-54 (-6.09 % of base) - System.Text.Ascii:NarrowUtf16ToAscii(ulong,ulong,ulong):ulong
; Assembly listing for method System.Text.Ascii:NarrowUtf16ToAscii(ulong,ulong,ulong):ulong (FullOpts)
; Emitting BLENDED_CODE for X64 with AVX512 - Unix
; FullOpts code
; optimized code
; rbp based frame
; fully interruptible
; No PGO data
-; 0 inlinees with PGO data; 13 single block inlinees; 17 inlinees without PGO data
+; 0 inlinees with PGO data; 21 single block inlinees; 25 inlinees without PGO data
; Final local variable assignments
;
; V00 arg0 [V00,T06] ( 9, 9 ) long -> rdi single-def
; V01 arg1 [V01,T04] ( 15, 12 ) long -> rsi single-def
; V02 arg2 [V02,T11] ( 9, 6 ) long -> rdx single-def
; V03 loc0 [V03,T00] ( 23, 30 ) long -> rax
; V04 loc1 [V04,T12] ( 13, 6.50) int -> rcx
;* V05 loc2 [V05 ] ( 0, 0 ) int -> zero-ref
; V06 loc3 [V06,T05] ( 7, 14 ) long -> registers
; V07 loc4 [V07,T22] ( 5, 2.50) long -> rdx
; V08 loc5 [V08,T16] ( 2, 4.50) long -> rcx
;# V09 OutArgs [V09 ] ( 1, 1 ) struct ( 0) [rsp+0x00] do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
; V10 tmp1 [V10,T23] ( 3, 1.50) long -> rax "Inline return value spill temp"
; V11 tmp2 [V11,T07] ( 5, 9.50) byref -> rax single-def "Inline stloc first use temp"
; V12 tmp3 [V12,T30] ( 14, 17.50) simd64 -> mm0 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[ushort]>
; V13 tmp4 [V13,T13] ( 5, 6 ) byref -> rcx single-def "Inline stloc first use temp"
-; V14 tmp5 [V14,T01] ( 12, 27 ) long -> r8 "Inline stloc first use temp"
-; V15 tmp6 [V15,T17] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
-; V16 tmp7 [V16,T34] ( 3, 12 ) simd64 -> mm2 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[ushort]>
-;* V17 tmp8 [V17 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
-; V18 tmp9 [V18,T24] ( 3, 1.50) long -> rax "Inline return value spill temp"
-; V19 tmp10 [V19,T08] ( 5, 9.50) byref -> rax single-def "Inline stloc first use temp"
-; V20 tmp11 [V20,T31] ( 14, 17.50) simd32 -> mm0 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-; V21 tmp12 [V21,T14] ( 5, 6 ) byref -> rcx single-def "Inline stloc first use temp"
-; V22 tmp13 [V22,T02] ( 12, 27 ) long -> r8 "Inline stloc first use temp"
-; V23 tmp14 [V23,T18] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
-; V24 tmp15 [V24,T35] ( 3, 12 ) simd32 -> mm2 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V25 tmp16 [V25 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V26 tmp17 [V26 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V27 tmp18 [V27 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V28 tmp19 [V28 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V29 tmp20 [V29 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V30 tmp21 [V30 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V31 tmp22 [V31 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V32 tmp23 [V32 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V33 tmp24 [V33 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-; V34 tmp25 [V34,T25] ( 3, 1.50) long -> rax "Inline return value spill temp"
-;* V35 tmp26 [V35,T27] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
-;* V36 tmp27 [V36 ] ( 0, 0 ) long -> zero-ref "Inline stloc first use temp"
-; V37 tmp28 [V37,T09] ( 5, 9.50) byref -> rax single-def "Inline stloc first use temp"
-; V38 tmp29 [V38,T32] ( 14, 17.50) simd16 -> mm0 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-; V39 tmp30 [V39,T15] ( 5, 6 ) byref -> rcx single-def "Inline stloc first use temp"
-;* V40 tmp31 [V40 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
-; V41 tmp32 [V41,T03] ( 11, 26.50) long -> r8 "Inline stloc first use temp"
-; V42 tmp33 [V42,T19] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
-; V43 tmp34 [V43,T36] ( 3, 12 ) simd16 -> mm2 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V44 tmp35 [V44 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
-; V45 tmp36 [V45,T33] ( 2, 16 ) simd16 -> mm0 "Spilling op1 side effects for HWIntrinsic"
-;* V46 tmp37 [V46 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
-;* V47 tmp38 [V47 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V48 tmp39 [V48 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V49 tmp40 [V49 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
-;* V50 tmp41 [V50 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V51 tmp42 [V51 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V52 tmp43 [V52 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
-;* V53 tmp44 [V53 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V54 tmp45 [V54 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V55 tmp46 [V55 ] ( 0, 0 ) simd16 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V56 tmp47 [V56 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V57 tmp48 [V57 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V58 tmp49 [V58 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
-;* V59 tmp50 [V59 ] ( 0, 0 ) long -> zero-ref "Inlining Arg"
-; V60 tmp51 [V60,T28] ( 3, 24 ) simd16 -> mm0 "dup spill"
-;* V61 tmp52 [V61 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[uint]>
-;* V62 tmp53 [V62 ] ( 0, 0 ) byref -> zero-ref "Inlining Arg"
-; V63 tmp54 [V63,T20] ( 3, 3 ) byref -> r8 single-def "Inlining Arg"
-; V64 tmp55 [V64,T21] ( 3, 3 ) byref -> rdx "Inlining Arg"
-;* V65 tmp56 [V65,T26] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-; V66 cse0 [V66,T10] ( 3, 8.50) long -> r10 "CSE #12: conservative"
-; V67 cse1 [V67,T37] ( 5, 6 ) simd64 -> mm1 "CSE #02: conservative"
-; V68 cse2 [V68,T38] ( 5, 6 ) simd32 -> mm1 "CSE #07: conservative"
-; V69 cse3 [V69,T39] ( 5, 6 ) simd16 -> mm1 "CSE #11: conservative"
-; V70 rat0 [V70,T29] ( 3, 24 ) simd64 -> mm3 "ReplaceWithLclVar is creating a new local variable"
+;* V14 tmp5 [V14 ] ( 0, 0 ) simd64 -> zero-ref "spilled call-like call argument"
+; V15 tmp6 [V15,T01] ( 12, 27 ) long -> r8 "Inline stloc first use temp"
+; V16 tmp7 [V16,T17] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
+; V17 tmp8 [V17,T36] ( 3, 12 ) simd64 -> mm3 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector512`1[ushort]>
+;* V18 tmp9 [V18 ] ( 0, 0 ) simd64 -> zero-ref "spilled call-like call argument"
+; V19 tmp10 [V19,T33] ( 2, 16 ) simd64 -> mm0 "Spilling op1 side effects for HWIntrinsic"
+;* V20 tmp11 [V20 ] ( 0, 0 ) simd64 -> zero-ref "spilled call-like call argument"
+;* V21 tmp12 [V21 ] ( 0, 0 ) simd64 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V22 tmp13 [V22 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V23 tmp14 [V23 ] ( 0, 0 ) simd64 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V24 tmp15 [V24 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V25 tmp16 [V25 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
+;* V26 tmp17 [V26 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V27 tmp18 [V27 ] ( 0, 0 ) simd64 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V28 tmp19 [V28 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+; V29 tmp20 [V29,T24] ( 3, 1.50) long -> rax "Inline return value spill temp"
+; V30 tmp21 [V30,T08] ( 5, 9.50) byref -> rax single-def "Inline stloc first use temp"
+; V31 tmp22 [V31,T31] ( 14, 17.50) simd32 -> mm0 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+; V32 tmp23 [V32,T14] ( 5, 6 ) byref -> rcx single-def "Inline stloc first use temp"
+;* V33 tmp24 [V33 ] ( 0, 0 ) simd32 -> zero-ref "spilled call-like call argument"
+; V34 tmp25 [V34,T02] ( 12, 27 ) long -> r8 "Inline stloc first use temp"
+; V35 tmp26 [V35,T18] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
+; V36 tmp27 [V36,T37] ( 3, 12 ) simd32 -> mm2 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V37 tmp28 [V37 ] ( 0, 0 ) simd32 -> zero-ref "spilled call-like call argument"
+; V38 tmp29 [V38,T34] ( 2, 16 ) simd32 -> mm0 "Spilling op1 side effects for HWIntrinsic"
+;* V39 tmp30 [V39 ] ( 0, 0 ) simd32 -> zero-ref "spilled call-like call argument"
+;* V40 tmp31 [V40 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V41 tmp32 [V41 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V42 tmp33 [V42 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V43 tmp34 [V43 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V44 tmp35 [V44 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V45 tmp36 [V45 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V46 tmp37 [V46 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V47 tmp38 [V47 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V48 tmp39 [V48 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V49 tmp40 [V49 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V50 tmp41 [V50 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V51 tmp42 [V51 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V52 tmp43 [V52 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V53 tmp44 [V53 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V54 tmp45 [V54 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V55 tmp46 [V55 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+; V56 tmp47 [V56,T25] ( 3, 1.50) long -> rax "Inline return value spill temp"
+;* V57 tmp48 [V57,T27] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+;* V58 tmp49 [V58 ] ( 0, 0 ) long -> zero-ref "Inline stloc first use temp"
