builtins.c: (expand_builtin_memcmp, expand_builtin_strncmp): s/cmpstrsi/cmpstrnsi

2005-07-12  Adrian Straetling  <straetling@de.ibm.com>

	* builtins.c: (expand_builtin_memcmp, expand_builtin_strncmp):
	s/cmpstrsi/cmpstrnsi
	(expand_builtin_strcmp): Rewrite to support both 'cmpstrsi' and
	'cmpstrnsi'.
	* optabs.c: (prepare_cmp_insn): Add availability of 'cmpstrn'.
	(init_optabs): Initialize cmpstrn_optab.
	* optabs.h: (enum insn_code cmpstrn_optab): Declare.
	* genopinit.c: (optabs[]): Add 'cmpstrn' to initialisation.
	* expr.c: (enum insn_code cmpstrn_optab): Declare.
	* config/i386/i386.md: s/cmpstr/cmpstrn
	* config/c4x/c4x.md: s/cmpstr/cmpstrn
	* doc/md.texi: Update documentation.

From-SVN: r101916

gcc/ChangeLog

+2005-07-12  Adrian Straetling  <straetling@de.ibm.com>
+
+	* builtins.c: (expand_builtin_memcmp, expand_builtin_strncmp):
+	s/cmpstrsi/cmpstrnsi
+	(expand_builtin_strcmp): Rewrite to support both 'cmpstrsi' and
+	'cmpstrnsi'.
+	* optabs.c: (prepare_cmp_insn): Add availability of 'cmpstrn'.
+	(init_optabs): Initialize cmpstrn_optab.
+	* optabs.h: (enum insn_code cmpstrn_optab): Declare.
+	* genopinit.c: (optabs[]): Add 'cmpstrn' to initialisation.
+	* expr.c: (enum insn_code cmpstrn_optab): Declare.
+	* config/i386/i386.md: s/cmpstr/cmpstrn
+	* config/c4x/c4x.md: s/cmpstr/cmpstrn
+	* doc/md.texi: Update documentation.
+
 2005-07-11  Richard Henderson  <rth@redhat.com>
 
 	* config/alpha/alpha.c (alpha_gimplify_va_arg_1): Use

gcc/builtins.c

@@ -3449,7 +3449,7 @@ expand_builtin_memcmp (tree exp ATTRIBUTE_UNUSED, tree arglist, rtx target,
 	return expand_expr (result, target, mode, EXPAND_NORMAL);
     }
 
-#if defined HAVE_cmpmemsi || defined HAVE_cmpstrsi
+#if defined HAVE_cmpmemsi || defined HAVE_cmpstrnsi
   {
     tree arg1 = TREE_VALUE (arglist);
     tree arg2 = TREE_VALUE (TREE_CHAIN (arglist));
@@ -3469,9 +3469,9 @@ expand_builtin_memcmp (tree exp ATTRIBUTE_UNUSED, tree arglist, rtx target,
       insn_mode = insn_data[(int) CODE_FOR_cmpmemsi].operand[0].mode;
     else
 #endif
-#ifdef HAVE_cmpstrsi
-    if (HAVE_cmpstrsi)
-      insn_mode = insn_data[(int) CODE_FOR_cmpstrsi].operand[0].mode;
+#ifdef HAVE_cmpstrnsi
+    if (HAVE_cmpstrnsi)
+      insn_mode = insn_data[(int) CODE_FOR_cmpstrnsi].operand[0].mode;
     else
 #endif
       return 0;
@@ -3504,9 +3504,9 @@ expand_builtin_memcmp (tree exp ATTRIBUTE_UNUSED, tree arglist, rtx target,
 			   GEN_INT (MIN (arg1_align, arg2_align)));
     else
 #endif
-#ifdef HAVE_cmpstrsi
-    if (HAVE_cmpstrsi)
-      insn = gen_cmpstrsi (result, arg1_rtx, arg2_rtx, arg3_rtx,
+#ifdef HAVE_cmpstrnsi
+    if (HAVE_cmpstrnsi)
+      insn = gen_cmpstrnsi (result, arg1_rtx, arg2_rtx, arg3_rtx,
 			    GEN_INT (MIN (arg1_align, arg2_align)));
     else
 #endif
@@ -3558,25 +3558,61 @@ expand_builtin_strcmp (tree exp, rtx target, enum machine_mode mode)
 	return expand_expr (result, target, mode, EXPAND_NORMAL);
     }
 
