[V6] Remove empty loop with assumed finiteness (PR tree-optimization/89713)

Some changes on documentation.

Feng

----

On Tue, Jun 4, 2019 at 5:24 PM Feng Xue OS <fxue@os.amperecomputing.com> wrote:
>
> Some changes on documentation.

Please name the option -ffinite-loops (plural), the patch is OK with this
change if you also adjust

> +      /* If the loop has any non-EH exit, we can assume it will terminate. */
> +      FOR_EACH_VEC_ELT (exits, i, ex)
> +       if (!(ex->flags & EDGE_EH))
> +         {

to look for "normal" edges only - in addition to EDGE_EH you
want to ignore EDGE_FAKE and EDGE_ABNORMAL.  EDGE_FAKE
are inserted by connect_infiinite_loops_to_exit and EDGE_ABNORMAL
can appear with setjmp/longjmp and friends.

I think this change also warrants mentioning in gcc-10/changes.html.

Thanks,
Richard.

> Feng
>
> ----
> diff --git a/gcc/ChangeLog b/gcc/ChangeLog
> index 37aab79..4fdc5c8 100644
> --- a/gcc/ChangeLog
> +++ b/gcc/ChangeLog
> @@ -1,3 +1,16 @@
> +2019-06-04  Feng Xue  <fxue@os.amperecomputing.com>
> +
> +       PR tree-optimization/89713
> +       * doc/invoke.texi (-ffinite-loop): Document new option.
> +       * common.opt (-ffinite-loop): New option.
> +       * tree-ssa-dce.c (mark_stmt_if_obviously_necessary): Mark
> +       IFN_GOACC_LOOP calls as necessary.
> +       * tree-ssa-loop-niter.c (finite_loop): Assume loop with an exit is
> +       finite.
> +       * omp-offload.c (oacc_xform_loop): Skip lowering if return value of
> +       IFN_GOACC_LOOP call is not used.
> +       * opts.c (default_options_table): Enable -ffinite-loop at -O2+.
> +
>  2019-06-04  Alan Modra  <amodra@gmail.com>
>
>         PR target/90689
> diff --git a/gcc/common.opt b/gcc/common.opt
> index 0e72fd0..f570815 100644
> --- a/gcc/common.opt
> +++ b/gcc/common.opt
> @@ -1437,6 +1437,10 @@ ffinite-math-only
>  Common Report Var(flag_finite_math_only) Optimization SetByCombined
>  Assume no NaNs or infinities are generated.
>
> +ffinite-loop
> +Common Report Var(flag_finite_loop) Optimization
> +Assume that loops with an exit will terminate and not loop indefinitely.
> +
>  ffixed-
>  Common Joined RejectNegative Var(common_deferred_options) Defer
>  -ffixed-<register>     Mark <register> as being unavailable to the compiler.
> diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> index 91c9bb8..2cb0b9a 100644
> --- a/gcc/doc/invoke.texi
> +++ b/gcc/doc/invoke.texi
> @@ -412,6 +412,7 @@ Objective-C and Objective-C++ Dialects}.
>  -fdevirtualize-at-ltrans  -fdse @gol
>  -fearly-inlining  -fipa-sra  -fexpensive-optimizations  -ffat-lto-objects @gol
>  -ffast-math  -ffinite-math-only  -ffloat-store  -fexcess-precision=@var{style} @gol
> +-ffinite-loop @gol
>  -fforward-propagate  -ffp-contract=@var{style}  -ffunction-sections @gol
>  -fgcse  -fgcse-after-reload  -fgcse-las  -fgcse-lm  -fgraphite-identity @gol
>  -fgcse-sm  -fhoist-adjacent-loads  -fif-conversion @gol
> @@ -8282,6 +8283,7 @@ also turns on the following optimization flags:
>  -fdelete-null-pointer-checks @gol
>  -fdevirtualize  -fdevirtualize-speculatively @gol
>  -fexpensive-optimizations @gol
> +-ffinite-loop @gol
>  -fgcse  -fgcse-lm  @gol
>  -fhoist-adjacent-loads @gol
>  -finline-small-functions @gol
> @@ -9503,6 +9505,15 @@ that may set @code{errno} but are otherwise free of side effects.  This flag is
>  enabled by default at @option{-O2} and higher if @option{-Os} is not also
>  specified.
>
> +@item -ffinite-loop
> +@opindex ffinite-loop
> +@opindex fno-finite-loop
> +Assume that a loop with an exit will eventually take the exit and not loop
> +indefinitely.  This allows the compiler to remove loops that otherwise have
> +no side-effects, not considering eventual endless looping as such.
> +
> +This option is enabled by default at @option{-O2}.
> +