+; V59 tmp50 [V59,T09] ( 5, 9.50) byref -> rax single-def "Inline stloc first use temp"
+; V60 tmp51 [V60,T32] ( 14, 17.50) simd16 -> mm0 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+; V61 tmp52 [V61,T15] ( 5, 6 ) byref -> rcx single-def "Inline stloc first use temp"
+;* V62 tmp53 [V62 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
+; V63 tmp54 [V63,T03] ( 11, 26.50) long -> r8 "Inline stloc first use temp"
+; V64 tmp55 [V64,T19] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
+; V65 tmp56 [V65,T38] ( 3, 12 ) simd16 -> mm2 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+;* V66 tmp57 [V66 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
+; V67 tmp58 [V67,T35] ( 2, 16 ) simd16 -> mm0 "Spilling op1 side effects for HWIntrinsic"
+;* V68 tmp59 [V68 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
+;* V69 tmp60 [V69 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V70 tmp61 [V70 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+;* V71 tmp62 [V71 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* V72 tmp63 [V72 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V73 tmp64 [V73 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+;* V74 tmp65 [V74 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* V75 tmp66 [V75 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V76 tmp67 [V76 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+;* V77 tmp68 [V77 ] ( 0, 0 ) simd16 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+;* V78 tmp69 [V78 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V79 tmp70 [V79 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+;* V80 tmp71 [V80 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* V81 tmp72 [V81 ] ( 0, 0 ) long -> zero-ref "Inlining Arg"
+; V82 tmp73 [V82,T28] ( 3, 24 ) simd16 -> mm0 "dup spill"
+;* V83 tmp74 [V83 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[uint]>
+;* V84 tmp75 [V84 ] ( 0, 0 ) byref -> zero-ref "Inlining Arg"
+; V85 tmp76 [V85,T20] ( 3, 3 ) byref -> r8 single-def "Inlining Arg"
+; V86 tmp77 [V86,T21] ( 3, 3 ) byref -> rdx "Inlining Arg"
+;* V87 tmp78 [V87,T26] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+; V88 cse0 [V88,T10] ( 3, 8.50) long -> r10 "CSE #05: conservative"
+; V89 cse1 [V89,T39] ( 5, 6 ) simd64 -> mm1 "CSE #01: conservative"
+; V90 cse2 [V90,T40] ( 5, 6 ) simd32 -> mm1 "CSE #03: conservative"
+; V91 cse3 [V91,T41] ( 5, 6 ) simd16 -> mm1 "CSE #04: conservative"
+; V92 cse4 [V92,T42] ( 5, 6 ) simd64 -> mm2 "CSE #02: conservative"
+; V93 rat0 [V93,T29] ( 3, 24 ) simd64 -> mm4 "ReplaceWithLclVar is creating a new local variable"
;
; Lcl frame size = 0
G_M6063_IG01:
push rbp
mov rbp, rsp
;; size=4 bbWeight=1 PerfScore 1.25
G_M6063_IG02:
xor eax, eax
cmp rdx, 32
jb G_M6063_IG26
;; size=12 bbWeight=1 PerfScore 1.50
G_M6063_IG03:
mov rcx, qword ptr [rdi]
mov r8, 0xD1FFAB1E
test rcx, r8
mov r8, rcx
jne G_M6063_IG28
cmp rdx, 128
jae G_M6063_IG19
cmp rdx, 64
jae G_M6063_IG11
mov rax, rdi
vmovups xmm0, xmmword ptr [rax]
vmovups xmm1, xmmword ptr [reloc @RWD00]
vptest xmm0, xmm1
jne G_M6063_IG09
mov rcx, rsi
vpackuswb xmm0, xmm0, xmm0
vmovsd qword ptr [rcx], xmm0
mov r8d, 8
test sil, 8
jne SHORT G_M6063_IG04
vmovups xmm0, xmmword ptr [rax+0x10]
vptest xmm0, xmm1
jne SHORT G_M6063_IG08
vpackuswb xmm0, xmm0, xmm0
vmovsd qword ptr [rcx+0x08], xmm0
;; size=118 bbWeight=0.50 PerfScore 16.62
G_M6063_IG04:
mov r8, rsi
and r8, 15
neg r8
add r8, 16
lea r9, [rdx-0x10]
align [0 bytes for IG05]
;; size=18 bbWeight=0.50 PerfScore 0.75
G_M6063_IG05:
vmovups xmm0, xmmword ptr [rax+2*r8]
lea r10, [r8+0x08]
vmovups xmm2, xmmword ptr [rax+2*r10]
vpor xmm3, xmm0, xmm2
vptest xmm3, xmm1
je SHORT G_M6063_IG07
;; size=27 bbWeight=4 PerfScore 51.33
G_M6063_IG06:
vptest xmm0, xmm1
jne SHORT G_M6063_IG08
vpackuswb xmm0, xmm0, xmm0
vmovsd qword ptr [rcx+r8], xmm0
mov r8, r10
jmp SHORT G_M6063_IG08
align [0 bytes for IG13]
;; size=22 bbWeight=0.50 PerfScore 4.62
G_M6063_IG07:
vpackuswb xmm0, xmm0, xmm2
vmovups xmmword ptr [rcx+r8], xmm0
add r8, 16
cmp r8, r9
jbe SHORT G_M6063_IG05
;; size=19 bbWeight=4 PerfScore 18.00
G_M6063_IG08:
mov rax, r8
jmp SHORT G_M6063_IG10
;; size=5 bbWeight=0.50 PerfScore 1.12
G_M6063_IG09:
xor eax, eax
;; size=2 bbWeight=0.50 PerfScore 0.12
G_M6063_IG10:
jmp G_M6063_IG26
;; size=5 bbWeight=0.50 PerfScore 1.00
G_M6063_IG11:
mov rax, rdi
vmovups ymm0, ymmword ptr [rax]
vmovups ymm1, ymmword ptr [reloc @RWD32]
vptest ymm0, ymm1
jne G_M6063_IG17
mov rcx, rsi
- vpmovwb ymm0, ymm2
- vpmovwb ymm0, ymm0
- vinserti128 ymm0, ymm2, xmm0, 1
+ vpackuswb ymm0, ymm0, ymm0
+ vpermq ymm0, ymm0, -40
vmovups xmmword ptr [rcx], xmm0
mov r8d, 16
test sil, 16
jne SHORT G_M6063_IG12
vmovups ymm0, ymmword ptr [rax+0x20]
vptest ymm0, ymm1
- jne G_M6063_IG16
- vpmovwb ymm0, ymm2
- vpmovwb ymm0, ymm0
- vinserti128 ymm0, ymm2, xmm0, 1
+ jne SHORT G_M6063_IG16
+ vpackuswb ymm0, ymm0, ymm0
+ vpermq ymm0, ymm0, -40
vmovups xmmword ptr [rcx+0x10], xmm0
- ;; size=102 bbWeight=0.50 PerfScore 24.00
+ ;; size=82 bbWeight=0.50 PerfScore 19.00
G_M6063_IG12:
mov r8, rsi
and r8, 31
neg r8
add r8, 32
lea r9, [rdx-0x20]
;; size=18 bbWeight=0.50 PerfScore 0.75
G_M6063_IG13:
vmovups ymm0, ymmword ptr [rax+2*r8]
vmovups ymm2, ymmword ptr [rax+2*r8+0x20]
vpor ymm3, ymm0, ymm2
vptest ymm3, ymm1
je SHORT G_M6063_IG15
;; size=24 bbWeight=4 PerfScore 65.33
G_M6063_IG14:
vptest ymm0, ymm1
jne SHORT G_M6063_IG16
- vpmovwb ymm0, ymm2
- vpmovwb ymm0, ymm0
- vinserti128 ymm1, ymm2, xmm0, 1
- vmovups xmmword ptr [rcx+r8], xmm1
+ vpackuswb ymm0, ymm0, ymm0
+ vpermq ymm2, ymm0, -40
+ vmovups xmmword ptr [rcx+r8], xmm2
add r8, 16
jmp SHORT G_M6063_IG16
align [0 bytes for IG21]
- ;; size=37 bbWeight=0.50 PerfScore 9.12
+ ;; size=29 bbWeight=0.50 PerfScore 6.62
G_M6063_IG15:
- vpmovwb ymm0, ymm0
- vpmovwb ymm2, ymm2
- vinserti128 ymm0, ymm0, xmm2, 1
+ vpackuswb ymm0, ymm0, ymm2
+ vpermq ymm0, ymm0, -40
vmovups ymmword ptr [rcx+r8], ymm0
add r8, 32
cmp r8, r9
jbe SHORT G_M6063_IG13
- ;; size=33 bbWeight=4 PerfScore 46.00
+ ;; size=25 bbWeight=4 PerfScore 26.00
G_M6063_IG16:
mov rax, r8
jmp SHORT G_M6063_IG18
;; size=5 bbWeight=0.50 PerfScore 1.12
G_M6063_IG17:
xor eax, eax
;; size=2 bbWeight=0.50 PerfScore 0.12
G_M6063_IG18:
jmp G_M6063_IG26
;; size=5 bbWeight=0.50 PerfScore 1.00
G_M6063_IG19:
mov rax, rdi
vmovups zmm0, zmmword ptr [rax]
vmovups zmm1, zmmword ptr [reloc @RWD64]
vptestmw k1, zmm1, zmm0
kortestd k1, k1
jne G_M6063_IG25
mov rcx, rsi
- vpmovwb zmm0, zmm2
- vpmovwb zmm0, zmm0
- vinserti64x4 zmm0, zmm2, ymm0, 1
+ vpackuswb zmm0, zmm0, zmm0
+ vmovups zmm2, zmmword ptr [reloc @RWD128]
+ vpermq zmm0, zmm2, zmm0
vmovups ymmword ptr [rcx], ymm0
mov r8d, 32
test sil, 32
jne SHORT G_M6063_IG20
vmovups zmm0, zmmword ptr [rax+0x40]
vptestmw k1, zmm1, zmm0
kortestd k1, k1
jne G_M6063_IG24
- vpmovwb zmm0, zmm2
- vpmovwb zmm0, zmm0
- vinserti64x4 zmm0, zmm2, ymm0, 1
+ vpackuswb zmm0, zmm0, zmm0
+ vpermq zmm0, zmm2, zmm0
vmovups ymmword ptr [rcx+0x20], ymm0
- ;; size=122 bbWeight=0.50 PerfScore 21.50
+ ;; size=118 bbWeight=0.50 PerfScore 18.00
G_M6063_IG20:
mov r8, rsi
and r8, 63
neg r8
add r8, 64
lea r9, [rdx-0x40]
;; size=18 bbWeight=0.50 PerfScore 0.75
G_M6063_IG21:
vmovups zmm0, zmmword ptr [rax+2*r8]
- vmovups zmm2, zmmword ptr [rax+2*r8+0x40]
- vmovaps zmm3, zmm0
- vpternlogd zmm3, zmm2, zmm1, -88
- vptestmw k1, zmm3, zmm3
+ vmovups zmm3, zmmword ptr [rax+2*r8+0x40]
+ vmovaps zmm4, zmm0
+ vpternlogd zmm4, zmm3, zmm1, -88
+ vptestmw k1, zmm4, zmm4
kortestd k1, k1
je SHORT G_M6063_IG23
;; size=41 bbWeight=4 PerfScore 55.00
G_M6063_IG22:
vptestmw k1, zmm1, zmm0
kortestd k1, k1
jne SHORT G_M6063_IG24
- vpmovwb zmm0, zmm2
- vpmovwb zmm0, zmm0
- vinserti64x4 zmm1, zmm2, ymm0, 1
- vmovups ymmword ptr [rcx+r8], ymm1
+ vpackuswb zmm0, zmm0, zmm0
+ vpermq zmm3, zmm2, zmm0
+ vmovups ymmword ptr [rcx+r8], ymm3
add r8, 32
jmp SHORT G_M6063_IG24
align [0 bytes for IG27]
- ;; size=44 bbWeight=0.50 PerfScore 8.62
+ ;; size=37 bbWeight=0.50 PerfScore 6.12
G_M6063_IG23:
- vpmovwb zmm0, zmm0
- vpmovwb zmm2, zmm2
- vinserti64x4 zmm0, zmm0, ymm2, 1
+ vpackuswb zmm0, zmm0, zmm3
+ vpermq zmm0, zmm2, zmm0
vmovups zmmword ptr [rcx+r8], zmm0
add r8, 64
cmp r8, r9
jbe SHORT G_M6063_IG21
- ;; size=35 bbWeight=4 PerfScore 46.00
+ ;; size=28 bbWeight=4 PerfScore 26.00
G_M6063_IG24:
mov rax, r8
jmp SHORT G_M6063_IG26
;; size=5 bbWeight=0.50 PerfScore 1.12
G_M6063_IG25:
xor eax, eax
;; size=2 bbWeight=0.50 PerfScore 0.12
G_M6063_IG26:
sub rdx, rax
cmp rdx, 4
jb SHORT G_M6063_IG30
lea rcx, [rax+rdx-0x04]
;; size=14 bbWeight=0.50 PerfScore 1.25
G_M6063_IG27:
mov r8, qword ptr [rdi+2*rax]
mov r9, 0xD1FFAB1E
test r8, r9
je SHORT G_M6063_IG29
;; size=19 bbWeight=4 PerfScore 14.00
G_M6063_IG28:
mov ecx, r8d
test ecx, 0xD1FFAB1E
jne SHORT G_M6063_IG31
lea rdx, [rsi+rax]
mov byte ptr [rdx], cl
shr ecx, 16
mov byte ptr [rdx+0x01], cl
shr r8, 32
mov ecx, r8d
add rax, 2
jmp SHORT G_M6063_IG31
;; size=36 bbWeight=0.50 PerfScore 3.75
G_M6063_IG29:
vmovd xmm0, r8
vpackuswb xmm0, xmm0, xmm0
vmovd dword ptr [rsi+rax], xmm0
add rax, 4
cmp rax, rcx
jbe SHORT G_M6063_IG27
;; size=23 bbWeight=4 PerfScore 26.00
G_M6063_IG30:
test dl, 2
je SHORT G_M6063_IG33
mov ecx, dword ptr [rdi+2*rax]
