spu.md (floatsidf2): Use convert_optab_libfunc instead of ufloat_optab->handlers directly.

2007-09-06  Andrew Pinski  <andrew_pinski@playstation.sony.com>
            Jan Hubicka  <jh@suse.cz>

        * config/spu/spu.md (floatsidf2): Use convert_optab_libfunc
        instead of ufloat_optab->handlers directly.
        (floatdidf2): Likewise.


Co-Authored-By: Jan Hubicka <jh@suse.cz>

From-SVN: r128202

gcc/ChangeLog

+2007-09-06  Andrew Pinski  <andrew_pinski@playstation.sony.com>
+            Jan Hubicka  <jh@suse.cz>
+
+	* config/spu/spu.md (floatsidf2): Use convert_optab_libfunc
+	instead of ufloat_optab->handlers directly.
+	(floatdidf2): Likewise.
+
 2007-09-06  Sandra Loosemore  <sandra@codesourcery.com>
 
 	* config/mips/mips.c:  Include diagnostic.h.

gcc/config/spu/spu.md

@@ -676,8 +676,10 @@
 
     start_sequence ();
     value =
-      emit_library_call_value (ufloat_optab->handlers[DFmode][SImode].libfunc,
+      emit_library_call_value (convert_optab_libfunc (ufloat_optab,
+                                                      DFmode, SImode),
                                NULL_RTX, LCT_NORMAL, DFmode, 1, r0, SImode);
+
     insns = get_insns ();
     end_sequence ();
     emit_libcall_block (insns, r1, value,
@@ -713,8 +715,10 @@
 
     start_sequence ();
     value =
-      emit_library_call_value (ufloat_optab->handlers[DFmode][DImode].libfunc,
+      emit_library_call_value (convert_optab_libfunc (ufloat_optab,
+                                                      DFmode, DImode),
                                NULL_RTX, LCT_NORMAL, DFmode, 1, r0, DImode);
+
     insns = get_insns ();
     end_sequence ();
     emit_libcall_block (insns, r1, value,