[Bug rtl-optimization/55278] [4.8/4.9 Regression] Botan performance regressions apparently due to LRA

[jakub at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=55278

--- Comment #6 from Jakub Jelinek <jakub at gcc dot gnu.org> 2013-05-07 22:34:15 UTC ---
To:
unsigned char KASUMI_SBOX_S7[128];
unsigned short KASUMI_SBOX_S9[512];

static inline unsigned short
rotate_left (unsigned short input, unsigned long rot)
{
  return ((input << rot) | (input >> (8 * sizeof (unsigned short) - rot)));
}

static inline unsigned short
reverse_bytes (unsigned short val)
{
  return rotate_left (val, 8);
}

static inline unsigned short
load_be (const unsigned char in[], unsigned long off)
{
  return reverse_bytes (*((const unsigned short *)in + off));
}

static inline void
store_be (unsigned short in, unsigned char out[2])
{
  *(unsigned short *)out = reverse_bytes (in);
}

static inline void
store_be4 (unsigned char out[], unsigned short x0, unsigned short x1,
      unsigned short x2, unsigned short x3)
{
  store_be (x0, out + (0 * sizeof (unsigned short)));
  store_be (x1, out + (1 * sizeof (unsigned short)));
  store_be (x2, out + (2 * sizeof (unsigned short)));
  store_be (x3, out + (3 * sizeof (unsigned short)));
}

unsigned short
FI (unsigned short I, unsigned short K)
{
  unsigned short D9 = (I >> 7);
  unsigned char D7 = (I & 0x7F);
  D9 = KASUMI_SBOX_S9[D9] ^ D7;
  D7 = KASUMI_SBOX_S7[D7] ^ (D9 & 0x7F);

  D7 ^= (K >> 9);
  D9 = KASUMI_SBOX_S9[D9 ^ (K & 0x1FF)] ^ D7;
  D7 = KASUMI_SBOX_S7[D7] ^ (D9 & 0x7F);
  return (D7 << 9) | D9;
}

__attribute__((noinline, noclone))
void
encrypt_n (unsigned short **EK, const unsigned char in[], unsigned char out[],
       unsigned long blocks)
{
  unsigned long i, j;
  for (i = 0; i != blocks; ++i)
    {
      unsigned short B0 = load_be (in, 0);
      unsigned short B1 = load_be (in, 1);
      unsigned short B2 = load_be (in, 2);
      unsigned short B3 = load_be (in, 3);
      for (j = 0; j != 8; j += 2)
    {
      const unsigned short *K = &(*EK)[8 * j];
      unsigned short R = B1 ^ (rotate_left (B0, 1) & K[0]);
      unsigned short L = B0 ^ (rotate_left (R, 1) | K[1]);
      L = FI (L ^ K[2], K[3]) ^ R;
      R = FI (R ^ K[4], K[5]) ^ L;
      L = FI (L ^ K[6], K[7]) ^ R;
      R = B2 ^= R;
      L = B3 ^= L;
      R = FI (R ^ K[10], K[11]) ^ L;
      L = FI (L ^ K[12], K[13]) ^ R;
      R = FI (R ^ K[14], K[15]) ^ L;
      R ^= (rotate_left (L, 1) & K[8]);
      L ^= (rotate_left (R, 1) | K[9]);
      B0 ^= L;
      B1 ^= R;
    }
      store_be4 (out, B0, B1, B2, B3);
      in += 8;
      out += 8;
    }
}

unsigned char in[4096], out[4096];

int
main ()
{
  unsigned short EKb[64], *EK = EKb;
  __builtin_memset (EKb, 0, sizeof EKb);
  asm volatile ("" : : : "memory");
  int i;
  for (i = 0; i < 100000; i++)
    encrypt_n (&EK, in, out, 4096 / 8);
  return 0;
}

actually (note different code in store_be and load_be).  I'm surprised that
the 16-bit rotations aren't detected/folded into rotations (or rotate_left
(u16, 8) into a bswap16).