test ecx, 0xD1FFAB1E
je SHORT G_M6063_IG32
;; size=16 bbWeight=0.50 PerfScore 2.25
G_M6063_IG31:
test ecx, 0xFF80
je SHORT G_M6063_IG34
jmp SHORT G_M6063_IG35
;; size=10 bbWeight=0.50 PerfScore 1.62
G_M6063_IG32:
lea r8, [rsi+rax]
mov byte ptr [r8], cl
shr ecx, 16
mov byte ptr [r8+0x01], cl
add rax, 2
;; size=18 bbWeight=0.50 PerfScore 1.62
G_M6063_IG33:
test dl, 1
je SHORT G_M6063_IG35
movzx rcx, word ptr [rdi+2*rax]
cmp ecx, 127
ja SHORT G_M6063_IG35
;; size=14 bbWeight=0.50 PerfScore 2.25
G_M6063_IG34:
mov byte ptr [rsi+rax], cl
inc rax
;; size=6 bbWeight=0.50 PerfScore 0.62
G_M6063_IG35:
vzeroupper
pop rbp
ret
;; size=5 bbWeight=1 PerfScore 2.50
RWD00 dq FF80FF80FF80FF80h, FF80FF80FF80FF80h
RWD16 dd 00000000h, 00000000h, 00000000h, 00000000h
RWD32 dq FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h
RWD64 dq FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h
+RWD128 dq 0000000000000000h, 0000000000000002h, 0000000000000004h, 0000000000000006h, 0000000000000001h, 0000000000000003h, 0000000000000005h, 0000000000000007h
-; Total bytes of code 886, prolog size 4, PerfScore 432.79, instruction count 210, allocated bytes for code 906 (MethodHash=53fae850) for method System.Text.Ascii:NarrowUtf16ToAscii(ulong,ulong,ulong):ulong (FullOpts)
+; Total bytes of code 832, prolog size 4, PerfScore 379.29, instruction count 203, allocated bytes for code 852 (MethodHash=53fae850) for method System.Text.Ascii:NarrowUtf16ToAscii(ulong,ulong,ulong):ulong (FullOpts)-39 (-4.58 % of base) - System.Runtime.Caching.MemoryCacheStatistics:InitDisposableMembers():this
; Assembly listing for method System.Runtime.Caching.MemoryCacheStatistics:InitDisposableMembers():this (FullOpts)
; Emitting BLENDED_CODE for X64 with AVX512 - Unix
; FullOpts code
; optimized code
; rbp based frame
; fully interruptible
; No PGO data
-; 0 inlinees with PGO data; 13 single block inlinees; 11 inlinees without PGO data
+; 0 inlinees with PGO data; 14 single block inlinees; 10 inlinees without PGO data
; Final local variable assignments
;
; V00 this [V00,T01] ( 9, 8 ) ref -> [rbp-0x38] this class-hnd EH-live single-def <System.Runtime.Caching.MemoryCacheStatistics>
-; V01 loc0 [V01,T19] ( 3, 2 ) ubyte -> [rbp-0x2C] do-not-enreg[M] EH-live
+; V01 loc0 [V01,T15] ( 3, 2 ) ubyte -> [rbp-0x2C] do-not-enreg[M] EH-live
;* V02 loc1 [V02 ] ( 0, 0 ) ref -> zero-ref class-hnd exact single-def <System.Threading.Timer>
-; V03 loc2 [V03,T18] ( 4, 2.50) ubyte -> [rbp-0x30] do-not-enreg[M] EH-live
+; V03 loc2 [V03,T14] ( 4, 2.50) ubyte -> [rbp-0x30] do-not-enreg[M] EH-live
;# V04 OutArgs [V04 ] ( 1, 1 ) struct ( 0) [rsp+0x00] do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
-; V05 tmp1 [V05,T06] ( 3, 6 ) ref -> rbx class-hnd exact single-def "NewObj constructor temp" <System.Runtime.Caching.CacheMemoryMonitor>
+; V05 tmp1 [V05,T05] ( 3, 6 ) ref -> rbx class-hnd exact single-def "NewObj constructor temp" <System.Runtime.Caching.CacheMemoryMonitor>
; V06 tmp2 [V06,T03] ( 4, 8 ) ref -> rbx class-hnd exact single-def "NewObj constructor temp" <System.Threading.TimerCallback>
-; V07 tmp3 [V07,T04] ( 4, 7 ) ref -> r15 class-hnd exact single-def "NewObj constructor temp" <System.Threading.Timer>
-; V08 tmp4 [V08,T07] ( 3, 6 ) ref -> r14 class-hnd exact single-def "NewObj constructor temp" <System.Runtime.Caching.GCHandleRef`1[System.Threading.Timer]>
+; V07 tmp3 [V07,T04] ( 4, 7 ) ref -> [rbp-0x40] class-hnd exact spill-single-def "NewObj constructor temp" <System.Threading.Timer>
+; V08 tmp4 [V08,T06] ( 3, 6 ) ref -> r12 class-hnd exact single-def "NewObj constructor temp" <System.Runtime.Caching.GCHandleRef`1[System.Threading.Timer]>
;* V09 tmp5 [V09 ] ( 0, 0 ) struct ( 8) zero-ref "location for address-of(RValue)" <System.Threading.AsyncFlowControl>
; V10 tmp6 [V10,T02] ( 5, 7 ) int -> r13 "Inlining Arg"
-; V11 tmp7 [V11,T13] ( 2, 3 ) int -> r14 "Inlining Arg"
+; V11 tmp7 [V11,T10] ( 2, 3 ) int -> r14 "Inlining Arg"
;* V12 tmp8 [V12 ] ( 0, 0 ) int -> zero-ref ld-addr-op "Inlining Arg"
-;* V13 tmp9 [V13,T22] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
+;* V13 tmp9 [V13,T17] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
;* V14 tmp10 [V14 ] ( 0, 0 ) int -> zero-ref ld-addr-op "Inlining Arg"
-;* V15 tmp11 [V15,T23] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
-; V16 tmp12 [V16,T00] ( 8, 15 ) ref -> r12 class-hnd exact single-def "NewObj constructor temp" <System.Threading.TimerQueueTimer>
-; V17 tmp13 [V17,T08] ( 3, 6 ) ref -> rbx class-hnd exact single-def "NewObj constructor temp" <System.Threading.TimerHolder>
-; V18 tmp14 [V18,T09] ( 3, 6 ) ref -> rbx class-hnd exact single-def "impAppendStmt" <System.Threading.TimerQueue[]>
-;* V19 tmp15 [V19 ] ( 0, 0 ) long -> zero-ref "impAppendStmt"
+;* V15 tmp11 [V15,T18] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
+; V16 tmp12 [V16,T00] ( 8, 15 ) ref -> [rbp-0x48] class-hnd exact spill-single-def "NewObj constructor temp" <System.Threading.TimerQueueTimer>
+; V17 tmp13 [V17,T07] ( 3, 6 ) ref -> r14 class-hnd exact single-def "NewObj constructor temp" <System.Threading.TimerHolder>
+; V18 tmp14 [V18,T08] ( 3, 6 ) ref -> [rbp-0x50] class-hnd exact spill-single-def "impAppendStmt" <System.Threading.TimerQueue[]>
+; V19 tmp15 [V19,T11] ( 2, 4 ) long -> rax "impAppendStmt"
;* V20 tmp16 [V20 ] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
-; V21 tmp17 [V21,T20] ( 3, 2 ) int -> rcx "Inline return value spill temp"
-; V22 tmp18 [V22,T05] ( 4, 7 ) int -> rcx "dup spill"
-;* V23 tmp19 [V23 ] ( 0, 0 ) int -> zero-ref single-def "Inline stloc first use temp"
-;* V24 tmp20 [V24 ] ( 0, 0 ) struct ( 8) zero-ref ld-addr-op "NewObj constructor temp" <System.Runtime.InteropServices.GCHandle>
-;* V25 tmp21 [V25 ] ( 0, 0 ) long -> zero-ref "Inline stloc first use temp"
-; V26 tmp22 [V26,T15] ( 4, 3.50) long -> rax "Inline stloc first use temp"
-;* V27 tmp23 [V27 ] ( 0, 0 ) ref -> zero-ref "field V09._thread (fldOffset=0x0)" P-INDEP
-; V28 tmp24 [V28,T21] ( 2, 2 ) long -> rax single-def "field V24._handle (fldOffset=0x0)" P-INDEP
-; V29 tmp25 [V29,T26] ( 2, 0 ) ref -> rdx single-def "argument with side effect"
-;* V30 tmp26 [V30 ] ( 0, 0 ) ref -> zero-ref single-def "argument with side effect"
-; V31 tmp27 [V31,T10] ( 3, 6 ) long -> rdx "index expr"
-; V32 PSPSym [V32,T24] ( 1, 1 ) long -> [rbp-0x40] do-not-enreg[V] "PSPSym"
-;* V33 cse0 [V33,T25] ( 0, 0 ) long -> zero-ref "CSE #03: moderate"
-; V34 cse1 [V34,T16] ( 3, 3 ) long -> rax "CSE #02: moderate"
-; V35 cse2 [V35,T17] ( 3, 3 ) int -> r14 "CSE #01: moderate"
-; V36 rat0 [V36,T14] ( 3, 4 ) long -> rax "TLS field access"
-; V37 rat1 [V37,T11] ( 3, 6 ) long -> rax "TLS access"
-; V38 rat2 [V38,T12] ( 3, 6 ) long -> rax "ThreadStaticBlockBase access"
+;* V21 tmp17 [V21 ] ( 0, 0 ) struct ( 8) zero-ref ld-addr-op "NewObj constructor temp" <System.Runtime.InteropServices.GCHandle>
+;* V22 tmp18 [V22 ] ( 0, 0 ) long -> zero-ref "Inline stloc first use temp"
+; V23 tmp19 [V23,T12] ( 4, 3.50) long -> rax "Inline stloc first use temp"
+;* V24 tmp20 [V24 ] ( 0, 0 ) ref -> zero-ref "field V09._thread (fldOffset=0x0)" P-INDEP
+; V25 tmp21 [V25,T16] ( 2, 2 ) long -> rax single-def "field V21._handle (fldOffset=0x0)" P-INDEP
+; V26 tmp22 [V26,T21] ( 2, 0 ) ref -> rdx single-def "argument with side effect"
+;* V27 tmp23 [V27 ] ( 0, 0 ) ref -> zero-ref single-def "argument with side effect"
+; V28 tmp24 [V28,T09] ( 3, 6 ) long -> rdx "index expr"
+; V29 PSPSym [V29,T19] ( 1, 1 ) long -> [rbp-0x60] do-not-enreg[V] "PSPSym"
+;* V30 cse0 [V30,T20] ( 0, 0 ) long -> zero-ref "CSE #02: moderate"
+; V31 cse1 [V31,T13] ( 3, 3 ) int -> r14 "CSE #01: moderate"
;
-; Lcl frame size = 24
+; Lcl frame size = 56
G_M44586_IG01:
push rbp
push r15
push r14
push r13
push r12
push rbx
- sub rsp, 24
- lea rbp, [rsp+0x40]
- mov qword ptr [rbp-0x40], rsp
+ sub rsp, 56
+ vzeroupper
+ lea rbp, [rsp+0x60]
+ mov qword ptr [rbp-0x60], rsp
mov gword ptr [rbp-0x38], rdi
- ;; size=27 bbWeight=1 PerfScore 8.75
+ ;; size=30 bbWeight=1 PerfScore 9.75
G_M44586_IG02:
mov dword ptr [rbp-0x2C], 1
;; size=7 bbWeight=1 PerfScore 1.00
G_M44586_IG03:
mov rdi, 0xD1FFAB1E ; System.Runtime.Caching.CacheMemoryMonitor
call CORINFO_HELP_NEWSFAST
mov rbx, rax
mov rdi, gword ptr [rbp-0x38]
mov edx, dword ptr [rdi+0x48]
mov rsi, gword ptr [rdi+0x20]
mov rdi, rbx
mov rax, 0xD1FFAB1E ; code for System.Runtime.Caching.CacheMemoryMonitor:.ctor(System.Runtime.Caching.MemoryCache,int):this
call [rax]System.Runtime.Caching.CacheMemoryMonitor:.ctor(System.Runtime.Caching.MemoryCache,int):this
mov rdi, gword ptr [rbp-0x38]
lea rdi, bword ptr [rdi+0x18]
mov rsi, rbx
call CORINFO_HELP_ASSIGN_REF
xor eax, eax
mov dword ptr [rbp-0x30], eax
;; size=65 bbWeight=1 PerfScore 14.00
G_M44586_IG04:
mov rax, 0xD1FFAB1E ; code for System.Threading.ExecutionContext:IsFlowSuppressed():ubyte
call [rax]System.Threading.ExecutionContext:IsFlowSuppressed():ubyte
test eax, eax
jne SHORT G_M44586_IG06
;; size=16 bbWeight=1 PerfScore 4.50
G_M44586_IG05:
mov rax, 0xD1FFAB1E ; code for System.Threading.ExecutionContext:SuppressFlow():System.Threading.AsyncFlowControl
call [rax]System.Threading.ExecutionContext:SuppressFlow():System.Threading.AsyncFlowControl
