B0.B16, T0.B16, T0.B16 VPMULL B0.D1, T1.D1, ACC1.Q1 VPMULL2 B0.D2, T1.D2, ACC0.Q1 VPMULL T0.D1, T2.D1, ACCM.Q1 mulRound(B1) mulRound(B2) mulRound(B3) mulRound(B4) mulRound(B5) mulRound(B6) mulRound(B7) MOVD pTblSave, pTbl reduce() CMP $128, srcPtrLen BGE octetsLoop startSingles: CBZ srcPtrLen, done ADD $14*16, pTbl // Preload H and its Karatsuba precomp VLD1.P (pTbl), [T1.B16, T2.B16] // Preload AES round keys ADD $128, ks VLD1.P 48(ks), [K8.B16, K9.B16, K10.B16] VMOV K10.B16, KLAST.B16 TBZ $4, NR,...