head_no_debug_asm_dump.txt

; Assembly listing for method System.Text.ASCIIUtility:NarrowUtf16ToAscii_Sse2(long,long,long):long
; Emitting BLENDED_CODE for X64 CPU with AVX - Unix
; Tier-1 compilation
; optimized code
; optimized using profile data
; rbp based frame
; fully interruptible
; with PGO: edge weights are valid, and fgCalledCount is 43814
; Final local variable assignments
;
;  V00 arg0         [V00,T01] (  6,106.31)    long  ->  rdi         single-def
;  V01 arg1         [V01,T02] (  8, 56.87)    long  ->  rsi         single-def
;  V02 arg2         [V02,T04] (  3,  3.00)    long  ->  rdx         single-def
;* V03 loc0         [V03,T05] (  0,  0   )     int  ->  zero-ref
;* V04 loc1         [V04,T06] (  0,  0   )    long  ->  zero-ref
;  V05 loc2         [V05,T10] (  2, 52.36)  simd16  ->  mm0
;* V06 loc3         [V06    ] (  0,  0   )  simd16  ->  zero-ref
;  V07 loc4         [V07,T07] ( 14,160.52)  simd16  ->  mm1
;  V08 loc5         [V08,T09] (  8,105.75)  simd16  ->  mm2
;  V09 loc6         [V09,T00] ( 12,310.81)    long  ->  rax
;  V10 loc7         [V10,T03] (  2, 52.25)    long  ->  rdx
;  V11 loc8         [V11,T08] (  3,153.97)  simd16  ->  mm2
;* V12 loc9         [V12    ] (  0,  0   )  simd16  ->  zero-ref
;# V13 OutArgs      [V13    ] (  1,  1   )  lclBlk ( 0) [rsp+00H]   "OutgoingArgSpace"
;
; Lcl frame size = 0

G_M2855_IG01:              ;; offset=0000H
       55                   push     rbp
       C5F877               vzeroupper
       488BEC               mov      rbp, rsp
						;; size=7 bbWeight=1    PerfScore 2.25
G_M2855_IG02:              ;; offset=0007H
       C5F91005B1000000     vmovupd  xmm0, xmmword ptr [reloc @RWD00]
       C5FA6F0F             vmovdqu  xmm1, xmmword ptr [rdi]
       C4E279170DA4000000   vptest   xmm1, xmmword ptr [reloc @RWD00]
       0F8592000000         jne      G_M2855_IG11
						;; size=27 bbWeight=1    PerfScore 13.00
G_M2855_IG03:              ;; offset=0022H
       C5F167D1             vpackuswb xmm2, xmm1, xmm1
       C5F9D616             vmovq    qword ptr [rsi], xmm2
       B808000000           mov      eax, 8
       40F6C608             test     sil, 8
       751C                 jne      SHORT G_M2855_IG05
						;; size=19 bbWeight=1.00 PerfScore 4.50
G_M2855_IG04:              ;; offset=0035H
       C5FA6F4F10           vmovdqu  xmm1, xmmword ptr [rdi+16]
       C4E279170D7D000000   vptest   xmm1, xmmword ptr [reloc @RWD00]
       754E                 jne      SHORT G_M2855_IG08
       C5F167D1             vpackuswb xmm2, xmm1, xmm1
       C5F9D65608           vmovq    qword ptr [rsi+8], xmm2
						;; size=25 bbWeight=0.59 PerfScore 7.72
G_M2855_IG05:              ;; offset=004EH
       488BC6               mov      rax, rsi
       4883E00F             and      rax, 15
       B910000000           mov      ecx, 16
       482BC8               sub      rcx, rax
       488BC1               mov      rax, rcx
       4883EA10             sub      rdx, 16
                            align    [0 bytes for IG06]
						;; size=22 bbWeight=1.00 PerfScore 1.50
G_M2855_IG06:              ;; offset=0064H
       C5FA6F0C47           vmovdqu  xmm1, xmmword ptr [rdi+2*rax]
       C5FA6F544710         vmovdqu  xmm2, xmmword ptr [rdi+2*rax+16]
       C5F1EBDA             vpor     xmm3, xmm1, xmm2
       C4E27917D8           vptest   xmm3, xmm0
       7516                 jne      SHORT G_M2855_IG09
						;; size=22 bbWeight=51.36 PerfScore 633.44
G_M2855_IG07:              ;; offset=007AH
       C5F167D2             vpackuswb xmm2, xmm1, xmm2
       C5F97F1406           vmovdqa  xmmword ptr [rsi+rax], xmm2
       4883C010             add      rax, 16
       483BC2               cmp      rax, rdx
       76D8                 jbe      SHORT G_M2855_IG06
						;; size=18 bbWeight=51.25 PerfScore 230.61
G_M2855_IG08:              ;; offset=008CH
       5D                   pop      rbp
       C3                   ret
						;; size=2 bbWeight=1.00 PerfScore 1.50
G_M2855_IG09:              ;; offset=008EH
       C4E279170D29000000   vptest   xmm1, xmmword ptr [reloc @RWD00]
       75F3                 jne      SHORT G_M2855_IG08
						;; size=11 bbWeight=0.11 PerfScore 0.69
G_M2855_IG10:              ;; offset=0099H
       C5F167D1             vpackuswb xmm2, xmm1, xmm1
       C5F9D61406           vmovq    qword ptr [rsi+rax], xmm2
       4883C008             add      rax, 8
       EBE4                 jmp      SHORT G_M2855_IG08
						;; size=15 bbWeight=0.03 PerfScore 0.18
G_M2855_IG11:              ;; offset=00A8H
       33C0                 xor      eax, eax
						;; size=2 bbWeight=0    PerfScore 0.00
G_M2855_IG12:              ;; offset=00AAH
       5D                   pop      rbp
       C3                   ret
						;; size=2 bbWeight=0    PerfScore 0.00
RWD00  	dq	FF80FF80FF80FF80h, FF80FF80FF80FF80h


; Total bytes of code 172, prolog size 7, PerfScore 913.98, instruction count 45, allocated bytes for code 186 (MethodHash=d994f4d8) for method System.Text.ASCIIUtility:NarrowUtf16ToAscii_Sse2(long,long,long):long
; ============================================================