如果我不想使用调用strcmp的开销,我会按照下面代码示例中描述的方法使用短字符串字面值进行字符串比较:
#ifdef LITTLE_ENDIAN //little-endian-addressing
#define BytesAsDWord_M(a, b, c, d)\
((ulong) ((a) | ((b) << 8) | ((ulong) (c) << 16) | ((ulong) (d) << 24)))
#define BytesAsWord_M(a, b)((ushort) ((a) | ((b) << 8)))
#else //LITTLE_ENDIAN //little-endian-addressing
#define BytesAsDWord_M(a, b, c, d)\
((ulong) ((d) | ((c) << 8) | ((b) << 16) | ((a) << 24)))
#define BytesAsWord_M(a, b) ((ushort) ((b) | ((a) << 8)))
#endif //LITTLE_ENDIAN //little-endian-addressing
bool AbsCompare(char* chr_p)
//compare string with "abs"
{
if (*((ulong*) &chr_p[1]) ==
BytesAsDWord_M('a', 'b', 's', '\0'))
return true;
return false;
}
如果编译时不启用优化选项,gcc会编译此示例。但是如果启用了优化选项,则会出现以下警告:
"dereferencing type-punned pointer will break strict-aliasing rules"(解引用类型转换后的指针将破坏严格别名规则)
-O3优化也无法产生有效代码,正如示例所示:
//abstest.c
#include <string.h>
typedef unsigned long ulong;
typedef unsigned short ushort;
#if BYTE_ORDER == LITTLE_ENDIAN //little-endian-addressing
#define BytesAsDWord_M(a, b, c, d)\
((ulong) ((a) | ((b) << 8) | ((ulong) (c) << 16) | ((ulong) (d) << 24)))
#define BytesAsWord_M(a, b)((ushort) ((a) | ((b) << 8)))
#else //BYTE_ORDER == LITTLE_ENDIAN //little-endian-addressing
#define BytesAsDWord_M(a, b, c, d)\
((ulong) ((d) | ((c) << 8) | ((b) << 16) | ((a) << 24)))
#define BytesAsWord_M(a, b) ((ushort) ((b) | ((a) << 8)))
#endif //BYTE_ORDER == LITTLE_ENDIAN //little-endian-addressing
int AbsCompare1(char* chr_p)
{
return *(ulong*) chr_p == BytesAsDWord_M('a', 'b', 's', '\0');
}
int AbsCompare2(char* chr_p)
{
return strcmp(chr_p, "abs");
}
int main(int argc __attribute__((unused)), char ** argv)
{
int i;
int j;
i = AbsCompare1(argv[0]);
j = AbsCompare2(argv[0]);
return i + j;
}
objdump -d -Mintel abstest:
080483d0 <AbsCompare1>:
80483d0: 55 push ebp
80483d1: 89 e5 mov ebp,esp
80483d3: 8b 45 08 mov eax,DWORD PTR [ebp+0x8]
80483d6: 5d pop ebp
80483d7: 81 38 61 62 73 00 cmp DWORD PTR [eax],0x736261
80483dd: 0f 94 c0 sete al
80483e0: 0f b6 c0 movzx eax,al
80483e3: c3 ret
080483f0 <AbsCompare2>:
80483f0: 55 push ebp
80483f1: 0f b6 0d 5c 85 04 08 movzx ecx,BYTE PTR ds:0x804855c
80483f8: 89 e5 mov ebp,esp
80483fa: 8b 55 08 mov edx,DWORD PTR [ebp+0x8]
80483fd: 0f b6 02 movzx eax,BYTE PTR [edx]
8048400: 29 c8 sub eax,ecx
8048402: 75 2b jne 804842f <AbsCompare2+0x3f>
8048404: 0f b6 42 01 movzx eax,BYTE PTR [edx+0x1]
8048408: 0f b6 0d 5d 85 04 08 movzx ecx,BYTE PTR ds:0x804855d
804840f: 29 c8 sub eax,ecx
8048411: 75 1c jne 804842f <AbsCompare2+0x3f>
8048413: 0f b6 42 02 movzx eax,BYTE PTR [edx+0x2]
8048417: 0f b6 0d 5e 85 04 08 movzx ecx,BYTE PTR ds:0x804855e
804841e: 29 c8 sub eax,ecx
8048420: 75 0d jne 804842f <AbsCompare2+0x3f>
8048422: 0f b6 42 03 movzx eax,BYTE PTR [edx+0x3]
8048426: 0f b6 15 5f 85 04 08 movzx edx,BYTE PTR ds:0x804855f
804842d: 29 d0 sub eax,edx
804842f: 5d pop ebp
8048430: c3 ret
有没有可能直接比较这个短文字而不用将chr_p嵌入联合体,特别是因为我想在任意索引处比较chr_p?
&chr_p[1]
这样的表达式几乎肯定会在某个时刻计算出一个非字对齐的地址。 - Michael Burr