_IG02:
-       cmp      eax, ebx
-       jg       SHORT G_M28531_IG06
-						;; size=4 bbWeight=1 PerfScore 1.25
-G_M28531_IG03:
-       cmp      ebx, eax
-       jg       SHORT G_M28531_IG05
-						;; size=4 bbWeight=0.50 PerfScore 0.62
-G_M28531_IG04:
-       mov      dword ptr [rbp-0x38], eax
-       jmp      SHORT G_M28531_IG07
-						;; size=5 bbWeight=0.25 PerfScore 0.75
-G_M28531_IG05:
-       mov      ebx, eax
-       mov      dword ptr [rbp-0x38], eax
-       jmp      SHORT G_M28531_IG07
-						;; size=7 bbWeight=0.50 PerfScore 1.62
-G_M28531_IG06:
-       mov      dword ptr [rbp-0x38], ebx
-						;; size=3 bbWeight=0.50 PerfScore 0.50
-G_M28531_IG07:
-       test     r15, r15
-       jne      SHORT G_M28531_IG10
+       cmp      r12d, ebx
+       jle      SHORT G_M28531_IG04
 						;; size=5 bbWeight=1 PerfScore 1.25
-G_M28531_IG08:
-       mov      rdi, qword ptr [r12+0x18]
+G_M28531_IG03:
+       mov      r12d, ebx
+						;; size=3 bbWeight=0.50 PerfScore 0.12
+G_M28531_IG04:
+       cmp      r12d, ebx
+       jg       G_M28531_IG18
+       mov      ebx, r12d
+       test     r15, r15
+       jne      SHORT G_M28531_IG08
+						;; size=17 bbWeight=1 PerfScore 2.75
+G_M28531_IG05:
+       mov      rdi, qword ptr [rax+0x18]
        mov      rdi, qword ptr [rdi+0x20]
        test     rdi, rdi
-       je       SHORT G_M28531_IG17
-						;; size=14 bbWeight=0.50 PerfScore 2.62
-G_M28531_IG09:
+       je       SHORT G_M28531_IG13
+						;; size=13 bbWeight=0.50 PerfScore 2.62
+G_M28531_IG06:
+       mov      qword ptr [rbp-0x38], rax
+						;; size=4 bbWeight=0.40 PerfScore 0.40
+G_M28531_IG07:
        mov      rcx, 0xD1FFAB1E      ; code for CORINFO_HELP_GET_GCSTATIC_BASE
        call     [rcx]CORINFO_HELP_GET_GCSTATIC_BASE
        mov      r15, gword ptr [rax]
-						;; size=15 bbWeight=0.50 PerfScore 2.62
-G_M28531_IG10:
+       mov      rax, qword ptr [rbp-0x38]
+						;; size=19 bbWeight=0.50 PerfScore 3.12
+G_M28531_IG08:
        xor      ecx, ecx
-       mov      dword ptr [rbp-0x34], ecx
-       test     ebx, ebx
-       jle      G_M28531_IG20
-						;; size=13 bbWeight=1 PerfScore 2.50
-G_M28531_IG11:
-       cmp      ebx, dword ptr [rbp-0x38]
-       jg       G_M28531_IG23
-       mov      rdi, qword ptr [r12+0x18]
-       mov      rax, qword ptr [rdi+0x18]
-       test     rax, rax
-       je       SHORT G_M28531_IG18
-						;; size=23 bbWeight=0.50 PerfScore 4.12
-G_M28531_IG12:
-       mov      r12, rax
-						;; size=3 bbWeight=0.40 PerfScore 0.10
-G_M28531_IG13:
+       mov      dword ptr [rbp-0x3C], ecx
+       test     r12d, r12d
+       jle      G_M28531_IG16
+						;; size=14 bbWeight=1 PerfScore 2.50
+G_M28531_IG09:
+       mov      rdi, qword ptr [rax+0x18]
+       mov      r12, qword ptr [rdi+0x18]
+       test     r12, r12
+       je       SHORT G_M28531_IG14
+						;; size=13 bbWeight=0.50 PerfScore 2.62
+G_M28531_IG10:
        mov      r11, r12
-       mov      edx, dword ptr [rbp-0x34]
+       mov      edx, dword ptr [rbp-0x3C]
        mov      rsi, gword ptr [r14+8*rdx]
        mov      rdx, gword ptr [r13+8*rdx]
        mov      rdi, r15
        call     [r11]
        test     eax, eax
-       jne      SHORT G_M28531_IG19
+       jne      SHORT G_M28531_IG15
 						;; size=25 bbWeight=3.96 PerfScore 38.61
-G_M28531_IG14:
-       mov      ecx, dword ptr [rbp-0x34]
-						;; size=3 bbWeight=1.98 PerfScore 1.98
-G_M28531_IG15:
+G_M28531_IG11:
+       mov      ecx, dword ptr [rbp-0x3C]
        mov      eax, ecx
-						;; size=2 bbWeight=0.50 PerfScore 0.12
-G_M28531_IG16:
+						;; size=5 bbWeight=0.50 PerfScore 0.62
+G_M28531_IG12:
        add      rsp, 24