-#ifdef HAVE_cmpstrsi
-  if (HAVE_cmpstrsi)
+#if defined HAVE_cmpstrsi || defined HAVE_cmpstrnsi
+  if (cmpstr_optab[SImode] != CODE_FOR_nothing
+      || cmpstrn_optab[SImode] != CODE_FOR_nothing)
     {
-    tree arg1 = TREE_VALUE (arglist);
-    tree arg2 = TREE_VALUE (TREE_CHAIN (arglist));
-    tree len, len1, len2;
-    rtx arg1_rtx, arg2_rtx, arg3_rtx;
-    rtx result, insn;
+      rtx arg1_rtx, arg2_rtx;
+      rtx result, insn = NULL_RTX;
       tree fndecl, fn;
       
+      tree arg1 = TREE_VALUE (arglist);
+      tree arg2 = TREE_VALUE (TREE_CHAIN (arglist));
       int arg1_align
 	= get_pointer_alignment (arg1, BIGGEST_ALIGNMENT) / BITS_PER_UNIT;
       int arg2_align
 	= get_pointer_alignment (arg2, BIGGEST_ALIGNMENT) / BITS_PER_UNIT;
+
+      /* If we don't have POINTER_TYPE, call the function.  */
+      if (arg1_align == 0 || arg2_align == 0)
+	return 0;
+
+      /* Stabilize the arguments in case gen_cmpstr(n)si fail.  */
+      arg1 = builtin_save_expr (arg1);
+      arg2 = builtin_save_expr (arg2);
+
+      arg1_rtx = get_memory_rtx (arg1);
+      arg2_rtx = get_memory_rtx (arg2);
+
+#ifdef HAVE_cmpstrsi
+      /* Try to call cmpstrsi.  */
+      if (HAVE_cmpstrsi)
+	{
 	  enum machine_mode insn_mode 
 	    = insn_data[(int) CODE_FOR_cmpstrsi].operand[0].mode;
 
-    len1 = c_strlen (arg1, 1);
-    len2 = c_strlen (arg2, 1);
+	  /* Make a place to write the result of the instruction.  */
+	  result = target;
+	  if (! (result != 0
+		 && REG_P (result) && GET_MODE (result) == insn_mode
+		 && REGNO (result) >= FIRST_PSEUDO_REGISTER))
+	    result = gen_reg_rtx (insn_mode);
+
+	  insn = gen_cmpstrsi (result, arg1_rtx, arg2_rtx,
+			       GEN_INT (MIN (arg1_align, arg2_align)));
+	}
+#endif
+#if HAVE_cmpstrnsi 
+      /* Try to determine at least one length and call cmpstrnsi.  */
+      if (!insn && HAVE_cmpstrnsi) 
+	{
+	  tree len;
+	  rtx arg3_rtx;
+
+	  enum machine_mode insn_mode 
+	    = insn_data[(int) CODE_FOR_cmpstrnsi].operand[0].mode;
+	  tree len1 = c_strlen (arg1, 1);
+	  tree len2 = c_strlen (arg2, 1);
 
 	  if (len1)
 	    len1 = size_binop (PLUS_EXPR, ssize_int (1), len1);
@@ -3611,9 +3647,8 @@ expand_builtin_strcmp (tree exp, rtx target, enum machine_mode mode)
 	  if (!len || TREE_SIDE_EFFECTS (len))
 	    return 0;
 
-    /* If we don't have POINTER_TYPE, call the function.  */
-    if (arg1_align == 0 || arg2_align == 0)
-      return 0;
+	  /* Stabilize the arguments in case gen_cmpstrnsi fails.  */
+	  arg3_rtx = expand_expr (len, NULL_RTX, VOIDmode, 0);
 
 	  /* Make a place to write the result of the instruction.  */
 	  result = target;
@@ -3622,15 +3657,11 @@ expand_builtin_strcmp (tree exp, rtx target, enum machine_mode mode)
 		 && REGNO (result) >= FIRST_PSEUDO_REGISTER))
 	    result = gen_reg_rtx (insn_mode);
 
-    /* Stabilize the arguments in case gen_cmpstrsi fails.  */
-    arg1 = builtin_save_expr (arg1);
-    arg2 = builtin_save_expr (arg2);
-
-    arg1_rtx = get_memory_rtx (arg1);
-    arg2_rtx = get_memory_rtx (arg2);
-    arg3_rtx = expand_expr (len, NULL_RTX, VOIDmode, 0);
-    insn = gen_cmpstrsi (result, arg1_rtx, arg2_rtx, arg3_rtx,
+	  insn = gen_cmpstrnsi (result, arg1_rtx, arg2_rtx, arg3_rtx,
 				GEN_INT (MIN (arg1_align, arg2_align)));
+	}
+#endif
+
       if (insn)
 	{
 	  emit_insn (insn);
@@ -3679,10 +3710,10 @@ expand_builtin_strncmp (tree exp, rtx target, enum machine_mode mode)
     }
 
