diff mbox series

tree-optimization/109893 - allow more backwards jump threading

Message ID 20240112141616.353D913782@imap1.dmz-prg2.suse.org
State New
Headers
Series tree-optimization/109893 - allow more backwards jump threading |

Checks

Context Check Description
linaro-tcwg-bot/tcwg_gcc_build--master-arm success Testing passed
linaro-tcwg-bot/tcwg_gcc_build--master-aarch64 success Testing passed
linaro-tcwg-bot/tcwg_gcc_check--master-arm fail Testing failed
linaro-tcwg-bot/tcwg_gcc_check--master-aarch64 fail Testing failed

Commit Message

Richard Biener Jan. 12, 2024, 2:16 p.m. UTC 
  Currently we scale the number of stmts allowed for forward
jump threading to limit those for backwards jump threading
by applying a factor of two to the counted stmts.  That doesn't
allow fine-grained adjustments, like by a single stmt as needed
for PR109893.  The following changes the factor to be a percentage
of the forward threading number and adjusts that percentage from
50 to 54, fixing the regression.

Bootstrapped and tested on x86_64-unknown-linux-gnu, I'm cross-checking
some FAILs I see.

	PR tree-optimization/109893
	* params.opt (fsm-scale-path-stmts): Change to percentage
	and default to 54 from 50.
	* doc/invoke.texi (--param fsm-scale-path-stmts): Adjust.
	* tree-ssa-threadbackward.cc
	(back_threader_profitability::possibly_profitable_path_p):
	Adjust param_fsm_scale_path_stmts uses.
	(back_threader_profitability::profitable_path_p): Likewise.

	* gcc.dg/tree-ssa/pr109893.c: New testcase.
---
 gcc/doc/invoke.texi                      |  4 +--
 gcc/params.opt                           |  4 +--
 gcc/testsuite/gcc.dg/tree-ssa/pr109893.c | 33 ++++++++++++++++++++++++
 gcc/tree-ssa-threadbackward.cc           | 17 ++++++------
 4 files changed, 46 insertions(+), 12 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr109893.c
diff mbox series

Patch

diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index b7a201317ce..7e19f0245de 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -16647,8 +16647,8 @@  Maximum number of arrays per scop.
 Max. size of loc list for which reverse ops should be added.
 
 @item fsm-scale-path-stmts
-Scale factor to apply to the number of statements in a threading path
-crossing a loop backedge when comparing to
+Percentage of max-jump-thread-duplication-stmts to allow for the number of
+statements in a threading path crossing a loop backedge.
 @option{--param=max-jump-thread-duplication-stmts}.
 
 @item uninit-control-dep-attempts
diff --git a/gcc/params.opt b/gcc/params.opt
index 5eb045b2e6c..dbfa8ece8e0 100644
--- a/gcc/params.opt
+++ b/gcc/params.opt
@@ -131,8 +131,8 @@  Common Joined UInteger Var(param_early_inlining_insns) Init(6) Optimization Para
 Maximal estimated growth of function body caused by early inlining of single call.
 
 -param=fsm-scale-path-stmts=
-Common Joined UInteger Var(param_fsm_scale_path_stmts) Init(2) IntegerRange(1, 10) Param Optimization
-Scale factor to apply to the number of statements in a threading path crossing a loop backedge when comparing to max-jump-thread-duplication-stmts.
+Common Joined UInteger Var(param_fsm_scale_path_stmts) Init(54) IntegerRange(1, 100) Param Optimization
+Percentage of max-jump-thread-duplication-stmts to allow for the number of statements in a threading path crossing a loop backedge.
 
 -param=fully-pipelined-fma=
 Common Joined UInteger Var(param_fully_pipelined_fma) Init(0) IntegerRange(0, 1) Param Optimization
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr109893.c b/gcc/testsuite/gcc.dg/tree-ssa/pr109893.c
new file mode 100644
index 00000000000..5c98664df72
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr109893.c
@@ -0,0 +1,33 @@ 
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-dom2" } */
+
+void foo(void);
+void bar(void);
+static char a;
+static int b, e, f;
+static int *c = &b, *g;
+int main() {
+    int *j = 0;
+    if (a) {
+        g = 0;
+        if (c)
+            bar();
+    } else {
+        j = &e;
+        c = 0;
+    }
+    if (c == &f == b || c == &e)
+        ;
+    else
+        __builtin_unreachable();
+    if (g || e) {
+        if (j == &e || j == 0)
+            ;
+        else
+            foo();
+    }
+    a = 4;
+}
+
+/* Jump threading in thread1 should enable to elide the call to foo.  */
+/* { dg-final { scan-tree-dump-not "foo" "dom2" } } */
diff --git a/gcc/tree-ssa-threadbackward.cc b/gcc/tree-ssa-threadbackward.cc
index fcebcdb5eaa..3091ddf4af1 100644
--- a/gcc/tree-ssa-threadbackward.cc
+++ b/gcc/tree-ssa-threadbackward.cc
@@ -741,8 +741,8 @@  back_threader_profitability::possibly_profitable_path_p
   if ((!m_threaded_multiway_branch
        || !loop->latch
        || loop->latch->index == EXIT_BLOCK)
-      && (m_n_insns * param_fsm_scale_path_stmts
-	  >= param_max_jump_thread_duplication_stmts))
+      && (m_n_insns * 100 >= (param_max_jump_thread_duplication_stmts
+			      * param_fsm_scale_path_stmts)))
     {
       if (dump_file && (dump_flags & TDF_DETAILS))
 	fprintf (dump_file,
@@ -751,8 +751,9 @@  back_threader_profitability::possibly_profitable_path_p
       return false;
     }
   *large_non_fsm = (!(m_threaded_through_latch && m_threaded_multiway_branch)
-		    && (m_n_insns * param_fsm_scale_path_stmts
-			>= param_max_jump_thread_duplication_stmts));
+		    && (m_n_insns * 100
+			>= (param_max_jump_thread_duplication_stmts
+			    * param_fsm_scale_path_stmts)));
 
   if (dump_file && (dump_flags & TDF_DETAILS))
     fputc ('\n', dump_file);
@@ -825,8 +826,8 @@  back_threader_profitability::profitable_path_p (const vec<basic_block> &m_path,
   if (!m_threaded_multiway_branch
       && *creates_irreducible_loop
       && (!(cfun->curr_properties & PROP_loop_opts_done)
-	  || (m_n_insns * param_fsm_scale_path_stmts
-	      >= param_max_jump_thread_duplication_stmts)))
+	  || (m_n_insns * 100 >= (param_max_jump_thread_duplication_stmts
+				  * param_fsm_scale_path_stmts))))
     {
       if (dump_file && (dump_flags & TDF_DETAILS))
 	fprintf (dump_file,
@@ -841,8 +842,8 @@  back_threader_profitability::profitable_path_p (const vec<basic_block> &m_path,
      case, drastically reduce the number of statements we are allowed
      to copy.  */
   if (!(m_threaded_through_latch && m_threaded_multiway_branch)
-      && (m_n_insns * param_fsm_scale_path_stmts
-	  >= param_max_jump_thread_duplication_stmts))
+      && (m_n_insns * 100 >= (param_max_jump_thread_duplication_stmts
+			      * param_fsm_scale_path_stmts)))
     {
       if (dump_file && (dump_flags & TDF_DETAILS))
 	fprintf (dump_file,