        pop      rbx
        pop      r12
        pop      r13
        pop      r14
        pop      r15
        pop      rbp
        ret      
 						;; size=15 bbWeight=0.50 PerfScore 2.12
-G_M28531_IG17:
-       mov      rdi, r12
+G_M28531_IG13:
+       mov      qword ptr [rbp-0x38], rax
+       mov      rdi, rax
        mov      rsi, 0xD1FFAB1E      ; global ptr
        mov      rcx, 0xD1FFAB1E      ; code for CORINFO_HELP_RUNTIMEHANDLE_METHOD
        call     [rcx]CORINFO_HELP_RUNTIMEHANDLE_METHOD
        mov      rdi, rax
-       jmp      G_M28531_IG09
-						;; size=33 bbWeight=0.10 PerfScore 0.60
-G_M28531_IG18:
-       mov      rdi, r12
+       jmp      SHORT G_M28531_IG07
+						;; size=34 bbWeight=0.10 PerfScore 0.70
+G_M28531_IG14:
+       mov      rdi, rax
        mov      rsi, 0xD1FFAB1E      ; global ptr
        mov      rax, 0xD1FFAB1E      ; code for CORINFO_HELP_RUNTIMEHANDLE_METHOD
        call     [rax]CORINFO_HELP_RUNTIMEHANDLE_METHOD
        mov      r12, rax
-       jmp      SHORT G_M28531_IG13
+       jmp      SHORT G_M28531_IG10
 						;; size=30 bbWeight=0.10 PerfScore 0.60
-G_M28531_IG19:
-       mov      ecx, dword ptr [rbp-0x34]
+G_M28531_IG15:
+       mov      ecx, dword ptr [rbp-0x3C]
        inc      ecx
-       mov      dword ptr [rbp-0x34], ecx
        cmp      ecx, ebx
-       jl       SHORT G_M28531_IG13
+       mov      dword ptr [rbp-0x3C], ecx
+       jl       SHORT G_M28531_IG10
 						;; size=12 bbWeight=3.96 PerfScore 13.86
-G_M28531_IG20:
+G_M28531_IG16:
        mov      eax, ebx
 						;; size=2 bbWeight=0.50 PerfScore 0.12
-G_M28531_IG21:
+G_M28531_IG17:
        add      rsp, 24
        pop      rbx
        pop      r12
        pop      r13
        pop      r14
        pop      r15
        pop      rbp
        ret      
 						;; size=15 bbWeight=0.50 PerfScore 2.12
-G_M28531_IG22:
-       mov      ecx, dword ptr [rbp-0x34]
-       inc      ecx
-       cmp      ecx, ebx
-       mov      dword ptr [rbp-0x34], ecx
-       jge      SHORT G_M28531_IG20
-						;; size=12 bbWeight=0.04 PerfScore 0.14
-G_M28531_IG23:
-       mov      rdi, qword ptr [r12+0x18]
-       mov      rdx, qword ptr [rdi+0x18]
-       test     rdx, rdx
-       je       SHORT G_M28531_IG26
-						;; size=14 bbWeight=0.04 PerfScore 0.21
-G_M28531_IG24:
-       mov      r11, rdx
-       mov      ecx, dword ptr [rbp-0x34]
-       mov      esi, ecx
-       mov      rsi, gword ptr [r14+8*rsi]
-       cmp      ecx, dword ptr [rbp-0x38]
-       jae      SHORT G_M28531_IG27
-       mov      dword ptr [rbp-0x34], ecx
-       mov      edx, ecx
-       mov      rdx, gword ptr [r13+8*rdx]
-       mov      rdi, r15
-       call     [r11]
-       test     eax, eax
-       jne      SHORT G_M28531_IG22
-						;; size=37 bbWeight=0.04 PerfScore 0.57
-G_M28531_IG25:
-       mov      ecx, dword ptr [rbp-0x34]
-       jmp      G_M28531_IG15
-						;; size=8 bbWeight=0.02 PerfScore 0.06
-G_M28531_IG26:
-       mov      rdi, r12
-       mov      rsi, 0xD1FFAB1E      ; global ptr
-       mov      rdx, 0xD1FFAB1E      ; code for CORINFO_HELP_RUNTIMEHANDLE_METHOD
-       call     [rdx]CORINFO_HELP_RUNTIMEHANDLE_METHOD
-       mov      rdx, rax
-       jmp      SHORT G_M28531_IG24
-						;; size=30 bbWeight=0.01 PerfScore 0.05
-G_M28531_IG27:
-       call     CORINFO_HELP_RNGCHKFAIL
+G_M28531_IG18:
+       mov      rax, 0xD1FFAB1E      ; code for System.ThrowHelper:ThrowArgumentOutOfRangeException()
+       call     [rax]System.ThrowHelper:ThrowArgumentOutOfRangeException()
        int3     
-						;; size=6 bbWeight=0 PerfScore 0.00
+						;; size=13 bbWeight=0 PerfScore 0.00
 
