Re: [PATCH] Replace evrp use in loop versioning with ranger.

[Aldy Hernandez <aldyh@redhat.com>]

[-- Attachment #1: Type: text/plain, Size: 3065 bytes --]

On Mon, Jul 26, 2021 at 7:28 PM Richard Sandiford
<richard.sandiford@arm.com> wrote:
>
> Aldy Hernandez <aldyh@redhat.com> writes:
> > On Mon, Jul 26, 2021 at 4:18 PM Richard Sandiford
> > <richard.sandiford@arm.com> wrote:
> >>
> >> Aldy Hernandez <aldyh@redhat.com> writes:
> >> > This patch replaces the evrp_range_analyzer in the loop versioning code
> >> > with an on-demand ranger.
> >> >
> >> > Everything was pretty straightforward, except that range_of_expr requires
> >> > a gimple statement as context to provide context aware ranges.  I didn't see
> >> > a convient place where the statement was saved, so I made a vector indexed
> >> > by SSA names.  As an alternative, I tried to use the loop's first statement,
> >> > but that proved to be insufficient.
> >>
> >> The mapping is one-to-many though: there can be multiple statements
> >> for each SSA name.  Maybe that doesn't matter in this context and
> >> any of the statements can act as a representative.
> >>
> >> I'm surprised that the loop's first statement didn't work though,
> >> since the SSA name is supposedly known to be loop-invariant.  What went
> >> wrong when you tried that?
> >
> > I was looking at the first statement of loop_info->block_list and one
> > of the dg.exp=loop-versioning* tests failed.  Perhaps I should have
> > used the loop itself, as in the attached patch.  With this patch all
> > of the loop-versioning tests pass.
> >
> >>
> >> > I am not familiar with loop versioning, but if the DOM walk was only
> >> > necessary for the calls to record_ranges_from_stmt, this too could be
> >> > removed as the ranger will work without it.
> >>
> >> Yeah, that was the only reason.  If the information is available at
> >> version_for_unity (I guess it is) then we should just avoid recording
> >> the versioning there if so.
> >>
> >> How expensive is the check?  If the result is worth caching, perhaps
> >> we should have two bitmaps: the existing one, and one that records
> >> whether we've checked a particular SSA name.
> >>
> >> If the check is relatively cheap then that won't be worth it though.
> >
> > If you're asking about the range_of_expr check, that's all cached, so
> > it should be pretty cheap.  Besides, we're no longer calculating
> > ranges for each statement in the IL, as we were doing in lv_dom_walker
> > with evrp's record_ranges_from_stmt.  Only statements of interest are
> > queried.
>
> Sounds good.  If the results are already cached then another level
> of caching (via the second bitmap I mentioned above) would obviously
> be a waste of time.

My callgrind harness for performance testing wasn't able to pick up
enough samples to measure the time spent in
pass_loop_versioning::execute.  I've seen this happen before with
passes that run too fast.  I'm afraid I don't have enough cycles to
continue working on this.

>
> > How about this patch, pending tests?
>
> OK, thanks, as a strict improvement over the status quo.  But it'd be
> even better without the dom walk :-)

I've removed the DOM walk, and re-tested.

OK to push?

Aldy

[-- Attachment #2: 0001-Replace-evrp-use-in-loop-versioning-with-ranger.patch --]
[-- Type: text/x-patch, Size: 5374 bytes --]

From 9b1cba95377e7b26b4f0495b1b5998d2f7f33a14 Mon Sep 17 00:00:00 2001
From: Aldy Hernandez <aldyh@redhat.com>
Date: Sat, 24 Jul 2021 12:29:28 +0200
Subject: [PATCH] Replace evrp use in loop versioning with ranger.

This patch replaces the evrp_range_analyzer in the loop versioning code
with a ranger.

Tested on x86-64 Linux.

gcc/ChangeLog:

	* gimple-loop-versioning.cc (lv_dom_walker::lv_dom_walker): Remove.
	(loop_versioning::lv_dom_walker::before_dom_children): Remove.
	(loop_versioning::lv_dom_walker::after_dom_children): Remove.
	(loop_versioning::prune_loop_conditions): Replace vr_values use
	with range_query interface.
	(loop_versioning::prune_conditions): Replace dom walk with
	straight iteration.
	(pass_loop_versioning::execute): Use ranger.
---
 gcc/gimple-loop-versioning.cc | 78 ++++++++---------------------------
 1 file changed, 18 insertions(+), 60 deletions(-)

diff --git a/gcc/gimple-loop-versioning.cc b/gcc/gimple-loop-versioning.cc
index 4b70c5a4aab..52eb6429171 100644
--- a/gcc/gimple-loop-versioning.cc
+++ b/gcc/gimple-loop-versioning.cc
@@ -30,19 +30,17 @@ along with GCC; see the file COPYING3.  If not see
 #include "tree-ssa-loop.h"
 #include "ssa.h"
 #include "tree-scalar-evolution.h"
-#include "tree-chrec.h"
 #include "tree-ssa-loop-ivopts.h"
 #include "fold-const.h"
 #include "tree-ssa-propagate.h"
 #include "tree-inline.h"
 #include "domwalk.h"
-#include "alloc-pool.h"
-#include "vr-values.h"
-#include "gimple-ssa-evrp-analyze.h"
 #include "tree-vectorizer.h"
 #include "omp-general.h"
 #include "predict.h"
 #include "tree-into-ssa.h"
+#include "gimple-range.h"
+#include "tree-cfg.h"
 
 namespace {
 
@@ -253,24 +251,6 @@ public:
   unsigned int run ();
 
 private:
-  /* Used to walk the dominator tree to find loop versioning conditions
-     that are always false.  */
-  class lv_dom_walker : public dom_walker
-  {
-  public:
-    lv_dom_walker (loop_versioning &);
-
-    edge before_dom_children (basic_block) FINAL OVERRIDE;
-    void after_dom_children (basic_block) FINAL OVERRIDE;
-
-  private:
-    /* The parent pass.  */
-    loop_versioning &m_lv;
-
-    /* Used to build context-dependent range information.  */
-    evrp_range_analyzer m_range_analyzer;
-  };
-
   /* Used to simplify statements based on conditions that are established
      by the version checks.  */
   class name_prop : public substitute_and_fold_engine
@@ -308,7 +288,7 @@ private:
   bool analyze_block (basic_block);
   bool analyze_blocks ();
 
-  void prune_loop_conditions (class loop *, vr_values *);
+  void prune_loop_conditions (class loop *);
   bool prune_conditions ();
 
   void merge_loop_info (class loop *, class loop *);
@@ -499,36 +479,6 @@ loop_info::worth_versioning_p () const
 	  && (!bitmap_empty_p (&unity_names) || subloops_benefit_p));
 }
 
-loop_versioning::lv_dom_walker::lv_dom_walker (loop_versioning &lv)
-  : dom_walker (CDI_DOMINATORS), m_lv (lv), m_range_analyzer (false)
-{
-}
-
-/* Process BB before processing the blocks it dominates.  */
-
-edge
-loop_versioning::lv_dom_walker::before_dom_children (basic_block bb)
-{
-  m_range_analyzer.enter (bb);
-
-  if (bb == bb->loop_father->header)
-    m_lv.prune_loop_conditions (bb->loop_father, &m_range_analyzer);
-
-  for (gimple_stmt_iterator si = gsi_start_bb (bb); !gsi_end_p (si);
-       gsi_next (&si))
-    m_range_analyzer.record_ranges_from_stmt (gsi_stmt (si), false);
-
-  return NULL;
-}
-
-/* Process BB after processing the blocks it dominates.  */
-
-void
-loop_versioning::lv_dom_walker::after_dom_children (basic_block bb)
-{
-  m_range_analyzer.leave (bb);
-}
-
 /* Decide whether to replace VAL with a new value in a versioned loop.
    Return the new value if so, otherwise return null.  */
 
@@ -1483,18 +1433,21 @@ loop_versioning::analyze_blocks ()
    LOOP.  */
 
 void
-loop_versioning::prune_loop_conditions (class loop *loop, vr_values *vrs)
+loop_versioning::prune_loop_conditions (class loop *loop)
 {
   loop_info &li = get_loop_info (loop);
 
   int to_remove = -1;
   bitmap_iterator bi;
   unsigned int i;
+  int_range_max r;
   EXECUTE_IF_SET_IN_BITMAP (&li.unity_names, 0, i, bi)
     {
       tree name = ssa_name (i);
-      const value_range_equiv *vr = vrs->get_value_range (name);
-      if (vr && !vr->may_contain_p (build_one_cst (TREE_TYPE (name))))
+      gimple *stmt = first_stmt (loop->header);
+
+      if (get_range_query (cfun)->range_of_expr (r, name, stmt)
+	  && !r.contains_p (build_one_cst (TREE_TYPE (name))))
 	{
 	  if (dump_enabled_p ())
 	    dump_printf_loc (MSG_NOTE, find_loop_location (loop),
@@ -1519,9 +1472,11 @@ loop_versioning::prune_conditions ()
   AUTO_DUMP_SCOPE ("prune_loop_conditions",
 		   dump_user_location_t::from_function_decl (m_fn->decl));
 
-  calculate_dominance_info (CDI_DOMINATORS);
-  lv_dom_walker dom_walker (*this);
-  dom_walker.walk (ENTRY_BLOCK_PTR_FOR_FN (m_fn));
+  basic_block bb;
+  FOR_EACH_BB_FN (bb, m_fn)
+    if (bb == bb->loop_father->header)
+      prune_loop_conditions (bb->loop_father);
+
   return m_num_conditions != 0;
 }
 
@@ -1810,7 +1765,10 @@ pass_loop_versioning::execute (function *fn)
   if (number_of_loops (fn) <= 1)
     return 0;
 
-  return loop_versioning (fn).run ();
+  enable_ranger (fn);
+  unsigned int ret = loop_versioning (fn).run ();
+  disable_ranger (fn);
+  return ret;
 }
 
 } // anon namespace
-- 
2.31.1