aarch64_vector128_store_unsafe

// store safe
G_M20155_IG01:
            stp     fp, lr, [sp,#-16]!
            mov     fp, sp
						;; size=8 bbWeight=1    PerfScore 1.50
G_M20155_IG02:
            ld1     {v16.8h}, [x0]
            umaxp   v17.8h, v16.8h, v16.8h
            umov    x3, v17.d[0]
            tst     x3, #0xd1ffab1e
            bne     G_M20155_IG04
						;; size=20 bbWeight=1    PerfScore 6.50
G_M20155_IG03:
            mov     x3, x1
            uzp1    v16.16b, v16.16b, v16.16b
            st1     {v16.8b}, [x3]
            mov     x4, #8
            tbnz    w1, #3, G_M20155_IG06
            add     x5, x0, #16
            ld1     {v16.8h}, [x5]
            umaxp   v17.8h, v16.8h, v16.8h
            umov    x5, v17.d[0]
            tst     x5, #0xd1ffab1e
            bne     G_M20155_IG08
            uzp1    v16.16b, v16.16b, v16.16b
            add     x4, x3, #8
            st1     {v16.8b}, [x4]
            b       G_M20155_IG06
            align   [0 bytes for IG07]
            align   [0 bytes]
            align   [0 bytes]
            align   [0 bytes]
						;; size=60 bbWeight=0.50 PerfScore 7.25
G_M20155_IG04:
            mov     x0, xzr
						;; size=4 bbWeight=0.50 PerfScore 0.25
G_M20155_IG05:
            ldp     fp, lr, [sp],#16
            ret     lr
						;; size=8 bbWeight=0.50 PerfScore 1.00
G_M20155_IG06:
            and     x1, x1, #15
            mov     x4, #16
            sub     x4, x4, x1
            sub     x1, x2, #16
						;; size=16 bbWeight=0.50 PerfScore 1.00
G_M20155_IG07:
            lsl     x2, x4, #1
            ldr     q16, [x0, x2]
            add     x2, x4, #8
            lsl     x5, x2, #1
            ldr     q17, [x0, x5]
            orr     v18.8h, v16.8h, v17.8h
            umaxp   v18.8h, v18.8h, v18.8h
            umov    x5, v18.d[0]
            tst     x5, #0xd1ffab1e
            bne     G_M20155_IG10
            add     x2, x3, x4
            uzp1    v16.16b, v16.16b, v17.16b
            st1     {v16.16b}, [x2]
            add     x4, x4, #16
            cmp     x4, x1
            bls     G_M20155_IG07
						;; size=64 bbWeight=4    PerfScore 68.00
G_M20155_IG08:
            mov     x0, x4
						;; size=4 bbWeight=0.50 PerfScore 0.25
G_M20155_IG09:
            ldp     fp, lr, [sp],#16
            ret     lr
						;; size=8 bbWeight=0.50 PerfScore 1.00
G_M20155_IG10:
            umaxp   v17.8h, v16.8h, v16.8h
            umov    x0, v17.d[0]
            tst     x0, #0xd1ffab1e
            bne     G_M20155_IG08
            add     x4, x3, x4
            uzp1    v16.16b, v16.16b, v16.16b
            st1     {v16.8b}, [x4]
            mov     x4, x2
            b       G_M20155_IG08
						;; size=36 bbWeight=0.50 PerfScore 3.75

; Total bytes of code 228, prolog size 8, PerfScore 113.30, instruction count 61, allocated bytes for code 228 (MethodHash=74c3b144) for method System.Text.Tests.Demo:NarrowUtf16ToAscii_Intrinsified(long,long,long):long
; ============================================================