Move pass_cse_sincos after vectorizer.

__builtin_cexpi can't be vectorized since there's gap between it and
vectorized sincos version(In libmvec, it passes a double and two
double pointer and returns nothing.) And it will lose some
vectorization opportunity if sin & cos are optimized to cexpi before
vectorizer.

I'm trying to add vect_recog_cexpi_pattern to split cexpi to sin and
cos, but it failed vectorizable_simd_clone_call since NULL is returned
by cgraph_node::get (fndecl).  So alternatively, the patch try to move
pass_cse_sincos after vectorizer, just before pas_cse_reciprocals.

Also original pass_cse_sincos additionaly expands pow&cabs, this patch
split that part into a separate pass named pass_expand_powcabs which
remains the old pass position.

gcc/ChangeLog:

	* passes.def: (Split pass_cse_sincos to pass_expand_powcabs
	and pass_cse_sincos, and move pass_cse_sincos after vectorizer).
	* timevar.def (TV_TREE_POWCABS): New timevar.
	* tree-pass.h (make_pass_expand_powcabs): Split from pass_cse_sincos.
	* tree-ssa-math-opts.cc (gimple_expand_builtin_cabs): Ditto.
	(class pass_expand_powcabs): Ditto.
	(pass_expand_powcabs::execute): Ditto.
	(make_pass_expand_powcabs): Ditto.
	(pass_cse_sincos::execute): Remove pow/cabs expand part.
	(make_pass_cse_sincos): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.dg/pow-sqrt-synth-1.c: Adjust testcase.

diff --git a/gcc/passes.def b/gcc/passes.def
index 375d3d6..6bb92ef 100644 (file)
--- a/gcc/passes.def
+++ b/gcc/passes.def
@@ -253,7 +253,7 @@ along with GCC; see the file COPYING3.  If not see
       NEXT_PASS (pass_ccp, true /* nonzero_p */);
       /* After CCP we rewrite no longer addressed locals into SSA
         form if possible.  */
-      NEXT_PASS (pass_cse_sincos);
+      NEXT_PASS (pass_expand_powcabs);
       NEXT_PASS (pass_optimize_bswap);
       NEXT_PASS (pass_laddress);
       NEXT_PASS (pass_lim);
@@ -328,6 +328,7 @@ along with GCC; see the file COPYING3.  If not see
       NEXT_PASS (pass_simduid_cleanup);
       NEXT_PASS (pass_lower_vector_ssa);
       NEXT_PASS (pass_lower_switch);
+      NEXT_PASS (pass_cse_sincos);
       NEXT_PASS (pass_cse_reciprocals);
       NEXT_PASS (pass_reassoc, false /* early_p */);
       NEXT_PASS (pass_strength_reduction);

diff --git a/gcc/testsuite/gcc.dg/pow-sqrt-synth-1.c b/gcc/testsuite/gcc.dg/pow-sqrt-synth-1.c
index 4a94325..484b29a 100644 (file)
--- a/gcc/testsuite/gcc.dg/pow-sqrt-synth-1.c
+++ b/gcc/testsuite/gcc.dg/pow-sqrt-synth-1.c
@@ -1,5 +1,5 @@
 /* { dg-do compile { target sqrt_insn } } */
-/* { dg-options "-fdump-tree-sincos -Ofast --param max-pow-sqrt-depth=8" } */
+/* { dg-options "-fdump-tree-powcabs -Ofast --param max-pow-sqrt-depth=8" } */
 /* { dg-additional-options "-mfloat-abi=softfp -mfpu=neon-vfpv4" { target arm*-*-* } } */
 
 double
@@ -34,4 +34,4 @@ vecfoo (double *a)
     a[i] = __builtin_pow (a[i], 1.25);
 }
 
-/* { dg-final { scan-tree-dump-times "synthesizing" 7 "sincos" } } */
+/* { dg-final { scan-tree-dump-times "synthesizing" 7 "powcabs" } } */

diff --git a/gcc/timevar.def b/gcc/timevar.def
index 2dae5e1..651af19 100644 (file)
--- a/gcc/timevar.def
+++ b/gcc/timevar.def
@@ -220,6 +220,7 @@ DEFTIMEVAR (TV_TREE_SWITCH_CONVERSION, "tree switch conversion")
 DEFTIMEVAR (TV_TREE_SWITCH_LOWERING,   "tree switch lowering")
 DEFTIMEVAR (TV_TREE_RECIP            , "gimple CSE reciprocals")
 DEFTIMEVAR (TV_TREE_SINCOS           , "gimple CSE sin/cos")
+DEFTIMEVAR (TV_TREE_POWCABS           , "gimple expand pow/cabs")
 DEFTIMEVAR (TV_TREE_WIDEN_MUL        , "gimple widening/fma detection")
 DEFTIMEVAR (TV_TRANS_MEM             , "transactional memory")
 DEFTIMEVAR (TV_TREE_STRLEN           , "tree strlen optimization")

diff --git a/gcc/tree-pass.h b/gcc/tree-pass.h
index 606d1d6..4dfe05e 100644 (file)
--- a/gcc/tree-pass.h
+++ b/gcc/tree-pass.h
@@ -444,6 +444,7 @@ extern gimple_opt_pass *make_pass_early_warn_uninitialized (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_late_warn_uninitialized (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_cse_reciprocals (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_cse_sincos (gcc::context *ctxt);
+extern gimple_opt_pass *make_pass_expand_powcabs (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_optimize_bswap (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_store_merging (gcc::context *ctxt);
 extern gimple_opt_pass *make_pass_optimize_widening_mul (gcc::context *ctxt);

diff --git a/gcc/tree-ssa-math-opts.cc b/gcc/tree-ssa-math-opts.cc
index a4492c9..58152b5 100644 (file)
--- a/gcc/tree-ssa-math-opts.cc
+++ b/gcc/tree-ssa-math-opts.cc
@@ -2226,8 +2226,7 @@ gimple_expand_builtin_cabs (gimple_stmt_iterator *gsi, location_t loc, tree arg)
 }
 