mov dword ptr [rbp-0x30], 1
;; size=19 bbWeight=0.50 PerfScore 2.12
G_M44586_IG06:
mov rdi, 0xD1FFAB1E ; System.Threading.TimerCallback
call CORINFO_HELP_NEWSFAST
mov rbx, rax
lea rdi, bword ptr [rbx+0x08]
mov rsi, gword ptr [rbp-0x38]
call CORINFO_HELP_ASSIGN_REF
mov rdi, 0xD1FFAB1E ; code for System.Runtime.Caching.MemoryCacheStatistics:CacheManagerTimerCallback(System.Object):this
mov qword ptr [rbx+0x18], rdi
mov rdi, 0xD1FFAB1E ; System.Threading.Timer
call CORINFO_HELP_NEWSFAST
- mov r15, rax
+ mov gword ptr [rbp-0x40], rax
mov rsi, gword ptr [rbp-0x38]
mov r14d, dword ptr [rsi+0x50]
mov r13d, r14d
cmp r13d, -1
- jl G_M44586_IG16
+ jl G_M44586_IG14
mov rdi, 0xD1FFAB1E ; System.Threading.TimerQueueTimer
call CORINFO_HELP_NEWSFAST
mov r12, rax
+ mov gword ptr [rbp-0x48], r12
lea rdi, bword ptr [r12+0x20]
mov rsi, rbx
call CORINFO_HELP_ASSIGN_REF
xor rax, rax
mov gword ptr [r12+0x28], rax
mov qword ptr [r12+0x48], -1
mov rax, 0xD1FFAB1E ; code for System.Threading.ExecutionContext:Capture():System.Threading.ExecutionContext
call [rax]System.Threading.ExecutionContext:Capture():System.Threading.ExecutionContext
lea rdi, bword ptr [r12+0x30]
mov rsi, rax
call CORINFO_HELP_ASSIGN_REF
- mov rdi, 0xD1FFAB1E ; global ptr
- test byte ptr [rdi], 1
- je G_M44586_IG14
- ;; size=175 bbWeight=1 PerfScore 26.00
+ mov rax, 0xD1FFAB1E ; global ptr
+ test byte ptr [rax], 1
+ je G_M44586_IG12
+ ;; size=180 bbWeight=1 PerfScore 27.75
G_M44586_IG07:
- mov rdi, 0xD1FFAB1E ; data for System.Threading.TimerQueue:<Instances>k__BackingField
- mov rbx, gword ptr [rdi]
- mov rdi, 0xD1FFAB1E
+ mov rax, 0xD1FFAB1E ; data for System.Threading.TimerQueue:<Instances>k__BackingField
+ mov rbx, gword ptr [rax]
+ mov gword ptr [rbp-0x50], rbx
mov rax, 0xD1FFAB1E ; function address
- call rax
- cmp dword ptr [rax], 2
- jl G_M44586_IG15
- mov rax, qword ptr [rax+0x08]
- mov rax, qword ptr [rax+0x10]
- test rax, rax
- je G_M44586_IG15
- ;; size=61 bbWeight=1 PerfScore 15.00
+ ;; size=27 bbWeight=1 PerfScore 3.50
G_M44586_IG08:
- mov ecx, dword ptr [rax+0x0A38]
- lea edx, [rcx-0x01]
- mov dword ptr [rax+0x0A38], edx
- movzx rax, cx
- test eax, eax
- je SHORT G_M44586_IG10
- ;; size=22 bbWeight=1 PerfScore 5.00
-G_M44586_IG09:
- sar ecx, 16
- jmp SHORT G_M44586_IG11
- ;; size=5 bbWeight=0.50 PerfScore 1.25
-G_M44586_IG10:
- mov rax, 0xD1FFAB1E ; code for System.Threading.ProcessorIdCache:RefreshCurrentProcessorId():int
- call [rax]System.Threading.ProcessorIdCache:RefreshCurrentProcessorId():int
- mov ecx, eax
- ;; size=14 bbWeight=0.50 PerfScore 1.75
-G_M44586_IG11:
- mov eax, ecx
+ call rax ; Interop+Sys:SchedGetCpu():int
+ mov eax, eax
mov rdx, 0xD1FFAB1E ; data for System.Threading.TimerQueue:<Instances>k__BackingField
mov rdx, gword ptr [rdx]
mov edi, dword ptr [rdx+0x08]
- xor edx, edx
- div rdx:rax, rdi
+ cqo
+ idiv rdx:rax, rdi
+ mov rbx, gword ptr [rbp-0x50]
mov edi, dword ptr [rbx+0x08]
cmp rdx, rdi
- jae G_M44586_IG17
+ jae G_M44586_IG15
mov rsi, gword ptr [rbx+8*rdx+0x10]
+ mov r12, gword ptr [rbp-0x48]
lea rdi, bword ptr [r12+0x08]
call CORINFO_HELP_ASSIGN_REF
+ mov rdi, 0xD1FFAB1E ; global ptr
+ cmp dword ptr [rdi], 0
+ jne SHORT G_M44586_IG13
+ ;; size=75 bbWeight=1 PerfScore 89.00
+G_M44586_IG09:
cmp r13d, -1
- je SHORT G_M44586_IG13
- ;; size=56 bbWeight=1 PerfScore 73.75
-G_M44586_IG12:
+ je SHORT G_M44586_IG11
+ ;; size=6 bbWeight=1 PerfScore 1.25
+G_M44586_IG10:
mov rdi, r12
mov esi, r13d
mov edx, r14d
mov rax, 0xD1FFAB1E ; code for System.Threading.TimerQueueTimer:Change(uint,uint):ubyte:this
call [rax]System.Threading.TimerQueueTimer:Change(uint,uint):ubyte:this
;; size=21 bbWeight=0.50 PerfScore 2.00
-G_M44586_IG13:
+G_M44586_IG11:
mov rdi, 0xD1FFAB1E ; System.Threading.TimerHolder
call CORINFO_HELP_NEWFAST
- mov rbx, rax
- lea rdi, bword ptr [rbx+0x08]
+ mov r14, rax
+ lea rdi, bword ptr [r14+0x08]
mov rsi, r12
call CORINFO_HELP_ASSIGN_REF
+ mov r15, gword ptr [rbp-0x40]
lea rdi, bword ptr [r15+0x08]
- mov rsi, rbx
+ mov rsi, r14
call CORINFO_HELP_ASSIGN_REF
- jmp SHORT G_M44586_IG18
- ;; size=44 bbWeight=1 PerfScore 7.00
-G_M44586_IG14:
+ jmp SHORT G_M44586_IG16
+ ;; size=48 bbWeight=1 PerfScore 8.00
+G_M44586_IG12:
mov rdi, 0xD1FFAB1E
mov esi, 946
call CORINFO_HELP_GETSHARED_NONGCSTATIC_BASE
jmp G_M44586_IG07
;; size=25 bbWeight=0 PerfScore 0.00
-G_M44586_IG15:
- mov edi, 2
- call CORINFO_HELP_GETSHARED_NONGCTHREADSTATIC_BASE_NOCTOR_OPTIMIZED
- jmp G_M44586_IG08
- ;; size=15 bbWeight=0 PerfScore 0.00
-G_M44586_IG16:
+G_M44586_IG13:
+ call CORINFO_HELP_POLL_GC
+ jmp SHORT G_M44586_IG09
+ ;; size=7 bbWeight=0 PerfScore 0.00
+G_M44586_IG14:
mov edi, 0x1710B
mov rsi, 0xD1FFAB1E
call CORINFO_HELP_STRCNS
mov rdx, rax
mov edi, r13d
mov esi, -1
mov rax, 0xD1FFAB1E ; code for System.ArgumentOutOfRangeException:ThrowLess[int](int,int,System.String)
call [rax]System.ArgumentOutOfRangeException:ThrowLess[int](int,int,System.String)
int3
;; size=44 bbWeight=0 PerfScore 0.00
-G_M44586_IG17:
+G_M44586_IG15:
call CORINFO_HELP_RNGCHKFAIL
int3
;; size=6 bbWeight=0 PerfScore 0.00
-G_M44586_IG18:
+G_M44586_IG16:
cmp dword ptr [rbp-0x30], 0
- je SHORT G_M44586_IG20
+ je SHORT G_M44586_IG18
;; size=6 bbWeight=1 PerfScore 3.00
-G_M44586_IG19:
+G_M44586_IG17:
mov rax, 0xD1FFAB1E ; code for System.Threading.ExecutionContext:RestoreFlow()
call [rax]System.Threading.ExecutionContext:RestoreFlow()
;; size=12 bbWeight=0.50 PerfScore 1.62
-G_M44586_IG20:
+G_M44586_IG18:
mov rdi, 0xD1FFAB1E ; System.Runtime.Caching.GCHandleRef`1[System.Threading.Timer]
call CORINFO_HELP_NEWSFAST
- mov r14, rax
+ mov r12, rax
mov rdi, r15
mov esi, 2
call System.Runtime.InteropServices.GCHandle:_InternalAlloc(System.Object,int):long
test rax, rax
- jne SHORT G_M44586_IG22
+ jne SHORT G_M44586_IG20
;; size=36 bbWeight=1 PerfScore 4.25
-G_M44586_IG21:
+G_M44586_IG19:
mov rdi, r15
mov esi, 2
mov rax, 0xD1FFAB1E ; code for System.Runtime.InteropServices.GCHandle:InternalAllocWithGCTransition(System.Object,int):long
call [rax]System.Runtime.InteropServices.GCHandle:InternalAllocWithGCTransition(System.Object,int):long
;; size=20 bbWeight=0.50 PerfScore 1.88
-G_M44586_IG22:
- mov qword ptr [r14+0x10], rax
+G_M44586_IG20:
+ mov qword ptr [r12+0x10], rax
mov rsi, gword ptr [rbp-0x38]
lea rdi, bword ptr [rsi+0x08]
- mov rsi, r14
+ mov rsi, r12
call CORINFO_HELP_ASSIGN_REF
xor edi, edi
mov dword ptr [rbp-0x2C], edi
- ;; size=25 bbWeight=1 PerfScore 5.00
-G_M44586_IG23:
- add rsp, 24
+ ;; size=26 bbWeight=1 PerfScore 5.00
+G_M44586_IG21:
+ add rsp, 56
pop rbx
pop r12
pop r13
pop r14
pop r15
pop rbp
ret
;; size=15 bbWeight=1 PerfScore 4.25
-G_M44586_IG24:
+G_M44586_IG22:
push rbp
push r15
push r14
push r13
push r12
push rbx
push rax
+ vzeroupper
mov rbp, qword ptr [rdi]
mov qword ptr [rsp], rbp
- lea rbp, [rbp+0x40]
- ;; size=22 bbWeight=0 PerfScore 0.00
-G_M44586_IG25:
+ lea rbp, [rbp+0x60]
+ ;; size=25 bbWeight=0 PerfScore 0.00
+G_M44586_IG23:
cmp dword ptr [rbp-0x30], 0
- je SHORT G_M44586_IG26
+ je SHORT G_M44586_IG24
mov rax, 0xD1FFAB1E ; code for System.Threading.ExecutionContext:RestoreFlow()
call [rax]System.Threading.ExecutionContext:RestoreFlow()
;; size=18 bbWeight=0 PerfScore 0.00
-G_M44586_IG26:
+G_M44586_IG24:
nop
;; size=1 bbWeight=0 PerfScore 0.00
-G_M44586_IG27:
+G_M44586_IG25:
add rsp, 8
pop rbx
pop r12
pop r13
pop r14
pop r15
pop rbp
ret
;; size=15 bbWeight=0 PerfScore 0.00
-G_M44586_IG28:
+G_M44586_IG26:
push rbp
push r15
push r14
push r13
push r12
push rbx
push rax
+ vzeroupper
mov rbp, qword ptr [rdi]
mov qword ptr [rsp], rbp
- lea rbp, [rbp+0x40]
- ;; size=22 bbWeight=0 PerfScore 0.00
-G_M44586_IG29:
+ lea rbp, [rbp+0x60]
+ ;; size=25 bbWeight=0 PerfScore 0.00
+G_M44586_IG27:
cmp dword ptr [rbp-0x2C], 0
- je SHORT G_M44586_IG30
+ je SHORT G_M44586_IG28
mov rdi, gword ptr [rbp-0x38]
mov rax, 0xD1FFAB1E ; code for System.Runtime.Caching.MemoryCacheStatistics:Dispose():this
call [rax]System.Runtime.Caching.MemoryCacheStatistics:Dispose():this
;; size=22 bbWeight=0 PerfScore 0.00
-G_M44586_IG30:
+G_M44586_IG28:
nop
;; size=1 bbWeight=0 PerfScore 0.00
-G_M44586_IG31:
+G_M44586_IG29:
add rsp, 8
pop rbx
pop r12
pop r13
pop r14
pop r15
pop rbp
ret
;; size=15 bbWeight=0 PerfScore 0.00
-; Total bytes of code 852, prolog size 27, PerfScore 182.12, instruction count 213, allocated bytes for code 852 (MethodHash=c52151d5) for method System.Runtime.Caching.MemoryCacheStatistics:InitDisposableMembers():this (FullOpts)
+; Total bytes of code 813, prolog size 30, PerfScore 182.88, instruction count 205, allocated bytes for code 813 (MethodHash=c52151d5) for method System.Runtime.Caching.MemoryCacheStatistics:InitDisposableMembers():this (FullOpts)-36 (-16.00 % of base) - System.Text.Ascii:NarrowUtf16ToAscii_Intrinsified_256(ulong,ulong,ulong):ulong
; Assembly listing for method System.Text.Ascii:NarrowUtf16ToAscii_Intrinsified_256(ulong,ulong,ulong):ulong (FullOpts)
; Emitting BLENDED_CODE for X64 with AVX512 - Unix
; FullOpts code
; optimized code
; rbp based frame
; fully interruptible
; No PGO data
-; 0 inlinees with PGO data; 0 single block inlinees; 4 inlinees without PGO data
+; 0 inlinees with PGO data; 4 single block inlinees; 8 inlinees without PGO data