   /* If c_strlen can determine an expression for one of the string
-     lengths, and it doesn't have side effects, then emit cmpstrsi
+     lengths, and it doesn't have side effects, then emit cmpstrnsi
      using length MIN(strlen(string)+1, arg3).  */
-#ifdef HAVE_cmpstrsi
-  if (HAVE_cmpstrsi)
+#ifdef HAVE_cmpstrnsi
+  if (HAVE_cmpstrnsi)
   {
     tree arg1 = TREE_VALUE (arglist);
     tree arg2 = TREE_VALUE (TREE_CHAIN (arglist));
@@ -3697,7 +3728,7 @@ expand_builtin_strncmp (tree exp, rtx target, enum machine_mode mode)
     int arg2_align
       = get_pointer_alignment (arg2, BIGGEST_ALIGNMENT) / BITS_PER_UNIT;
     enum machine_mode insn_mode
-      = insn_data[(int) CODE_FOR_cmpstrsi].operand[0].mode;
+      = insn_data[(int) CODE_FOR_cmpstrnsi].operand[0].mode;
 
     len1 = c_strlen (arg1, 1);
     len2 = c_strlen (arg2, 1);
@@ -3750,7 +3781,7 @@ expand_builtin_strncmp (tree exp, rtx target, enum machine_mode mode)
 	   && REGNO (result) >= FIRST_PSEUDO_REGISTER))
       result = gen_reg_rtx (insn_mode);
 
-    /* Stabilize the arguments in case gen_cmpstrsi fails.  */
+    /* Stabilize the arguments in case gen_cmpstrnsi fails.  */
     arg1 = builtin_save_expr (arg1);
     arg2 = builtin_save_expr (arg2);
     len = builtin_save_expr (len);
@@ -3758,7 +3789,7 @@ expand_builtin_strncmp (tree exp, rtx target, enum machine_mode mode)
     arg1_rtx = get_memory_rtx (arg1);
     arg2_rtx = get_memory_rtx (arg2);
     arg3_rtx = expand_expr (len, NULL_RTX, VOIDmode, 0);
-    insn = gen_cmpstrsi (result, arg1_rtx, arg2_rtx, arg3_rtx,
+    insn = gen_cmpstrnsi (result, arg1_rtx, arg2_rtx, arg3_rtx,
 			  GEN_INT (MIN (arg1_align, arg2_align)));
     if (insn)
       {

gcc/config/c4x/c4x.md

@@ -5714,7 +5714,7 @@
  }")
 
 
-(define_insn "*cmpstrqi"
+(define_insn "*cmpstrnqi"
   [(set (match_operand:QI 0 "ext_reg_operand" "=d")
         (compare:QI (mem:BLK (match_operand:QI 1 "addr_reg_operand" "+a"))
                     (mem:BLK (match_operand:QI 2 "addr_reg_operand" "+a"))))
@@ -5731,7 +5731,7 @@
     return \"\";
  }")
 
-(define_expand "cmpstrqi"
+(define_expand "cmpstrnqi"
   [(parallel [(set (match_operand:QI 0 "reg_operand" "")
                    (compare:QI (match_operand:BLK 1 "general_operand" "")
                                (match_operand:BLK 2 "general_operand" "")))

gcc/config/i386/i386.md

@@ -17446,7 +17446,7 @@
    (set_attr "memory" "store")
    (set_attr "mode" "QI")])
 
-(define_expand "cmpstrsi"
+(define_expand "cmpstrnsi"
   [(set (match_operand:SI 0 "register_operand" "")
 	(compare:SI (match_operand:BLK 1 "general_operand" "")
 		    (match_operand:BLK 2 "general_operand" "")))
@@ -17487,7 +17487,7 @@
 	  emit_move_insn (operands[0], const0_rtx);
 	  DONE;
 	}
-      emit_insn (gen_cmpstrqi_nz_1 (addr1, addr2, countreg, align,
+      emit_insn (gen_cmpstrnqi_nz_1 (addr1, addr2, countreg, align,
 				     operands[1], operands[2]));
     }
   else
@@ -17496,7 +17496,7 @@
 	emit_insn (gen_cmpdi_1_rex64 (countreg, countreg));
       else
 	emit_insn (gen_cmpsi_1 (countreg, countreg));
-      emit_insn (gen_cmpstrqi_1 (addr1, addr2, countreg, align,
+      emit_insn (gen_cmpstrnqi_1 (addr1, addr2, countreg, align,
 				  operands[1], operands[2]));
     }
 
