S/390: Fix rounding for _Decimal128 to _Decimal32 conversion

We do not have a direct conversion instruction from 128 bit DFP to 32
bit DFP so this needs to be done in two steps.  The first needs to be
done with the "prepare for shorter precision rounding mode" in order
to produce a correct result.

gcc/ChangeLog:

2016-03-11  Andreas Krebbel  <krebbel@linux.vnet.ibm.com>

	* config/s390/s390.md ("trunctddd2"): Turn former define_insn into
	define_expand.
	("*trunctddd2"): New pattern definition.
	("trunctdsd2"): Set prep_for_short_prec rounding mode for the
	TD->DD truncation.

gcc/testsuite/ChangeLog:

2016-03-11  Andreas Krebbel  <krebbel@linux.vnet.ibm.com>

	* gcc.target/s390/dfp-1.c: New test.

From-SVN: r234134

gcc/ChangeLog

 2016-03-11  Andreas Krebbel  <krebbel@linux.vnet.ibm.com>
 
+	* config/s390/s390.md ("trunctddd2"): Turn former define_insn into
+	define_expand.
+	("*trunctddd2"): New pattern definition.
+	("trunctdsd2"): Set prep_for_short_prec rounding mode for the
+	TD->DD truncation.
+
+2016-03-11  Andreas Krebbel  <krebbel@linux.vnet.ibm.com>
+
 	* config/s390/s390.md (BFP_RND_*, DFP_RND_*): Add new constant
 	definitions for BFP and DFP rounding modes.
 	("fixuns_truncdddi2", "fixuns_trunctddi2")

gcc/config/s390/s390.md

@@ -4847,12 +4847,22 @@
 ; trunctddd2 and truncddsd2 instruction pattern(s).
 ;
 
-(define_insn "trunctddd2"
+
+(define_expand "trunctddd2"
+  [(parallel
+    [(set (match_operand:DD 0 "register_operand" "")
+	  (float_truncate:DD (match_operand:TD 1 "register_operand" "")))
+     (unspec:DI [(const_int DFP_RND_CURRENT)] UNSPEC_ROUND)
+     (clobber (scratch:TD))])]
+  "TARGET_HARD_DFP")
+
+(define_insn "*trunctddd2"
   [(set (match_operand:DD 0 "register_operand" "=f")
 	(float_truncate:DD (match_operand:TD 1 "register_operand" "f")))
-   (clobber (match_scratch:TD 2 "=f"))]
+   (unspec:DI [(match_operand:DI 2 "const_mask_operand" "I")] UNSPEC_ROUND)
+   (clobber (match_scratch:TD 3 "=f"))]
   "TARGET_HARD_DFP"
-  "ldxtr\t%2,0,%1,0\;ldr\t%0,%2"
+  "ldxtr\t%3,%2,%1,0\;ldr\t%0,%3"
   [(set_attr "length"  "6")
    (set_attr "type"    "ftruncdd")])
 
@@ -4868,6 +4878,7 @@
   [(parallel
     [(set (match_dup 3)
 	  (float_truncate:DD (match_operand:TD 1 "register_operand" "")))
+     (unspec:DI [(const_int DFP_RND_PREP_FOR_SHORT_PREC)] UNSPEC_ROUND)
      (clobber (match_scratch:TD 2 ""))])
    (set (match_operand:SD 0 "register_operand" "")
 	(float_truncate:SD (match_dup 3)))]

gcc/testsuite/ChangeLog

+2016-03-11  Andreas Krebbel  <krebbel@linux.vnet.ibm.com>
+
+	* gcc.target/s390/dfp-1.c: New test.
+
 2016-03-10  Nick Clifton  <nickc@redhat.com>
 
 	PR target/70044

gcc/testsuite/gcc.target/s390/dfp-1.c

+/* We do not have a direct conversion instruction from 128 bit DFP to
+   32 bit DFP so this needs to be done in two steps.  The first needs
+   to be done with the "prepare for shorter precision rounding mode"
+   in order to produce a correct result.  Otherwise the 8th digit of
+   the number will change from 4 to 5 in the first rounding step which
+   then will turn the last digit of the 32 bit DFP number (the 3) into
+   a 4.  Although with direct rounding it would stay a 3.  */
+
+/* { dg-do run } */
+/* { dg-options "-O3 -march=z10 -mzarch" } */
+
+_Decimal32 __attribute__((noinline))
+foo (_Decimal128 a)
+{
+  return (_Decimal32)a;
+}
+
+int
+main ()
+{
+    if (foo (1.23456349999999999DL) != 1.234563DF)
+    __builtin_abort ();
+}