; Final local variable assignments
;
; V00 arg0 [V00,T04] ( 3, 3 ) long -> rdi single-def
; V01 arg1 [V01,T03] ( 5, 3.50) long -> rsi single-def
; V02 arg2 [V02,T05] ( 3, 2.50) long -> rdx single-def
; V03 loc0 [V03,T01] ( 5, 10.50) byref -> rdi single-def
; V04 loc1 [V04,T07] ( 14, 18.50) simd32 -> mm0 <System.Runtime.Intrinsics.Vector256`1[ushort]>
; V05 loc2 [V05,T02] ( 5, 6 ) byref -> rax single-def
; V06 loc3 [V06,T00] ( 12, 27 ) long -> rcx
; V07 loc4 [V07,T06] ( 2, 4.50) long -> rdx
-; V08 loc5 [V08,T08] ( 3, 12 ) simd32 -> mm2 <System.Runtime.Intrinsics.Vector256`1[ushort]>
+; V08 loc5 [V08,T09] ( 3, 12 ) simd32 -> mm2 <System.Runtime.Intrinsics.Vector256`1[ushort]>
;# V09 OutArgs [V09 ] ( 1, 1 ) struct ( 0) [rsp+0x00] do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
-;* V10 tmp1 [V10 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V11 tmp2 [V11 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V12 tmp3 [V12 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V13 tmp4 [V13 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V10 tmp1 [V10 ] ( 0, 0 ) simd32 -> zero-ref "spilled call-like call argument"
+;* V11 tmp2 [V11 ] ( 0, 0 ) simd32 -> zero-ref "spilled call-like call argument"
+; V12 tmp3 [V12,T08] ( 2, 16 ) simd32 -> mm0 "Spilling op1 side effects for HWIntrinsic"
+;* V13 tmp4 [V13 ] ( 0, 0 ) simd32 -> zero-ref "spilled call-like call argument"
;* V14 tmp5 [V14 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
;* V15 tmp6 [V15 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V16 tmp7 [V16 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V17 tmp8 [V17 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V18 tmp9 [V18 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-; V19 cse0 [V19,T09] ( 5, 7 ) simd32 -> mm1 "CSE #02: moderate"
+;* V16 tmp7 [V16 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V17 tmp8 [V17 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V18 tmp9 [V18 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V19 tmp10 [V19 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V20 tmp11 [V20 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V21 tmp12 [V21 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V22 tmp13 [V22 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V23 tmp14 [V23 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V24 tmp15 [V24 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V25 tmp16 [V25 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V26 tmp17 [V26 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V27 tmp18 [V27 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V28 tmp19 [V28 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V29 tmp20 [V29 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+; V30 cse0 [V30,T10] ( 5, 7 ) simd32 -> mm1 "CSE #01: moderate"
;
; Lcl frame size = 0
G_M60588_IG01:
push rbp
mov rbp, rsp
;; size=4 bbWeight=1 PerfScore 1.25
G_M60588_IG02:
vmovups ymm0, ymmword ptr [rdi]
vmovups ymm1, ymmword ptr [reloc @RWD00]
vptest ymm0, ymm1
jne G_M60588_IG10
;; size=23 bbWeight=1 PerfScore 15.00
G_M60588_IG03:
mov rax, rsi
- vpmovwb ymm0, ymm2
- vpmovwb ymm0, ymm0
- vinserti128 ymm0, ymm2, xmm0, 1
+ vpackuswb ymm0, ymm0, ymm0
+ vpermq ymm0, ymm0, -40
vmovups xmmword ptr [rax], xmm0
mov ecx, 16
test sil, 16
jne SHORT G_M60588_IG04
vmovups ymm0, ymmword ptr [rdi+0x20]
vptest ymm0, ymm1
- jne G_M60588_IG08
- vpmovwb ymm0, ymm2
- vpmovwb ymm0, ymm0
- vinserti128 ymm0, ymm2, xmm0, 1
+ jne SHORT G_M60588_IG08
+ vpackuswb ymm0, ymm0, ymm0
+ vpermq ymm0, ymm0, -40
vmovups xmmword ptr [rax+0x10], xmm0
- ;; size=75 bbWeight=0.50 PerfScore 16.38
+ ;; size=55 bbWeight=0.50 PerfScore 11.38
G_M60588_IG04:
and rsi, 31
mov rcx, rsi
neg rcx
add rcx, 32
add rdx, -32
align [0 bytes for IG05]
;; size=18 bbWeight=0.50 PerfScore 0.62
G_M60588_IG05:
vmovups ymm0, ymmword ptr [rdi+2*rcx]
vmovups ymm2, ymmword ptr [rdi+2*rcx+0x20]
vpor ymm3, ymm0, ymm2
vptest ymm3, ymm1
je SHORT G_M60588_IG07
;; size=22 bbWeight=4 PerfScore 65.33
G_M60588_IG06:
vptest ymm0, ymm1
jne SHORT G_M60588_IG08
- vpmovwb ymm0, ymm2
- vpmovwb ymm0, ymm0
- vinserti128 ymm1, ymm2, xmm0, 1
- vmovups xmmword ptr [rax+rcx], xmm1
+ vpackuswb ymm0, ymm0, ymm0
+ vpermq ymm2, ymm0, -40
+ vmovups xmmword ptr [rax+rcx], xmm2
add rcx, 16
jmp SHORT G_M60588_IG08
- ;; size=36 bbWeight=0.50 PerfScore 9.12
+ ;; size=28 bbWeight=0.50 PerfScore 6.62
G_M60588_IG07:
- vpmovwb ymm0, ymm0
- vpmovwb ymm2, ymm2
- vinserti128 ymm0, ymm0, xmm2, 1
+ vpackuswb ymm0, ymm0, ymm2
+ vpermq ymm0, ymm0, -40
vmovups ymmword ptr [rax+rcx], ymm0
add rcx, 32
cmp rcx, rdx
jbe SHORT G_M60588_IG05
- ;; size=32 bbWeight=4 PerfScore 46.00
+ ;; size=24 bbWeight=4 PerfScore 26.00
G_M60588_IG08:
mov rax, rcx
;; size=3 bbWeight=0.50 PerfScore 0.12
G_M60588_IG09:
vzeroupper
pop rbp
ret
;; size=5 bbWeight=0.50 PerfScore 1.25
G_M60588_IG10:
xor eax, eax
;; size=2 bbWeight=0.50 PerfScore 0.12
G_M60588_IG11:
vzeroupper
pop rbp
ret
;; size=5 bbWeight=0.50 PerfScore 1.25
RWD00 dq FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h
-; Total bytes of code 225, prolog size 4, PerfScore 156.46, instruction count 55, allocated bytes for code 225 (MethodHash=910c1353) for method System.Text.Ascii:NarrowUtf16ToAscii_Intrinsified_256(ulong,ulong,ulong):ulong (FullOpts)
+; Total bytes of code 189, prolog size 4, PerfScore 128.96, instruction count 51, allocated bytes for code 189 (MethodHash=910c1353) for method System.Text.Ascii:NarrowUtf16ToAscii_Intrinsified_256(ulong,ulong,ulong):ulong (FullOpts)-18 (-6.57 % of base) - System.Text.Ascii:NarrowUtf16ToAscii_Intrinsified_512(ulong,ulong,ulong):ulong
; Assembly listing for method System.Text.Ascii:NarrowUtf16ToAscii_Intrinsified_512(ulong,ulong,ulong):ulong (FullOpts)
; Emitting BLENDED_CODE for X64 with AVX512 - Unix
; FullOpts code
; optimized code
; rbp based frame
; fully interruptible
; No PGO data
-; 0 inlinees with PGO data; 4 single block inlinees; 0 inlinees without PGO data
+; 0 inlinees with PGO data; 8 single block inlinees; 4 inlinees without PGO data
; Final local variable assignments
;
; V00 arg0 [V00,T04] ( 3, 3 ) long -> rdi single-def
; V01 arg1 [V01,T03] ( 5, 3.50) long -> rsi single-def
; V02 arg2 [V02,T05] ( 3, 2.50) long -> rdx single-def
; V03 loc0 [V03,T01] ( 5, 10.50) byref -> rdi single-def
; V04 loc1 [V04,T08] ( 14, 18.50) simd64 -> mm0 <System.Runtime.Intrinsics.Vector512`1[ushort]>
; V05 loc2 [V05,T02] ( 5, 6 ) byref -> rax single-def
; V06 loc3 [V06,T00] ( 12, 27 ) long -> rcx
; V07 loc4 [V07,T06] ( 2, 4.50) long -> rdx
-; V08 loc5 [V08,T09] ( 3, 12 ) simd64 -> mm2 <System.Runtime.Intrinsics.Vector512`1[ushort]>
+; V08 loc5 [V08,T10] ( 3, 12 ) simd64 -> mm3 <System.Runtime.Intrinsics.Vector512`1[ushort]>
;# V09 OutArgs [V09 ] ( 1, 1 ) struct ( 0) [rsp+0x00] do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
-;* V10 tmp1 [V10 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
-; V11 cse0 [V11,T10] ( 5, 7 ) simd64 -> mm1 "CSE #02: moderate"
-; V12 rat0 [V12,T07] ( 3, 24 ) simd64 -> mm3 "ReplaceWithLclVar is creating a new local variable"
+;* V10 tmp1 [V10 ] ( 0, 0 ) simd64 -> zero-ref "spilled call-like call argument"
+;* V11 tmp2 [V11 ] ( 0, 0 ) simd64 -> zero-ref "spilled call-like call argument"
+; V12 tmp3 [V12,T09] ( 2, 16 ) simd64 -> mm0 "Spilling op1 side effects for HWIntrinsic"
+;* V13 tmp4 [V13 ] ( 0, 0 ) simd64 -> zero-ref "spilled call-like call argument"
+;* V14 tmp5 [V14 ] ( 0, 0 ) simd64 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V15 tmp6 [V15 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V16 tmp7 [V16 ] ( 0, 0 ) simd64 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V17 tmp8 [V17 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V18 tmp9 [V18 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ushort]>
+;* V19 tmp10 [V19 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V20 tmp11 [V20 ] ( 0, 0 ) simd64 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+;* V21 tmp12 [V21 ] ( 0, 0 ) simd64 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector512`1[ubyte]>
+; V22 cse0 [V22,T11] ( 5, 7 ) simd64 -> mm1 "CSE #01: moderate"
+; V23 cse1 [V23,T12] ( 5, 6 ) simd64 -> mm2 "CSE #02: moderate"
+; V24 rat0 [V24,T07] ( 3, 24 ) simd64 -> mm4 "ReplaceWithLclVar is creating a new local variable"
;
; Lcl frame size = 0
G_M60939_IG01:
push rbp
mov rbp, rsp
;; size=4 bbWeight=1 PerfScore 1.25
G_M60939_IG02:
vmovups zmm0, zmmword ptr [rdi]
vmovups zmm1, zmmword ptr [reloc @RWD00]
vptestmw k1, zmm1, zmm0
kortestd k1, k1
jne G_M60939_IG10
;; size=33 bbWeight=1 PerfScore 12.00
G_M60939_IG03:
mov rax, rsi
- vpmovwb zmm0, zmm2
- vpmovwb zmm0, zmm0
- vinserti64x4 zmm0, zmm2, ymm0, 1
+ vpackuswb zmm0, zmm0, zmm0
+ vmovups zmm2, zmmword ptr [reloc @RWD64]
+ vpermq zmm0, zmm2, zmm0
vmovups ymmword ptr [rax], ymm0
mov ecx, 32
test sil, 32
jne SHORT G_M60939_IG04
vmovups zmm0, zmmword ptr [rdi+0x40]
vptestmw k1, zmm1, zmm0
kortestd k1, k1
jne G_M60939_IG08
- vpmovwb zmm0, zmm2
- vpmovwb zmm0, zmm0
- vinserti64x4 zmm0, zmm2, ymm0, 1
+ vpackuswb zmm0, zmm0, zmm0
+ vpermq zmm0, zmm2, zmm0
vmovups ymmword ptr [rax+0x20], ymm0
- ;; size=85 bbWeight=0.50 PerfScore 15.38
+ ;; size=81 bbWeight=0.50 PerfScore 11.88