 /* Go through all calls to sin, cos and cexpi and call execute_cse_sincos_1
-   on the SSA_NAME argument of each of them.  Also expand powi(x,n) into
-   an optimal number of multiplies, when n is a constant.  */
+   on the SSA_NAME argument of each of them.  */
 
 namespace {
 
@@ -2254,8 +2253,6 @@ public:
   /* opt_pass methods: */
   bool gate (function *) final override
     {
-      /* We no longer require either sincos or cexp, since powi expansion
-        piggybacks on this pass.  */
       return optimize;
     }
 
@@ -2275,24 +2272,15 @@ pass_cse_sincos::execute (function *fun)
   FOR_EACH_BB_FN (bb, fun)
     {
       gimple_stmt_iterator gsi;
-      bool cleanup_eh = false;
 
       for (gsi = gsi_after_labels (bb); !gsi_end_p (gsi); gsi_next (&gsi))
         {
          gimple *stmt = gsi_stmt (gsi);
 
-         /* Only the last stmt in a bb could throw, no need to call
-            gimple_purge_dead_eh_edges if we change something in the middle
-            of a basic block.  */
-         cleanup_eh = false;
-
          if (is_gimple_call (stmt)
              && gimple_call_lhs (stmt))
            {
-             tree arg, arg0, arg1, result;
-             HOST_WIDE_INT n;
-             location_t loc;
-
+             tree arg;
              switch (gimple_call_combined_fn (stmt))
                {
                CASE_CFN_COS:
@@ -2309,7 +2297,94 @@ pass_cse_sincos::execute (function *fun)
                  if (TREE_CODE (arg) == SSA_NAME)
                    cfg_changed |= execute_cse_sincos_1 (arg);
                  break;
+               default:
+                 break;
+               }
+           }
+       }
+    }
+
+  statistics_counter_event (fun, "sincos statements inserted",
+                           sincos_stats.inserted);
+  statistics_counter_event (fun, "conv statements removed",
+                           sincos_stats.conv_removed);
+
+  return cfg_changed ? TODO_cleanup_cfg : 0;
+}
+
+} // anon namespace
+
+gimple_opt_pass *
+make_pass_cse_sincos (gcc::context *ctxt)
+{
+  return new pass_cse_sincos (ctxt);
+}
+
+/* Expand powi(x,n) into an optimal number of multiplies, when n is a constant.
+   Also expand CABS.  */
+namespace {
+
+const pass_data pass_data_expand_powcabs =
+{
+  GIMPLE_PASS, /* type */
+  "powcabs", /* name */
+  OPTGROUP_NONE, /* optinfo_flags */
+  TV_TREE_POWCABS, /* tv_id */
+  PROP_ssa, /* properties_required */
+  0, /* properties_provided */
+  0, /* properties_destroyed */
+  0, /* todo_flags_start */
+  TODO_update_ssa, /* todo_flags_finish */
+};
+
+class pass_expand_powcabs : public gimple_opt_pass
+{
+public:
+  pass_expand_powcabs (gcc::context *ctxt)
+    : gimple_opt_pass (pass_data_expand_powcabs, ctxt)
+  {}
 
+  /* opt_pass methods: */
+  bool gate (function *) final override
+    {
+      return optimize;
+    }
+
+  unsigned int execute (function *) final override;
+
+}; // class pass_expand_powcabs
+
+unsigned int
+pass_expand_powcabs::execute (function *fun)
+{
+  basic_block bb;
+  bool cfg_changed = false;
+
+  calculate_dominance_info (CDI_DOMINATORS);
+
+  FOR_EACH_BB_FN (bb, fun)
+    {
+      gimple_stmt_iterator gsi;
+      bool cleanup_eh = false;
+
+      for (gsi = gsi_after_labels (bb); !gsi_end_p (gsi); gsi_next (&gsi))
+        {
+         gimple *stmt = gsi_stmt (gsi);
+
+         /* Only the last stmt in a bb could throw, no need to call
+            gimple_purge_dead_eh_edges if we change something in the middle
+            of a basic block.  */
+         cleanup_eh = false;
+
+         if (is_gimple_call (stmt)
+             && gimple_call_lhs (stmt))
+           {
+             tree arg0, arg1, result;
+             HOST_WIDE_INT n;
+             location_t loc;
+
+             switch (gimple_call_combined_fn (stmt))
+               {
                CASE_CFN_POW:
                  arg0 = gimple_call_arg (stmt, 0);
                  arg1 = gimple_call_arg (stmt, 1);
@@ -2405,20 +2480,15 @@ pass_cse_sincos::execute (function *fun)
        cfg_changed |= gimple_purge_dead_eh_edges (bb);
     }
 
-  statistics_counter_event (fun, "sincos statements inserted",
-                           sincos_stats.inserted);
-  statistics_counter_event (fun, "conv statements removed",
-                           sincos_stats.conv_removed);
-
   return cfg_changed ? TODO_cleanup_cfg : 0;
 }
 
 } // anon namespace
 
 gimple_opt_pass *
-make_pass_cse_sincos (gcc::context *ctxt)
+make_pass_expand_powcabs (gcc::context *ctxt)
 {
-  return new pass_cse_sincos (ctxt);
+  return new pass_expand_powcabs (ctxt);
 }
 
 /* Return true if stmt is a type conversion operation that can be stripped