[X64] MihaZupan/runtime/cheaper-vector-narrow #390
Comments
Top method improvements-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 AVX - 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] ( 12, 17.50) simd32 -> mm0 <System.Runtime.Intrinsics.Vector256`1[ushort]>
+; 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 -> mm3 <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,T11] ( 3, 1.50) simd32 -> mm0 "CSE #02: moderate"
-; V20 cse1 [V20,T12] ( 3, 1.50) simd32 -> mm0 "CSE #04: moderate"
-; V21 cse2 [V21,T09] ( 7, 10.50) simd32 -> mm2 "CSE #01: moderate"
-; V22 cse3 [V22,T10] ( 5, 7 ) simd32 -> mm1 "CSE #03: 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
- vmovups ymm2, ymmword ptr [reloc @RWD32]
- vpand ymm0, ymm2, ymm0
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
- vpand ymm0, ymm2, ymm0
+ 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 13.71
+ ;; 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 ymm3, ymmword ptr [rdi+2*rcx+0x20]
- vpor ymm4, ymm0, ymm3
- vptest ymm4, ymm1
+ 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
- vpand ymm3, ymm2, ymm0
- vpand ymm0, ymm2, ymm0
- vpackuswb ymm2, ymm3, ymm0
- vpermq ymm1, ymm2, -40
- 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 6.96
+ ;; size=28 bbWeight=0.50 PerfScore 6.62
G_M60588_IG07:
- vpand ymm0, ymm2, ymm0
- vpand ymm3, ymm2, ymm3
- vpackuswb ymm0, ymm0, ymm3
+ 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 28.67
+ ;; 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
-RWD32 dq 00FF00FF00FF00FFh, 00FF00FF00FF00FFh, 00FF00FF00FF00FFh, 00FF00FF00FF00FFh
-; Total bytes of code 225, prolog size 4, PerfScore 134.29, instruction count 58, 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)-36 (-5.99 % 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 AVX - Unix
; FullOpts code
; optimized code
; rbp based frame
; fully interruptible
; No PGO data
-; 0 inlinees with PGO data; 9 single block inlinees; 16 inlinees without PGO data
+; 0 inlinees with PGO data; 13 single block inlinees; 20 inlinees without PGO data
; Final local variable assignments
;
; V00 arg0 [V00,T05] ( 8, 8.50) long -> rdi single-def
; V01 arg1 [V01,T04] ( 12, 10.50) long -> rsi single-def
; V02 arg2 [V02,T09] ( 7, 5 ) long -> rdx single-def
; V03 loc0 [V03,T00] ( 22, 29.50) long -> rax
; V04 loc1 [V04,T10] ( 13, 6.50) int -> rcx
;* V05 loc2 [V05 ] ( 0, 0 ) int -> zero-ref
; V06 loc3 [V06,T03] ( 7, 14 ) long -> registers
; V07 loc4 [V07,T18] ( 5, 2.50) long -> rdx
; V08 loc5 [V08,T13] ( 2, 4.50) long -> rcx
;# V09 OutArgs [V09 ] ( 1, 1 ) struct ( 0) [rsp+0x00] do-not-enreg[XS] addr-exposed "OutgoingArgSpace"
; V10 tmp1 [V10,T19] ( 3, 1.50) long -> rax "Inline return value spill temp"
; V11 tmp2 [V11,T06] ( 5, 9.50) byref -> rax single-def "Inline stloc first use temp"
-; V12 tmp3 [V12,T25] ( 12, 16.50) simd32 -> mm0 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+; V12 tmp3 [V12,T24] ( 14, 17.50) simd32 -> mm0 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
; V13 tmp4 [V13,T11] ( 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,T14] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
-; V16 tmp7 [V16,T27] ( 3, 12 ) simd32 -> mm3 "Inline stloc first use temp" <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 tmp10 [V19 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V20 tmp11 [V20 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V14 tmp5 [V14 ] ( 0, 0 ) simd32 -> zero-ref "spilled call-like call argument"