G_M60939_IG04:
and rsi, 63
mov rcx, rsi
neg rcx
add rcx, 64
add rdx, -64
align [0 bytes for IG05]
;; size=18 bbWeight=0.50 PerfScore 0.62
G_M60939_IG05:
vmovups zmm0, zmmword ptr [rdi+2*rcx]
- vmovups zmm2, zmmword ptr [rdi+2*rcx+0x40]
- vmovaps zmm3, zmm0
- vpternlogd zmm3, zmm2, zmm1, -88
- vptestmw k1, zmm3, zmm3
+ vmovups zmm3, zmmword ptr [rdi+2*rcx+0x40]
+ vmovaps zmm4, zmm0
+ vpternlogd zmm4, zmm3, zmm1, -88
+ vptestmw k1, zmm4, zmm4
kortestd k1, k1
je SHORT G_M60939_IG07
;; size=41 bbWeight=4 PerfScore 55.00
G_M60939_IG06:
vptestmw k1, zmm1, zmm0
kortestd k1, k1
jne SHORT G_M60939_IG08
- vpmovwb zmm0, zmm2
- vpmovwb zmm0, zmm0
- vinserti64x4 zmm1, zmm2, ymm0, 1
- vmovups ymmword ptr [rax+rcx], ymm1
+ vpackuswb zmm0, zmm0, zmm0
+ vpermq zmm3, zmm2, zmm0
+ vmovups ymmword ptr [rax+rcx], ymm3
add rcx, 32
jmp SHORT G_M60939_IG08
- ;; size=43 bbWeight=0.50 PerfScore 8.62
+ ;; size=36 bbWeight=0.50 PerfScore 6.12
G_M60939_IG07:
- vpmovwb zmm0, zmm0
- vpmovwb zmm2, zmm2
- vinserti64x4 zmm0, zmm0, ymm2, 1
+ vpackuswb zmm0, zmm0, zmm3
+ vpermq zmm0, zmm2, zmm0
vmovups zmmword ptr [rax+rcx], zmm0
add rcx, 64
cmp rcx, rdx
jbe SHORT G_M60939_IG05
- ;; size=35 bbWeight=4 PerfScore 46.00
+ ;; size=28 bbWeight=4 PerfScore 26.00
G_M60939_IG08:
mov rax, rcx
;; size=3 bbWeight=0.50 PerfScore 0.12
G_M60939_IG09:
vzeroupper
pop rbp
ret
;; size=5 bbWeight=0.50 PerfScore 1.25
G_M60939_IG10:
xor eax, eax
;; size=2 bbWeight=0.50 PerfScore 0.12
G_M60939_IG11:
vzeroupper
pop rbp
ret
;; size=5 bbWeight=0.50 PerfScore 1.25
RWD00 dq FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h, FF80FF80FF80FF80h
+RWD64 dq 0000000000000000h, 0000000000000002h, 0000000000000004h, 0000000000000006h, 0000000000000001h, 0000000000000003h, 0000000000000005h, 0000000000000007h
-; Total bytes of code 274, prolog size 4, PerfScore 141.62, instruction count 60, allocated bytes for code 286 (MethodHash=483911f4) for method System.Text.Ascii:NarrowUtf16ToAscii_Intrinsified_512(ulong,ulong,ulong):ulong (FullOpts)
+; Total bytes of code 256, prolog size 4, PerfScore 115.62, instruction count 57, allocated bytes for code 268 (MethodHash=483911f4) for method System.Text.Ascii:NarrowUtf16ToAscii_Intrinsified_512(ulong,ulong,ulong):ulong (FullOpts)-16 (-2.19 % of base) - System.Net.NetworkInformation.NetworkChange:add_NetworkAvailabilityChanged(System.Net.NetworkInformation.NetworkAvailabilityChangedEventHandler)
; Assembly listing for method System.Net.NetworkInformation.NetworkChange:add_NetworkAvailabilityChanged(System.Net.NetworkInformation.NetworkAvailabilityChangedEventHandler) (FullOpts)
; Emitting BLENDED_CODE for X64 with AVX512 - Unix
; FullOpts code
; optimized code
; rbp based frame
; fully interruptible
; No PGO data
-; 0 inlinees with PGO data; 13 single block inlinees; 9 inlinees without PGO data
+; 0 inlinees with PGO data; 14 single block inlinees; 8 inlinees without PGO data
; Final local variable assignments
;
-; V00 arg0 [V00,T01] ( 4, 3.50) ref -> rbx class-hnd single-def <System.Net.NetworkInformation.NetworkAvailabilityChangedEventHandler>
-; V01 loc0 [V01,T15] ( 4, 1 ) ref -> [rbp-0x38] class-hnd exact EH-live spill-single-def <System.Object>
+; V00 arg0 [V00,T01] ( 4, 3.50) ref -> [rbp-0x38] class-hnd single-def <System.Net.NetworkInformation.NetworkAvailabilityChangedEventHandler>
+; V01 loc0 [V01,T10] ( 4, 1 ) ref -> [rbp-0x40] class-hnd exact EH-live spill-single-def <System.Object>
; V02 loc1 [V02 ] ( 5, 2 ) ubyte -> [rbp-0x28] do-not-enreg[X] addr-exposed ld-addr-op
; V03 loc2 [V03 ] ( 3, 1 ) struct ( 8) [rbp-0x30] do-not-enreg[XS] must-init addr-exposed ld-addr-op <System.Threading.AsyncFlowControl>
;# V04 OutArgs [V04 ] ( 1, 1 ) struct ( 0) [rsp+0x00] do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
-; V05 tmp1 [V05,T10] ( 2, 2 ) ref -> r15 class-hnd exact single-def "impAppendStmt" <System.Collections.Generic.Dictionary`2[System.Net.NetworkInformation.NetworkAvailabilityChangedEventHandler,System.Threading.ExecutionContext]>
-; V06 tmp2 [V06,T03] ( 3, 3 ) ref -> r15 class-hnd exact single-def "NewObj constructor temp" <System.Threading.Timer>
-; V07 tmp3 [V07,T11] ( 2, 2 ) ref -> r14 class-hnd exact single-def "Inlining Arg" <System.Threading.TimerCallback>
-;* V08 tmp4 [V08,T16] ( 0, 0 ) int -> zero-ref ld-addr-op "Inlining Arg"
-;* V09 tmp5 [V09,T19] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
-;* V10 tmp6 [V10,T17] ( 0, 0 ) int -> zero-ref ld-addr-op "Inlining Arg"
-;* V11 tmp7 [V11,T20] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
-; V12 tmp8 [V12,T00] ( 7, 7 ) ref -> r13 class-hnd exact single-def "NewObj constructor temp" <System.Threading.TimerQueueTimer>
-; V13 tmp9 [V13,T04] ( 3, 3 ) ref -> r14 class-hnd exact single-def "NewObj constructor temp" <System.Threading.TimerHolder>
-; V14 tmp10 [V14,T05] ( 3, 3 ) ref -> r14 class-hnd exact single-def "impAppendStmt" <System.Threading.TimerQueue[]>
-;* V15 tmp11 [V15 ] ( 0, 0 ) long -> zero-ref "impAppendStmt"
+; V05 tmp1 [V05,T06] ( 2, 2 ) ref -> r15 class-hnd exact single-def "impAppendStmt" <System.Collections.Generic.Dictionary`2[System.Net.NetworkInformation.NetworkAvailabilityChangedEventHandler,System.Threading.ExecutionContext]>
+; V06 tmp2 [V06,T02] ( 3, 3 ) ref -> [rbp-0x48] class-hnd exact spill-single-def "NewObj constructor temp" <System.Threading.Timer>
+; V07 tmp3 [V07,T07] ( 2, 2 ) ref -> r14 class-hnd exact single-def "Inlining Arg" <System.Threading.TimerCallback>
+;* V08 tmp4 [V08,T11] ( 0, 0 ) int -> zero-ref ld-addr-op "Inlining Arg"
+;* V09 tmp5 [V09,T14] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
+;* V10 tmp6 [V10,T12] ( 0, 0 ) int -> zero-ref ld-addr-op "Inlining Arg"
+;* V11 tmp7 [V11,T15] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
+; V12 tmp8 [V12,T00] ( 7, 7 ) ref -> [rbp-0x50] class-hnd exact spill-single-def "NewObj constructor temp" <System.Threading.TimerQueueTimer>
+; V13 tmp9 [V13,T03] ( 3, 3 ) ref -> rbx class-hnd exact single-def "NewObj constructor temp" <System.Threading.TimerHolder>
+; V14 tmp10 [V14,T04] ( 3, 3 ) ref -> [rbp-0x58] class-hnd exact spill-single-def "impAppendStmt" <System.Threading.TimerQueue[]>
+; V15 tmp11 [V15,T09] ( 2, 2 ) long -> rax "impAppendStmt"
;* V16 tmp12 [V16 ] ( 0, 0 ) int -> zero-ref "Inline return value spill temp"
-; V17 tmp13 [V17,T13] ( 3, 1.50) int -> rcx "Inline return value spill temp"
-; V18 tmp14 [V18,T02] ( 4, 4 ) int -> rcx "dup spill"
-;* V19 tmp15 [V19 ] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
-; V20 tmp16 [V20,T12] ( 2, 2 ) ref -> rdx class-hnd exact single-def "Inlining Arg" <System.Threading.ExecutionContext>
-; V21 tmp17 [V21 ] ( 3, 1 ) ref -> [rbp-0x30] do-not-enreg[X] addr-exposed "field V03._thread (fldOffset=0x0)" P-DEP
-;* V22 tmp18 [V22 ] ( 0, 0 ) ref -> zero-ref single-def "argument with side effect"
-;* V23 tmp19 [V23 ] ( 0, 0 ) ref -> zero-ref single-def "argument with side effect"
-; V24 tmp20 [V24,T06] ( 3, 3 ) long -> rdx "index expr"
-; V25 PSPSym [V25,T18] ( 1, 1 ) long -> [rbp-0x40] do-not-enreg[V] "PSPSym"
-;* V26 cse0 [V26,T21] ( 0, 0 ) long -> zero-ref "CSE #02: moderate"
-; V27 cse1 [V27,T14] ( 3, 1.50) long -> rax "CSE #01: moderate"
-; V28 rat0 [V28,T09] ( 3, 2 ) long -> rax "TLS field access"
-; V29 rat1 [V29,T07] ( 3, 3 ) long -> rax "TLS access"
-; V30 rat2 [V30,T08] ( 3, 3 ) long -> rax "ThreadStaticBlockBase access"
+; V17 tmp13 [V17,T08] ( 2, 2 ) ref -> rdx class-hnd exact single-def "Inlining Arg" <System.Threading.ExecutionContext>
+; V18 tmp14 [V18 ] ( 3, 1 ) ref -> [rbp-0x30] do-not-enreg[X] addr-exposed "field V03._thread (fldOffset=0x0)" P-DEP
+;* V19 tmp15 [V19 ] ( 0, 0 ) ref -> zero-ref single-def "argument with side effect"
+;* V20 tmp16 [V20 ] ( 0, 0 ) ref -> zero-ref single-def "argument with side effect"
+; V21 tmp17 [V21,T05] ( 3, 3 ) long -> rdx "index expr"
+; V22 PSPSym [V22,T13] ( 1, 1 ) long -> [rbp-0x60] do-not-enreg[V] "PSPSym"
+;* V23 cse0 [V23,T16] ( 0, 0 ) long -> zero-ref "CSE #01: moderate"
;
-; Lcl frame size = 32
+; Lcl frame size = 64
G_M59891_IG01:
push rbp
push r15
push r14
push r13
push rbx
- sub rsp, 32
- lea rbp, [rsp+0x40]
+ sub rsp, 64
+ vzeroupper
+ lea rbp, [rsp+0x60]
xor eax, eax
mov qword ptr [rbp-0x30], rax
- mov qword ptr [rbp-0x40], rsp
+ mov qword ptr [rbp-0x60], rsp
mov rbx, rdi
- ;; size=30 bbWeight=1 PerfScore 8.25
+ ;; size=33 bbWeight=1 PerfScore 9.25
G_M59891_IG02:
+ mov gword ptr [rbp-0x38], rbx
test rbx, rbx
- je G_M59891_IG18
- ;; size=9 bbWeight=1 PerfScore 1.25
+ je G_M59891_IG17
+ ;; size=13 bbWeight=1 PerfScore 2.25
G_M59891_IG03:
+ mov rbx, gword ptr [rbp-0x38]
mov rsi, 0xD1FFAB1E ; const ptr
mov rdi, gword ptr [rsi]
- mov gword ptr [rbp-0x38], rdi
+ mov gword ptr [rbp-0x40], rdi
xor esi, esi
mov dword ptr [rbp-0x28], esi
- ;; size=22 bbWeight=0.50 PerfScore 2.25
+ ;; size=26 bbWeight=0.50 PerfScore 2.75
G_M59891_IG04:
cmp byte ptr [rbp-0x28], 0
- jne G_M59891_IG16
+ jne G_M59891_IG15
lea rsi, [rbp-0x28]
call System.Threading.Monitor:ReliableEnter(System.Object,byref)
mov rax, 0xD1FFAB1E ; data for System.Net.NetworkInformation.NetworkChange:s_socket
cmp gword ptr [rax], 0
jne SHORT G_M59891_IG05
mov rax, 0xD1FFAB1E ; code for System.Net.NetworkInformation.NetworkChange:CreateSocket()
