c - C语言中位反转(从MSB-> LSB到LSB-> MSB)的高效算法

标签 c algorithm bit-manipulation

实现以下目标的最有效算法是什么:

0010 0000 => 0000 0100

转换是从 MSB->LSB 到 LSB->MSB。所有位必须反转；也就是说，这不是字节顺序交换。

最佳答案

注意:下面的所有算法都是用 C 语言编写的，但应该可以移植到您选择的语言中(当它们没有那么快时不要看我:)

选项

低内存(32 位 int，32 位机器)(来自 here ):

unsigned int
reverse(register unsigned int x)
{
    x = (((x & 0xaaaaaaaa) >> 1) | ((x & 0x55555555) << 1));
    x = (((x & 0xcccccccc) >> 2) | ((x & 0x33333333) << 2));
    x = (((x & 0xf0f0f0f0) >> 4) | ((x & 0x0f0f0f0f) << 4));
    x = (((x & 0xff00ff00) >> 8) | ((x & 0x00ff00ff) << 8));
    return((x >> 16) | (x << 16));

}

来自著名的Bit Twiddling Hacks page :

最快(查找表):

static const unsigned char BitReverseTable256[] = 
{
  0x00, 0x80, 0x40, 0xC0, 0x20, 0xA0, 0x60, 0xE0, 0x10, 0x90, 0x50, 0xD0, 0x30, 0xB0, 0x70, 0xF0, 
  0x08, 0x88, 0x48, 0xC8, 0x28, 0xA8, 0x68, 0xE8, 0x18, 0x98, 0x58, 0xD8, 0x38, 0xB8, 0x78, 0xF8, 
  0x04, 0x84, 0x44, 0xC4, 0x24, 0xA4, 0x64, 0xE4, 0x14, 0x94, 0x54, 0xD4, 0x34, 0xB4, 0x74, 0xF4, 
  0x0C, 0x8C, 0x4C, 0xCC, 0x2C, 0xAC, 0x6C, 0xEC, 0x1C, 0x9C, 0x5C, 0xDC, 0x3C, 0xBC, 0x7C, 0xFC, 
  0x02, 0x82, 0x42, 0xC2, 0x22, 0xA2, 0x62, 0xE2, 0x12, 0x92, 0x52, 0xD2, 0x32, 0xB2, 0x72, 0xF2, 
  0x0A, 0x8A, 0x4A, 0xCA, 0x2A, 0xAA, 0x6A, 0xEA, 0x1A, 0x9A, 0x5A, 0xDA, 0x3A, 0xBA, 0x7A, 0xFA,
  0x06, 0x86, 0x46, 0xC6, 0x26, 0xA6, 0x66, 0xE6, 0x16, 0x96, 0x56, 0xD6, 0x36, 0xB6, 0x76, 0xF6, 
  0x0E, 0x8E, 0x4E, 0xCE, 0x2E, 0xAE, 0x6E, 0xEE, 0x1E, 0x9E, 0x5E, 0xDE, 0x3E, 0xBE, 0x7E, 0xFE,
  0x01, 0x81, 0x41, 0xC1, 0x21, 0xA1, 0x61, 0xE1, 0x11, 0x91, 0x51, 0xD1, 0x31, 0xB1, 0x71, 0xF1,
  0x09, 0x89, 0x49, 0xC9, 0x29, 0xA9, 0x69, 0xE9, 0x19, 0x99, 0x59, 0xD9, 0x39, 0xB9, 0x79, 0xF9, 
  0x05, 0x85, 0x45, 0xC5, 0x25, 0xA5, 0x65, 0xE5, 0x15, 0x95, 0x55, 0xD5, 0x35, 0xB5, 0x75, 0xF5,
  0x0D, 0x8D, 0x4D, 0xCD, 0x2D, 0xAD, 0x6D, 0xED, 0x1D, 0x9D, 0x5D, 0xDD, 0x3D, 0xBD, 0x7D, 0xFD,
  0x03, 0x83, 0x43, 0xC3, 0x23, 0xA3, 0x63, 0xE3, 0x13, 0x93, 0x53, 0xD3, 0x33, 0xB3, 0x73, 0xF3, 
  0x0B, 0x8B, 0x4B, 0xCB, 0x2B, 0xAB, 0x6B, 0xEB, 0x1B, 0x9B, 0x5B, 0xDB, 0x3B, 0xBB, 0x7B, 0xFB,
  0x07, 0x87, 0x47, 0xC7, 0x27, 0xA7, 0x67, 0xE7, 0x17, 0x97, 0x57, 0xD7, 0x37, 0xB7, 0x77, 0xF7, 
  0x0F, 0x8F, 0x4F, 0xCF, 0x2F, 0xAF, 0x6F, 0xEF, 0x1F, 0x9F, 0x5F, 0xDF, 0x3F, 0xBF, 0x7F, 0xFF
};

