替换x86 pcmpestrm汇编指令

template<int MODE> 
static inline __m128i SSE4_cmpestrm(__m128i str1, int len1, __m128i str2, int len2) { 
#ifdef __clang__ 
  /// Use asm reg rather than Yz output constraint to workaround LLVM bug 13199 - 
  /// clang doesn't support Y-prefixed asm constraints. 
  register volatile __m128i result asm ("xmm0"); 
  __asm__ __volatile__ ("pcmpestrm %5, %2, %1": "=x"(result) : "x"(str1), "xm"(str2), "a"(len1), "d"(len2), "i"(MODE) : "cc"); 
#else 
  __m128i result; 
  __asm__ __volatile__ ("pcmpestrm %5, %2, %1": "=Yz"(result) : "x"(str1), "xm"(str2), "a"(len1), "d"(len2), "i"(MODE) : "cc"); 
#endif 
  return result; 
}

从指令介绍中看，不同的模式所执行的操作差异较大，完全实现指令功能所需代码行太多。结合代码中对接口的调用，实际使用到的模式为PCMPSTR_EQUAL_ANY |PCMPSTR_UBYTE_OPS。即按照字节长度做匹配，对比str2中的每个字符是否在str1中出现，若出现，则将对应bit位置置1。

根据识别到的功能进行代码实现：

#include <arm_neon.h>
typedefunion __attribute__((aligned(16))) __oword {
int32x4_t m128i;
uint8_tm128i_u8[16];
} __oword;
template <intMODE>
staticinlineuint16_tSSE4_cmpestrm(int32x4_tstr1, intlen1, int32x4_tstr2, intlen2){
    __oword a, b;
    a.m128i = str1;
    b.m128i = str2;
    uint16_t result = 0;
    uint16_t i = 0;
    uint16_t j = 0;
    // Impala中用到的模式 STRCHR_MODE = PCMPSTR_EQUAL_ANY | PCMPSTR_UBYTE_OPS
    for (i = 0; i < len2; i++)
    {
        for (j = 0; j < len1; j++)
        {
            if (a.m128i_u8[j] == b.m128i_u8[i])
            {
                result |= (1 << i);
            }
        }
    }
    return result;
}