The following patch fixes
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59133
The problem was in creation a new additional pseudo by RTL
infrastructure and assigning it a wrong class.
The patch was bootstrapped and tested on x86/x86-64 and ppc64.
Committed as rev. 205141.
2013-11-20 Vladimir Makarov <vmaka...@redhat.com>
PR rtl-optimization/59133
* lra.c (expand_reg_data): Add new argument. Set up ALL_REGS for
new pseudos.
(lra_create_new_reg_with_unique_value): Pass new argument value.
(lra_emit_add, lra_emit_move): Ditto.
* lra-constraints.c (in_class_p): Add check for move for a new
insn.
(change_class): Rename to lra_change_class. Move to lra-int.h.
(get_reload_reg, narrow_reload_pseudo_class): Adjust calls of
change_class.
(process_addr_reg, process_addr): Ditto.
(curr_insn_transform): Ditto. Add check on old pseudo for
optional reload.
* lra-int.h (lra_get_regno_hard_regno): Move below.
(lra_change_class): Renamed change_class from lra.c.
2013-11-20 Vladimir Makarov <vmaka...@redhat.com>
PR rtl-optimization/59133
* gcc.target/i386/pr59133.c: New.
Index: lra-constraints.c
===================================================================
--- lra-constraints.c (revision 204792)
+++ lra-constraints.c (working copy)
@@ -269,7 +269,11 @@ in_class_p (rtx reg, enum reg_class cl,
typically moves that have many alternatives, and restricting
reload pseudos for one alternative may lead to situations
where other reload pseudos are no longer allocatable. */
- || INSN_UID (curr_insn) >= new_insn_uid_start)
+ || (INSN_UID (curr_insn) >= new_insn_uid_start
+ && curr_insn_set != NULL
+ && (OBJECT_P (SET_SRC (curr_insn_set))
+ || (GET_CODE (SET_SRC (curr_insn_set)) == SUBREG
+ && OBJECT_P (SUBREG_REG (SET_SRC (curr_insn_set)))))))
/* When we don't know what class will be used finally for reload
pseudos, we use ALL_REGS. */
return ((regno >= new_regno_start && rclass == ALL_REGS)
@@ -381,21 +385,6 @@ init_curr_insn_input_reloads (void)
curr_insn_input_reloads_num = 0;
}
-/* Change class of pseudo REGNO to NEW_CLASS. Print info about it
- using TITLE. Output a new line if NL_P. */
-static void
-change_class (int regno, enum reg_class new_class,
- const char *title, bool nl_p)
-{
- lra_assert (regno >= FIRST_PSEUDO_REGISTER);
- if (lra_dump_file != NULL)
- fprintf (lra_dump_file, "%s to class %s for r%d",
- title, reg_class_names[new_class], regno);
- setup_reg_classes (regno, new_class, NO_REGS, new_class);
- if (lra_dump_file != NULL && nl_p)
- fprintf (lra_dump_file, "\n");
-}
-
/* Create a new pseudo using MODE, RCLASS, ORIGINAL or reuse already
created input reload pseudo (only if TYPE is not OP_OUT). The
result pseudo is returned through RESULT_REG. Return TRUE if we
@@ -442,7 +431,7 @@ get_reload_reg (enum op_type type, enum
dump_value_slim (lra_dump_file, original, 1);
}
if (new_class != lra_get_allocno_class (regno))
- change_class (regno, new_class, ", change", false);
+ lra_change_class (regno, new_class, ", change to", false);
if (lra_dump_file != NULL)
fprintf (lra_dump_file, "\n");
return false;
@@ -667,7 +656,7 @@ narrow_reload_pseudo_class (rtx reg, enu
if (! REG_P (reg) || (int) REGNO (reg) < new_regno_start)
return;
if (in_class_p (reg, cl, &rclass) && rclass != cl)
- change_class (REGNO (reg), rclass, " Change", true);
+ lra_change_class (REGNO (reg), rclass, " Change to", true);
}
/* Generate reloads for matching OUT and INS (array of input operand
@@ -1133,7 +1122,7 @@ process_addr_reg (rtx *loc, rtx *before,
}
else if (new_class != NO_REGS && rclass != new_class)
{
- change_class (regno, new_class, " Change", true);
+ lra_change_class (regno, new_class, " Change to", true);
return false;
}
else
@@ -2796,7 +2785,7 @@ process_address (int nop, rtx *before, r
regno = REGNO (*ad.base_term);
if (regno >= FIRST_PSEUDO_REGISTER
&& cl != lra_get_allocno_class (regno))
- change_class (regno, cl, " Change", true);
+ lra_change_class (regno, cl, " Change to", true);
new_reg = SET_SRC (set);
delete_insns_since (PREV_INSN (last_insn));
}
@@ -3316,7 +3305,7 @@ curr_insn_transform (void)
if (new_class != NO_REGS && get_reg_class (regno) != new_class)
{
lra_assert (ok_p);
- change_class (regno, new_class, " Change", true);
+ lra_change_class (regno, new_class, " Change to", true);
}
}
}
@@ -3395,7 +3384,7 @@ curr_insn_transform (void)
&& lra_former_scratch_operand_p (curr_insn, i))
{
int regno = REGNO (op);
- change_class (regno, NO_REGS, " Change", true);
+ lra_change_class (regno, NO_REGS, " Change to", true);
if (lra_get_regno_hard_regno (regno) >= 0)
/* We don't have to mark all insn affected by the
spilled pseudo as there is only one such insn, the
@@ -3410,6 +3399,7 @@ curr_insn_transform (void)
&& lra_undo_inheritance_iter < LRA_MAX_INHERITANCE_PASSES
&& goal_alt[i] != NO_REGS && REG_P (op)
&& (regno = REGNO (op)) >= FIRST_PSEUDO_REGISTER
+ && regno < new_regno_start
&& ! lra_former_scratch_p (regno)
&& reg_renumber[regno] < 0
&& (curr_insn_set == NULL_RTX
Index: lra-int.h
===================================================================
--- lra-int.h (revision 204792)
+++ lra-int.h (working copy)
@@ -33,16 +33,6 @@ along with GCC; see the file COPYING3. I
base and index registers might require a reload too. */
#define LRA_MAX_INSN_RELOADS (MAX_RECOG_OPERANDS * 3)
-/* Return the hard register which given pseudo REGNO assigned to.
