Replacing pcmpestrm on Arm

This function is used to check whether each byte element (m128i_u8[index]) in str2 exists in str1. If yes, the corresponding bit in the result is set to 1.

For details about the intrinsic function corresponding to pcmpestrm, see Intrinsics Guide.

• Code on x86:

  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;
  }

• Alternative for Kunpeng processors:

  #include <arm_neon.h>
  typedef union __attribute__((aligned(16))) __oword{
  int32x4_t m128i;
  uint8_t m128i_u8[16];
  } __oword;
  template<int MODE>
  static inline uint16_t SSE4_cmpestrm(int32x4_t str1, int len1, int32x4_t str2, int len2) {
      __oword a, b;
  a.m128i = str1;
  b.m128i = str2;
  uint16_t result = 0;
  uint16_t i = 0;
  uint16_t j = 0; 
  / / Mode used in Impala: 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;
  }