+; V15 tmp6 [V15,T01] ( 12, 27 ) long -> r8 "Inline stloc first use temp"
+; V16 tmp7 [V16,T14] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
+; V17 tmp8 [V17,T28] ( 3, 12 ) simd32 -> mm2 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V18 tmp9 [V18 ] ( 0, 0 ) simd32 -> zero-ref "spilled call-like call argument"
+; V19 tmp10 [V19,T26] ( 2, 16 ) simd32 -> mm0 "Spilling op1 side effects for HWIntrinsic"
+;* V20 tmp11 [V20 ] ( 0, 0 ) simd32 -> zero-ref "spilled call-like call argument"
;* V21 tmp12 [V21 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
;* V22 tmp13 [V22 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V23 tmp14 [V23 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-;* V24 tmp15 [V24 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V25 tmp16 [V25 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
-; V26 tmp17 [V26,T20] ( 3, 1.50) long -> rax "Inline return value spill temp"
-;* V27 tmp18 [V27,T22] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
-;* V28 tmp19 [V28 ] ( 0, 0 ) long -> zero-ref "Inline stloc first use temp"
-; V29 tmp20 [V29,T07] ( 5, 9.50) byref -> rax single-def "Inline stloc first use temp"
-; V30 tmp21 [V30,T24] ( 14, 17.50) simd16 -> mm0 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-; V31 tmp22 [V31,T12] ( 5, 6 ) byref -> rcx single-def "Inline stloc first use temp"
-;* V32 tmp23 [V32 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
-; V33 tmp24 [V33,T02] ( 11, 26.50) long -> r8 "Inline stloc first use temp"
-; V34 tmp25 [V34,T15] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
-; V35 tmp26 [V35,T28] ( 3, 12 ) simd16 -> mm2 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V36 tmp27 [V36 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
-; V37 tmp28 [V37,T26] ( 2, 16 ) simd16 -> mm0 "Spilling op1 side effects for HWIntrinsic"
-;* V38 tmp29 [V38 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
-;* V39 tmp30 [V39 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V40 tmp31 [V40 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V41 tmp32 [V41 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
-;* V42 tmp33 [V42 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V43 tmp34 [V43 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V44 tmp35 [V44 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
-;* V45 tmp36 [V45 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V46 tmp37 [V46 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V47 tmp38 [V47 ] ( 0, 0 ) simd16 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V48 tmp39 [V48 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-;* V49 tmp40 [V49 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
-;* V50 tmp41 [V50 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
-;* V51 tmp42 [V51 ] ( 0, 0 ) long -> zero-ref "Inlining Arg"
-; V52 tmp43 [V52,T23] ( 3, 24 ) simd16 -> mm0 "dup spill"
-;* V53 tmp44 [V53 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[uint]>
-;* V54 tmp45 [V54 ] ( 0, 0 ) byref -> zero-ref "Inlining Arg"
-; V55 tmp46 [V55,T16] ( 3, 3 ) byref -> r8 single-def "Inlining Arg"
-; V56 tmp47 [V56,T17] ( 3, 3 ) byref -> rdx "Inlining Arg"
-;* V57 tmp48 [V57,T21] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
-; V58 cse0 [V58,T08] ( 3, 8.50) long -> r10 "CSE #07: moderate"
-; V59 cse1 [V59,T32] ( 3, 1.50) simd32 -> mm0 "CSE #02: moderate"
-; V60 cse2 [V60,T33] ( 3, 1.50) simd32 -> mm0 "CSE #04: moderate"
-; V61 cse3 [V61,T29] ( 7, 10.50) simd32 -> mm2 "CSE #01: aggressive"
