diff mbox

PATCH: Emit vzerouppers after reload

Message ID 20101102220602.GA9756@intel.com
State New
Headers show

Commit Message

H.J. Lu Nov. 2, 2010, 10:06 p.m. UTC 
On Tue, Nov 02, 2010 at 02:35:17PM -0700, H.J. Lu wrote:
> On Tue, Nov 02, 2010 at 11:06:06AM -0700, H.J. Lu wrote:
> > Hi,
> > 
> > This patch changes vzeroupper optimization to emit vzerouppers after
> > reload.  I checked in it as approved by Uros offline.
> > 
> > Thanks.
> > 
> > 
> > H.J.
> > ---
> > gcc/
> > 
> > 2010-11-02  Uros Bizjak  <ubizjak@gmail.com>
> > 	    H.J. Lu  <hongjiu.lu@intel.com>
> > 
> > 	* config/i386/i386-protos.h (ix86_split_call_vzeroupper): New.
> > 	(ix86_split_call_pop_vzeroupper): Likewise.
> > 
> > 	* config/i386/i386.c (move_or_delete_vzeroupper_2): Rewrite
> > 	the loop.
> > 	(ix86_expand_call): Use UNSPEC_CALL_NEEDS_VZEROUPPER.
> > 	(ix86_split_call_vzeroupper): New.
> > 	(ix86_split_call_pop_vzeroupper): Likewise.
> > 
> > 	* config/i386/i386.md (UNSPEC_CALL_NEEDS_VZEROUPPER): New.
> > 	(*call_pop_0_vzeroupper): Likewise.
> > 	(*call_pop_1_vzeroupper): Likewise.
> > 	(*sibcall_pop_1_vzeroupper): Likewise.
> > 	(*call_0_vzeroupper): Likewise.
> > 	(*call_1_vzeroupper): Likewise.
> > 	(*sibcall_1_vzeroupper): Likewise.
> > 	(*call_1_rex64_vzeroupper): Likewise.
> > 	(*call_1_rex64_ms_sysv_vzeroupper): New.
> > 	(*call_1_rex64_large_vzeroupper): Likewise.
> > 	(*sibcall_1_rex64_vzeroupper): Likewise.
> > 	(*call_value_pop_0_vzeroupper): New.
> > 	(*call_value_pop_1_vzeroupper): Likewise.
> > 	(*sibcall_value_pop_1_vzeroupper): Likewise.
> > 	(*call_value_0_vzeroupper): New.
> > 	(*call_value_0_rex64_vzeroupper): Use
> > 	(*call_value_0_rex64_ms_sysv_vzeroupper): Likewise.
> > 	(*call_value_1_vzeroupper): Likewise.
> > 	(*sibcall_value_1_vzeroupper): Likewise.
> > 	(*call_value_1_rex64_vzeroupper): Likewise.
> > 	(*call_value_1_rex64_ms_sysv_vzeroupper): Likewise.
> > 	(*call_value_1_rex64_large_vzeroupper): Likewise.
> > 	(*sibcall_value_1_rex64_vzeroupper): Likewise.
> > 
> 
> I checkec in this patch as an obvious fix to correct a typo.
> 
> 

ix86_split_call_pop_vzeroupper isn't needed. call pop vzeroupper
patterns should use parallel and just call ix86_split_call_vzeroupper.
Checked in as an obvious fix.


H.J.
---
diff mbox

Patch

Index: ChangeLog
===================================================================
--- ChangeLog	(revision 166215)
+++ ChangeLog	(working copy)
@@ -1,5 +1,20 @@ 
 2010-11-02  H.J. Lu  <hongjiu.lu@intel.com>
 
+	* config/i386/i386-protos.h (ix86_split_call_pop_vzeroupper):
+	Removed.
+	* config/i386/i386.c (ix86_split_call_pop_vzeroupper): Likewise.
+
+	* config/i386/i386.md (*call_pop_0_vzeroupper): Use parallel
+	and call ix86_split_call_vzeroupper instead of
+	ix86_split_call_pop_vzeroupper.
+	(*call_pop_1_vzeroupper): Likewise.
+	(*sibcall_pop_1_vzeroupper): Likewise.
+	(*call_value_pop_0_vzeroupper): Likewise.
+	(*call_value_pop_1_vzeroupper): Likewise.
+	(*sibcall_value_pop_1_vzeroupper): Likewise.
+
+2010-11-02  H.J. Lu  <hongjiu.lu@intel.com>
+
 	* config/i386/i386.md (*sibcall_1_rex64_vzeroupper): Fix a
 	typo.
 
Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md	(revision 166215)
+++ config/i386/i386.md	(working copy)
@@ -11262,18 +11262,19 @@ 
 })
 
 (define_insn_and_split "*call_pop_0_vzeroupper"
-  [(call (mem:QI (match_operand:SI 0 "constant_call_address_operand" ""))
-	 (match_operand:SI 1 "" ""))
-   (set (reg:SI SP_REG)
-	(plus:SI (reg:SI SP_REG)
-		 (match_operand:SI 2 "immediate_operand" "")))
+  [(parallel
+    [(call (mem:QI (match_operand:SI 0 "constant_call_address_operand" ""))
+	   (match_operand:SI 1 "" ""))
+     (set (reg:SI SP_REG)
+	  (plus:SI (reg:SI SP_REG)
+		   (match_operand:SI 2 "immediate_operand" "")))])
    (unspec [(match_operand 3 "const_int_operand" "")]
    	   UNSPEC_CALL_NEEDS_VZEROUPPER)]
   "TARGET_VZEROUPPER && !TARGET_64BIT"
   "#"
   "&& reload_completed"
   [(const_int 0)]
-  "ix86_split_call_pop_vzeroupper (curr_insn, operands[3]); DONE;"
+  "ix86_split_call_vzeroupper (curr_insn, operands[3]); DONE;"
   [(set_attr "type" "call")])
 
 (define_insn "*call_pop_0"
@@ -11292,18 +11293,19 @@ 
   [(set_attr "type" "call")])
 
 (define_insn_and_split "*call_pop_1_vzeroupper"
-  [(call (mem:QI (match_operand:SI 0 "call_insn_operand" "lsm"))
-	 (match_operand:SI 1 "" ""))
-   (set (reg:SI SP_REG)
-	(plus:SI (reg:SI SP_REG)
-		 (match_operand:SI 2 "immediate_operand" "i")))
+  [(parallel
+    [(call (mem:QI (match_operand:SI 0 "call_insn_operand" "lsm"))
+	   (match_operand:SI 1 "" ""))
+     (set (reg:SI SP_REG)
+	  (plus:SI (reg:SI SP_REG)
+		   (match_operand:SI 2 "immediate_operand" "i")))])
    (unspec [(match_operand 3 "const_int_operand" "")]
    	   UNSPEC_CALL_NEEDS_VZEROUPPER)]
   "TARGET_VZEROUPPER && !TARGET_64BIT && !SIBLING_CALL_P (insn)"
   "#"
   "&& reload_completed"
   [(const_int 0)]
-  "ix86_split_call_pop_vzeroupper (curr_insn, operands[3]); DONE;"
+  "ix86_split_call_vzeroupper (curr_insn, operands[3]); DONE;"
   [(set_attr "type" "call")])
 
 (define_insn "*call_pop_1"
@@ -11321,18 +11323,19 @@ 
   [(set_attr "type" "call")])
 
 (define_insn_and_split "*sibcall_pop_1_vzeroupper"
-  [(call (mem:QI (match_operand:SI 0 "sibcall_insn_operand" "s,U"))
-	 (match_operand:SI 1 "" ""))
-   (set (reg:SI SP_REG)
-	(plus:SI (reg:SI SP_REG)
-		 (match_operand:SI 2 "immediate_operand" "i,i")))
+ [(parallel
+   [(call (mem:QI (match_operand:SI 0 "sibcall_insn_operand" "s,U"))
+	   (match_operand:SI 1 "" ""))
+     (set (reg:SI SP_REG)
+	  (plus:SI (reg:SI SP_REG)
+		   (match_operand:SI 2 "immediate_operand" "i,i")))])
    (unspec [(match_operand 3 "const_int_operand" "")]
    	   UNSPEC_CALL_NEEDS_VZEROUPPER)]
   "TARGET_VZEROUPPER && !TARGET_64BIT && SIBLING_CALL_P (insn)"
   "#"
   "&& reload_completed"
   [(const_int 0)]
-  "ix86_split_call_pop_vzeroupper (curr_insn, operands[3]); DONE;"
+  "ix86_split_call_vzeroupper (curr_insn, operands[3]); DONE;"
   [(set_attr "type" "call")])
 
 (define_insn "*sibcall_pop_1"
@@ -17269,19 +17272,20 @@ 
 ;; disrupt insn-recog's switch tables.
 
 (define_insn_and_split "*call_value_pop_0_vzeroupper"
-  [(set (match_operand 0 "" "")
-	(call (mem:QI (match_operand:SI 1 "constant_call_address_operand" ""))
-	      (match_operand:SI 2 "" "")))
-   (set (reg:SI SP_REG)
-	(plus:SI (reg:SI SP_REG)
-		 (match_operand:SI 3 "immediate_operand" "")))
+  [(parallel
+    [(set (match_operand 0 "" "")
+	  (call (mem:QI (match_operand:SI 1 "constant_call_address_operand" ""))
+		(match_operand:SI 2 "" "")))
+     (set (reg:SI SP_REG)
+	  (plus:SI (reg:SI SP_REG)
+		   (match_operand:SI 3 "immediate_operand" "")))])
    (unspec [(match_operand 4 "const_int_operand" "")]
    	   UNSPEC_CALL_NEEDS_VZEROUPPER)]
   "TARGET_VZEROUPPER && !TARGET_64BIT"
   "#"
   "&& reload_completed"
   [(const_int 0)]
-  "ix86_split_call_pop_vzeroupper (curr_insn, operands[4]); DONE;"
+  "ix86_split_call_vzeroupper (curr_insn, operands[4]); DONE;"
   [(set_attr "type" "callv")])
 