-; Total bytes of code 380, prolog size 23, PerfScore 88.40, instruction count 121, allocated bytes for code 380 (MethodHash=5711908c) for method System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon],System.Collections.Generic.IEqualityComparer`1[System.__Canon]):int (FullOpts)
+; Total bytes of code 279, prolog size 23, PerfScore 83.42, instruction count 88, allocated bytes for code 279 (MethodHash=5711908c) for method System.MemoryExtensions:CommonPrefixLength[System.__Canon](System.ReadOnlySpan`1[System.__Canon],System.ReadOnlySpan`1[System.__Canon],System.Collections.Generic.IEqualityComparer`1[System.__Canon]):int (FullOpts)
 ; ============================================================

-67 (-18.31 % of base) - System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]):int

 ; Assembly listing for method System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]):int (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; fully interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 4 single block inlinees; 3 inlinees without PGO data
 ; Final local variable assignments
 ;
 ;* V00 arg0         [V00    ] (  0,  0   )  struct (16) zero-ref    multireg-arg ld-addr-op single-def <System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]>
 ;* V01 arg1         [V01    ] (  0,  0   )  struct (16) zero-ref    multireg-arg ld-addr-op single-def <System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]>
-;  V02 arg2         [V02,T03] (  6,  7.50)     ref  ->  r15         class-hnd single-def <System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]>
-;  V03 loc0         [V03,T00] ( 11, 17.04)     int  ->  [rbp-0x2C] 
+;  V02 arg2         [V02,T03] (  5,  7.46)     ref  ->  r15         class-hnd single-def <System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]>
+;  V03 loc0         [V03,T07] (  2,  1   )     int  ->  rax        
 ;  V04 OutArgs      [V04    ] (  1,  1   )  struct (64) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <UNNAMED>
 ;* V05 tmp1         [V05    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
 ;* V06 tmp2         [V06    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]>
 ;* V07 tmp3         [V07    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
 ;* V08 tmp4         [V08    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
 ;* V09 tmp5         [V09    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]>
 ;* V10 tmp6         [V10    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
-;  V11 tmp7         [V11,T04] (  6,  6.50)   byref  ->  r14         "field V00._reference (fldOffset=0x0)" P-INDEP
-;  V12 tmp8         [V12,T02] ( 11,  9   )     int  ->  rbx         "field V00._length (fldOffset=0x8)" P-INDEP
-;  V13 tmp9         [V13,T05] (  6,  6.50)   byref  ->  r13         "field V01._reference (fldOffset=0x0)" P-INDEP
-;  V14 tmp10        [V14,T06] (  8,  4.04)     int  ->  r12         "field V01._length (fldOffset=0x8)" P-INDEP
-;  V15 tmp11        [V15,T07] (  2,  1   )   byref  ->  r13         single-def "field V06._reference (fldOffset=0x0)" P-INDEP
+;  V11 tmp7         [V11,T04] (  5,  6.46)   byref  ->  r14         "field V00._reference (fldOffset=0x0)" P-INDEP
+;  V12 tmp8         [V12,T02] (  8,  7.96)     int  ->  rbx         "field V00._length (fldOffset=0x8)" P-INDEP
+;  V13 tmp9         [V13,T05] (  5,  6.46)   byref  ->  r13         "field V01._reference (fldOffset=0x0)" P-INDEP
+;  V14 tmp10        [V14,T06] (  7,  4   )     int  ->  r12         "field V01._length (fldOffset=0x8)" P-INDEP
+;  V15 tmp11        [V15,T08] (  2,  1   )   byref  ->  r13         single-def "field V06._reference (fldOffset=0x0)" P-INDEP
 ;* V16 tmp12        [V16    ] (  0,  0   )     int  ->  zero-ref    "field V06._length (fldOffset=0x8)" P-INDEP
-;  V17 tmp13        [V17,T08] (  2,  1   )   byref  ->  r14         single-def "field V09._reference (fldOffset=0x0)" P-INDEP
+;  V17 tmp13        [V17,T09] (  2,  1   )   byref  ->  r14         single-def "field V09._reference (fldOffset=0x0)" P-INDEP
 ;* V18 tmp14        [V18    ] (  0,  0   )     int  ->  zero-ref    "field V09._length (fldOffset=0x8)" P-INDEP
-;  V19 tmp15        [V19,T10] (  4, 16   )  simd32  ->  mm0         "argument with side effect"
+;  V19 tmp15        [V19,T10] (  2, 15.84)  simd32  ->  mm0         "argument with side effect"
 ;  V20 cse0         [V20,T01] (  3, 11.88)    long  ->  rdi         "CSE #02: aggressive"
-;  V21 cse1         [V21,T09] (  3,  0.12)    long  ->  rdi         "CSE #04: conservative"
+;  V21 rat0         [V21,T00] (  6, 16.84)    long  ->  [rbp-0x30]  "Widened IV V03"
 ;
 ; Lcl frame size = 72
 