unsigned int v; // reverse 32-bit value, 8 bits at time
unsigned int c; // c will get v reversed

// Option 1:
c = (BitReverseTable256[v & 0xff] << 24) | 
    (BitReverseTable256[(v >> 8) & 0xff] << 16) | 
    (BitReverseTable256[(v >> 16) & 0xff] << 8) |
    (BitReverseTable256[(v >> 24) & 0xff]);

// Option 2:
unsigned char * p = (unsigned char *) &v;
unsigned char * q = (unsigned char *) &c;
q[3] = BitReverseTable256[p[0]]; 
q[2] = BitReverseTable256[p[1]]; 
q[1] = BitReverseTable256[p[2]]; 
q[0] = BitReverseTable256[p[3]];

您可以将这个想法扩展到 64 位 int，或者以内存换取速度(假设您的 L1 数据缓存足够大)，并使用 64K- 一次反转 16 位条目查找表。

其他

简单

unsigned int v;     // input bits to be reversed
unsigned int r = v & 1; // r will be reversed bits of v; first get LSB of v
int s = sizeof(v) * CHAR_BIT - 1; // extra shift needed at end

for (v >>= 1; v; v >>= 1)
{   
  r <<= 1;
  r |= v & 1;
  s--;
}
r <<= s; // shift when v's highest bits are zero

更快(32 位处理器)

unsigned char b = x;
b = ((b * 0x0802LU & 0x22110LU) | (b * 0x8020LU & 0x88440LU)) * 0x10101LU >> 16;

更快(64 位处理器)

unsigned char b; // reverse this (8-bit) byte
b = (b * 0x0202020202ULL & 0x010884422010ULL) % 1023;

如果要在 32 位 int 上执行此操作，只需反转每个字节中的位，并反转字节的顺序。即:

unsigned int toReverse;
unsigned int reversed;
unsigned char inByte0 = (toReverse & 0xFF);
unsigned char inByte1 = (toReverse & 0xFF00) >> 8;
unsigned char inByte2 = (toReverse & 0xFF0000) >> 16;
unsigned char inByte3 = (toReverse & 0xFF000000) >> 24;
reversed = (reverseBits(inByte0) << 24) | (reverseBits(inByte1) << 16) | (reverseBits(inByte2) << 8) | (reverseBits(inByte3);

结果

我对两个最有前途的解决方案、查找表和按位与(第一个)进行了基准测试。测试机器是一台笔记本电脑，配备 4GB DDR2-800 和 Core 2 Duo T7500 @ 2.4GHz，4MB L2 缓存； YMMV。我在 64 位 Linux 上使用 gcc 4.3.2。 OpenMP(和 GCC 绑定(bind))用于高分辨率计时器。

反向.c

#include <stdlib.h>
#include <stdio.h>
#include <omp.h>

unsigned int
reverse(register unsigned int x)
{
    x = (((x & 0xaaaaaaaa) >> 1) | ((x & 0x55555555) << 1));
    x = (((x & 0xcccccccc) >> 2) | ((x & 0x33333333) << 2));
    x = (((x & 0xf0f0f0f0) >> 4) | ((x & 0x0f0f0f0f) << 4));
    x = (((x & 0xff00ff00) >> 8) | ((x & 0x00ff00ff) << 8));
    return((x >> 16) | (x << 16));

