Hello,
Following Richard's comment
http://gcc.gnu.org/ml/gcc-patches/2011-12/msg01469.html attached is
a new version of the patch to prevent reg-moves for non allocatable definitions.
Currently testing and bootstrap on ppc64-redhat-linux, enabling SMS on
loops with SC 1.
OK for 4.7 once testing completes?
Thanks,
Revital
Changelog:
gcc/
* ddg.c (def_non_allocatable_p): New function.
(add_cross_iteration_register_deps): Call it.
testsuite/
* gcc.dg/sms-11.c: New file.
Index: ddg.c
===================================================================
--- ddg.c (revision 182479)
+++ ddg.c (working copy)
@@ -263,6 +263,23 @@ create_ddg_dep_no_link (ddg_ptr g, ddg_n
add_edge_to_ddg (g, e);
}
+/* Return true if one of the definitions in INSN is not allocatable.
+ Otherwise return false. */
+static bool
+def_non_allocatable_p (rtx insn)
+{
+ df_ref *def;
+
+ for (def = DF_INSN_DEFS (insn); *def; def++)
+ {
+ enum machine_mode mode = GET_MODE (DF_REF_REG (*def));
+
+ if (!have_regs_of_mode[mode])
+ return true;
+ }
+
+ return false;
+}
/* Given a downwards exposed register def LAST_DEF (which is the last
definition of that register in the bb), add inter-loop true dependences
@@ -335,7 +352,8 @@ add_cross_iteration_register_deps (ddg_p
if (DF_REF_ID (last_def) != DF_REF_ID (first_def)
|| !flag_modulo_sched_allow_regmoves
|| JUMP_P (use_node->insn)
- || autoinc_var_is_used_p (DF_REF_INSN (last_def), use_insn))
+ || autoinc_var_is_used_p (DF_REF_INSN (last_def), use_insn)
+ || def_non_allocatable_p (DF_REF_INSN (last_def)))
create_ddg_dep_no_link (g, use_node, first_def_node, ANTI_DEP,
REG_DEP, 1);
Index: testsuite/gcc.dg/sms-11.c
===================================================================
--- testsuite/gcc.dg/sms-11.c (revision 0)
+++ testsuite/gcc.dg/sms-11.c (revision 0)
@@ -0,0 +1,37 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -fmodulo-sched -fmodulo-sched-allow-regmoves
-fdump-rtl-sms" } */
+
+extern void abort (void);
+
+float out[4][4] = { 6, 6, 7, 5, 6, 7, 5, 5, 6, 4, 4, 4, 6, 2, 3, 4 };
+
+void
+invert (void)
+{
+ int i, j, k = 0, swap;
+ float tmp[4][4] = { 5, 6, 7, 5, 6, 7, 5, 5, 4, 4, 4, 4, 3, 2, 3, 4 };
+
+ for (i = 0; i < 4; i++)
+ {
+ for (j = i + 1; j < 4; j++)
+ if (tmp[j][i] > tmp[i][i])
+ swap = j;
+
+ if (swap != i)
+ tmp[i][k] = tmp[swap][k];
+ }
+
+ for (i = 0; i < 4; i++)
+ for (j = 0; j < 4; j++)
+ if (tmp[i][j] != out[i][j])
+ abort ();
+}
+
+int
+main ()
+{
+ invert ();
+ return 0;
+}
+
+/* { dg-final { cleanup-rtl-dump "sms" } } */