call [rax]System.Net.NetworkInformation.NetworkChange:CreateSocket()
;; size=47 bbWeight=0.50 PerfScore 6.00
G_M59891_IG05:
mov rax, 0xD1FFAB1E ; data for System.Net.NetworkInformation.NetworkChange:s_availabilityTimer
cmp gword ptr [rax], 0
- jne G_M59891_IG15
+ jne G_M59891_IG14
mov rax, 0xD1FFAB1E ; code for System.Threading.ExecutionContext:SuppressFlow():System.Threading.AsyncFlowControl
call [rax]System.Threading.ExecutionContext:SuppressFlow():System.Threading.AsyncFlowControl
mov gword ptr [rbp-0x30], rax
;; size=36 bbWeight=0.50 PerfScore 4.25
G_M59891_IG06:
mov rdi, 0xD1FFAB1E ; System.Threading.Timer
call CORINFO_HELP_NEWSFAST
- mov r15, rax
+ mov gword ptr [rbp-0x48], rax
mov rdi, 0xD1FFAB1E ; const ptr
mov r14, gword ptr [rdi]
mov rdi, 0xD1FFAB1E ; System.Threading.TimerQueueTimer
call CORINFO_HELP_NEWSFAST
mov r13, rax
+ mov gword ptr [rbp-0x50], r13
lea rdi, bword ptr [r13+0x20]
mov rsi, r14
call CORINFO_HELP_ASSIGN_REF
xor rax, rax
mov gword ptr [r13+0x28], rax
mov qword ptr [r13+0x48], -1
mov rax, 0xD1FFAB1E ; code for System.Threading.ExecutionContext:Capture():System.Threading.ExecutionContext
call [rax]System.Threading.ExecutionContext:Capture():System.Threading.ExecutionContext
lea rdi, bword ptr [r13+0x30]
mov rsi, rax
call CORINFO_HELP_ASSIGN_REF
- mov rdi, 0xD1FFAB1E ; global ptr
- test byte ptr [rdi], 1
- je G_M59891_IG11
- ;; size=118 bbWeight=0.50 PerfScore 9.25
+ mov rax, 0xD1FFAB1E ; global ptr
+ test byte ptr [rax], 1
+ je G_M59891_IG10
+ ;; size=123 bbWeight=0.50 PerfScore 10.12
G_M59891_IG07:
- mov rdi, 0xD1FFAB1E ; data for System.Threading.TimerQueue:<Instances>k__BackingField
- mov r14, gword ptr [rdi]
- mov rdi, 0xD1FFAB1E
- mov rax, 0xD1FFAB1E ; function address
- call rax
- cmp dword ptr [rax], 2
- jl G_M59891_IG12
- mov rax, qword ptr [rax+0x08]
- mov rax, qword ptr [rax+0x10]
- test rax, rax
- je G_M59891_IG12
- ;; size=61 bbWeight=0.50 PerfScore 7.50
+ mov gword ptr [rbp-0x38], rbx
+ ;; size=4 bbWeight=0.25 PerfScore 0.25
G_M59891_IG08:
- mov ecx, dword ptr [rax+0x0A38]
- lea edx, [rcx-0x01]
- mov dword ptr [rax+0x0A38], edx
- movzx rax, cx
- test eax, eax
- je SHORT G_M59891_IG09
- sar ecx, 16
- jmp SHORT G_M59891_IG10
- ;; size=27 bbWeight=0.50 PerfScore 3.75
+ mov rax, 0xD1FFAB1E ; data for System.Threading.TimerQueue:<Instances>k__BackingField
+ mov r14, gword ptr [rax]
+ mov gword ptr [rbp-0x58], r14
+ mov rax, 0xD1FFAB1E ; function address
+ ;; size=27 bbWeight=0.50 PerfScore 1.75
G_M59891_IG09:
- mov rax, 0xD1FFAB1E ; code for System.Threading.ProcessorIdCache:RefreshCurrentProcessorId():int
- call [rax]System.Threading.ProcessorIdCache:RefreshCurrentProcessorId():int
- mov ecx, eax
- ;; size=14 bbWeight=0.50 PerfScore 1.75
-G_M59891_IG10:
- mov eax, ecx
+ call rax ; Interop+Sys:SchedGetCpu():int
+ mov eax, eax
mov rdx, 0xD1FFAB1E ; data for System.Threading.TimerQueue:<Instances>k__BackingField
mov rdx, gword ptr [rdx]
mov edi, dword ptr [rdx+0x08]
- xor edx, edx
- div rdx:rax, rdi
+ cqo
+ idiv rdx:rax, rdi
+ mov r14, gword ptr [rbp-0x58]
mov edi, dword ptr [r14+0x08]
cmp rdx, rdi
- jae SHORT G_M59891_IG13
+ jae G_M59891_IG12
mov rsi, gword ptr [r14+8*rdx+0x10]
+ mov r13, gword ptr [rbp-0x50]
lea rdi, bword ptr [r13+0x08]
call CORINFO_HELP_ASSIGN_REF
mov rdi, 0xD1FFAB1E ; System.Threading.TimerHolder
call CORINFO_HELP_NEWFAST
- mov r14, rax
- lea rdi, bword ptr [r14+0x08]
+ mov rbx, rax
+ lea rdi, bword ptr [rbx+0x08]
mov rsi, r13
call CORINFO_HELP_ASSIGN_REF
+ mov r15, gword ptr [rbp-0x48]
lea rdi, bword ptr [r15+0x08]
- mov rsi, r14
+ mov rsi, rbx
call CORINFO_HELP_ASSIGN_REF
mov rdi, 0xD1FFAB1E ; data for System.Net.NetworkInformation.NetworkChange:s_availabilityTimer
mov rsi, r15
call CORINFO_HELP_ASSIGN_REF
- jmp SHORT G_M59891_IG14
- ;; size=108 bbWeight=0.50 PerfScore 40.50
-G_M59891_IG11:
+ mov rdi, 0xD1FFAB1E ; global ptr
+ cmp dword ptr [rdi], 0
+ je SHORT G_M59891_IG13
+ jmp SHORT G_M59891_IG11
+ ;; size=141 bbWeight=0.50 PerfScore 49.25
+G_M59891_IG10:
mov rdi, 0xD1FFAB1E
mov esi, 946
call CORINFO_HELP_GETSHARED_NONGCSTATIC_BASE
- jmp G_M59891_IG07
- ;; size=25 bbWeight=0 PerfScore 0.00
-G_M59891_IG12:
- mov edi, 2
- call CORINFO_HELP_GETSHARED_NONGCTHREADSTATIC_BASE_NOCTOR_OPTIMIZED
+ mov gword ptr [rbp-0x38], rbx
jmp G_M59891_IG08
- ;; size=15 bbWeight=0 PerfScore 0.00
-G_M59891_IG13:
+ ;; size=29 bbWeight=0 PerfScore 0.00
+G_M59891_IG11:
+ call CORINFO_HELP_POLL_GC
+ jmp SHORT G_M59891_IG13
+ ;; size=7 bbWeight=0 PerfScore 0.00
+G_M59891_IG12:
call CORINFO_HELP_RNGCHKFAIL
int3
;; size=6 bbWeight=0 PerfScore 0.00
-G_M59891_IG14:
+G_M59891_IG13:
lea rdi, [rbp-0x30]
mov rax, 0xD1FFAB1E ; code for System.Threading.AsyncFlowControl:Undo():this
call [rax]System.Threading.AsyncFlowControl:Undo():this
- ;; size=16 bbWeight=0.50 PerfScore 1.88
-G_M59891_IG15:
+ mov rbx, gword ptr [rbp-0x38]
+ ;; size=20 bbWeight=0.50 PerfScore 2.38
+G_M59891_IG14:
mov rax, 0xD1FFAB1E ; const ptr
mov r15, gword ptr [rax]
mov rax, 0xD1FFAB1E ; code for System.Threading.ExecutionContext:Capture():System.Threading.ExecutionContext
call [rax]System.Threading.ExecutionContext:Capture():System.Threading.ExecutionContext
mov rdx, rax
mov rdi, r15
mov rsi, rbx
xor ecx, ecx
mov rax, 0xD1FFAB1E ; code for System.Collections.Generic.Dictionary`2[System.__Canon,System.__Canon]:TryInsert(System.__Canon,System.__Canon,ubyte):ubyte:this
call [rax]System.Collections.Generic.Dictionary`2[System.__Canon,System.__Canon]:TryInsert(System.__Canon,System.__Canon,ubyte):ubyte:this
- jmp SHORT G_M59891_IG17
+ jmp SHORT G_M59891_IG16
;; size=50 bbWeight=0.50 PerfScore 5.88
-G_M59891_IG16:
+G_M59891_IG15:
mov rax, 0xD1FFAB1E ; code for System.Threading.Monitor:ThrowLockTakenException()
call [rax]System.Threading.Monitor:ThrowLockTakenException()
int3
;; size=13 bbWeight=0 PerfScore 0.00
-G_M59891_IG17:
+G_M59891_IG16:
cmp byte ptr [rbp-0x28], 0
- je SHORT G_M59891_IG18
- mov rdi, gword ptr [rbp-0x38]
+ je SHORT G_M59891_IG17
+ mov rdi, gword ptr [rbp-0x40]
call System.Threading.Monitor:Exit(System.Object)
;; size=15 bbWeight=0.50 PerfScore 2.50
-G_M59891_IG18:
+G_M59891_IG17:
nop
;; size=1 bbWeight=1 PerfScore 0.25
-G_M59891_IG19:
- add rsp, 32
+G_M59891_IG18:
+ add rsp, 64
pop rbx
pop r13
pop r14
pop r15
pop rbp
ret
;; size=13 bbWeight=1 PerfScore 3.75
-G_M59891_IG20:
+G_M59891_IG19:
push rbp
push r15
push r14
push r13
push rbx
sub rsp, 16
+ vzeroupper
mov rbp, qword ptr [rdi]
mov qword ptr [rsp], rbp
- lea rbp, [rbp+0x40]
- ;; size=23 bbWeight=0 PerfScore 0.00
-G_M59891_IG21:
+ lea rbp, [rbp+0x60]
+ ;; size=26 bbWeight=0 PerfScore 0.00
+G_M59891_IG20:
lea rdi, [rbp-0x30]
mov rax, 0xD1FFAB1E ; code for System.Threading.AsyncFlowControl:Undo():this
call [rax]System.Threading.AsyncFlowControl:Undo():this
nop
;; size=17 bbWeight=0 PerfScore 0.00
-G_M59891_IG22:
+G_M59891_IG21:
add rsp, 16
pop rbx
pop r13
pop r14
pop r15
pop rbp
ret
;; size=13 bbWeight=0 PerfScore 0.00
-G_M59891_IG23:
+G_M59891_IG22:
push rbp
push r15
push r14
push r13
push rbx
sub rsp, 16
+ vzeroupper
mov rbp, qword ptr [rdi]
mov qword ptr [rsp], rbp
- lea rbp, [rbp+0x40]
- ;; size=23 bbWeight=0 PerfScore 0.00
-G_M59891_IG24:
+ lea rbp, [rbp+0x60]
+ ;; size=26 bbWeight=0 PerfScore 0.00
+G_M59891_IG23:
cmp byte ptr [rbp-0x28], 0
- je SHORT G_M59891_IG25
- mov rdi, gword ptr [rbp-0x38]
+ je SHORT G_M59891_IG24
+ mov rdi, gword ptr [rbp-0x40]
call System.Threading.Monitor:Exit(System.Object)
;; size=15 bbWeight=0 PerfScore 0.00
-G_M59891_IG25:
+G_M59891_IG24:
nop
;; size=1 bbWeight=0 PerfScore 0.00
-G_M59891_IG26:
+G_M59891_IG25:
add rsp, 16
pop rbx
pop r13
pop r14
pop r15
pop rbp
ret
;; size=13 bbWeight=0 PerfScore 0.00
-; Total bytes of code 731, prolog size 30, PerfScore 99.00, instruction count 181, allocated bytes for code 731 (MethodHash=6153160c) for method System.Net.NetworkInformation.NetworkChange:add_NetworkAvailabilityChanged(System.Net.NetworkInformation.NetworkAvailabilityChangedEventHandler) (FullOpts)
+; Total bytes of code 715, prolog size 33, PerfScore 100.62, instruction count 178, allocated bytes for code 715 (MethodHash=6153160c) for method System.Net.NetworkInformation.NetworkChange:add_NetworkAvailabilityChanged(System.Net.NetworkInformation.NetworkAvailabilityChangedEventHandler) (FullOpts)-12 (-3.46 % of base) - System.HexConverter:TryDecodeFromUtf16_Vector128(System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref):ubyte
; Assembly listing for method System.HexConverter:TryDecodeFromUtf16_Vector128(System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref):ubyte (FullOpts)
; Emitting BLENDED_CODE for X64 with AVX512 - Unix
; FullOpts code
; optimized code
; rbp based frame
; fully interruptible
; No PGO data
; 0 inlinees with PGO data; 6 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[ushort]>
;* V01 arg1 [V01 ] ( 0, 0 ) struct (16) zero-ref multireg-arg ld-addr-op single-def <System.Span`1[ubyte]>
; V02 arg2 [V02,T06] ( 4, 3 ) byref -> rbx single-def
; V03 loc0 [V03,T00] ( 12, 42.50) long -> r15
; V04 loc1 [V04,T02] ( 3, 9 ) long -> r13
;* V05 loc2 [V05,T19] ( 0, 0 ) byref -> zero-ref single-def
;* V06 loc3 [V06,T20] ( 0, 0 ) byref -> zero-ref single-def
