在本文的上一章,S盒置换的C语言实现的最佳方案是将8位S盒扩展至16位,确定了S盒数组的大小与数据单元的大小,首先回顾相应的C代码:
#include <stdint.h>
static uint8_t s_sbox8[256] = {
0xd6,0x90,0xe9,0xfe,0xcc,0xe1,0x3d,0xb7,0x16,0xb6,0x14,0xc2,0x28,0xfb,0x2c,0x05,
0x2b,0x67,0x9a,0x76,0x2a,0xbe,0x04,0xc3,0xaa,0x44,0x13,0x26,0x49,0x86,0x06,0x99,
0x9c,0x42,0x50,0xf4,0x91,0xef,0x98,0x7a,0x33,0x54,0x0b,0x43,0xed,0xcf,0xac,0x62,
0xe4,0xb3,0x1c,0xa9,0xc9,0x08,0xe8,0x95,0x80,0xdf,0x94,0xfa,0x75,0x8f,0x3f,0xa6,
0x47,0x07,0xa7,0xfc,0xf3,0x73,0x17,0xba,0x83,0x59,0x3c,0x19,0xe6,0x85,0x4f,0xa8,
0x68,0x6b,0x81,0xb2,0x71,0x64,0xda,0x8b,0xf8,0xeb,0x0f,0x4b,0x70,0x56,0x9d,0x35,
0x1e,0x24,0x0e,0x5e,0x63,0x58,0xd1,0xa2,0x25,0x22,0x7c,0x3b,0x01,0x21,0x78,0x87,
0xd4,0x00,0x46,0x57,0x9f,0xd3,0x27,0x52,0x4c,0x36,0x02,0xe7,0xa0,0xc4,0xc8,0x9e,
0xea,0xbf,0x8a,0xd2,0x40,0xc7,0x38,0xb5,0xa3,0xf7,0xf2,0xce,0xf9,0x61,0x15,0xa1,
0xe0,0xae,0x5d,0xa4,0x9b,0x34,0x1a,0x55,0xad,0x93,0x32,0x30,0xf5,0x8c,0xb1,0xe3,
0x1d,0xf6,0xe2,0x2e,0x82,0x66,0xca,0x60,0xc0,0x29,0x23,0xab,0x0d,0x53,0x4e,0x6f,
0xd5,0xdb,0x37,0x45,0xde,0xfd,0x8e,0x2f,0x03,0xff,0x6a,0x72,0x6d,0x6c,0x5b,0x51,
0x8d,0x1b,0xaf,0x92,0xbb,0xdd,0xbc,0x7f,0x11,0xd9,0x5c,0x41,0x1f,0x10,0x5a,0xd8,
0x0a,0xc1,0x31,0x88,0xa5,0xcd,0x7b,0xbd,0x2d,0x74,0xd0,0x12,0xb8,0xe5,0xb4,0xb0,
0x89,0x69,0x97,0x4a,0x0c,0x96,0x77,0x7e,0x65,0xb9,0xf1,0x09,0xc5,0x6e,0xc6,0x84,
0x18,0xf0,0x7d,0xec,0x3a,0xdc,0x4d,0x20,0x79,0xee,0x5f,0x3e,0xd7,0xcb,0x39,0x48
};
static uint16_t s_sbox[65536];
void sbox_init(void)
{
uint64_t i;
for(i = 0; i < 65536; i++) {
s_sbox[i] = s_sbox8[i & 0xff] ^ (s_sbox8[i >> 8] << 8);
}
}
uint32_t sbox(uint32_t src)
{
uint32_t dst;
dst = s_sbox[src & 0xffff] ^ (s_sbox[(src >> 16)] << 16);
return(dst);
}
为了测试结果更加精确,将性能测试程序的循环次数从1亿增加到2亿次:
#include <stdio.h>
#include <string.h>
#include <stdint.h>
#include <stdlib.h>
#include <unistd.h>
uint32_t sbox(uint32_t src);
void sbox_init(void);
int main(int argc, char *argv[])
{
uint32_t i, data;
sbox_init();
data = 0x00010203;
for(i = 0; i < 200000000; i++) {
data = sbox(data);
}
printf("data = %08x\n", data);
exit(EXIT_SUCCESS);
}
以此为基础,用x64汇编人工优化函数sbox()的实现,首先看GCC编译得到的汇编代码:
movl %edi, %eax
movzwl %di, %edi
shrl $16, %eax
movzwl s_sbox(%rdi,%rdi), %edx
mov %eax, %eax
movzwl s_sbox(%rax,%rax), %eax
sall $16, %eax
xorl %edx, %eax
ret
然后按照个人习惯精简一下得到:
movzwq %di, %rax
shrq $16, %rdi
movzwq s_sbox(%rax,%rax), %rax
movzwq s_sbox(%rdi,%rdi), %rdx
shlq $16, %rdx
xorq %rdx, %rax
ret
汇编代码修改前性能测试结果:
[root@sxy-lenovo step4]# time ./test_sbox
data = 5adc1e2b
real 0m0.900s
user 0m0.899s
sys 0m0.002s
汇编代码修改后性能测试结果:
[root@sxy-lenovo step8]# time ./test_sbox
data = 5adc1e2b
real 0m0.805s
user 0m0.805s
sys 0m0.000s
还是有相当成效的。