[X64] [MihaZupan] Improve Ascii.FromUtf16 and FromHexString #395
Comments
Top method improvements-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)Larger list of diffs: https://gist.github.com/MihuBot/f60c7254060f436ae9c12ded701c85f8 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Job completed in 17 minutes.
Diffs
Artifacts:
The text was updated successfully, but these errors were encountered: