Hi!
The shift count operand of shifts/rotates uses int type which is different
from lhs/rhs1 type. If shift/rotate counts are constant, vectorizable_shift
converts it to the right type, but then the types in
vect_get_constant_vectors aren't compatible and we end up folding a ushort
VCE of int, which on big-endian results in 0 shift count.
Fixed thusly, acked by Richard on IRC, bootstrapped/regtested on
x86_64-linux and i686-linux, committed to trunk.
2012-03-29 Jakub Jelinek <ja...@redhat.com>
PR tree-optimization/52760
* tree-vect-slp.c (vect_get_constant_vectors): Convert constant_p
shift count for {L,R}{SHIFT,ROTATE}_EXPR to TREE_TYPE (vector_type).
* gcc.c-torture/execute/pr52760.c: New test.
--- gcc/tree-vect-slp.c.jj 2012-03-26 11:53:20.000000000 +0200
+++ gcc/tree-vect-slp.c 2012-03-29 13:32:26.153408588 +0200
@@ -2337,8 +2337,23 @@ vect_get_constant_vectors (tree op, slp_
op = gimple_call_arg (stmt, op_num);
break;
+ case LSHIFT_EXPR:
+ case RSHIFT_EXPR:
+ case LROTATE_EXPR:
+ case RROTATE_EXPR:
+ op = gimple_op (stmt, op_num + 1);
+ /* Unlike the other binary operators, shifts/rotates have
+ the shift count being int, instead of the same type as
+ the lhs, so make sure the scalar is the right type if
+ we are dealing with vectors of
+ long long/long/short/char. */
+ if (op_num == 1 && constant_p)
+ op = fold_convert (TREE_TYPE (vector_type), op);
+ break;
+
default:
op = gimple_op (stmt, op_num + 1);
+ break;
}
}
--- gcc/testsuite/gcc.c-torture/execute/pr52760.c.jj 2012-03-29
11:29:08.185685328 +0200
+++ gcc/testsuite/gcc.c-torture/execute/pr52760.c 2012-03-29
11:28:40.000000000 +0200
@@ -0,0 +1,27 @@
+/* PR tree-optimization/52760 */
+
+struct T { unsigned short a, b, c, d; };
+
+__attribute__((noinline, noclone)) void
+foo (int x, struct T *y)
+{
+ int i;
+
+ for (i = 0; i < x; i++)
+ {
+ y[i].a = ((0x00ff & y[i].a >> 8) | (0xff00 & y[i].a << 8));
+ y[i].b = ((0x00ff & y[i].b >> 8) | (0xff00 & y[i].b << 8));
+ y[i].c = ((0x00ff & y[i].c >> 8) | (0xff00 & y[i].c << 8));
+ y[i].d = ((0x00ff & y[i].d >> 8) | (0xff00 & y[i].d << 8));
+ }
+}
+
+int
+main ()
+{
+ struct T t = { 0x0001, 0x0203, 0x0405, 0x0607 };
+ foo (1, &t);
+ if (t.a != 0x0100 || t.b != 0x0302 || t.c != 0x0504 || t.d != 0x0706)
+ __builtin_abort ();
+ return 0;
+}
Jakub
