i386-protos.h (ix86_setup_incoming_varargs, [...]): Declare.

	* i386-protos.h (ix86_setup_incoming_varargs, ix86_va_arg,
	ix86_va_start, ix86_build_va_list): Declare.
	* i386.c (ix86_setup_incoming_varargs, ix86_va_arg,
	ix86_va_start, ix86_build_va_list): New global functions.
	* i386.md (sse_prologue_save_insn): New insn.
	(sse_prologue_save): New expander.
	* i386.h (EXPAND_BUILTIN_VA_ARG, EXPAND_BUILTIN_VA_START,
	BUILD_VA_LIST_TYPE, SETUP_INCOMING_VARARGS): New macros.

From-SVN: r45862

gcc/ChangeLog

+Fri Sep 28 19:18:40 CEST 2001  Jan Hubicka  <jh@suse.cz>
+
+	* i386-protos.h (ix86_setup_incoming_varargs, ix86_va_arg,
+	ix86_va_start, ix86_build_va_list): Declare.
+	* i386.c (ix86_setup_incoming_varargs, ix86_va_arg,
+	ix86_va_start, ix86_build_va_list): New global functions.
+	* i386.md (sse_prologue_save_insn): New insn.
+	(sse_prologue_save): New expander.
+	* i386.h (EXPAND_BUILTIN_VA_ARG, EXPAND_BUILTIN_VA_START,
+	BUILD_VA_LIST_TYPE, SETUP_INCOMING_VARARGS): New macros.
+
 2001-09-28  Neil Booth  <neil@daikokuya.demon.co.uk>
 
 	* cpplex.c (new_buff, _cpp_get_buff, _cpp_extend_buff):

gcc/config/i386/i386-protos.h

@@ -140,6 +140,11 @@ extern bool ix86_function_value_regno_p PARAMS ((int));
 extern bool ix86_function_arg_regno_p PARAMS ((int));
 extern int ix86_function_arg_boundary PARAMS ((enum machine_mode, tree));
 extern int ix86_return_in_memory PARAMS ((tree));
+extern void ix86_va_start PARAMS ((int, tree, rtx));
+extern rtx ix86_va_arg PARAMS ((tree, tree));
+extern void ix86_setup_incoming_varargs PARAMS ((CUMULATIVE_ARGS *,
+						 enum machine_mode,
+						 tree, int *, int));
 
 extern rtx ix86_force_to_memory PARAMS ((enum machine_mode, rtx));
 extern void ix86_free_from_memory PARAMS ((enum machine_mode));
@@ -175,6 +180,7 @@ extern rtx ix86_expand_builtin PARAMS ((tree, rtx, rtx, enum machine_mode, int))
 
 #ifdef TREE_CODE
 extern int ix86_return_pops_args PARAMS ((tree, tree, int));
+extern tree ix86_build_va_list PARAMS ((void));
 
 extern int ix86_data_alignment PARAMS ((tree, int));
 extern int ix86_local_alignment PARAMS ((tree, int));

gcc/config/i386/i386.h

@@ -1604,6 +1604,35 @@ typedef struct ix86_args {
        || ! FLOAT_MODE_P (TYPE_MODE (TREE_TYPE (TREE_TYPE (DECL)))) \
        || FLOAT_MODE_P (TYPE_MODE (TREE_TYPE (TREE_TYPE (cfun->decl))))))
 
+/* Perform any needed actions needed for a function that is receiving a
+   variable number of arguments.
+
+   CUM is as above.
+
+   MODE and TYPE are the mode and type of the current parameter.
+
+   PRETEND_SIZE is a variable that should be set to the amount of stack
+   that must be pushed by the prolog to pretend that our caller pushed
+   it.
+
+   Normally, this macro will push all remaining incoming registers on the
+   stack and set PRETEND_SIZE to the length of the registers pushed.  */
+
+#define SETUP_INCOMING_VARARGS(CUM,MODE,TYPE,PRETEND_SIZE,NO_RTL) \
+  ix86_setup_incoming_varargs (&CUM, MODE, TYPE, &PRETEND_SIZE, NO_RTL)
+
+/* Define the `__builtin_va_list' type for the ABI.  */
+#define BUILD_VA_LIST_TYPE(VALIST) \
+  (VALIST) = ix86_build_va_list ()
+
+/* Implement `va_start' for varargs and stdarg.  */
+#define EXPAND_BUILTIN_VA_START(stdarg, valist, nextarg) \
+  ix86_va_start (stdarg, valist, nextarg)
+
+/* Implement `va_arg'.  */
+#define EXPAND_BUILTIN_VA_ARG(valist, type) \
+  ix86_va_arg (valist, type)
+
 /* This macro is invoked at the end of compilation.  It is used here to
    output code for -fpic that will load the return address into %ebx.  */
 