-; V62 cse4 [V62,T30] ( 5, 6 ) simd32 -> mm1 "CSE #03: moderate"
-; V63 cse5 [V63,T31] ( 5, 6 ) simd16 -> mm1 "CSE #06: moderate"
+;* V23 tmp14 [V23 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V24 tmp15 [V24 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* 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 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V28 tmp19 [V28 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* 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 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V33 tmp24 [V33 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V34 tmp25 [V34 ] ( 0, 0 ) simd32 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector256`1[ushort]>
+;* V35 tmp26 [V35 ] ( 0, 0 ) simd32 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+;* V36 tmp27 [V36 ] ( 0, 0 ) simd32 -> zero-ref "Inlining Arg" <System.Runtime.Intrinsics.Vector256`1[ubyte]>
+; V37 tmp28 [V37,T20] ( 3, 1.50) long -> rax "Inline return value spill temp"
+;* V38 tmp29 [V38,T22] ( 0, 0 ) int -> zero-ref "Inline stloc first use temp"
+;* V39 tmp30 [V39 ] ( 0, 0 ) long -> zero-ref "Inline stloc first use temp"
+; V40 tmp31 [V40,T07] ( 5, 9.50) byref -> rax single-def "Inline stloc first use temp"
+; V41 tmp32 [V41,T25] ( 14, 17.50) simd16 -> mm0 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+; V42 tmp33 [V42,T12] ( 5, 6 ) byref -> rcx single-def "Inline stloc first use temp"
+;* V43 tmp34 [V43 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
+; V44 tmp35 [V44,T02] ( 11, 26.50) long -> r8 "Inline stloc first use temp"
+; V45 tmp36 [V45,T15] ( 2, 4.50) long -> r9 "Inline stloc first use temp"
+; V46 tmp37 [V46,T29] ( 3, 12 ) simd16 -> mm2 "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+;* V47 tmp38 [V47 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
+; V48 tmp39 [V48,T27] ( 2, 16 ) simd16 -> mm0 "Spilling op1 side effects for HWIntrinsic"
+;* V49 tmp40 [V49 ] ( 0, 0 ) simd16 -> zero-ref "spilled call-like call argument"
+;* 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 "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* 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 "Inlining Arg" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+;* V59 tmp50 [V59 ] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+;* V60 tmp51 [V60 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[ushort]>
+;* V61 tmp52 [V61 ] ( 0, 0 ) simd16 -> zero-ref "Inline return value spill temp" <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+;* V62 tmp53 [V62 ] ( 0, 0 ) long -> zero-ref "Inlining Arg"
+; V63 tmp54 [V63,T23] ( 3, 24 ) simd16 -> mm0 "dup spill"
+;* V64 tmp55 [V64 ] ( 0, 0 ) simd16 -> zero-ref "Inline stloc first use temp" <System.Runtime.Intrinsics.Vector128`1[uint]>
+;* V65 tmp56 [V65 ] ( 0, 0 ) byref -> zero-ref "Inlining Arg"
+; V66 tmp57 [V66,T16] ( 3, 3 ) byref -> r8 single-def "Inlining Arg"
+; V67 tmp58 [V67,T17] ( 3, 3 ) byref -> rdx "Inlining Arg"
+;* V68 tmp59 [V68,T21] ( 0, 0 ) ubyte -> zero-ref "Inline return value spill temp"
+; V69 cse0 [V69,T08] ( 3, 8.50) long -> r10 "CSE #03: moderate"
+; V70 cse1 [V70,T30] ( 5, 6 ) simd32 -> mm1 "CSE #01: moderate"
+; V71 cse2 [V71,T31] ( 5, 6 ) simd16 -> mm1 "CSE #02: moderate"
;
; 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_IG18
;; 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_IG20
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=105 bbWeight=0.50 PerfScore 16.00