 G_M4499_IG01:
        push     rbp
        push     r15
        push     r14
        push     r13
        push     r12
        push     rbx
        sub      rsp, 72
        lea      rbp, [rsp+0x70]
        mov      r14, rdi
        mov      ebx, esi
        mov      r13, rdx
        mov      r12d, ecx
        mov      r15, r8
 						;; size=33 bbWeight=1 PerfScore 8.00
 G_M4499_IG02:
        test     r15, r15
-       je       G_M4499_IG16
+       je       G_M4499_IG11
 						;; size=9 bbWeight=1 PerfScore 1.25
 G_M4499_IG03:
        mov      rdi, 0xD1FFAB1E      ; global ptr
        test     byte  ptr [rdi], 1
-       je       G_M4499_IG18
+       je       G_M4499_IG13
 						;; size=19 bbWeight=0.50 PerfScore 2.12
 G_M4499_IG04:
        mov      rdi, 0xD1FFAB1E      ; data for System.Collections.Generic.EqualityComparer`1[System.Numerics.Vector`1[float]]:<Default>k__BackingField
        cmp      r15, gword ptr [rdi]
-       je       G_M4499_IG16
+       je       G_M4499_IG11
        cmp      r12d, ebx
-       jg       SHORT G_M4499_IG05
-       cmp      ebx, r12d
-       jle      SHORT G_M4499_IG06
-       mov      ebx, r12d
-       jmp      SHORT G_M4499_IG06
-						;; size=34 bbWeight=0.50 PerfScore 4.50
-G_M4499_IG05:
+       jle      SHORT G_M4499_IG05
        mov      r12d, ebx
-						;; size=3 bbWeight=0.50 PerfScore 0.12
-G_M4499_IG06:
+						;; size=27 bbWeight=0.50 PerfScore 2.88
+G_M4499_IG05:
+       cmp      r12d, ebx
+       jg       G_M4499_IG14
+       mov      ebx, r12d
        xor      eax, eax
-       test     ebx, ebx
-       jle      SHORT G_M4499_IG08
-       cmp      ebx, r12d
-       jg       SHORT G_M4499_IG14
-						;; size=11 bbWeight=0.50 PerfScore 1.38
-G_M4499_IG07:
-       mov      dword ptr [rbp-0x2C], eax
-       mov      edi, eax
+       test     r12d, r12d
+       jle      SHORT G_M4499_IG07
+						;; size=19 bbWeight=0.50 PerfScore 1.50
+G_M4499_IG06:
+       mov      qword ptr [rbp-0x30], rax
+       mov      rdi, rax
        shl      rdi, 5
        vmovups  ymm0, ymmword ptr [r14+rdi]
        vmovups  ymm1, ymmword ptr [rdi+r13]
        vmovups  ymmword ptr [rsp+0x20], ymm1
        vmovups  ymmword ptr [rsp], ymm0
        mov      rdi, r15
        mov      r11, 0xD1FFAB1E      ; code for System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]:Equals(System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):bool:this
        call     [r11]System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]:Equals(System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):bool:this
        test     eax, eax
-       je       SHORT G_M4499_IG10
-       mov      r12d, dword ptr [rbp-0x2C]
+       je       SHORT G_M4499_IG09
+       mov      r12, qword ptr [rbp-0x30]
        inc      r12d
        cmp      r12d, ebx
-       mov      eax, r12d
-       jl       SHORT G_M4499_IG07
-						;; size=67 bbWeight=3.96 PerfScore 84.15
-G_M4499_IG08:
+       mov      rax, r12
+       jl       SHORT G_M4499_IG06
+						;; size=69 bbWeight=3.96 PerfScore 84.15
+G_M4499_IG07:
        mov      eax, ebx
 						;; size=2 bbWeight=0.50 PerfScore 0.12
+G_M4499_IG08:
+       vzeroupper 
+       add      rsp, 72
+       pop      rbx
+       pop      r12
+       pop      r13
+       pop      r14
+       pop      r15
+       pop      rbp
+       ret      
+						;; size=18 bbWeight=0.50 PerfScore 2.62
 G_M4499_IG09:
-       vzeroupper 
-       add      rsp, 72
-       pop      rbx
-       pop      r12
-       pop      r13
-       pop      r14
-       pop      r15
-       pop      rbp
-       ret      
-						;; size=18 bbWeight=0.50 PerfScore 2.62
+       mov      rax, qword ptr [rbp-0x30]
+						;; size=4 bbWeight=0.50 PerfScore 0.50
 G_M4499_IG10:
-       mov      edi, dword ptr [rbp-0x2C]
-						;; size=3 bbWeight=1.98 PerfScore 1.98
-G_M4499_IG11:
-       mov      eax, edi
-						;; size=2 bbWeight=0.50 PerfScore 0.12
-G_M4499_IG12:
        vzeroupper 
        add      rsp, 72
        pop      rbx
        pop      r12
        pop      r13
        pop      r14
        pop      r15
        pop      rbp
        ret      
 						;; size=18 bbWeight=0.50 PerfScore 2.62
-G_M4499_IG13:
-       mov      edi, dword ptr [rbp-0x2C]
-       inc      edi
-       cmp      edi, ebx
-       mov      eax, edi
-       jge      SHORT G_M4499_IG08
-						;; size=11 bbWeight=0.04 PerfScore 0.11
-G_M4499_IG14:
-       mov      edi, eax
-       shl      rdi, 5
-       vmovups  ymm0, ymmword ptr [r14+rdi]
-       mov      dword ptr [rbp-0x2C], eax
-       cmp      eax, r12d
-       jae      SHORT G_M4499_IG19
-       vmovups  ymm1, ymmword ptr [rdi+r13]
-       vmovups  ymmword ptr [rsp+0x20], ymm1
-       vmovups  ymmword ptr [rsp], ymm0
-       mov      rdi, r15
-       mov      r11, 0xD1FFAB1E      ; function address
-       call     [r11]System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]:Equals(System.Numerics.Vector`1[float],System.Numerics.Vector`1[float]):bool:this
-       test     eax, eax
-       jne      SHORT G_M4499_IG13
-						;; size=57 bbWeight=0.04 PerfScore 0.79
-G_M4499_IG15:
-       mov      edi, dword ptr [rbp-0x2C]
-       jmp      SHORT G_M4499_IG11
-						;; size=5 bbWeight=0.02 PerfScore 0.06
-G_M4499_IG16:
+G_M4499_IG11:
        mov      rdi, r14
        mov      esi, ebx
        mov      rdx, r13
        mov      ecx, r12d
        mov      rax, 0xD1FFAB1E      ; code for System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]):int
 						;; size=21 bbWeight=0.50 PerfScore 0.62
-G_M4499_IG17:
+G_M4499_IG12:
        vzeroupper 
        add      rsp, 72
        pop      rbx
        pop      r12
        pop      r13
        pop      r14
        pop      r15
        pop      rbp
        tail.jmp [rax]System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]]):int
 						;; size=20 bbWeight=0.50 PerfScore 4.12
-G_M4499_IG18:
+G_M4499_IG13:
        mov      rdi, 0xD1FFAB1E      ; System.Collections.Generic.EqualityComparer`1[System.Numerics.Vector`1[float]]
        mov      rax, 0xD1FFAB1E      ; code for CORINFO_HELP_GET_GCSTATIC_BASE
        call     [rax]CORINFO_HELP_GET_GCSTATIC_BASE
        jmp      G_M4499_IG04
 						;; size=27 bbWeight=0 PerfScore 0.00
-G_M4499_IG19:
-       call     CORINFO_HELP_RNGCHKFAIL
+G_M4499_IG14:
+       mov      rax, 0xD1FFAB1E      ; code for System.ThrowHelper:ThrowArgumentOutOfRangeException()
+       call     [rax]System.ThrowHelper:ThrowArgumentOutOfRangeException()
        int3     
-						;; size=6 bbWeight=0 PerfScore 0.00
+						;; size=13 bbWeight=0 PerfScore 0.00
 
