Re: [PATCH 2/2] [PATCH] Fix tree-opt/110252: wrong code due to phiopt using flow sensitive info during match

[Richard Biener <richard.guenther@gmail.com>]

On Sat, Jul 15, 2023 at 5:21 AM Andrew Pinski via Gcc-patches
<gcc-patches@gcc.gnu.org> wrote:
>
> Match will query ranger via tree_nonzero_bits/get_nonzero_bits for 2 and 3rd
> operand of the COND_EXPR and phiopt tries to do create the COND_EXPR even if we moving
> one statement. That one statement could have some flow sensitive information on it
> based on the condition that is for the COND_EXPR but that might create wrong code
> if the statement was moved out.
>
> This is similar to the previous version of the patch except now we use
> flow_sensitive_info_storage instead of manually doing the save/restore
> and also handle all defs on a gimple statement rather than just for lhs
> of the gimple statement. Oh and a few more testcases were added that
> was failing before.
>
> OK? Bootsrapped and tested on x86_64-linux-gnu with no regressions.

OK.

Thanks,
Richard.

>         PR tree-optimization/110252
>
> gcc/ChangeLog:
>
>         * tree-ssa-phiopt.cc (class auto_flow_sensitive): New class.
>         (auto_flow_sensitive::auto_flow_sensitive): New constructor.
>         (auto_flow_sensitive::~auto_flow_sensitive): New deconstructor.
>         (match_simplify_replacement): Temporarily
>         remove the flow sensitive info on the two statements that might
>         be moved.
>
> gcc/testsuite/ChangeLog:
>
>         * gcc.dg/tree-ssa/phi-opt-25b.c: Updated as
>         __builtin_parity loses the nonzerobits info.
>         * gcc.c-torture/execute/pr110252-1.c: New test.
>         * gcc.c-torture/execute/pr110252-2.c: New test.
>         * gcc.c-torture/execute/pr110252-3.c: New test.
>         * gcc.c-torture/execute/pr110252-4.c: New test.
> ---
>  .../gcc.c-torture/execute/pr110252-1.c        | 15 ++++++
>  .../gcc.c-torture/execute/pr110252-2.c        | 10 ++++
>  .../gcc.c-torture/execute/pr110252-3.c        | 13 +++++
>  .../gcc.c-torture/execute/pr110252-4.c        |  8 +++
>  gcc/testsuite/gcc.dg/tree-ssa/phi-opt-25b.c   |  6 +--
>  gcc/tree-ssa-phiopt.cc                        | 51 +++++++++++++++++--
>  6 files changed, 96 insertions(+), 7 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.c-torture/execute/pr110252-1.c
>  create mode 100644 gcc/testsuite/gcc.c-torture/execute/pr110252-2.c
>  create mode 100644 gcc/testsuite/gcc.c-torture/execute/pr110252-3.c
>  create mode 100644 gcc/testsuite/gcc.c-torture/execute/pr110252-4.c
>
> diff --git a/gcc/testsuite/gcc.c-torture/execute/pr110252-1.c b/gcc/testsuite/gcc.c-torture/execute/pr110252-1.c
> new file mode 100644
> index 00000000000..4ae93ca0647
> --- /dev/null
> +++ b/gcc/testsuite/gcc.c-torture/execute/pr110252-1.c
> @@ -0,0 +1,15 @@
> +/* This is reduced from sel-sched.cc which was noticed was being miscompiled too. */
> +int g(int min_need_stall) __attribute__((__noipa__));
> +int g(int min_need_stall)
> +{
> +  return  min_need_stall < 0 ? 1 : ((min_need_stall) < (1) ? (min_need_stall) : (1));
> +}
> +int main(void)
> +{
> +  for(int i = -100; i <= 100; i++)
> +    {
> +      int t = g(i);
> +      if (t != (i!=0))
> +        __builtin_abort();
> +    }
> +}
> diff --git a/gcc/testsuite/gcc.c-torture/execute/pr110252-2.c b/gcc/testsuite/gcc.c-torture/execute/pr110252-2.c
> new file mode 100644
> index 00000000000..7f1a7dbf134
> --- /dev/null
> +++ b/gcc/testsuite/gcc.c-torture/execute/pr110252-2.c
> @@ -0,0 +1,10 @@
> +signed char f() __attribute__((__noipa__));
> +signed char f() { return 0; }
> +int main()
> +{
> +  int g = f() - 1;
> +  int e = g < 0 ? 1 : ((g >> (8-2))!=0);
> +  asm("":"+r"(e));
> +  if (e != 1)
> +    __builtin_abort();
> +}
> diff --git a/gcc/testsuite/gcc.c-torture/execute/pr110252-3.c b/gcc/testsuite/gcc.c-torture/execute/pr110252-3.c
> new file mode 100644
> index 00000000000..c24bf1ab1e4
> --- /dev/null
> +++ b/gcc/testsuite/gcc.c-torture/execute/pr110252-3.c
> @@ -0,0 +1,13 @@
> +
> +unsigned int a = 1387579096U;
> +void sinkandcheck(unsigned b) __attribute__((noipa));
> +void sinkandcheck(unsigned b)
> +{
> +        if (a != b)
> +        __builtin_abort();
> +}
> +int main() {
> +    a = 1 < (~a) ? 1 : (~a);
> +    sinkandcheck(1);
> +    return 0;
> +}
> diff --git a/gcc/testsuite/gcc.c-torture/execute/pr110252-4.c b/gcc/testsuite/gcc.c-torture/execute/pr110252-4.c
> new file mode 100644
> index 00000000000..f97edd3f069
> --- /dev/null
> +++ b/gcc/testsuite/gcc.c-torture/execute/pr110252-4.c
> @@ -0,0 +1,8 @@
> +
> +int a, b = 2, c = 2;
> +int main() {
> +  b = ~(1 % (a ^ (b - (1 && c) || c & b)));
> +  if (b < -1)
> +    __builtin_abort();
> +  return 0;
> +}
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-25b.c b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-25b.c
> index 7298da0c96e..0fd9b004a03 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-25b.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-25b.c
> @@ -65,8 +65,6 @@ int test_popcountll(unsigned long long x, unsigned long long y)
>    return x ? __builtin_popcountll(y) : 0;
>  }
>
> -/* 3 types of functions (not including parity), each with 3 types and there are 2 goto each */
> -/* { dg-final { scan-tree-dump-times "goto " 18 "optimized" } } */
> +/* 4 types of functions, each with 3 types and there are 2 goto each */
> +/* { dg-final { scan-tree-dump-times "goto " 24 "optimized" } } */
>  /* { dg-final { scan-tree-dump-times "x_..D. != 0" 12 "optimized" } } */
> -/* parity case will be optimized to x!=0 & parity(y) . */
> -/* { dg-final { scan-tree-dump-times " & " 3 "optimized" } } */
> diff --git a/gcc/tree-ssa-phiopt.cc b/gcc/tree-ssa-phiopt.cc
> index 467c9fd108a..9d542fd345f 100644
> --- a/gcc/tree-ssa-phiopt.cc
> +++ b/gcc/tree-ssa-phiopt.cc
> @@ -708,6 +708,45 @@ move_stmt (gimple *stmt, gimple_stmt_iterator *gsi, auto_bitmap &inserted_exprs)
>    reset_flow_sensitive_info (name);
>  }
>
> +/* RAII style class to temporarily remove flow sensitive
> +   from ssa names defined by a gimple statement.  */
> +class auto_flow_sensitive
> +{
> +public:
> +  auto_flow_sensitive (gimple *s);
> +  ~auto_flow_sensitive ();
> +private:
> +  auto_vec<std::pair<tree, flow_sensitive_info_storage>, 2> stack;
> +};
> +
> +/* Constructor for auto_flow_sensitive. Saves
> +   off the ssa names' flow sensitive information
> +   that was defined by gimple statement S and
> +   resets it to be non-flow based ones. */
> +
> +auto_flow_sensitive::auto_flow_sensitive (gimple *s)
> +{
> +  if (!s)
> +    return;
> +  ssa_op_iter it;
> +  tree def;
> +  FOR_EACH_SSA_TREE_OPERAND (def, s, it, SSA_OP_DEF)
> +    {
> +      flow_sensitive_info_storage storage;
> +      storage.save_and_clear (def);
> +      stack.safe_push (std::make_pair (def, storage));
> +    }
> +}
> +
> +/* Deconstructor, restores the flow sensitive information
> +   for the SSA names that had been saved off.  */
> +
> +auto_flow_sensitive::~auto_flow_sensitive ()
> +{
> +  for (auto p : stack)
> +    p.second.restore (p.first);
> +}
> +
>  /*  The function match_simplify_replacement does the main work of doing the
>      replacement using match and simplify.  Return true if the replacement is done.
>      Otherwise return false.
> @@ -793,9 +832,15 @@ match_simplify_replacement (basic_block cond_bb, basic_block middle_bb,
>      return false;
>
>    tree type = TREE_TYPE (gimple_phi_result (phi));
> -  result = gimple_simplify_phiopt (early_p, type, stmt,
> -                                  arg_true, arg_false,
> -                                  &seq);
> +  {
> +    auto_flow_sensitive s1(stmt_to_move);
> +    auto_flow_sensitive s_alt(stmt_to_move_alt);
> +
> +    result = gimple_simplify_phiopt (early_p, type, stmt,
> +                                    arg_true, arg_false,
> +                                   &seq);
> +  }
> +
>    if (!result)
>      return false;
>
> --
> 2.31.1
>