}

int main()
{
    unsigned int *ints = malloc(100000000*sizeof(unsigned int));
    unsigned int *ints2 = malloc(100000000*sizeof(unsigned int));
    for(unsigned int i = 0; i < 100000000; i++)
      ints[i] = rand();

    unsigned int *inptr = ints;
    unsigned int *outptr = ints2;
    unsigned int *endptr = ints + 100000000;
    // Starting the time measurement
    double start = omp_get_wtime();
    // Computations to be measured
    while(inptr != endptr)
    {
      (*outptr) = reverse(*inptr);
      inptr++;
      outptr++;
    }
    // Measuring the elapsed time
    double end = omp_get_wtime();
    // Time calculation (in seconds)
    printf("Time: %f seconds\n", end-start);

    free(ints);
    free(ints2);

    return 0;
}

reverse_lookup.c

#include <stdlib.h>
#include <stdio.h>
#include <omp.h>

static const unsigned char BitReverseTable256[] = 
{
  0x00, 0x80, 0x40, 0xC0, 0x20, 0xA0, 0x60, 0xE0, 0x10, 0x90, 0x50, 0xD0, 0x30, 0xB0, 0x70, 0xF0, 
  0x08, 0x88, 0x48, 0xC8, 0x28, 0xA8, 0x68, 0xE8, 0x18, 0x98, 0x58, 0xD8, 0x38, 0xB8, 0x78, 0xF8, 
  0x04, 0x84, 0x44, 0xC4, 0x24, 0xA4, 0x64, 0xE4, 0x14, 0x94, 0x54, 0xD4, 0x34, 0xB4, 0x74, 0xF4, 
  0x0C, 0x8C, 0x4C, 0xCC, 0x2C, 0xAC, 0x6C, 0xEC, 0x1C, 0x9C, 0x5C, 0xDC, 0x3C, 0xBC, 0x7C, 0xFC, 
  0x02, 0x82, 0x42, 0xC2, 0x22, 0xA2, 0x62, 0xE2, 0x12, 0x92, 0x52, 0xD2, 0x32, 0xB2, 0x72, 0xF2, 
  0x0A, 0x8A, 0x4A, 0xCA, 0x2A, 0xAA, 0x6A, 0xEA, 0x1A, 0x9A, 0x5A, 0xDA, 0x3A, 0xBA, 0x7A, 0xFA,
  0x06, 0x86, 0x46, 0xC6, 0x26, 0xA6, 0x66, 0xE6, 0x16, 0x96, 0x56, 0xD6, 0x36, 0xB6, 0x76, 0xF6, 
  0x0E, 0x8E, 0x4E, 0xCE, 0x2E, 0xAE, 0x6E, 0xEE, 0x1E, 0x9E, 0x5E, 0xDE, 0x3E, 0xBE, 0x7E, 0xFE,
  0x01, 0x81, 0x41, 0xC1, 0x21, 0xA1, 0x61, 0xE1, 0x11, 0x91, 0x51, 0xD1, 0x31, 0xB1, 0x71, 0xF1,
  0x09, 0x89, 0x49, 0xC9, 0x29, 0xA9, 0x69, 0xE9, 0x19, 0x99, 0x59, 0xD9, 0x39, 0xB9, 0x79, 0xF9, 
  0x05, 0x85, 0x45, 0xC5, 0x25, 0xA5, 0x65, 0xE5, 0x15, 0x95, 0x55, 0xD5, 0x35, 0xB5, 0x75, 0xF5,
  0x0D, 0x8D, 0x4D, 0xCD, 0x2D, 0xAD, 0x6D, 0xED, 0x1D, 0x9D, 0x5D, 0xDD, 0x3D, 0xBD, 0x7D, 0xFD,
  0x03, 0x83, 0x43, 0xC3, 0x23, 0xA3, 0x63, 0xE3, 0x13, 0x93, 0x53, 0xD3, 0x33, 0xB3, 0x73, 0xF3, 
  0x0B, 0x8B, 0x4B, 0xCB, 0x2B, 0xAB, 0x6B, 0xEB, 0x1B, 0x9B, 0x5B, 0xDB, 0x3B, 0xBB, 0x7B, 0xFB,
  0x07, 0x87, 0x47, 0xC7, 0x27, 0xA7, 0x67, 0xE7, 0x17, 0x97, 0x57, 0xD7, 0x37, 0xB7, 0x77, 0xF7, 
  0x0F, 0x8F, 0x4F, 0xCF, 0x2F, 0xAF, 0x6F, 0xEF, 0x1F, 0x9F, 0x5F, 0xDF, 0x3F, 0xBF, 0x7F, 0xFF
};

int main()
{
    unsigned int *ints = malloc(100000000*sizeof(unsigned int));
    unsigned int *ints2 = malloc(100000000*sizeof(unsigned int));
    for(unsigned int i = 0; i < 100000000; i++)
      ints[i] = rand();

    unsigned int *inptr = ints;
    unsigned int *outptr = ints2;
    unsigned int *endptr = ints + 100000000;
    // Starting the time measurement
    double start = omp_get_wtime();
    // Computations to be measured
    while(inptr != endptr)
    {
    unsigned int in = *inptr;  