>  @item -ftree-dominator-opts
>  @opindex ftree-dominator-opts
>  Perform a variety of simple scalar cleanups (constant/copy
> diff --git a/gcc/omp-offload.c b/gcc/omp-offload.c
> index 97ae47b..369122f 100644
> --- a/gcc/omp-offload.c
> +++ b/gcc/omp-offload.c
> @@ -300,7 +300,7 @@ oacc_xform_loop (gcall *call)
>    tree chunk_size = NULL_TREE;
>    unsigned mask = (unsigned) TREE_INT_CST_LOW (gimple_call_arg (call, 5));
>    tree lhs = gimple_call_lhs (call);
> -  tree type = TREE_TYPE (lhs);
> +  tree type = NULL_TREE;
>    tree diff_type = TREE_TYPE (range);
>    tree r = NULL_TREE;
>    gimple_seq seq = NULL;
> @@ -308,6 +308,15 @@ oacc_xform_loop (gcall *call)
>    unsigned outer_mask = mask & (~mask + 1); // Outermost partitioning
>    unsigned inner_mask = mask & ~outer_mask; // Inner partitioning (if any)
>
> +  /* Skip lowering if return value of IFN_GOACC_LOOP call is not used. */
> +  if (!lhs)
> +    {
> +      gsi_replace_with_seq (&gsi, seq, true);
> +      return;
> +    }
> +
> +  type = TREE_TYPE (lhs);
> +
>  #ifdef ACCEL_COMPILER
>    chunk_size = gimple_call_arg (call, 4);
>    if (integer_minus_onep (chunk_size)  /* Force static allocation.  */
> diff --git a/gcc/opts.c b/gcc/opts.c
> index 64f94ac..0db9dda 100644
> --- a/gcc/opts.c
> +++ b/gcc/opts.c
> @@ -494,6 +494,7 @@ static const struct default_options default_options_table[] =
>      { OPT_LEVELS_2_PLUS, OPT_fdevirtualize, NULL, 1 },
>      { OPT_LEVELS_2_PLUS, OPT_fdevirtualize_speculatively, NULL, 1 },
>      { OPT_LEVELS_2_PLUS, OPT_fexpensive_optimizations, NULL, 1 },
> +    { OPT_LEVELS_2_PLUS, OPT_ffinite_loop, NULL, 1 },
>      { OPT_LEVELS_2_PLUS, OPT_fgcse, NULL, 1 },
>      { OPT_LEVELS_2_PLUS, OPT_fhoist_adjacent_loads, NULL, 1 },
>      { OPT_LEVELS_2_PLUS, OPT_findirect_inlining, NULL, 1 },
> diff --git a/gcc/testsuite/g++.dg/tree-ssa/empty-loop.C b/gcc/testsuite/g++.dg/tree-ssa/empty-loop.C
> new file mode 100644
> index 0000000..e374155
> --- /dev/null
> +++ b/gcc/testsuite/g++.dg/tree-ssa/empty-loop.C
> @@ -0,0 +1,33 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -fdump-tree-cddce2 -ffinite-loop" } */
> +
> +#include <string>
> +#include <vector>
> +#include <list>
> +#include <set>
> +#include <map>
> +
> +using namespace std;
> +
> +int foo (vector<string> &v, list<string> &l, set<string> &s, map<int, string> &m)
> +{
> +  for (vector<string>::iterator it = v.begin (); it != v.end (); ++it)
> +    it->length();
> +
> +  for (list<string>::iterator it = l.begin (); it != l.end (); ++it)
> +    it->length();
> +
> +  for (map<int, string>::iterator it = m.begin (); it != m.end (); ++it)
> +    it->first + it->second.length();
> +
> +  for (set<string>::iterator it0 = s.begin (); it0 != s.end(); ++it0)
> +    for (vector<string>::reverse_iterator it1 = v.rbegin(); it1 != v.rend(); ++it1)
> +      {
> +        it0->length();
> +        it1->length();
> +      }
> +
> +  return 0;
> +}
> +/* { dg-final { scan-tree-dump-not "if" "cddce2"} } */
> +
> diff --git a/gcc/testsuite/gcc.dg/const-1.c b/gcc/testsuite/gcc.dg/const-1.c
> index a5b2b16..13e3451 100644
> --- a/gcc/testsuite/gcc.dg/const-1.c
> +++ b/gcc/testsuite/gcc.dg/const-1.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile { target nonpic } } */
> -/* { dg-options "-O2 -Wsuggest-attribute=const" } */
> +/* { dg-options "-O2 -Wsuggest-attribute=const -fno-finite-loop" } */
>
>  extern int extern_const(int a) __attribute__ ((const));
>
> diff --git a/gcc/testsuite/gcc.dg/graphite/graphite.exp b/gcc/testsuite/gcc.dg/graphite/graphite.exp
> index ea61446..b294b9c 100644
> --- a/gcc/testsuite/gcc.dg/graphite/graphite.exp
> +++ b/gcc/testsuite/gcc.dg/graphite/graphite.exp
> @@ -56,7 +56,7 @@ set vect_files        [lsort [glob -nocomplain $srcdir/$subdir/vect-*.c ] ]
>