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_IG18
;; 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
- vmovups ymm2, ymmword ptr [reloc @RWD64]
- vpand ymm0, ymm2, ymm0
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
- vpand ymm0, ymm2, ymm0
+ 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 21.33
+ ;; 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 ymm3, ymmword ptr [rax+2*r8+0x20]
- vpor ymm4, ymm0, ymm3
- vptest ymm4, ymm1
+ 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
- vpand ymm3, ymm2, ymm0
- vpand ymm0, ymm2, ymm0
- vpackuswb ymm2, ymm3, ymm0
- vpermq ymm1, ymm2, -40
- 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 IG19]
- ;; size=37 bbWeight=0.50 PerfScore 6.96
+ ;; size=29 bbWeight=0.50 PerfScore 6.62
G_M6063_IG15:
- vpand ymm0, ymm2, ymm0
- vpand ymm3, ymm2, ymm3
- vpackuswb ymm0, ymm0, ymm3
+ 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 28.67
+ ;; 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:
sub rdx, rax
cmp rdx, 4
jb SHORT G_M6063_IG22
lea rcx, [rax+rdx-0x04]
;; size=14 bbWeight=0.50 PerfScore 1.25
G_M6063_IG19:
mov r8, qword ptr [rdi+2*rax]
mov r9, 0xD1FFAB1E
test r8, r9
je SHORT G_M6063_IG21
;; size=19 bbWeight=4 PerfScore 14.00
G_M6063_IG20:
mov ecx, r8d
test ecx, 0xD1FFAB1E
jne SHORT G_M6063_IG23
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_IG23
;; size=36 bbWeight=0.50 PerfScore 3.75
G_M6063_IG21:
vmovd xmm0, r8
vpackuswb xmm0, xmm0, xmm0
vmovd dword ptr [rsi+rax], xmm0
add rax, 4
cmp rax, rcx
jbe SHORT G_M6063_IG19
;; size=23 bbWeight=4 PerfScore 26.00
G_M6063_IG22:
test dl, 2
je SHORT G_M6063_IG25
mov ecx, dword ptr [rdi+2*rax]
test ecx, 0xD1FFAB1E
je SHORT G_M6063_IG24
;; size=16 bbWeight=0.50 PerfScore 2.25
G_M6063_IG23:
test ecx, 0xFF80
je SHORT G_M6063_IG26
jmp SHORT G_M6063_IG27
;; size=10 bbWeight=0.50 PerfScore 1.62
G_M6063_IG24:
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_IG25:
test dl, 1
je SHORT G_M6063_IG27
movzx rcx, word ptr [rdi+2*rax]
cmp ecx, 127
ja SHORT G_M6063_IG27
;; size=14 bbWeight=0.50 PerfScore 2.25
G_M6063_IG26:
mov byte ptr [rsi+rax], cl
inc rax
;; size=6 bbWeight=0.50 PerfScore 0.62
G_M6063_IG27:
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 00FF00FF00FF00FFh, 00FF00FF00FF00FFh, 00FF00FF00FF00FFh, 00FF00FF00FF00FFh
-; Total bytes of code 601, prolog size 4, PerfScore 275.88, instruction count 156, allocated bytes for code 605 (MethodHash=53fae850) for method System.Text.Ascii:NarrowUtf16ToAscii(ulong,ulong,ulong):ulong (FullOpts)
+; Total bytes of code 565, prolog size 4, PerfScore 270.54, instruction count 149, allocated bytes for code 573 (MethodHash=53fae850) for method System.Text.Ascii:NarrowUtf16ToAscii(ulong,ulong,ulong):ulong (FullOpts)-19 (-5.40 % 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 AVX - 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,T22] ( 3, 24 ) simd16 -> mm8 <System.Runtime.Intrinsics.Vector128`1[ushort]>
-; V09 loc6 [V09,T23] ( 3, 24 ) simd16 -> mm9 <System.Runtime.Intrinsics.Vector128`1[ushort]>
+; V08 loc5 [V08,T21] ( 3, 24 ) simd16 -> mm7 <System.Runtime.Intrinsics.Vector128`1[ushort]>
+; V09 loc6 [V09,T22] ( 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 -> mm10 <System.Runtime.Intrinsics.Vector128`1[ubyte]>
+; V12 loc9 [V12,T24] ( 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 -> mm10 "dup spill"
+; V17 tmp1 [V17,T23] ( 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,T24] ( 3, 17 ) simd16 -> mm0 hoist "CSE #01: aggressive"
