Hi All,
We can't support nonlinear inductions other than neg when vectorizing
early breaks and iteration count is known.
For early break we currently require a peeled epilog but in these cases
we can't compute the remaining values.
Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.
tested on cross cc1 for amdgcn-amdhsa and issue fixed.
Ok for master?
Thanks,
Tamar
gcc/ChangeLog:
PR middle-end/113163
* tree-vect-loop-manip.cc (vect_can_peel_nonlinear_iv_p):
gcc/testsuite/ChangeLog:
PR middle-end/113163
* gcc.target/gcn/pr113163.c: New test.
--- inline copy of patch --
diff --git a/gcc/testsuite/gcc.target/gcn/pr113163.c
b/gcc/testsuite/gcc.target/gcn/pr113163.c
new file mode 100644
index
0000000000000000000000000000000000000000..99b0fdbaf3a3152ca008b5109abf6e80d8cb3d6a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/gcn/pr113163.c
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O2 -ftree-vectorize" } */
+
+struct _reent { union { struct { char _l64a_buf[8]; } _reent; } _new; };
+static const char R64_ARRAY[] =
"./0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz";
+char *
+_l64a_r (struct _reent *rptr,
+ long value)
+{
+ char *ptr;
+ char *result;
+ int i, index;
+ unsigned long tmp = (unsigned long)value & 0xffffffff;
+ result =
+ ((
+ rptr
+ )->_new._reent._l64a_buf)
+ ;
+ ptr = result;
+ for (i = 0; i < 6; ++i)
+ {
+ if (tmp == 0)
+ {
+ *ptr = '\0';
+ break;
+ }
+ *ptr++ = R64_ARRAY[index];
+ tmp >>= 6;
+ }
+}
diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc
index
3810983a80c8b989be9fd9a9993642069fd39b99..f1bf43b3731868e7b053c186302fbeaf515be8cf
100644
--- a/gcc/tree-vect-loop-manip.cc
+++ b/gcc/tree-vect-loop-manip.cc
@@ -2075,6 +2075,22 @@ vect_can_peel_nonlinear_iv_p (loop_vec_info loop_vinfo,
return false;
}
+ /* We can't support partial vectors and early breaks with an induction
+ type other than add or neg since we require the epilog and can't
+ perform the peeling. PR113163. */
+ if (LOOP_VINFO_EARLY_BREAKS (loop_vinfo)
+ && LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant ()
+ && LOOP_VINFO_USING_PARTIAL_VECTORS_P (loop_vinfo)
+ && induction_type != vect_step_op_neg)
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
+ "Peeling for epilogue is not supported"
+ " for nonlinear induction except neg"
+ " when iteration count is known and early breaks.\n");
+ return false;
+ }
+
return true;
}
--
diff --git a/gcc/testsuite/gcc.target/gcn/pr113163.c
b/gcc/testsuite/gcc.target/gcn/pr113163.c
new file mode 100644
index
0000000000000000000000000000000000000000..99b0fdbaf3a3152ca008b5109abf6e80d8cb3d6a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/gcn/pr113163.c
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O2 -ftree-vectorize" } */
+
+struct _reent { union { struct { char _l64a_buf[8]; } _reent; } _new; };
+static const char R64_ARRAY[] =
"./0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz";
+char *
+_l64a_r (struct _reent *rptr,
+ long value)
+{
+ char *ptr;
+ char *result;
+ int i, index;
+ unsigned long tmp = (unsigned long)value & 0xffffffff;
+ result =
+ ((
+ rptr
+ )->_new._reent._l64a_buf)
+ ;
+ ptr = result;
+ for (i = 0; i < 6; ++i)
+ {
+ if (tmp == 0)
+ {
+ *ptr = '\0';
+ break;
+ }
+ *ptr++ = R64_ARRAY[index];
+ tmp >>= 6;
+ }
+}
diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc
index
3810983a80c8b989be9fd9a9993642069fd39b99..f1bf43b3731868e7b053c186302fbeaf515be8cf
100644
--- a/gcc/tree-vect-loop-manip.cc
+++ b/gcc/tree-vect-loop-manip.cc
@@ -2075,6 +2075,22 @@ vect_can_peel_nonlinear_iv_p (loop_vec_info loop_vinfo,
return false;
}
+ /* We can't support partial vectors and early breaks with an induction
+ type other than add or neg since we require the epilog and can't
+ perform the peeling. PR113163. */
+ if (LOOP_VINFO_EARLY_BREAKS (loop_vinfo)
+ && LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant ()
+ && LOOP_VINFO_USING_PARTIAL_VECTORS_P (loop_vinfo)
+ && induction_type != vect_step_op_neg)
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
+ "Peeling for epilogue is not supported"
+ " for nonlinear induction except neg"
+ " when iteration count is known and early breaks.\n");
+ return false;
+ }
+
return true;
}