- Negative value means that the register got memory or we don't know
- allocation yet. */
-static inline int
-lra_get_regno_hard_regno (int regno)
-{
- resize_reg_info ();
- return reg_renumber[regno];
-}
-
typedef struct lra_live_range *lra_live_range_t;
/* The structure describes program points where a given pseudo lives.
@@ -394,6 +384,31 @@ extern void lra_eliminate_reg_if_possibl
+/* Return the hard register which given pseudo REGNO assigned to.
+ Negative value means that the register got memory or we don't know
+ allocation yet. */
+static inline int
+lra_get_regno_hard_regno (int regno)
+{
+ resize_reg_info ();
+ return reg_renumber[regno];
+}
+
+/* Change class of pseudo REGNO to NEW_CLASS. Print info about it
+ using TITLE. Output a new line if NL_P. */
+static void inline
+lra_change_class (int regno, enum reg_class new_class,
+ const char *title, bool nl_p)
+{
+ lra_assert (regno >= FIRST_PSEUDO_REGISTER);
+ if (lra_dump_file != NULL)
+ fprintf (lra_dump_file, "%s class %s for r%d",
+ title, reg_class_names[new_class], regno);
+ setup_reg_classes (regno, new_class, NO_REGS, new_class);
+ if (lra_dump_file != NULL && nl_p)
+ fprintf (lra_dump_file, "\n");
+}
+
/* Update insn operands which are duplication of NOP operand. The
insn is represented by its LRA internal representation ID. */
static inline void
Index: lra.c
===================================================================
--- lra.c (revision 204792)
+++ lra.c (working copy)
@@ -130,11 +130,13 @@ static void invalidate_insn_data_regno_i
/* Expand all regno related info needed for LRA. */
static void
-expand_reg_data (void)
+expand_reg_data (int old)
{
resize_reg_info ();
expand_reg_info ();
ira_expand_reg_equiv ();
+ for (int i = (int) max_reg_num () - 1; i >= old; i--)
+ lra_change_class (i, ALL_REGS, " Set", true);
}
/* Create and return a new reg of ORIGINAL mode. If ORIGINAL is NULL
@@ -178,7 +180,7 @@ lra_create_new_reg_with_unique_value (en
title, REGNO (new_reg));
fprintf (lra_dump_file, "\n");
}
- expand_reg_data ();
+ expand_reg_data (max_reg_num ());
setup_reg_classes (REGNO (new_reg), rclass, NO_REGS, rclass);
return new_reg;
}
@@ -417,7 +419,7 @@ lra_emit_add (rtx x, rtx y, rtx z)
/* Functions emit_... can create pseudos -- so expand the pseudo
data. */
if (old != max_reg_num ())
- expand_reg_data ();
+ expand_reg_data (old);
}
/* The number of emitted reload insns so far. */
@@ -443,7 +445,7 @@ lra_emit_move (rtx x, rtx y)
/* Function emit_move can create pseudos -- so expand the pseudo
data. */
if (old != max_reg_num ())
- expand_reg_data ();
+ expand_reg_data (old);
return;
}
lra_emit_add (x, XEXP (y, 0), XEXP (y, 1));
Index: testsuite/gcc.target/i386/pr59133.c
===================================================================
--- testsuite/gcc.target/i386/pr59133.c (revision 0)
+++ testsuite/gcc.target/i386/pr59133.c (working copy)
@@ -0,0 +1,42 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -ffast-math -march=core-avx2" } */
+
+#define XX 0
+#define YY 1
+#define ZZ 2
+#define DIM 3
+typedef float matrix[DIM][DIM];
+typedef float rvec[DIM];
+extern int det (matrix);
+extern void foo(matrix);
+
+void bar1 (int n,int *index,rvec x[],matrix trans)
+{
+ float xt,yt,zt;
+ int i,ii;
+
+ for(i=0; (i<n); i++) {
+ ii=index ? index[i] : i;
+ xt=x[ii][XX];
+ yt=x[ii][YY];
+ zt=x[ii][ZZ];
+ x[ii][XX]=trans[XX][XX]*xt+trans[XX][YY]*yt+trans[XX][ZZ]*zt;
+ x[ii][YY]=trans[YY][XX]*xt+trans[YY][YY]*yt+trans[YY][ZZ]*zt;
+ x[ii][ZZ]=trans[ZZ][XX]*xt+trans[ZZ][YY]*yt+trans[ZZ][ZZ]*zt;
+ }
+}
+
+
+void bar2 (int n, rvec x[])
+{
+ int m;
+ matrix trans;
+
+ foo (trans);
+
+ if (det (trans) < 0) {
+ for(m=0; (m<DIM); m++)
+ trans[ZZ][m] = -trans[ZZ][m];
+ }
+ bar1 (n,(int*) 0,x,trans);
+}