    // Option 1:
    //*outptr = (BitReverseTable256[in & 0xff] << 24) | 
    //    (BitReverseTable256[(in >> 8) & 0xff] << 16) | 
    //    (BitReverseTable256[(in >> 16) & 0xff] << 8) |
    //    (BitReverseTable256[(in >> 24) & 0xff]);

    // Option 2:
    unsigned char * p = (unsigned char *) &(*inptr);
    unsigned char * q = (unsigned char *) &(*outptr);
    q[3] = BitReverseTable256[p[0]]; 
    q[2] = BitReverseTable256[p[1]]; 
    q[1] = BitReverseTable256[p[2]]; 
    q[0] = BitReverseTable256[p[3]];

      inptr++;
      outptr++;
    }
    // Measuring the elapsed time
    double end = omp_get_wtime();
    // Time calculation (in seconds)
    printf("Time: %f seconds\n", end-start);

    free(ints);
    free(ints2);

    return 0;
}

我在几种不同的优化中尝试了这两种方法，在每个级别进行了 3 次试验，每次试验都反转了 1 亿个随机unsigned ints。对于查找表选项，我尝试了按位黑客页面上给出的两种方案(选项 1 和 2)。结果如下所示。

按位与

mrj10@mjlap:~/code$ gcc -fopenmp -std=c99 -o reverse reverse.c
mrj10@mjlap:~/code$ ./reverse
Time: 2.000593 seconds
mrj10@mjlap:~/code$ ./reverse
Time: 1.938893 seconds
mrj10@mjlap:~/code$ ./reverse
Time: 1.936365 seconds
mrj10@mjlap:~/code$ gcc -fopenmp -std=c99 -O2 -o reverse reverse.c
mrj10@mjlap:~/code$ ./reverse
Time: 0.942709 seconds
mrj10@mjlap:~/code$ ./reverse
Time: 0.991104 seconds
mrj10@mjlap:~/code$ ./reverse
Time: 0.947203 seconds
mrj10@mjlap:~/code$ gcc -fopenmp -std=c99 -O3 -o reverse reverse.c
mrj10@mjlap:~/code$ ./reverse
Time: 0.922639 seconds
mrj10@mjlap:~/code$ ./reverse
Time: 0.892372 seconds
mrj10@mjlap:~/code$ ./reverse
Time: 0.891688 seconds

查找表(选项 1)

mrj10@mjlap:~/code$ gcc -fopenmp -std=c99 -o reverse_lookup reverse_lookup.c
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.201127 seconds              
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.196129 seconds              
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.235972 seconds              
mrj10@mjlap:~/code$ gcc -fopenmp -std=c99 -O2 -o reverse_lookup reverse_lookup.c
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 0.633042 seconds              
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 0.655880 seconds              
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 0.633390 seconds              
mrj10@mjlap:~/code$ gcc -fopenmp -std=c99 -O3 -o reverse_lookup reverse_lookup.c
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 0.652322 seconds              
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 0.631739 seconds              
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 0.652431 seconds

查找表(选项 2)

mrj10@mjlap:~/code$ gcc -fopenmp -std=c99 -o reverse_lookup reverse_lookup.c
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.671537 seconds
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.688173 seconds
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.664662 seconds
mrj10@mjlap:~/code$ gcc -fopenmp -std=c99 -O2 -o reverse_lookup reverse_lookup.c
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.049851 seconds
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.048403 seconds
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.085086 seconds
mrj10@mjlap:~/code$ gcc -fopenmp -std=c99 -O3 -o reverse_lookup reverse_lookup.c
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.082223 seconds
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.053431 seconds
mrj10@mjlap:~/code$ ./reverse_lookup
Time: 1.081224 seconds

结论

如果您担心性能，请使用带有选项 1 的查找表(字节寻址速度慢得不足为奇)。如果您需要从系统中挤出内存的最后一个字节(如果您关心位反转的性能，您可能会这样做)，按位与方法的优化版本也不会太差劲。