>  # Tests to be compiled.
>  set dg-do-what-default compile
> -dg-runtest $scop_files        "" "-O2 -fgraphite -fdump-tree-graphite-all"
> +dg-runtest $scop_files        "" "-O2 -fgraphite -fdump-tree-graphite-all -fno-finite-loop"
>  dg-runtest $id_files          "" "-O2 -fgraphite-identity -ffast-math -fdump-tree-graphite-details"
>
>  # Tests to be run.
> diff --git a/gcc/testsuite/gcc.dg/loop-unswitch-1.c b/gcc/testsuite/gcc.dg/loop-unswitch-1.c
> index f6fc41d..735eeef 100644
> --- a/gcc/testsuite/gcc.dg/loop-unswitch-1.c
> +++ b/gcc/testsuite/gcc.dg/loop-unswitch-1.c
> @@ -1,6 +1,6 @@
>  /* For PR rtl-optimization/27735  */
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -funswitch-loops -fdump-tree-unswitch-details" } */
> +/* { dg-options "-O2 -funswitch-loops -fdump-tree-unswitch-details -fno-finite-loop" } */
>
>  void set_color(void);
>  void xml_colorize_line(unsigned int *p, int state)
> diff --git a/gcc/testsuite/gcc.dg/predict-9.c b/gcc/testsuite/gcc.dg/predict-9.c
> index 7e5ba08..3710eef 100644
> --- a/gcc/testsuite/gcc.dg/predict-9.c
> +++ b/gcc/testsuite/gcc.dg/predict-9.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -fdisable-tree-evrp -fdump-tree-profile_estimate" } */
> +/* { dg-options "-O2 -fdisable-tree-evrp -fdump-tree-profile_estimate -fno-finite-loop" } */
>
>  extern int global;
>  extern int global2;
> diff --git a/gcc/testsuite/gcc.dg/pure-2.c b/gcc/testsuite/gcc.dg/pure-2.c
> index fe6e2bc..6ac372b 100644
> --- a/gcc/testsuite/gcc.dg/pure-2.c
> +++ b/gcc/testsuite/gcc.dg/pure-2.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -Wsuggest-attribute=pure" } */
> +/* { dg-options "-O2 -Wsuggest-attribute=pure -fno-finite-loop" } */
>  /* { dg-add-options bind_pic_locally } */
>
>  extern int extern_const(int a) __attribute__ ((pure));
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/20040211-1.c b/gcc/testsuite/gcc.dg/tree-ssa/20040211-1.c
> index d289e5d..e4d331e 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/20040211-1.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/20040211-1.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -fdump-tree-cddce2" } */
> +/* { dg-options "-O2 -fdump-tree-cddce2 -fno-finite-loop" } */
>
>  struct rtx_def;
>  typedef struct rtx_def *rtx;
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/dce-2.c b/gcc/testsuite/gcc.dg/tree-ssa/dce-2.c
> new file mode 100644
> index 0000000..ffca49c
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/dce-2.c
> @@ -0,0 +1,37 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -fdump-tree-cddce1 -ffinite-loop" } */
> +
> +typedef struct list {
> +    char pad[15];
> +    struct list *next;
> +} list;
> +
> +int data;
> +
> +list *head, *tail;
> +
> +int __attribute__((pure)) pfn (int);
> +
> +int foo (unsigned u, int s)
> +{
> +  unsigned i;
> +  list *p;
> +  int j;
> +
> +  for (i = 0; i < u; i += 2)
> +    ;
> +
> +  for (p = head; p; p = p->next)
> +    ;
> +
> +  for (j = data; j & s; j = pfn (j + 3))
> +    ;
> +
> +  for (p = head; p != tail; p = p->next)
> +    for (j = data + 1; j > s; j = pfn (j + 2))
> +      ;
> +
> +  return 0;
> +}
> +/* { dg-final { scan-tree-dump-not "if" "cddce1"} } */
> +
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/loop-10.c b/gcc/testsuite/gcc.dg/tree-ssa/loop-10.c
> index a29c9fb..c605005 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/loop-10.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/loop-10.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -fdump-tree-optimized" } */
> +/* { dg-options "-O2 -fdump-tree-optimized -fno-finite-loop" } */
>  /* { dg-require-effective-target int32plus } */
>
>  int bar (void);
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/split-path-6.c b/gcc/testsuite/gcc.dg/tree-ssa/split-path-6.c