@@ -17528,7 +17528,7 @@
 ;; memcmp recognizers.  The `cmpsb' opcode does nothing if the count is
 ;; zero.  Emit extra code to make sure that a zero-length compare is EQ.
 
-(define_expand "cmpstrqi_nz_1"
+(define_expand "cmpstrnqi_nz_1"
   [(parallel [(set (reg:CC FLAGS_REG)
 		   (compare:CC (match_operand 4 "memory_operand" "")
 			       (match_operand 5 "memory_operand" "")))
@@ -17541,7 +17541,7 @@
   ""
   "")
 
-(define_insn "*cmpstrqi_nz_1"
+(define_insn "*cmpstrnqi_nz_1"
   [(set (reg:CC FLAGS_REG)
 	(compare:CC (mem:BLK (match_operand:SI 4 "register_operand" "0"))
 		    (mem:BLK (match_operand:SI 5 "register_operand" "1"))))
@@ -17557,7 +17557,7 @@
    (set_attr "mode" "QI")
    (set_attr "prefix_rep" "1")])
 
-(define_insn "*cmpstrqi_nz_rex_1"
+(define_insn "*cmpstrnqi_nz_rex_1"
   [(set (reg:CC FLAGS_REG)
 	(compare:CC (mem:BLK (match_operand:DI 4 "register_operand" "0"))
 		    (mem:BLK (match_operand:DI 5 "register_operand" "1"))))
@@ -17575,7 +17575,7 @@
 
 ;; The same, but the count is not known to not be zero.
 
-(define_expand "cmpstrqi_1"
+(define_expand "cmpstrnqi_1"
   [(parallel [(set (reg:CC FLAGS_REG)
 		(if_then_else:CC (ne (match_operand 2 "register_operand" "")
 				     (const_int 0))
@@ -17591,7 +17591,7 @@
   ""
   "")
 
-(define_insn "*cmpstrqi_1"
+(define_insn "*cmpstrnqi_1"
   [(set (reg:CC FLAGS_REG)
 	(if_then_else:CC (ne (match_operand:SI 6 "register_operand" "2")
 			     (const_int 0))
@@ -17610,7 +17610,7 @@
    (set_attr "mode" "QI")
    (set_attr "prefix_rep" "1")])
 
-(define_insn "*cmpstrqi_rex_1"
+(define_insn "*cmpstrnqi_rex_1"
   [(set (reg:CC FLAGS_REG)
 	(if_then_else:CC (ne (match_operand:DI 6 "register_operand" "2")
 			     (const_int 0))
@@ -17693,9 +17693,9 @@
    (set_attr "mode" "QI")
    (set_attr "prefix_rep" "1")])
 
-;; Peephole optimizations to clean up after cmpstr*.  This should be
+;; Peephole optimizations to clean up after cmpstrn*.  This should be
 ;; handled in combine, but it is not currently up to the task.
-;; When used for their truth value, the cmpstr* expanders generate
+;; When used for their truth value, the cmpstrn* expanders generate
 ;; code like this:
 ;;
 ;;   repz cmpsb
@@ -17706,7 +17706,7 @@
 ;;
 ;; The intermediate three instructions are unnecessary.
 
-;; This one handles cmpstr*_nz_1...
+;; This one handles cmpstrn*_nz_1...
 (define_peephole2
   [(parallel[
      (set (reg:CC FLAGS_REG)
@@ -17738,7 +17738,7 @@
      (clobber (match_dup 2))])]
   "")
 
-;; ...and this one handles cmpstr*_1.
+;; ...and this one handles cmpstrn*_1.
 (define_peephole2
   [(parallel[
      (set (reg:CC FLAGS_REG)

gcc/doc/md.texi

@@ -3269,8 +3269,8 @@ operand.
 
 The use for multiple @code{setmem@var{m}} is as for @code{movmem@var{m}}.
 