警告

是的，我知道基准测试代码完全是破解版。关于如何改进它的建议非常受欢迎。我知道的事情:

  • 我无权访问 ICC。这可能会更快(如果您可以对此进行测试，请在评论中回复)。
  • 64K 查找表可能适用于一些具有较大 L1D 的现代微架构。
  • -mtune=native 不适用于 -O2/-O3(ld 因一些疯狂的符号重新定义错误而爆炸)，所以我不相信生成的代码已针对我的微体系结构进行了调整.
  • 可能有一种方法可以使用 SSE 稍微更快地完成此操作。我不知道怎么做，但有了快速复制、按位打包和调配指令，一定会有一些东西在那里。
  • 我只知道足够多的 x86 汇编是危险的；这是 GCC 在 -O3 上为选项 1 生成的代码，所以比我更有知识的人可以检查一下:

32 位

.L3:
movl    (%r12,%rsi), %ecx
movzbl  %cl, %eax
movzbl  BitReverseTable256(%rax), %edx
movl    %ecx, %eax
shrl    $24, %eax
mov     %eax, %eax
movzbl  BitReverseTable256(%rax), %eax
sall    $24, %edx
orl     %eax, %edx
movzbl  %ch, %eax
shrl    $16, %ecx
movzbl  BitReverseTable256(%rax), %eax
movzbl  %cl, %ecx
sall    $16, %eax
orl     %eax, %edx
movzbl  BitReverseTable256(%rcx), %eax
sall    $8, %eax
orl     %eax, %edx
movl    %edx, (%r13,%rsi)
addq    $4, %rsi
cmpq    $400000000, %rsi
jne     .L3

编辑:我还尝试在我的机器上使用 uint64_t 类型来查看是否有任何性能提升。性能比 32 位快大约 10%，而且无论您只是使用 64 位类型同时反转两个 32 位 int 类型的位，还是实际上反转 64 位值一半的位。汇编代码如下(对于前一种情况，一次将两个32位int类型的位取反):

.L3:
movq    (%r12,%rsi), %rdx
movq    %rdx, %rax
shrq    $24, %rax
andl    $255, %eax
movzbl  BitReverseTable256(%rax), %ecx
movzbq  %dl,%rax
movzbl  BitReverseTable256(%rax), %eax
salq    $24, %rax
orq     %rax, %rcx
movq    %rdx, %rax
shrq    $56, %rax
movzbl  BitReverseTable256(%rax), %eax
salq    $32, %rax
orq     %rax, %rcx
movzbl  %dh, %eax
shrq    $16, %rdx
movzbl  BitReverseTable256(%rax), %eax
salq    $16, %rax
orq     %rax, %rcx
movzbq  %dl,%rax
shrq    $16, %rdx
movzbl  BitReverseTable256(%rax), %eax
salq    $8, %rax
orq     %rax, %rcx
movzbq  %dl,%rax
shrq    $8, %rdx
movzbl  BitReverseTable256(%rax), %eax
salq    $56, %rax
orq     %rax, %rcx
movzbq  %dl,%rax
shrq    $8, %rdx
movzbl  BitReverseTable256(%rax), %eax
andl    $255, %edx
salq    $48, %rax
orq     %rax, %rcx
movzbl  BitReverseTable256(%rdx), %eax
salq    $40, %rax
orq     %rax, %rcx
movq    %rcx, (%r13,%rsi)
addq    $8, %rsi
cmpq    $400000000, %rsi
jne     .L3

关于c - C语言中位反转(从MSB-> LSB到LSB-> MSB)的高效算法，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/746171/

上一篇：c - 如何在C中将字符串转换为整数？

下一篇：c - 'switch' 比 'if' 快吗？

相关文章：

c - 使用按位运算符的 Sizeof 函数

c++ - Qt QImage像素操作问题

c - 跟踪链表的初始值

c# - 在分布式系统中组织事件的执行并避免死锁

algorithm - 非重叠区间的所有最大子集的输出敏感快速枚举

algorithm - 函数式语言中的等价类和联合/查找

java - 移位以获得余数

c - "sorted"的确切含义

c - 如何表示二进制透明度？

C 宏产生意外行为

©2024 IT工具网  联系我们