+; V57 cse0 [V57,T25] ( 2, 9 ) simd16 -> mm0 hoist "CSE #01: aggressive"
; V58 cse1 [V58,T26] ( 2, 9 ) simd16 -> mm1 hoist "CSE #02: aggressive"
; V59 cse2 [V59,T27] ( 2, 9 ) simd16 -> mm2 hoist "CSE #03: aggressive"
; V60 cse3 [V60,T28] ( 2, 9 ) simd16 -> mm3 hoist "CSE #04: aggressive"
; V61 cse4 [V61,T29] ( 2, 9 ) simd16 -> mm4 hoist "CSE #05: aggressive"
; V62 cse5 [V62,T30] ( 2, 9 ) simd16 -> mm5 hoist "CSE #06: aggressive"
; V63 cse6 [V63,T31] ( 2, 9 ) simd16 -> mm6 hoist "CSE #07: aggressive"
-; V64 cse7 [V64,T32] ( 2, 9 ) simd16 -> mm7 hoist "CSE #08: aggressive"
-; V65 cse8 [V65,T04] ( 3, 6 ) long -> r14 "CSE #09: aggressive"
+; V64 cse7 [V64,T04] ( 3, 6 ) long -> r14 "CSE #08: aggressive"
;
; 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]
- vmovups xmm7, xmmword ptr [reloc @RWD112]
jmp SHORT G_M6966_IG04
align [0 bytes for IG03]
- ;; size=76 bbWeight=1 PerfScore 27.00
+ ;; size=68 bbWeight=1 PerfScore 24.00
G_M6966_IG03:
mov r15, r13
;; size=3 bbWeight=4 PerfScore 1.00
G_M6966_IG04:
- vmovups xmm8, xmmword ptr [rdi+2*r15]
- vmovups xmm9, xmmword ptr [rdi+2*r15+0x10]
- vpand xmm10, xmm0, xmm8
- vpand xmm11, xmm0, xmm9
- vpackuswb xmm10, xmm10, xmm11
- vpaddb xmm11, xmm1, xmm10
- vpsubusb xmm11, xmm11, xmm2
- vpsubb xmm11, xmm11, xmm3
- vpand xmm10, xmm4, xmm10
- vpsubb xmm10, xmm10, xmm5
- vpaddusb xmm10, xmm10, xmm6
- vpminub xmm10, xmm11, xmm10
- vpor xmm8, xmm8, xmm9
- vptest xmm8, xmm7
+ vmovups xmm7, xmmword ptr [rdi+2*r15]
+ vmovups xmm8, xmmword ptr [rdi+2*r15+0x10]
+ 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
+ vpor xmm7, xmm7, xmm8
+ vptest xmm7, xmm6
jne SHORT G_M6966_IG06
- ;; size=71 bbWeight=8 PerfScore 132.00
+ ;; size=61 bbWeight=8 PerfScore 126.67
G_M6966_IG05:
- vpaddusb xmm8, xmm10, xmmword ptr [reloc @RWD128]
- vpmovmskb r8d, xmm8
+ vpaddusb xmm7, xmm9, xmmword ptr [reloc @RWD112]
+ vpmovmskb r8d, xmm7
test r8d, r8d
je SHORT G_M6966_IG08
- ;; size=18 bbWeight=4 PerfScore 21.00
+ ;; 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 xmm8, xmm10, xmmword ptr [reloc @RWD144]
- vpshufb xmm8, xmm8, xmmword ptr [reloc @RWD160]
+ 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], xmm8
+ 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 00FF00FF00FF00FFh, 00FF00FF00FF00FFh
-RWD16 dq C6C6C6C6C6C6C6C6h, C6C6C6C6C6C6C6C6h
-RWD32 dq 0606060606060606h, 0606060606060606h
-RWD48 dq F0F0F0F0F0F0F0F0h, F0F0F0F0F0F0F0F0h
-RWD64 dq DFDFDFDFDFDFDFDFh, DFDFDFDFDFDFDFDFh
-RWD80 dq 4141414141414141h, 4141414141414141h
-RWD96 dq 0A0A0A0A0A0A0A0Ah, 0A0A0A0A0A0A0A0Ah
-RWD112 dq FF80FF80FF80FF80h, FF80FF80FF80FF80h
-RWD128 dq 7070707070707070h, 7070707070707070h
-RWD144 dq 0110011001100110h, 0110011001100110h
-RWD160 dq 0E0C0A0806040200h, 0000000000000000h
+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 352, prolog size 20, PerfScore 259.38, instruction count 89, allocated bytes for code 352 (MethodHash=bb7ae4c9) for method System.HexConverter:TryDecodeFromUtf16_Vector128(System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref):ubyte (FullOpts)
+; Total bytes of code 333, prolog size 20, PerfScore 251.04, instruction count 86, allocated bytes for code 333 (MethodHash=bb7ae4c9) for method System.HexConverter:TryDecodeFromUtf16_Vector128(System.ReadOnlySpan`1[ushort],System.Span`1[ubyte],byref):ubyte (FullOpts) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Job completed in 22 minutes.
Diffs
Artifacts:
The text was updated successfully, but these errors were encountered: