这是Linux中ARM A64 / NEON加密实施的汇编快照。
是否有关于如何在ARM A64 / NEON程序集中实现AES的解释？明确地说，AESE和AESMC做了什么？
__asm__(" ld1 {v0.16b}, %[in] ;"
" ld1 {v1.2d}, [%[key]], #16 ;"---> How does this assembly work?
" cmp %w[rounds], #10 ;"
" bmi 0f ;"
" bne 3f ;"
" mov v3.16b, v1.16b ;"
" b 2f ;"
"0: mov v2.16b, v1.16b ;"
" ld1 {v3.2d}, [%[key]], #16 ;"
"1: aese v0.16b, v2.16b ;"
" aesmc v0.16b, v0.16b ;" ---> AESMC is for?
"2: ld1 {v1.2d}, [%[key]], #16 ;"
" aese v0.16b, v3.16b ;"
" aesmc v0.16b, v0.16b ;"
"3: ld1 {v2.2d}, [%[key]], #16 ;"
" subs %w[rounds], %w[rounds], #3 ;"
" aese v0.16b, v1.16b ;"
" aesmc v0.16b, v0.16b ;"
" ld1 {v3.2d}, [%[key]], #16 ;"
" bpl 1b ;"
" aese v0.16b, v2.16b ;"
" eor v0.16b, v0.16b, v3.16b ;"
" st1 {v0.16b}, %[out] ;"
: [out] "=Q"(*out),
[key] "=r"(dummy0),
[rounds] "=r"(dummy1)
: [in] "Q"(*in),
"1"(ctx->key_enc),
"2"(num_rounds(ctx) - 2)
: "cc");