 (define_insn "*call_value_pop_0"
@@ -17296,19 +17300,20 @@ 
   [(set_attr "type" "callv")])
 
 (define_insn_and_split "*call_value_pop_1_vzeroupper"
-  [(set (match_operand 0 "" "")
-	(call (mem:QI (match_operand:SI 1 "call_insn_operand" "lsm"))
-	      (match_operand:SI 2 "" "")))
-   (set (reg:SI SP_REG)
-	(plus:SI (reg:SI SP_REG)
-		 (match_operand:SI 3 "immediate_operand" "i")))
+  [(parallel
+    [(set (match_operand 0 "" "")
+	  (call (mem:QI (match_operand:SI 1 "call_insn_operand" "lsm"))
+		(match_operand:SI 2 "" "")))
+     (set (reg:SI SP_REG)
+	  (plus:SI (reg:SI SP_REG)
+		   (match_operand:SI 3 "immediate_operand" "i")))])
    (unspec [(match_operand 4 "const_int_operand" "")]
    	   UNSPEC_CALL_NEEDS_VZEROUPPER)]
   "TARGET_VZEROUPPER && !TARGET_64BIT && !SIBLING_CALL_P (insn)"
   "#"
   "&& reload_completed"
   [(const_int 0)]
-  "ix86_split_call_pop_vzeroupper (curr_insn, operands[4]); DONE;"
+  "ix86_split_call_vzeroupper (curr_insn, operands[4]); DONE;"
   [(set_attr "type" "callv")])
 
 (define_insn "*call_value_pop_1"
@@ -17323,19 +17328,20 @@ 
   [(set_attr "type" "callv")])
 
 (define_insn_and_split "*sibcall_value_pop_1_vzeroupper"
-  [(set (match_operand 0 "" "")
-	(call (mem:QI (match_operand:SI 1 "sibcall_insn_operand" "s,U"))
-	      (match_operand:SI 2 "" "")))
-   (set (reg:SI SP_REG)
-	(plus:SI (reg:SI SP_REG)
-		 (match_operand:SI 3 "immediate_operand" "i,i")))
+ [(parallel
+   [(set (match_operand 0 "" "")
+	  (call (mem:QI (match_operand:SI 1 "sibcall_insn_operand" "s,U"))
+		(match_operand:SI 2 "" "")))
+     (set (reg:SI SP_REG)
+	  (plus:SI (reg:SI SP_REG)
+		   (match_operand:SI 3 "immediate_operand" "i,i")))])
    (unspec [(match_operand 4 "const_int_operand" "")]
    	   UNSPEC_CALL_NEEDS_VZEROUPPER)]
   "TARGET_VZEROUPPER && !TARGET_64BIT && SIBLING_CALL_P (insn)"
   "#"
   "&& reload_completed"
   [(const_int 0)]
-  "ix86_split_call_pop_vzeroupper (curr_insn, operands[4]); DONE;"
+  "ix86_split_call_vzeroupper (curr_insn, operands[4]); DONE;"
   [(set_attr "type" "callv")])
 
 (define_insn "*sibcall_value_pop_1"
Index: config/i386/i386-protos.h
===================================================================
--- config/i386/i386-protos.h	(revision 166214)
+++ config/i386/i386-protos.h	(working copy)
@@ -120,7 +120,6 @@  extern void ix86_expand_sse4_unpack (rtx
 extern bool ix86_expand_int_addcc (rtx[]);
 extern rtx ix86_expand_call (rtx, rtx, rtx, rtx, rtx, int);
 extern void ix86_split_call_vzeroupper (rtx, rtx);
-extern void ix86_split_call_pop_vzeroupper (rtx, rtx);
 extern void x86_initialize_trampoline (rtx, rtx, rtx);
 extern rtx ix86_zero_extend_to_Pmode (rtx);
 extern void ix86_split_long_move (rtx[]);
Index: config/i386/i386.c
===================================================================
--- config/i386/i386.c	(revision 166214)
+++ config/i386/i386.c	(working copy)
@@ -21561,16 +21561,6 @@  ix86_split_call_vzeroupper (rtx insn, rt
   emit_call_insn (call);
 }
 
-void
-ix86_split_call_pop_vzeroupper (rtx insn, rtx vzeroupper)
-{
-  rtx call = XVECEXP (PATTERN (insn), 0, 0);
-  rtx pop = XVECEXP (PATTERN (insn), 0, 1);
-  emit_insn (gen_avx_vzeroupper (vzeroupper));
-  emit_call_insn (gen_rtx_PARALLEL (VOIDmode,
-				    gen_rtvec (2, call, pop)));
-}
-
 /* Output the assembly for a call instruction.  */
 
 const char *