-; Total bytes of code 366, prolog size 33, PerfScore 114.72, instruction count 112, allocated bytes for code 366 (MethodHash=df29ee6c) for method System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]):int (FullOpts)
+; Total bytes of code 299, prolog size 33, PerfScore 110.52, instruction count 88, allocated bytes for code 299 (MethodHash=df29ee6c) for method System.MemoryExtensions:CommonPrefixLength[System.Numerics.Vector`1[float]](System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.ReadOnlySpan`1[System.Numerics.Vector`1[float]],System.Collections.Generic.IEqualityComparer`1[System.Numerics.Vector`1[float]]):int (FullOpts)
 ; ============================================================

-66 (-38.37 % of base) - System.MemoryExtensions:CommonPrefixLength[System.Nullable`1[int]](System.ReadOnlySpan`1[System.Nullable`1[int]],System.ReadOnlySpan`1[System.Nullable`1[int]]):int

 ; Assembly listing for method System.MemoryExtensions:CommonPrefixLength[System.Nullable`1[int]](System.ReadOnlySpan`1[System.Nullable`1[int]],System.ReadOnlySpan`1[System.Nullable`1[int]]):int (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; fully interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 11 single block inlinees; 6 inlinees without PGO data
 ; Final local variable assignments
 ;
 ;* V00 arg0         [V00    ] (  0,  0   )  struct (16) zero-ref    multireg-arg ld-addr-op single-def <System.ReadOnlySpan`1[System.Nullable`1[int]]>
 ;* V01 arg1         [V01    ] (  0,  0   )  struct (16) zero-ref    multireg-arg ld-addr-op single-def <System.ReadOnlySpan`1[System.Nullable`1[int]]>
 ;* V02 loc0         [V02    ] (  0,  0   )    long  ->  zero-ref   
 ;* V03 loc1         [V03    ] (  0,  0   )    long  ->  zero-ref   
-;  V04 loc2         [V04,T02] ( 11, 17.54)     int  ->  rax        
+;  V04 loc2         [V04,T12] (  3,  1.99)     int  ->  rax        
 ;# V05 OutArgs      [V05    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
 ;* V06 tmp1         [V06    ] (  0,  0   )   byref  ->  zero-ref    "impAppendStmt"
 ;* V07 tmp2         [V07    ] (  0,  0   )    long  ->  zero-ref    "Inline return value spill temp"
 ;* V08 tmp3         [V08    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V09 tmp4         [V09    ] (  0,  0   )    long  ->  zero-ref    "Inlining Arg"
 ;* V10 tmp5         [V10    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "Inlining Arg" <System.ReadOnlySpan`1[System.Nullable`1[int]]>
 ;* V11 tmp6         [V11    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "Inlining Arg" <System.ReadOnlySpan`1[System.Nullable`1[int]]>
 ;* V12 tmp7         [V12    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
 ;* V13 tmp8         [V13    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[System.Nullable`1[int]]>
 ;* V14 tmp9         [V14    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
 ;* V15 tmp10        [V15    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
 ;* V16 tmp11        [V16    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[System.Nullable`1[int]]>
 ;* V17 tmp12        [V17    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
 ;* V18 tmp13        [V18    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V19 tmp14        [V19    ] (  0,  0   )  struct ( 8) zero-ref    ld-addr-op "Inlining Arg" <System.Nullable`1[int]>
 ;* V20 tmp15        [V20    ] (  0,  0   )  struct ( 8) zero-ref    ld-addr-op "Inlining Arg" <System.Nullable`1[int]>
 ;* V21 tmp16        [V21    ] (  0,  0   )   ubyte  ->  zero-ref    "Inline return value spill temp"
 ;* V22 tmp17        [V22    ] (  0,  0   )     int  ->  zero-ref    ld-addr-op "Inlining Arg"
 ;* V23 tmp18        [V23    ] (  0,  0   )     int  ->  zero-ref    "Inlining Arg"
