* config/i386/i386.md (movmsk_df): New insn.

	(signbitdf): Split out of signbit<mode>2.  Generate movmsk_df
	sequence for TARGET_SSE_MATH.



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@164630 138bc75d-0d04-0410-961f-82ee72b054a4

2 files changed, 67 insertions, 16 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 9678b50258c..9433f5a17cc 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2010-09-26  Uros Bizjak  <ubizjak@gmail.com>
+
+	* config/i386/i386.md (movmsk_df): New insn.
+	(signbitdf): Split out of signbit<mode>2.  Generate movmsk_df
+	sequence for TARGET_SSE_MATH.
+
 2010-09-26  Richard Sandiford  <rdsandiford@googlemail.com>
 
 	* config/mips/mips.c (mips_builtin_decls): Declare.
@@ -82,8 +88,7 @@
 	const_value_known.
 	(cgraph_externally_visible_p): Use cgraph_used_from_object_file_p.
 	(function_and_variable_visibility): Set resolution for local vars
-	and functions.
-	use varpool_used_from_object_file_p.
+	and functions; use varpool_used_from_object_file_p.
 	* varasm.c (resolution_to_local_definition_p, resolution_local_p): New
 	static functions.
 	(default_binds_local_p_1): Use resolutoin info.
@@ -121,16 +126,17 @@
 	* tree.c (local_define_builtin): Handle ECF_LEAF.
 	(build_common_builtin_nodes): Set ECF_LEAF where needed.
 	* tree.h (ECF_LEAF): New.
-	* ipa-reference.c (propagate_bits): For leaf calls propagate ever overwrittable
-	and unavailable functions.
+	* ipa-reference.c (propagate_bits): For leaf calls propagate ever
+	overwrittable and unavailable functions.
 	(ipa_init): Put all_module_statics into optimization_summary_obstack.
 	(copy_global_bitmap): Do not copy all_module_statics.
 	(read_write_all_from_decl): Use cgraph_node argument; handle ECF_LEAF.
 	(propagate): Handle overwritable and unavailable leaf functions;
 	initialize global info for overwritable and unavailable leaf functions;
 	do not free all module statics.
-	(ipa_reference_get_not_read_global, ipa_reference_get_not_written_global):
-	leaf calls don't clobber local statics.
+	(ipa_reference_get_not_read_global,
+	ipa_reference_get_not_written_global): leaf calls don't clobber
+	local statics.
 	* calls.c (flags_from_decl_or_type): Handle leaf.
 	* tree-cfg.c (stmt_can_make_abnormal_goto): Leaf functions can't do
 	abnormal gotos.
@@ -138,9 +144,7 @@
 2010-09-24  Basile Starynkevitch  <basile@starynkevitch.net>
 
 	* gengtype.c: Reindented.
-
 	* gengtype.h: Reindented.
-
 	* gengtype-parse.c: Reindented.
 
 2010-09-24  Jan Hubicka  <jh@suse.cz>
@@ -203,11 +207,11 @@
 
 2010-09-24  Iain Sandoe  <iains@gcc.gnu.org>
 	    Dominique Dhumieres  <dominiq@lps.ens.fr>
-	    
+
 	PR bootstrap/45751
 	* gcc/config/darwin-driver.c (darwin_default_min_version):
 	Adjust size passed to memcpy in two places.
-	
+
 2010-09-24  Richard Guenther  <rguenther@suse.de>
 
 	* c-decl.c (pop_scope): Always set file-scope DECL_CONTEXT.
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index fddacd53791..0d76acb0ad5 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -14980,18 +14980,65 @@
   DONE;
 })
 
-(define_expand "signbit<mode>2"
+(define_expand "signbitxf2"
   [(use (match_operand:SI 0 "register_operand" ""))
-   (use (match_operand:X87MODEF 1 "register_operand" ""))]
+   (use (match_operand:XF 1 "register_operand" ""))]
+  "TARGET_USE_FANCY_MATH_387"
+{
+  rtx scratch = gen_reg_rtx (HImode);
+
+  emit_insn (gen_fxamxf2_i387 (scratch, operands[1]));
+  emit_insn (gen_andsi3 (operands[0],
+	     gen_lowpart (SImode, scratch), GEN_INT (0x200)));
+  DONE;
+})
+
+(define_insn "movmsk_df"
+  [(set (match_operand:SI 0 "register_operand" "=r")
+	(unspec:SI
+	  [(match_operand:DF 1 "register_operand" "x")]
+	  UNSPEC_MOVMSK))]
+  "SSE_FLOAT_MODE_P (DFmode) && TARGET_SSE_MATH"
+  "%vmovmskpd\t{%1, %0|%0, %1}"
+  [(set_attr "type" "ssemov")
+   (set_attr "prefix" "maybe_vex")
+   (set_attr "mode" "DF")])
+
+;; Use movmskpd in SSE mode to avoid store forwarding stall
+;; for 32bit targets and movq+shrq sequence for 64bit targets.
+(define_expand "signbitdf2"
+  [(use (match_operand:SI 0 "register_operand" ""))
+   (use (match_operand:DF 1 "register_operand" ""))]
   "TARGET_USE_FANCY_MATH_387
-   && !(SSE_FLOAT_MODE_P (<MODE>mode) && TARGET_SSE_MATH)"
+   || (SSE_FLOAT_MODE_P (DFmode) && TARGET_SSE_MATH)"
 {
-  rtx mask = GEN_INT (0x0200);
+  if (SSE_FLOAT_MODE_P (DFmode) && TARGET_SSE_MATH)
+    {
+      emit_insn (gen_movmsk_df (operands[0], operands[1]));
+      emit_insn (gen_andsi3 (operands[0], operands[0], const1_rtx));
+    }
+  else
+    {
+      rtx scratch = gen_reg_rtx (HImode);
 
+      emit_insn (gen_fxamdf2_i387 (scratch, operands[1]));
+      emit_insn (gen_andsi3 (operands[0],
+		 gen_lowpart (SImode, scratch), GEN_INT (0x200)));
+    }
+  DONE;
+})
+
+(define_expand "signbitsf2"
+  [(use (match_operand:SI 0 "register_operand" ""))
+   (use (match_operand:SF 1 "register_operand" ""))]
+  "TARGET_USE_FANCY_MATH_387
+   && !(SSE_FLOAT_MODE_P (SFmode) && TARGET_SSE_MATH)"
+{
   rtx scratch = gen_reg_rtx (HImode);
 
-  emit_insn (gen_fxam<mode>2_i387 (scratch, operands[1]));
-  emit_insn (gen_andsi3 (operands[0], gen_lowpart (SImode, scratch), mask));
+  emit_insn (gen_fxamsf2_i387 (scratch, operands[1]));
+  emit_insn (gen_andsi3 (operands[0],
+	     gen_lowpart (SImode, scratch), GEN_INT (0x200)));
   DONE;
 })