-@cindex @code{cmpstr@var{m}} instruction pattern
-@item @samp{cmpstr@var{m}}
+@cindex @code{cmpstrn@var{m}} instruction pattern
+@item @samp{cmpstrn@var{m}}
 String compare instruction, with five operands.  Operand 0 is the output;
 it has mode @var{m}.  The remaining four operands are like the operands
 of @samp{movmem@var{m}}.  The two memory blocks specified are compared
@@ -3281,6 +3281,25 @@ that may access an invalid page or segment and cause a fault.  The
 effect of the instruction is to store a value in operand 0 whose sign
 indicates the result of the comparison.
 
+@cindex @code{cmpstr@var{m}} instruction pattern
+@item @samp{cmpstr@var{m}}
+String compare instruction, without known maximum length.  Operand 0 is the
+output; it has mode @var{m}.  The second and third operand are the blocks of
+memory to be compared; both are @code{mem:BLK} with an address in mode
+@code{Pmode}.
+
+The fourth operand is the known shared alignment of the source and
+destination, in the form of a @code{const_int} rtx.  Thus, if the
+compiler knows that both source and destination are word-aligned,
+it may provide the value 4 for this operand.
+
+The two memory blocks specified are compared byte by byte in lexicographic
+order starting at the beginning of each string.  The instruction is not allowed
+to prefetch more than one byte at a time since either string may end in the
+first byte and reading past that may access an invalid page or segment and
+cause a fault.  The effect of the instruction is to store a value in operand 0
+whose sign indicates the result of the comparison.
+
 @cindex @code{cmpmem@var{m}} instruction pattern
 @item @samp{cmpmem@var{m}}
 Block compare instruction, with five operands like the operands

gcc/expr.c

@@ -202,9 +202,10 @@ enum insn_code movmem_optab[NUM_MACHINE_MODES];
 /* This array records the insn_code of insns to perform block sets.  */
 enum insn_code setmem_optab[NUM_MACHINE_MODES];
 
-/* These arrays record the insn_code of two different kinds of insns
+/* These arrays record the insn_code of three different kinds of insns
    to perform block compares.  */
 enum insn_code cmpstr_optab[NUM_MACHINE_MODES];
+enum insn_code cmpstrn_optab[NUM_MACHINE_MODES];
 enum insn_code cmpmem_optab[NUM_MACHINE_MODES];
 
 /* Synchronization primitives.  */

gcc/genopinit.c

@@ -169,6 +169,7 @@ static const char * const optabs[] =
   "reload_out_optab[$A] = CODE_FOR_$(reload_out$a$)",
   "movmem_optab[$A] = CODE_FOR_$(movmem$a$)",
   "cmpstr_optab[$A] = CODE_FOR_$(cmpstr$a$)",
+  "cmpstrn_optab[$A] = CODE_FOR_$(cmpstrn$a$)",
   "cmpmem_optab[$A] = CODE_FOR_$(cmpmem$a$)",
   "setmem_optab[$A] = CODE_FOR_$(setmem$a$)",
   "sync_add_optab[$A] = CODE_FOR_$(sync_add$I$a$)",

gcc/optabs.c

@@ -3426,6 +3426,8 @@ prepare_cmp_insn (rtx *px, rtx *py, enum rtx_code *pcomparison, rtx size,
 	  if (cmp_code == CODE_FOR_nothing)
 	    cmp_code = cmpstr_optab[cmp_mode];
 	  if (cmp_code == CODE_FOR_nothing)
+	    cmp_code = cmpstrn_optab[cmp_mode];
+	  if (cmp_code == CODE_FOR_nothing)
 	    continue;
 
 	  /* Must make sure the size fits the insn's mode.  */
@@ -5090,6 +5092,7 @@ init_optabs (void)
     {
       movmem_optab[i] = CODE_FOR_nothing;
       cmpstr_optab[i] = CODE_FOR_nothing;
+      cmpstrn_optab[i] = CODE_FOR_nothing;
       cmpmem_optab[i] = CODE_FOR_nothing;
       setmem_optab[i] = CODE_FOR_nothing;
 

gcc/optabs.h

@@ -450,6 +450,7 @@ extern enum insn_code setmem_optab[NUM_MACHINE_MODES];
 /* These arrays record the insn_code of two different kinds of insns
    to perform block compares.  */
 extern enum insn_code cmpstr_optab[NUM_MACHINE_MODES];
+extern enum insn_code cmpstrn_optab[NUM_MACHINE_MODES];
 extern enum insn_code cmpmem_optab[NUM_MACHINE_MODES];
 
 /* Synchronization primitives.  This first set is atomic operation for