-;  V24 tmp19        [V24,T06] (  5,  6   )   byref  ->  rdi         "field V00._reference (fldOffset=0x0)" P-INDEP
-;  V25 tmp20        [V25,T04] ( 10,  9.50)     int  ->  rsi         "field V00._length (fldOffset=0x8)" P-INDEP
-;  V26 tmp21        [V26,T07] (  5,  6   )   byref  ->  rdx         "field V01._reference (fldOffset=0x0)" P-INDEP
-;  V27 tmp22        [V27,T09] (  7,  4.04)     int  ->  rcx         "field V01._length (fldOffset=0x8)" P-INDEP
+;  V24 tmp19        [V24,T05] (  4,  6.96)   byref  ->  rdi         "field V00._reference (fldOffset=0x0)" P-INDEP
+;  V25 tmp20        [V25,T04] (  7,  8.96)     int  ->  rsi         "field V00._length (fldOffset=0x8)" P-INDEP
+;  V26 tmp21        [V26,T06] (  4,  5.96)   byref  ->  rdx         "field V01._reference (fldOffset=0x0)" P-INDEP
+;  V27 tmp22        [V27,T09] (  6,  5.50)     int  ->  rcx         "field V01._length (fldOffset=0x8)" P-INDEP
 ;* V28 tmp23        [V28    ] (  0,  0   )   byref  ->  zero-ref    "field V10._reference (fldOffset=0x0)" P-INDEP
 ;* V29 tmp24        [V29    ] (  0,  0   )     int  ->  zero-ref    "field V10._length (fldOffset=0x8)" P-INDEP
 ;* V30 tmp25        [V30    ] (  0,  0   )   byref  ->  zero-ref    "field V11._reference (fldOffset=0x0)" P-INDEP
 ;* V31 tmp26        [V31    ] (  0,  0   )     int  ->  zero-ref    "field V11._length (fldOffset=0x8)" P-INDEP
-;  V32 tmp27        [V32,T12] (  2,  1   )   byref  ->  rdx         single-def "field V13._reference (fldOffset=0x0)" P-INDEP
+;  V32 tmp27        [V32,T14] (  2,  1   )   byref  ->  rdx         single-def "field V13._reference (fldOffset=0x0)" P-INDEP
 ;* V33 tmp28        [V33    ] (  0,  0   )     int  ->  zero-ref    "field V13._length (fldOffset=0x8)" P-INDEP
-;  V34 tmp29        [V34,T13] (  2,  1   )   byref  ->  rdi         single-def "field V16._reference (fldOffset=0x0)" P-INDEP
+;  V34 tmp29        [V34,T13] (  2,  2   )   byref  ->  rdi         single-def "field V16._reference (fldOffset=0x0)" P-INDEP
 ;* V35 tmp30        [V35    ] (  0,  0   )     int  ->  zero-ref    "field V16._length (fldOffset=0x8)" P-INDEP
-;  V36 tmp31        [V36,T08] (  4,  8   )   ubyte  ->  registers   "field V19.hasValue (fldOffset=0x0)" P-INDEP
-;  V37 tmp32        [V37,T10] (  4,  6   )     int  ->  registers   "field V19.value (fldOffset=0x4)" P-INDEP
-;  V38 tmp33        [V38,T05] (  6,  8   )   ubyte  ->  registers   "field V20.hasValue (fldOffset=0x0)" P-INDEP
-;  V39 tmp34        [V39,T11] (  4,  6   )     int  ->  rbx         "field V20.value (fldOffset=0x4)" P-INDEP
-;  V40 tmp35        [V40,T00] (  6, 24   )   byref  ->  registers   "BlockOp address local"
-;  V41 tmp36        [V41,T01] (  6, 24   )   byref  ->   r8         "BlockOp address local"
-;  V42 cse0         [V42,T03] (  3, 11.88)    long  ->   r8         "CSE #02: aggressive"
-;  V43 cse1         [V43,T14] (  3,  0.12)    long  ->   r8         "CSE #04: conservative"
+;  V36 tmp31        [V36,T08] (  2,  7.92)   ubyte  ->   r9         "field V19.hasValue (fldOffset=0x0)" P-INDEP
+;  V37 tmp32        [V37,T10] (  2,  5.94)     int  ->  rcx         "field V19.value (fldOffset=0x4)" P-INDEP
+;  V38 tmp33        [V38,T07] (  3,  7.92)   ubyte  ->  r10         "field V20.hasValue (fldOffset=0x0)" P-INDEP
+;  V39 tmp34        [V39,T11] (  2,  5.94)     int  ->  rax         "field V20.value (fldOffset=0x4)" P-INDEP
+;  V40 tmp35        [V40,T00] (  3, 23.76)   byref  ->  rcx         "BlockOp address local"
+;  V41 tmp36        [V41,T01] (  3, 23.76)   byref  ->  rax         "BlockOp address local"
+;  V42 cse0         [V42,T03] (  3, 11.88)    long  ->  rax         "CSE #02: aggressive"
+;  V43 rat0         [V43,T02] (  7, 18.33)    long  ->   r8         "Widened IV V04"
 ;
-; Lcl frame size = 8
+; Lcl frame size = 0
 
