Re: [lno] [RFC] if-conversion and auto vectorizer

[Devang Patel <dpatel at apple dot com>]

OK. So far I have coded transformation to transform

bar ()
{
  int A[N+1], B[N+1], C[N+1], D[N+1];
  int i;

  for (i = 1; i<N; i++)
    {
      if (A[i] > 0)
        {
          A[i] = A[i] + C[i];
          B[i] = A[i] + 1;
        }
      else
        {
          A[i] = D[i];
          B[i] = D[i] + 1;
        }
    }
  ibar(A);
  ibar(B);
}

into :

bar ()
{
  int i;
  int D[17];
  int C[17];
  int B[17];
  int A[17];
  int T.5;
  int T.4;
  int T.3;
  int T.2;
  int T.1;
  int T.0;

  # BLOCK 0
  # PRED: ENTRY [100.0%]  (fallthru,exec)
  # SUCC: 1 [100.0%]  (fallthru,exec)

  # BLOCK 1
  # PRED: 6 [100.0%]  (fallthru) 0 [100.0%]  (fallthru,exec)
  # i_1 = PHI <1(0), i_15(6)>;
<L0>:;
  T.0_3 = if (1)
    {
      A[i_1];
    };
  if (T.0_3 > 0) goto <L1>; else goto <L2>;
  # SUCC: 3 [21.0%]  (false,exec) 2 [79.0%]  (true,exec)

  # BLOCK 2
  # PRED: 1 [79.0%]  (true,exec)
<L1>:;
  T.1_9 = if (1 && T.0_3 > 0)
    {
      C[i_1];
    };
  T.2_10 = if (1 && T.0_3 > 0)
    {
      T.0_3 + T.1_9;
    };
  A[i_1] = if (1 && T.0_3 > 0)
    {
      T.2_10
    };
  T.3_12 = if (1 && T.0_3 > 0)
    {
      T.2_10 + 1;
    };
  B[i_1] = if (1 && T.0_3 > 0)
    {
      T.3_12
    };
  goto <bb 4> (<L3>);
  # SUCC: 4 [100.0%]  (fallthru,exec)

  # BLOCK 3
  # PRED: 1 [21.0%]  (false,exec)
<L2>:;
  T.4_5 = if (1 && !(T.0_3 > 0))
    {
      D[i_1];
    };
  A[i_1] = if (1 && !(T.0_3 > 0))
    {
      T.4_5
    };
  T.5_7 = if (1 && !(T.0_3 > 0))
    {
      T.4_5 + 1;
    };
  B[i_1] = if (1 && !(T.0_3 > 0))
    {
      T.5_7
    };
  # SUCC: 4 [100.0%]  (fallthru,exec)

  # BLOCK 4
  # PRED: 3 [100.0%]  (fallthru,exec) 2 [100.0%]  (fallthru,exec)
<L3>:;
  i_15 = i_1 + 1;
  if (i_15 <= 15) goto <L8>; else goto <L5>;
  # SUCC: 5 [11.0%]  (false,exec) 6 [89.0%]  (true,exec)

  # BLOCK 6
  # PRED: 4 [89.0%]  (true,exec)
<L8>:;
  goto <bb 1> (<L0>);
  # SUCC: 1 [100.0%]  (fallthru)

  # BLOCK 5
  # PRED: 4 [11.0%]  (false,exec)
<L5>:;
  ibar (&A);
  ibar (&B);
  return;
  # SUCC: EXIT [100.0%]

}

I spent lot of time unnecessary to create super block inside loop by
merging block 2 and 3 into block 1.

If vectorizer can not vectorize this loop then it will be reverted to
original form using loop versioning. Am I on the right track ?

Thanks,
--
Devang

Attachment: tree_if_conv.ver_0.diff.gz
Description: GNU Zip compressed data