Hi!
When using the bswap pass infrastructure, BIT_NOT_EXPRs aren't allowed in
the middle, but due to the way process_store handles those it can appear
around the value, which is something output_merged_store didn't handle.
Fixed thusly, where we handle not just the case when the bswap (or nop)
value needs inversion as whole, but also cases where only a few portions of
it need xoring with some mask.
Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
2018-01-15 Jakub Jelinek <ja...@redhat.com>
PR tree-optimization/83843
* gimple-ssa-store-merging.c
(imm_store_chain_info::output_merged_store): Handle bit_not_p on
store_immediate_info for bswap/nop orig_stores.
* gcc.dg/store_merging_18.c: New test.
--- gcc/gimple-ssa-store-merging.c.jj 2018-01-04 00:43:17.629703230 +0100
+++ gcc/gimple-ssa-store-merging.c 2018-01-15 12:29:14.105789381 +0100
@@ -3619,6 +3619,15 @@ imm_store_chain_info::output_merged_stor
gimple_seq_add_stmt_without_update (&seq, stmt);
src = gimple_assign_lhs (stmt);
}
+ inv_op = invert_op (split_store, 2, int_type, xor_mask);
+ if (inv_op != NOP_EXPR)
+ {
+ stmt = gimple_build_assign (make_ssa_name (int_type),
+ inv_op, src, xor_mask);
+ gimple_set_location (stmt, loc);
+ gimple_seq_add_stmt_without_update (&seq, stmt);
+ src = gimple_assign_lhs (stmt);
+ }
break;
default:
src = ops[0];
--- gcc/testsuite/gcc.dg/store_merging_18.c.jj 2018-01-15 12:43:49.607227365
+0100
+++ gcc/testsuite/gcc.dg/store_merging_18.c 2018-01-15 12:43:24.882245004
+0100
@@ -0,0 +1,51 @@
+/* PR tree-optimization/83843 */
+/* { dg-do run } */
+/* { dg-options "-O2 -fdump-tree-store-merging" } */
+/* { dg-final { scan-tree-dump-times "Merging successful" 3 "store-merging" {
target store_merge } } } */
+
+__attribute__((noipa)) void
+foo (unsigned char *buf, unsigned char *tab)
+{
+ unsigned v = tab[1] ^ (tab[0] << 8);
+ buf[0] = ~(v >> 8);
+ buf[1] = ~v;
+}
+
+__attribute__((noipa)) void
+bar (unsigned char *buf, unsigned char *tab)
+{
+ unsigned v = tab[1] ^ (tab[0] << 8);
+ buf[0] = (v >> 8);
+ buf[1] = ~v;
+}
+
+__attribute__((noipa)) void
+baz (unsigned char *buf, unsigned char *tab)
+{
+ unsigned v = tab[1] ^ (tab[0] << 8);
+ buf[0] = ~(v >> 8);
+ buf[1] = v;
+}
+
+int
+main ()
+{
+ volatile unsigned char l1 = 0;
+ volatile unsigned char l2 = 1;
+ unsigned char buf[2];
+ unsigned char tab[2] = { l1 + 1, l2 * 2 };
+ foo (buf, tab);
+ if (buf[0] != (unsigned char) ~1 || buf[1] != (unsigned char) ~2)
+ __builtin_abort ();
+ buf[0] = l1 + 7;
+ buf[1] = l2 * 8;
+ bar (buf, tab);
+ if (buf[0] != 1 || buf[1] != (unsigned char) ~2)
+ __builtin_abort ();
+ buf[0] = l1 + 9;
+ buf[1] = l2 * 10;
+ baz (buf, tab);
+ if (buf[0] != (unsigned char) ~1 || buf[1] != 2)
+ __builtin_abort ();
+ return 0;
+}
Jakub