@@ -2775,6 +2804,7 @@ extern int const svr4_dbx_register_map[FIRST_PSEUDO_REGISTER];
 #define EH_RETURN_DATA_REGNO(N)	((N) < 2 ? (N) : INVALID_REGNUM)
 #define EH_RETURN_STACKADJ_RTX	gen_rtx_REG (Pmode, 2)
 
+
 /* Select a format to encode pointers in exception handling data.  CODE
    is 0 for data, 1 for code labels, 2 for function pointers.  GLOBAL is
    true if the symbol may be affected by dynamic relocations.

gcc/config/i386/i386.md

@@ -19066,3 +19066,63 @@
 }
   [(set_attr "type" "sse")])
 
+(define_expand "sse_prologue_save"
+  [(parallel [(set (match_operand:BLK 0 "" "")
+		   (unspec:BLK [(reg:DI 21)
+				(reg:DI 22)
+				(reg:DI 23)
+				(reg:DI 24)
+				(reg:DI 25)
+				(reg:DI 26)
+				(reg:DI 27)
+				(reg:DI 28)] 13))
+	      (use (match_operand:DI 1 "register_operand" ""))
+	      (use (match_operand:DI 2 "immediate_operand" ""))
+	      (use (label_ref:DI (match_operand 3 "" "")))])]
+  "TARGET_64BIT"
+  "")
+
+(define_insn "*sse_prologue_save_insn"
+  [(set (mem:BLK (plus:DI (match_operand:DI 0 "register_operand" "R")
+			  (match_operand:DI 4 "const_int_operand" "n")))
+	(unspec:BLK [(reg:DI 21)
+		     (reg:DI 22)
+		     (reg:DI 23)
+		     (reg:DI 24)
+		     (reg:DI 25)
+		     (reg:DI 26)
+		     (reg:DI 27)
+		     (reg:DI 28)] 13))
+   (use (match_operand:DI 1 "register_operand" "r"))
+   (use (match_operand:DI 2 "const_int_operand" "i"))
+   (use (label_ref:DI (match_operand 3 "" "X")))]
+  "TARGET_64BIT
+   && INTVAL (operands[4]) + SSE_REGPARM_MAX * 16 - 16 < 128
+   && INTVAL (operands[4]) + INTVAL (operands[2]) * 16 >= -128"
+  "*
+{
+  int i;
+  operands[0] = gen_rtx_MEM (Pmode,
+			     gen_rtx_PLUS (Pmode, operands[0], operands[4]));
+  output_asm_insn (\"jmp\\t%A1\", operands);
+  for (i = SSE_REGPARM_MAX - 1; i >= INTVAL (operands[2]); i--)
+    {
+      operands[4] = adjust_address (operands[0], DImode, i*16);
+      operands[5] = gen_rtx_REG (TImode, SSE_REGNO (i));
+      PUT_MODE (operands[4], TImode);
+      if (GET_CODE (XEXP (operands[0], 0)) != PLUS)
+        output_asm_insn (\"rex\", operands);
+      output_asm_insn (\"movaps\\t{%5, %4|%4, %5}\", operands);
+    }
+  ASM_OUTPUT_INTERNAL_LABEL (asm_out_file, \"L\",
+			     CODE_LABEL_NUMBER (operands[3]));
+  RET;
+}
+  "
+  [(set_attr "type" "other")
+   (set_attr "length_immediate" "0")
+   (set_attr "length_address" "0")
+   (set_attr "length" "135")
+   (set_attr "memory" "store")
+   (set_attr "modrm" "0")
+   (set_attr "mode" "DI")])

gcc/doc/invoke.texi

@@ -274,7 +274,7 @@ in the following sections.
 -fschedule-insns  -fschedule-insns2 @gol
 -fsingle-precision-constant  -fssa -fssa-ccp -fssa-dce @gol
 -fstrength-reduce  -fstrict-aliasing  -fthread-jumps  -ftrapv @gol
--funroll-all-loops  -funroll-loops  @gol
+-funroll-all-loops  -funroll-loops -fmessy-debugging @gol
 --param @var{name}=@var{value}
 -O  -O0  -O1  -O2  -O3  -Os}
 
@@ -3415,6 +3415,18 @@ Not all of the optimizations performed by GCC have @option{-f} options
 to control them.
 
 @table @gcctabopt
+@item -fmessy-debugging
+@opindex fmessy-debugging
+Some optimizations can be stronger if compiler give up ability to generate
+at least approximately usefull debug information for optimized programs.
+These transformation are not done when @option{-g} switch is not specified,
+as politics is to get the code with @option{-g} and without equivalent,
+except for debugging section.
+
+This optimization enables such transformations.  It is still compatible with
+@option{-g}, but debugging resulting programs will be even higher challenge.
+
+@table @gcctabopt
 @item -fstrength-reduce
 @opindex fstrength-reduce
 Perform the optimizations of loop strength reduction and