; V07 loc4 [V07 ] ( 2, 1 ) int -> [rbp-0x28] do-not-enreg[X] addr-exposed ld-addr-op
-; V08 loc5 [V08,T23] ( 3, 24 ) simd16 -> mm7 <System.Runtime.Intrinsics.Vector128`1[ushort]>
-; V09 loc6 [V09,T24] ( 3, 24 ) simd16 -> mm8 <System.Runtime.Intrinsics.Vector128`1[ushort]>
+; V08 loc5 [V08,T22] ( 3, 24 ) simd16 -> mm7 <System.Runtime.Intrinsics.Vector128`1[ushort]>
+; V09 loc6 [V09,T23] ( 3, 24 ) simd16 -> mm8 <System.Runtime.Intrinsics.Vector128`1[ushort]>
;* V10 loc7 [V10 ] ( 0, 0 ) simd16 -> zero-ref <System.Runtime.Intrinsics.Vector128`1[ubyte]>
;* V11 loc8 [V11 ] ( 0, 0 ) simd16 -> zero-ref <System.Runtime.Intrinsics.Vector128`1[ubyte]>
; V12 loc9 [V12,T25] ( 3, 16 ) simd16 -> mm9 <System.Runtime.Intrinsics.Vector128`1[ubyte]>
;* V13 loc10 [V13 ] ( 0, 0 ) simd16 -> zero-ref <System.Runtime.Intrinsics.Vector128`1[ubyte]>
;* V14 loc11 [V14 ] ( 0, 0 ) simd16 -> zero-ref <System.Runtime.Intrinsics.Vector128`1[short]>
;* V15 loc12 [V15 ] ( 0, 0 ) simd16 -> zero-ref <System.Runtime.Intrinsics.Vector128`1[short]>
;# V16 OutArgs [V16 ] ( 1, 1 ) struct ( 0) [rsp+0x00] do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
-; V17 tmp1 [V17,T21] ( 3, 48 ) simd16 -> mm9 "dup spill"
+; V17 tmp1 [V17,T24] ( 3, 24 ) simd16 -> mm9
;* V18 tmp2 [V18 ] ( 0, 0 ) struct (16) zero-ref "impAppendStmt" <System.ReadOnlySpan`1[ushort]>
;* V19 tmp3 [V19 ] ( 0, 0 ) struct (16) zero-ref "spilled call-like call argument" <System.Span`1[ubyte]>
; V20 tmp4 [V20,T12] ( 2, 2 ) int -> rax "impAppendStmt"
;* V21 tmp5 [V21 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
;* V22 tmp6 [V22 ] ( 0, 0 ) struct (16) zero-ref ld-addr-op "Inlining Arg" <System.ReadOnlySpan`1[ushort]>
;* V23 tmp7 [V23 ] ( 0, 0 ) struct (16) zero-ref ld-addr-op "Inlining Arg" <System.Span`1[ubyte]>
;* V24 tmp8 [V24 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
;* V25 tmp9 [V25 ] ( 0, 0 ) simd16 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
;* V26 tmp10 [V26 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
;* V27 tmp11 [V27 ] ( 0, 0 ) simd16 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
;* V28 tmp12 [V28 ] ( 0, 0 ) simd16 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
;* V29 tmp13 [V29 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
;* V30 tmp14 [V30 ] ( 0, 0 ) simd16 -> zero-ref ld-addr-op "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
;* V31 tmp15 [V31 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
;* V32 tmp16 [V32 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
; V33 tmp17 [V33,T07] ( 4, 4 ) int -> r8 "Inlining Arg"
;* V34 tmp18 [V34 ] ( 0, 0 ) struct (16) zero-ref multireg-arg ld-addr-op "NewObj constructor temp" <System.ReadOnlySpan`1[ushort]>
; V35 tmp19 [V35,T10] ( 2, 2 ) byref -> rdi single-def "Inlining Arg"
; V36 tmp20 [V36,T13] ( 2, 2 ) int -> rsi "Inlining Arg"
; V37 tmp21 [V37,T08] ( 4, 4 ) int -> r8 "Inlining Arg"
;* V38 tmp22 [V38 ] ( 0, 0 ) struct (16) zero-ref multireg-arg ld-addr-op "NewObj constructor temp" <System.Span`1[ubyte]>
; V39 tmp23 [V39,T11] ( 2, 2 ) byref -> rdx single-def "Inlining Arg"
; V40 tmp24 [V40,T14] ( 2, 2 ) int -> rcx "Inlining Arg"
; V41 tmp25 [V41,T01] ( 4, 17.50) byref -> rdi single-def "field V00._reference (fldOffset=0x0)" P-INDEP
; V42 tmp26 [V42,T05] ( 5, 3.50) int -> rsi single-def "field V00._length (fldOffset=0x8)" P-INDEP
; V43 tmp27 [V43,T03] ( 3, 5.50) byref -> rdx single-def "field V01._reference (fldOffset=0x0)" P-INDEP
; V44 tmp28 [V44,T09] ( 3, 2 ) int -> rcx single-def "field V01._length (fldOffset=0x8)" P-INDEP
;* V45 tmp29 [V45 ] ( 0, 0 ) byref -> zero-ref single-def "field V18._reference (fldOffset=0x0)" P-INDEP
;* V46 tmp30 [V46 ] ( 0, 0 ) int -> zero-ref "field V18._length (fldOffset=0x8)" P-INDEP
;* V47 tmp31 [V47 ] ( 0, 0 ) byref -> zero-ref "field V19._reference (fldOffset=0x0)" P-INDEP
;* V48 tmp32 [V48 ] ( 0, 0 ) int -> zero-ref "field V19._length (fldOffset=0x8)" P-INDEP
;* V49 tmp33 [V49 ] ( 0, 0 ) byref -> zero-ref single-def "field V22._reference (fldOffset=0x0)" P-INDEP
;* V50 tmp34 [V50 ] ( 0, 0 ) int -> zero-ref "field V22._length (fldOffset=0x8)" P-INDEP
;* V51 tmp35 [V51 ] ( 0, 0 ) byref -> zero-ref single-def "field V23._reference (fldOffset=0x0)" P-INDEP
;* V52 tmp36 [V52 ] ( 0, 0 ) int -> zero-ref "field V23._length (fldOffset=0x8)" P-INDEP
; V53 tmp37 [V53,T15] ( 2, 1 ) byref -> rdi single-def "field V34._reference (fldOffset=0x0)" P-INDEP
; V54 tmp38 [V54,T17] ( 2, 1 ) int -> rsi "field V34._length (fldOffset=0x8)" P-INDEP
; V55 tmp39 [V55,T16] ( 2, 1 ) byref -> rdx single-def "field V38._reference (fldOffset=0x0)" P-INDEP
; V56 tmp40 [V56,T18] ( 2, 1 ) int -> rcx "field V38._length (fldOffset=0x8)" P-INDEP
; V57 cse0 [V57,T26] ( 2, 9 ) simd16 -> mm0 hoist "CSE #01: aggressive"
; V58 cse1 [V58,T27] ( 2, 9 ) simd16 -> mm1 hoist "CSE #02: aggressive"
; V59 cse2 [V59,T28] ( 2, 9 ) simd16 -> mm2 hoist "CSE #03: aggressive"
; V60 cse3 [V60,T29] ( 2, 9 ) simd16 -> mm3 hoist "CSE #04: aggressive"
; V61 cse4 [V61,T30] ( 2, 9 ) simd16 -> mm4 hoist "CSE #05: aggressive"
; V62 cse5 [V62,T31] ( 2, 9 ) simd16 -> mm5 hoist "CSE #06: aggressive"
; V63 cse6 [V63,T32] ( 2, 9 ) simd16 -> mm6 hoist "CSE #07: aggressive"
; V64 cse7 [V64,T04] ( 3, 6 ) long -> r14 "CSE #08: aggressive"
-; V65 rat0 [V65,T22] ( 3, 48 ) simd16 -> mm7 "ReplaceWithLclVar is creating a new local variable"
+; V65 rat0 [V65,T21] ( 3, 48 ) simd16 -> mm7 "ReplaceWithLclVar is creating a new local variable"
;
; Lcl frame size = 16
G_M6966_IG01:
push rbp
push r15
push r14
push r13
push rbx
sub rsp, 16
lea rbp, [rsp+0x30]
mov rbx, r8
;; size=20 bbWeight=1 PerfScore 6.00
G_M6966_IG02:
xor r15d, r15d
mov r14d, esi
lea r13, [r14-0x10]
vmovups xmm0, xmmword ptr [reloc @RWD00]
vmovups xmm1, xmmword ptr [reloc @RWD16]
vmovups xmm2, xmmword ptr [reloc @RWD32]
vmovups xmm3, xmmword ptr [reloc @RWD48]
vmovups xmm4, xmmword ptr [reloc @RWD64]
vmovups xmm5, xmmword ptr [reloc @RWD80]
vmovups xmm6, xmmword ptr [reloc @RWD96]
jmp SHORT G_M6966_IG04
align [0 bytes for IG03]
;; size=68 bbWeight=1 PerfScore 24.00
G_M6966_IG03:
mov r15, r13
;; size=3 bbWeight=4 PerfScore 1.00
G_M6966_IG04:
vmovups xmm7, xmmword ptr [rdi+2*r15]
vmovups xmm8, xmmword ptr [rdi+2*r15+0x10]
- vpmovwb xmm7, xmm9
- vpmovwb xmm8, xmm10
- vmovlhps xmm9, xmm9, xmm10
+ vpackuswb xmm9, xmm7, xmm8
vpaddb xmm10, xmm0, xmm9
vpsubusb xmm10, xmm10, xmm1
vpsubb xmm10, xmm10, xmm2
vpand xmm9, xmm3, xmm9
vpsubb xmm9, xmm9, xmm4
vpaddusb xmm9, xmm9, xmm5
vpminub xmm9, xmm10, xmm9
vpternlogd xmm7, xmm8, xmm6, -88
vptest xmm7, xmm7
jne SHORT G_M6966_IG06
- ;; size=75 bbWeight=8 PerfScore 160.00
+ ;; size=63 bbWeight=8 PerfScore 128.00
G_M6966_IG05:
vpaddusb xmm7, xmm9, xmmword ptr [reloc @RWD112]
vpmovmskb r8d, xmm7
test r8d, r8d
je SHORT G_M6966_IG08
;; size=17 bbWeight=4 PerfScore 21.00
G_M6966_IG06:
mov r8d, r15d
cmp r8d, esi
ja G_M6966_IG11
mov eax, r8d
lea rdi, bword ptr [rdi+2*rax]
sub esi, r8d
mov r8, r15
shr r8, 1
cmp r8d, ecx
ja SHORT G_M6966_IG11
mov eax, r8d
add rdx, rax
sub ecx, r8d
lea r8, [rbp-0x28]
mov rax, 0xD1FFAB1E ; code for System.HexConverter:TryDecodeFromUtf16_Scalar(System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref):ubyte
call [rax]System.HexConverter:TryDecodeFromUtf16_Scalar(System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref):ubyte
add r15d, dword ptr [rbp-0x28]
mov dword ptr [rbx], r15d
;; size=65 bbWeight=0.50 PerfScore 6.00
G_M6966_IG07:
add rsp, 16
pop rbx
pop r13
pop r14
pop r15
pop rbp
ret
;; size=13 bbWeight=0.50 PerfScore 1.88
G_M6966_IG08:
vpmaddubsw xmm7, xmm9, xmmword ptr [reloc @RWD128]
vpshufb xmm7, xmm7, xmmword ptr [reloc @RWD144]
mov rax, r15
shr rax, 1
vmovd qword ptr [rdx+rax], xmm7
add r15, 16
cmp r15, r14
je SHORT G_M6966_IG09
cmp r15, r13
jbe G_M6966_IG04
jmp G_M6966_IG03
;; size=53 bbWeight=4 PerfScore 62.00
G_M6966_IG09:
mov dword ptr [rbx], esi
mov eax, 1
;; size=7 bbWeight=0.50 PerfScore 0.62
G_M6966_IG10:
add rsp, 16
pop rbx
pop r13
pop r14
pop r15
pop rbp
ret
;; size=13 bbWeight=0.50 PerfScore 1.88
G_M6966_IG11:
mov rax, 0xD1FFAB1E ; code for System.ThrowHelper:ThrowArgumentOutOfRangeException()
call [rax]System.ThrowHelper:ThrowArgumentOutOfRangeException()
int3
;; size=13 bbWeight=0 PerfScore 0.00
RWD00 dq C6C6C6C6C6C6C6C6h, C6C6C6C6C6C6C6C6h
RWD16 dq 0606060606060606h, 0606060606060606h
RWD32 dq F0F0F0F0F0F0F0F0h, F0F0F0F0F0F0F0F0h
RWD48 dq DFDFDFDFDFDFDFDFh, DFDFDFDFDFDFDFDFh
RWD64 dq 4141414141414141h, 4141414141414141h
RWD80 dq 0A0A0A0A0A0A0A0Ah, 0A0A0A0A0A0A0A0Ah
RWD96 dq FF80FF80FF80FF80h, FF80FF80FF80FF80h
RWD112 dq 7070707070707070h, 7070707070707070h
RWD128 dq 0110011001100110h, 0110011001100110h
RWD144 dq 0E0C0A0806040200h, 0000000000000000h
-; Total bytes of code 347, prolog size 20, PerfScore 284.38, instruction count 88, allocated bytes for code 347 (MethodHash=bb7ae4c9) for method System.HexConverter:TryDecodeFromUtf16_Vector128(System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref):ubyte (FullOpts)
+; Total bytes of code 335, prolog size 20, PerfScore 252.38, instruction count 86, allocated bytes for code 335 (MethodHash=bb7ae4c9) for method System.HexConverter:TryDecodeFromUtf16_Vector128(System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref):ubyte (FullOpts)