[PATCH] Limit path splitting to loops we optimize for speed

[PATCH] Limit path splitting to loops we optimize for speed

[Jeff Law]

[-- Attachment #1: Type: text/plain, Size: 488 bytes --]


It's not currently clear what the final disposition for the path 
splitting code will be.  However, there's no reason not to implement 
Richi's request that we only do this transformation when optimizing for 
speed and at optimization levels higher than -O2.

This patch limits the transformation to loops where 
optimize_loop_for_speed_p is true.  The patch also moves the 
transformation to -O3.

Bootstrapped & regression tested on x86_64-linux-gnu.  Installed on the 
trunk.



Jeff

[-- Attachment #2: patch --]
[-- Type: text/plain, Size: 4895 bytes --]

commit 47545a4249a6d9ff3003e0e98a11aced97c6c7e1
Author: Jeff Law <law@redhat.com>
Date:   Thu Dec 17 16:32:19 2015 -0700

    [PATCH] Limit path splitting to loops we optimize for speed
    
    	* doc/invoke.texi (-O2 options): Remove -fsplit-paths.
    	(-O3 options): Add -fsplit-paths.
    	* gimple-ssa-split-paths.c: Include predict.h
    	(split_paths): Only split paths in a loop that should be
    	optimized for speed.
    	* opts.c (default_options_table): Move -fsplit-paths from -O2 to
    	-O3.
    
    	* gcc.dg/tree-ssa/split-path-1.c: Explicitly ask for path
    	splitting optimizations.

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index a1f71bd..070b2dd 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,13 @@
+2015-12-17  Jeff Law  <law@redhat.com>
+
+	* doc/invoke.texi (-O2 options): Remove -fsplit-paths.
+	(-O3 options): Add -fsplit-paths.
+	* gimple-ssa-split-paths.c: Include predict.h
+	(split_paths): Only split paths in a loop that should be
+	optimized for speed.
+	* opts.c (default_options_table): Move -fsplit-paths from -O2 to
+	-O3.
+
 2015-12-17  Nathan Sidwell  <nathan@acm.org>
 
 	* ipa-icf.c (sem_item_optimizer::merge): Don't pick 'main' as the
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index cdc5d2c..60530c0 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -7836,7 +7836,6 @@ also turns on the following optimization flags:
 -frerun-cse-after-loop  @gol
 -fsched-interblock  -fsched-spec @gol
 -fschedule-insns  -fschedule-insns2 @gol
--fsplit-paths @gol
 -fstrict-aliasing -fstrict-overflow @gol
 -ftree-builtin-call-dce @gol
 -ftree-switch-conversion -ftree-tail-merge @gol
@@ -7853,7 +7852,7 @@ Optimize yet more.  @option{-O3} turns on all optimizations specified
 by @option{-O2} and also turns on the @option{-finline-functions},
 @option{-funswitch-loops}, @option{-fpredictive-commoning},
 @option{-fgcse-after-reload}, @option{-ftree-loop-vectorize},
-@option{-ftree-loop-distribute-patterns},
+@option{-ftree-loop-distribute-patterns}, @option{-fsplit-paths}
 @option{-ftree-slp-vectorize}, @option{-fvect-cost-model},
 @option{-ftree-partial-pre} and @option{-fipa-cp-clone} options.
 
diff --git a/gcc/gimple-ssa-split-paths.c b/gcc/gimple-ssa-split-paths.c
index 602e916..540fdf3 100644
--- a/gcc/gimple-ssa-split-paths.c
+++ b/gcc/gimple-ssa-split-paths.c
@@ -29,6 +29,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "cfgloop.h"
 #include "gimple-iterator.h"
 #include "tracer.h"
+#include "predict.h"
 
 /* Given LATCH, the latch block in a loop, see if the shape of the
    path reaching LATCH is suitable for being split by duplication.
@@ -180,9 +181,14 @@ split_paths ()
 
   FOR_EACH_LOOP (loop, LI_FROM_INNERMOST)
     {
+      /* Only split paths if we are optimizing this loop for speed.  */
+      if (!optimize_loop_for_speed_p (loop))
+	continue;
+
       /* See if there is a block that we can duplicate to split the
 	 path to the loop latch.  */
-      basic_block bb = find_block_to_duplicate_for_splitting_paths (loop->latch);
+      basic_block bb
+	= find_block_to_duplicate_for_splitting_paths (loop->latch);
 
       /* BB is the merge point for an IF-THEN-ELSE we want to transform.
 
diff --git a/gcc/opts.c b/gcc/opts.c
index d46f304..7ab585f 100644
--- a/gcc/opts.c
+++ b/gcc/opts.c
@@ -523,11 +523,11 @@ static const struct default_options default_options_table[] =
     { OPT_LEVELS_2_PLUS, OPT_fisolate_erroneous_paths_dereference, NULL, 1 },
     { OPT_LEVELS_2_PLUS, OPT_fipa_ra, NULL, 1 },
     { OPT_LEVELS_2_PLUS, OPT_flra_remat, NULL, 1 },
-    { OPT_LEVELS_2_PLUS, OPT_fsplit_paths, NULL, 1 },
 
     /* -O3 optimizations.  */
     { OPT_LEVELS_3_PLUS, OPT_ftree_loop_distribute_patterns, NULL, 1 },
     { OPT_LEVELS_3_PLUS, OPT_fpredictive_commoning, NULL, 1 },
+    { OPT_LEVELS_3_PLUS, OPT_fsplit_paths, NULL, 1 },
     /* Inlining of functions reducing size is a good idea with -Os
        regardless of them being declared inline.  */
     { OPT_LEVELS_3_PLUS_AND_SIZE, OPT_finline_functions, NULL, 1 },
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index d5ae299..baa159d 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2015-12-17  Jeff Law  <law@redhat.com>
+
+	* gcc.dg/tree-ssa/split-path-1.c: Explicitly ask for path
+	splitting optimizations.
+
 2015-12-17  Nathan Sidwell  <nathan@acm.org>
 
 	* gcc.dg/ipa/ipa-icf-merge-1.c: New.
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/split-path-1.c b/gcc/testsuite/gcc.dg/tree-ssa/split-path-1.c
index 5c96241..b24f6a9 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/split-path-1.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/split-path-1.c
@@ -1,5 +1,5 @@
 /* { dg-do run } */
-/* { dg-options "-O2 -fdump-tree-split-paths-details " } */
+/* { dg-options "-O2 -fsplit-paths -fdump-tree-split-paths-details " } */
 
 #include <stdio.h>
 #include <stdlib.h>