> index e9b4f26..7c47906 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/split-path-6.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/split-path-6.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -fsplit-paths -fno-tree-cselim -fdump-tree-split-paths-details -w" } */
> +/* { dg-options "-O2 -fsplit-paths -fno-tree-cselim -fdump-tree-split-paths-details -w -fno-finite-loop" } */
>
>  struct __sFILE
>  {
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
> index d829b04..b7a3d77 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
> @@ -1,5 +1,5 @@
>  /* { dg-do compile } */
> -/* { dg-options "-O2 -fdump-tree-thread2-details -fdump-tree-thread3-details -fdump-tree-thread4-details" } */
> +/* { dg-options "-O2 -fdump-tree-thread2-details -fdump-tree-thread3-details -fdump-tree-thread4-details -fno-finite-loop" } */
>  /* { dg-final { scan-tree-dump "FSM" "thread2" } } */
>  /* { dg-final { scan-tree-dump "FSM" "thread3" } } */
>  /* { dg-final { scan-tree-dump "FSM" "thread4" { xfail *-*-* } } } */
> diff --git a/gcc/tree-ssa-dce.c b/gcc/tree-ssa-dce.c
> index 2478219..179605e 100644
> --- a/gcc/tree-ssa-dce.c
> +++ b/gcc/tree-ssa-dce.c
> @@ -245,6 +245,17 @@ mark_stmt_if_obviously_necessary (gimple *stmt, bool aggressive)
>             mark_stmt_necessary (stmt, true);
>             return;
>           }
> +        /* IFN_GOACC_LOOP calls are necessary in that they are used to
> +           represent parameter (i.e. step, bound) of a lowered OpenACC
> +           partitioned loop. But this kind of partitioned loop might not
> +           survive from aggressive loop removal for it has loop exit and
> +           is assumed to be finite. Therefore, we need to explicitly mark
> +           these calls. (An example is libgomp.oacc-c-c++-common/pr84955.c) */
> +        if (gimple_call_internal_p (stmt, IFN_GOACC_LOOP))
> +          {
> +            mark_stmt_necessary (stmt, true);
> +            return;
> +          }
>         if (!gimple_call_lhs (stmt))
>           return;
>         break;
> diff --git a/gcc/tree-ssa-loop-niter.c b/gcc/tree-ssa-loop-niter.c
> index 470b6a2..c25cb1d 100644
> --- a/gcc/tree-ssa-loop-niter.c
> +++ b/gcc/tree-ssa-loop-niter.c
> @@ -2798,6 +2798,27 @@ finite_loop_p (struct loop *loop)
>                  loop->num);
>        return true;
>      }
> +
> +  if (flag_finite_loop)
> +    {
> +      unsigned i;
> +      vec<edge> exits = get_loop_exit_edges (loop);
> +      edge ex;
> +
> +      /* If the loop has any non-EH exit, we can assume it will terminate. */
> +      FOR_EACH_VEC_ELT (exits, i, ex)
> +       if (!(ex->flags & EDGE_EH))
> +         {
> +           exits.release ();
> +           if (dump_file)
> +             fprintf (dump_file, "Assume loop %i to be finite: it has an exit "
> +                      "and -ffinite-loop is on.\n", loop->num);
> +           return true;
> +          }
> +
> +      exits.release ();
> +    }
> +
>    return false;
>  }
>
> diff --git a/libgomp/testsuite/libgomp.oacc-c-c++-common/pr84955-1.c b/libgomp/testsuite/libgomp.oacc-c-c++-common/pr84955-1.c
> new file mode 100644
> index 0000000..845268b
> --- /dev/null
> +++ b/libgomp/testsuite/libgomp.oacc-c-c++-common/pr84955-1.c
> @@ -0,0 +1,31 @@
> +/* { dg-do compile }  */
> +/* { dg-options "-O2 -fdump-tree-cddce2 -ffinite-loop" } */
> +
> +int
> +f1 (void)
> +{
> +  int i, j;
> +
> +#pragma acc parallel loop tile(2,3)
> +  for (i = 1; i < 10; i++)
> +    for (j = 1; j < 10; j++)
> +      for (;;)
> +       ;
> +
> +  return i + j;
> +}
> +
> +int
> +f2 (void)
> +{
> +  int i, j, k;
> +
> +#pragma acc parallel loop tile(2,3)
> +  for (i = 1; i < 10; i++)
> +    for (j = 1; j < 10; j++)
> +      for (k = 1; k < 10; k++)
> +       ;
> +
> +  return i + j;
> +}
> +/* { dg-final { scan-tree-dump-not "if" "cddce2"} } */