re PR target/47440 (Use LCM for vzeroupper insertion)

	PR target/47440
	* config/i386/i386.c (gate_insert_vzeroupper): New function.
	(rest_of_handle_insert_vzeroupper): Ditto.
	(struct rtl_opt_pass pass_insert_vzeroupper): New.
	(ix86_option_override): Register vzeroupper insertion pass here.
	(ix86_check_avx256_register): Handle SUBREGs properly.
	(ix86_init_machine_status): Remove optimize_mode_switching[AVX_U128]
	initialization.

From-SVN: r193503

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index ebebb1d56ea4c5144ca378d1c7e1fb2161de3a58..9d31d63164e345c96d977ad671ae1e93ac751a80 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,15 @@
+2012-11-14  Uros Bizjak  <ubizjak@gmail.com>
+           Vladimir Yakovlev  <vladimir.b.yakovlev@intel.com>
+
+       PR target/47440
+       * config/i386/i386.c (gate_insert_vzeroupper): New function.
+       (rest_of_handle_insert_vzeroupper): Ditto.
+       (struct rtl_opt_pass pass_insert_vzeroupper): New.
+       (ix86_option_override): Register vzeroupper insertion pass here.
+       (ix86_check_avx256_register): Handle SUBREGs properly.
+       (ix86_init_machine_status): Remove optimize_mode_switching[AVX_U128]
+       initialization.
+
 2012-11-14  David Edelsohn  <dje.gcc@gmail.com>
 
        * configure.ac (HAVE_LD_LARGE_TOC): Add AIX test.
@@ -34,8 +46,8 @@
 
        * cgraph.c (insert_new_cgraph_node_version): Use cgraph_get_node
        instead of cgraph_get_create_node.
-       * config/i386/i386.c (ix86_get_function_versions_dispatcher): Move ifunc
-       not supported code to the end.
+       * config/i386/i386.c (ix86_get_function_versions_dispatcher): Move
+       ifunc not supported code to the end.
 
 2012-11-13  Martin Jambor  <mjambor@suse.cz>
 

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index eee2b93771d05fcca517d4b5a3402a22002ecc03..c295849506f23cdca86aa132386191229eff5a4d 100644 (file)
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -2301,6 +2301,52 @@ static const char *const cpu_names[TARGET_CPU_DEFAULT_max] =
   "btver2"
 };
 \f
+static bool
+gate_insert_vzeroupper (void)
+{
+  return TARGET_VZEROUPPER;
+}
+
+static unsigned int
+rest_of_handle_insert_vzeroupper (void)
+{
+  int i;
+
+  /* vzeroupper instructions are inserted immediately after reload to
+     account for possible spills from 256bit registers.  The pass
+     reuses mode switching infrastructure by re-running mode insertion
+     pass, so disable entities that have already been processed.  */
+  for (i = 0; i < MAX_386_ENTITIES; i++)
+    ix86_optimize_mode_switching[i] = 0;
+
+  ix86_optimize_mode_switching[AVX_U128] = 1;
+
+  /* Call optimize_mode_switching.  */
+  pass_mode_switching.pass.execute ();
+  return 0;
+}
+
+struct rtl_opt_pass pass_insert_vzeroupper =
+{
+ {
+  RTL_PASS,
+  "vzeroupper",                                /* name */
+  OPTGROUP_NONE,                       /* optinfo_flags */
+  gate_insert_vzeroupper,              /* gate */
+  rest_of_handle_insert_vzeroupper,    /* execute */
+  NULL,                                        /* sub */
+  NULL,                                        /* next */
+  0,                                   /* static_pass_number */
+  TV_NONE,                             /* tv_id */
+  0,                                   /* properties_required */
+  0,                                   /* properties_provided */
+  0,                                   /* properties_destroyed */
+  0,                                   /* todo_flags_start */
+  TODO_df_finish | TODO_verify_rtl_sharing |
+  0,                                   /* todo_flags_finish */
+ }
+};
+
 /* Return true if a red-zone is in use.  */
 
 static inline bool
@@ -3705,7 +3751,16 @@ ix86_option_override_internal (bool main_args_p)
 static void
 ix86_option_override (void)
 {
+  static struct register_pass_info insert_vzeroupper_info
+    = { &pass_insert_vzeroupper.pass, "reload",
+       1, PASS_POS_INSERT_AFTER
+      };
+
   ix86_option_override_internal (true);
+
+
+  /* This needs to be done at start up.  It's convenient to do it here.  */
+  register_pass (&insert_vzeroupper_info);
 }
 
 /* Update register usage after having seen the compiler flags.  */
@@ -14988,10 +15043,15 @@ output_387_binary_op (rtx insn, rtx *operands)
 /* Check if a 256bit AVX register is referenced inside of EXP.   */
 
 static int
-ix86_check_avx256_register (rtx *exp, void *data ATTRIBUTE_UNUSED)
+ix86_check_avx256_register (rtx *pexp, void *data ATTRIBUTE_UNUSED)
 {
-  if (REG_P (*exp)
-      && VALID_AVX256_REG_OR_OI_MODE (GET_MODE (*exp)))
+  rtx exp = *pexp;
+
+  if (GET_CODE (exp) == SUBREG)
+    exp = SUBREG_REG (exp);
+
+  if (REG_P (exp)
+      && VALID_AVX256_REG_OR_OI_MODE (GET_MODE (exp)))
     return 1;
 
   return 0;
@@ -23449,7 +23509,6 @@ ix86_init_machine_status (void)
   f = ggc_alloc_cleared_machine_function ();
   f->use_fast_prologue_epilogue_nregs = -1;
   f->call_abi = ix86_abi;
-  f->optimize_mode_switching[AVX_U128] = TARGET_VZEROUPPER;
 
   return f;
 }