 G_M39229_IG01:
        push     rbp
-       push     rbx
-       push     rax
-       lea      rbp, [rsp+0x10]
-						;; size=8 bbWeight=1 PerfScore 3.50
+       mov      rbp, rsp
+						;; size=4 bbWeight=1 PerfScore 1.25
 G_M39229_IG02:
        cmp      ecx, esi
-       jg       SHORT G_M39229_IG04
+       jle      SHORT G_M39229_IG04
 						;; size=4 bbWeight=1 PerfScore 1.25
 G_M39229_IG03:
-       cmp      esi, ecx
-       jle      SHORT G_M39229_IG05
-       mov      esi, ecx
-       jmp      SHORT G_M39229_IG05
-       align    [0 bytes for IG07]
-						;; size=8 bbWeight=0.50 PerfScore 1.75
-G_M39229_IG04:
        mov      ecx, esi
 						;; size=2 bbWeight=0.50 PerfScore 0.12
-G_M39229_IG05:
-       xor      eax, eax
-       test     esi, esi
+G_M39229_IG04:
+       cmp      ecx, esi
+       jg       SHORT G_M39229_IG14
+       mov      esi, ecx
+       xor      r8d, r8d
+       test     ecx, ecx
        jle      SHORT G_M39229_IG12
-						;; size=6 bbWeight=1 PerfScore 1.50
-G_M39229_IG06:
-       cmp      esi, ecx
-       jg       SHORT G_M39229_IG16
-						;; size=4 bbWeight=0.50 PerfScore 0.62
-G_M39229_IG07:
-       mov      r8d, eax
-       shl      r8, 3
-       lea      rcx, bword ptr [rdi+r8]
+       align    [0 bytes for IG05]
+						;; size=13 bbWeight=1 PerfScore 3.00
+G_M39229_IG05:
+       lea      rax, [8*r8]
+       lea      rcx, bword ptr [rdi+rax]
        movzx    r9, byte  ptr [rcx]
-       mov      r10d, dword ptr [rcx+0x04]
-       add      r8, rdx
-       movzx    r11, byte  ptr [r8]
-       mov      ebx, dword ptr [r8+0x04]
+       mov      ecx, dword ptr [rcx+0x04]
+       add      rax, rdx
+       movzx    r10, byte  ptr [rax]
+       mov      eax, dword ptr [rax+0x04]
        test     r9d, r9d
        jne      SHORT G_M39229_IG10
-						;; size=35 bbWeight=3.96 PerfScore 42.57
-G_M39229_IG08:
-       test     r11d, r11d
+						;; size=34 bbWeight=3.96 PerfScore 41.58
+G_M39229_IG06:
+       test     r10d, r10d
        je       SHORT G_M39229_IG11
 						;; size=5 bbWeight=1.98 PerfScore 2.48
+G_M39229_IG07:
+       mov      eax, r8d
+       jmp      SHORT G_M39229_IG09
+						;; size=5 bbWeight=0.50 PerfScore 1.12
+G_M39229_IG08:
+       mov      eax, r8d
+						;; size=3 bbWeight=0.99 PerfScore 0.25
 G_M39229_IG09:
-       add      rsp, 8
-       pop      rbx
        pop      rbp
        ret      
-						;; size=7 bbWeight=0.50 PerfScore 1.12
+						;; size=2 bbWeight=0.50 PerfScore 0.75
 G_M39229_IG10:
-       test     r11d, r11d
-       je       SHORT G_M39229_IG09
-       cmp      r10d, ebx
-       jne      SHORT G_M39229_IG09
-						;; size=10 bbWeight=1.98 PerfScore 4.95
+       test     r10d, r10d
+       je       SHORT G_M39229_IG07
+       cmp      ecx, eax
+       jne      SHORT G_M39229_IG08
+						;; size=9 bbWeight=1.98 PerfScore 4.95
 G_M39229_IG11:
-       inc      eax
-       cmp      eax, esi
-       jl       SHORT G_M39229_IG07
-						;; size=6 bbWeight=3.96 PerfScore 5.94
+       inc      r8d
+       cmp      r8d, esi
+       jl       SHORT G_M39229_IG05
+						;; size=8 bbWeight=3.96 PerfScore 5.94
 G_M39229_IG12:
        mov      eax, esi
 						;; size=2 bbWeight=0.50 PerfScore 0.12
 G_M39229_IG13:
-       add      rsp, 8
-       pop      rbx
        pop      rbp
        ret      
-						;; size=7 bbWeight=0.50 PerfScore 1.12
+						;; size=2 bbWeight=0.50 PerfScore 0.75
 G_M39229_IG14:
-       test     r9d, r9d
-       je       SHORT G_M39229_IG09
-       cmp      r11d, ebx
-       jne      SHORT G_M39229_IG09
-						;; size=10 bbWeight=0.02 PerfScore 0.05
-G_M39229_IG15:
-       inc      eax
-       cmp      eax, esi
-       jge      SHORT G_M39229_IG12
-						;; size=6 bbWeight=0.04 PerfScore 0.06
-G_M39229_IG16:
-       mov      r8d, eax
-       shl      r8, 3
-       lea      r9, bword ptr [rdi+r8]
-       movzx    r10, byte  ptr [r9]
-       mov      r11d, dword ptr [r9+0x04]
-       cmp      eax, ecx
-       jae      SHORT G_M39229_IG18
-       add      r8, rdx
-       movzx    r9, byte  ptr [r8]
-       mov      ebx, dword ptr [r8+0x04]
-       test     r10d, r10d
-       jne      SHORT G_M39229_IG14
-						;; size=39 bbWeight=0.04 PerfScore 0.48
-G_M39229_IG17:
-       test     r9d, r9d
-       jne      SHORT G_M39229_IG09
-       jmp      SHORT G_M39229_IG15
-						;; size=7 bbWeight=0.02 PerfScore 0.07
-G_M39229_IG18:
-       call     CORINFO_HELP_RNGCHKFAIL
+       mov      rax, 0xD1FFAB1E      ; code for System.ThrowHelper:ThrowArgumentOutOfRangeException()
+       call     [rax]System.ThrowHelper:ThrowArgumentOutOfRangeException()
        int3     
-						;; size=6 bbWeight=0 PerfScore 0.00
+						;; size=13 bbWeight=0 PerfScore 0.00
 
