vext.8 q10, qzr, q0, #4
// receive the initial 64B data, xor the initial crc value
- vld1.64 {q0-q1}, [arg2, :128]!
- vld1.64 {q2-q3}, [arg2, :128]!
- vld1.64 {q4-q5}, [arg2, :128]!
- vld1.64 {q6-q7}, [arg2, :128]!
+ vld1.64 {q0-q1}, [arg2]!
+ vld1.64 {q2-q3}, [arg2]!
+ vld1.64 {q4-q5}, [arg2]!
+ vld1.64 {q6-q7}, [arg2]!
CPU_LE( vrev64.8 q0, q0 )
CPU_LE( vrev64.8 q1, q1 )
CPU_LE( vrev64.8 q2, q2 )
_fold_64_B_loop:
.macro fold64, reg1, reg2
- vld1.64 {q11-q12}, [arg2, :128]!
+ vld1.64 {q11-q12}, [arg2]!
vmull.p64 q8, \reg1\()h, d21
vmull.p64 \reg1, \reg1\()l, d20
vmull.p64 q7, d15, d21
veor.8 q7, q7, q8
- vld1.64 {q0}, [arg2, :128]!
+ vld1.64 {q0}, [arg2]!
CPU_LE( vrev64.8 q0, q0 )
vswp d0, d1
veor.8 q7, q7, q0
vmov.i8 q0, #0
vmov s3, arg1_low32 // get the initial crc value
- vld1.64 {q7}, [arg2, :128]!
+ vld1.64 {q7}, [arg2]!
CPU_LE( vrev64.8 q7, q7 )
vswp d14, d15
veor.8 q7, q7, q0