-; Total bytes of code 172, prolog size 8, PerfScore 67.72, instruction count 69, allocated bytes for code 172 (MethodHash=a15e66c2) for method System.MemoryExtensions:CommonPrefixLength[System.Nullable`1[int]](System.ReadOnlySpan`1[System.Nullable`1[int]],System.ReadOnlySpan`1[System.Nullable`1[int]]):int (FullOpts)
+; Total bytes of code 106, prolog size 4, PerfScore 63.57, instruction count 41, allocated bytes for code 106 (MethodHash=a15e66c2) for method System.MemoryExtensions:CommonPrefixLength[System.Nullable`1[int]](System.ReadOnlySpan`1[System.Nullable`1[int]],System.ReadOnlySpan`1[System.Nullable`1[int]]):int (FullOpts)
 ; ============================================================

-2 (-3.28 % of base) - System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[byte](byref,byref)

 ; Assembly listing for method System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[byte](byref,byref) (FullOpts)
 ; Emitting BLENDED_CODE for generic X64 + VEX + EVEX on Unix
 ; FullOpts code
 ; optimized code
 ; rbp based frame
 ; partially interruptible
 ; No PGO data
 ; 0 inlinees with PGO data; 2 single block inlinees; 2 inlinees without PGO data
 ; Final local variable assignments
 ;
-;  V00 arg0         [V00,T00] (  6,  4.50)   byref  ->  rdi         single-def
-;  V01 arg1         [V01,T01] (  6,  4.50)   byref  ->  rsi         single-def
+;  V00 arg0         [V00,T00] (  7,  7   )   byref  ->  rdi         single-def
+;  V01 arg1         [V01,T01] (  7,  5.50)   byref  ->  rsi         single-def
 ;# V02 OutArgs      [V02    ] (  1,  1   )  struct ( 0) [rsp+0x00]  do-not-enreg[XS] addr-exposed "OutgoingArgSpace" <Empty>
-;  V03 tmp1         [V03,T04] (  3,  3   )     int  ->  rcx         "Inlining Arg"
+;  V03 tmp1         [V03,T03] (  3,  3   )     int  ->  rcx         "Inlining Arg"
 ;* V04 tmp2         [V04    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[byte]>
 ;* V05 tmp3         [V05    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
-;  V06 tmp4         [V06,T05] (  3,  3   )     int  ->  rax         "Inlining Arg"
+;  V06 tmp4         [V06,T02] (  3,  6   )     int  ->  rax         "Inlining Arg"
 ;* V07 tmp5         [V07    ] (  0,  0   )  struct (16) zero-ref    ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[byte]>
 ;* V08 tmp6         [V08    ] (  0,  0   )   byref  ->  zero-ref    "Inlining Arg"
-;  V09 tmp7         [V09,T06] (  2,  1   )   byref  ->  rax         single-def "field V04._reference (fldOffset=0x0)" P-INDEP
+;  V09 tmp7         [V09,T07] (  2,  1   )   byref  ->  rax         single-def "field V04._reference (fldOffset=0x0)" P-INDEP
 ;* V10 tmp8         [V10    ] (  0,  0   )     int  ->  zero-ref    "field V04._length (fldOffset=0x8)" P-INDEP
-;  V11 tmp9         [V11,T07] (  2,  1   )   byref  ->  rcx         single-def "field V07._reference (fldOffset=0x0)" P-INDEP
+;  V11 tmp9         [V11,T06] (  2,  2   )   byref  ->  rcx         single-def "field V07._reference (fldOffset=0x0)" P-INDEP
 ;* V12 tmp10        [V12    ] (  0,  0   )     int  ->  zero-ref    "field V07._length (fldOffset=0x8)" P-INDEP
-;  V13 cse0         [V13,T02] (  5,  3.50)     int  ->  rcx         "CSE #01: aggressive"
-;  V14 cse1         [V14,T03] (  5,  3.50)     int  ->  rax         "CSE #02: aggressive"
+;  V13 cse0         [V13,T04] (  3,  2.50)     int  ->  rcx         "CSE #01: aggressive"
+;  V14 cse1         [V14,T05] (  3,  2.50)     int  ->  rax         "CSE #02: aggressive"
 ;
 ; Lcl frame size = 0
 
 G_M21521_IG01:
        push     rbp
        mov      rbp, rsp
 						;; size=4 bbWeight=1 PerfScore 1.25
 G_M21521_IG02:
        mov      eax, dword ptr [rsi+0x08]
        mov      ecx, dword ptr [rdi+0x08]
        cmp      eax, ecx
-       jg       SHORT G_M21521_IG04
+       jle      SHORT G_M21521_IG04
 						;; size=10 bbWeight=1 PerfScore 5.25
 G_M21521_IG03:
-       cmp      ecx, eax
-       jle      SHORT G_M21521_IG05
-       cmp      eax, ecx
-       ja       SHORT G_M21521_IG06
-       mov      rcx, bword ptr [rdi]
-       mov      bword ptr [rdi], rcx
-       mov      dword ptr [rdi+0x08], eax
-       jmp      SHORT G_M21521_IG05
-						;; size=19 bbWeight=0.50 PerfScore 4.25
-G_M21521_IG04:
        cmp      ecx, eax
        ja       SHORT G_M21521_IG06
        mov      rax, bword ptr [rsi]
        mov      bword ptr [rsi], rax
        mov      dword ptr [rsi+0x08], ecx
 						;; size=13 bbWeight=0.50 PerfScore 2.62
+G_M21521_IG04:
+       mov      eax, dword ptr [rsi+0x08]
+       cmp      eax, dword ptr [rdi+0x08]
+       ja       SHORT G_M21521_IG06
+       mov      rcx, bword ptr [rdi]
+       mov      bword ptr [rdi], rcx
+       mov      dword ptr [rdi+0x08], eax
+						;; size=17 bbWeight=1 PerfScore 10.00
 G_M21521_IG05:
        pop      rbp
        ret      
 						;; size=2 bbWeight=1 PerfScore 1.50
 G_M21521_IG06:
        mov      rax, 0xD1FFAB1E      ; code for System.ThrowHelper:ThrowArgumentOutOfRangeException()
        call     [rax]System.ThrowHelper:ThrowArgumentOutOfRangeException()
        int3     
 						;; size=13 bbWeight=0 PerfScore 0.00
 
-; Total bytes of code 61, prolog size 4, PerfScore 14.88, instruction count 24, allocated bytes for code 61 (MethodHash=9db7abee) for method System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[byte](byref,byref) (FullOpts)
+; Total bytes of code 59, prolog size 4, PerfScore 20.62, instruction count 22, allocated bytes for code 59 (MethodHash=9db7abee) for method System.MemoryExtensions:SliceLongerSpanToMatchShorterLength[byte](byref,byref) (FullOpts)
 ; ============================================================

Larger list of diffs: https://gist.github.com/MihuBot/0feabda3b251f61abc34597cd2ab12fc

[MihuBot]

@xtqqczze

[xtqqczze]

dotnet/runtime#121104