sched1: Fix -fcompare-debug issue in schedule_region [PR105586] In schedule_region(), a basic block that does not contain any real insns is not scheduled and the dfa state at the entry of the bb is not copied to the fallthru basic block. However a DEBUG insn is treated as a real insn, and if a bb contains non-real insns and a DEBUG insn, it's dfa state is copied to the fallthru bb. This was resulting in -fcompare-debug failure as the incoming dfa state of the fallthru block is different with -g. We should always copy the dfa state of a bb to it's fallthru bb even if the bb does not contain real insns.
2022-08-22 Surya Kumari Jangala <jskum...@linux.ibm.com> gcc/ PR rtl-optimization/105586 * sched-rgn.cc (schedule_region): Always copy dfa state to fallthru block. gcc/testsuite/ PR rtl-optimization/105586 * gcc.target/powerpc/pr105586.c: New test. diff --git a/gcc/sched-rgn.cc b/gcc/sched-rgn.cc index 0dc2a8f2851..6c9202c0b2b 100644 --- a/gcc/sched-rgn.cc +++ b/gcc/sched-rgn.cc @@ -3082,6 +3082,24 @@ free_bb_state_array (void) bb_state = NULL; } +static void +save_state_for_fallthru_edge (basic_block last_bb, state_t state) +{ + edge f = find_fallthru_edge (last_bb->succs); + if (f + && (!f->probability.initialized_p () + || (f->probability.to_reg_br_prob_base () * 100 + / REG_BR_PROB_BASE + >= param_sched_state_edge_prob_cutoff))) + { + memcpy (bb_state[f->dest->index], state, + dfa_state_size); + if (sched_verbose >= 5) + fprintf (sched_dump, "saving state for edge %d->%d\n", + f->src->index, f->dest->index); + } +} + /* Schedule a region. A region is either an inner loop, a loop-free subroutine, or a single basic block. Each bb in the region is scheduled after its flow predecessors. */ @@ -3155,6 +3173,7 @@ schedule_region (int rgn) if (no_real_insns_p (head, tail)) { gcc_assert (first_bb == last_bb); + save_state_for_fallthru_edge (last_bb, bb_state[first_bb->index]); continue; } @@ -3173,26 +3192,13 @@ schedule_region (int rgn) curr_bb = first_bb; if (dbg_cnt (sched_block)) { - edge f; int saved_last_basic_block = last_basic_block_for_fn (cfun); schedule_block (&curr_bb, bb_state[first_bb->index]); gcc_assert (EBB_FIRST_BB (bb) == first_bb); sched_rgn_n_insns += sched_n_insns; realloc_bb_state_array (saved_last_basic_block); - f = find_fallthru_edge (last_bb->succs); - if (f - && (!f->probability.initialized_p () - || (f->probability.to_reg_br_prob_base () * 100 - / REG_BR_PROB_BASE - >= param_sched_state_edge_prob_cutoff))) - { - memcpy (bb_state[f->dest->index], curr_state, - dfa_state_size); - if (sched_verbose >= 5) - fprintf (sched_dump, "saving state for edge %d->%d\n", - f->src->index, f->dest->index); - } + save_state_for_fallthru_edge (last_bb, curr_state); } else { diff --git a/gcc/testsuite/gcc.target/powerpc/pr105586.c b/gcc/testsuite/gcc.target/powerpc/pr105586.c new file mode 100644 index 00000000000..bd397f58bc0 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr105586.c @@ -0,0 +1,19 @@ +/* { dg-options "-mdejagnu-tune=power4 -O2 -fcompare-debug -fno-if-conversion -fno-guess-branch-probability" } */ + +extern int bar(int i); + +typedef unsigned long u64; +int g; + +__int128 h; + +void +foo(int a, int b) { + int i; + char u8_1 = g, u8_3 = a; + u64 u64_1 = bar(0), u64_3 = u8_3 * u64_1; + __int128 u128_1 = h ^ __builtin_expect(i, 0); + u64 u64_4 = u64_1 << ((__builtin_sub_overflow_p(0, u8_1, (u64)0) ^ u128_1) & 8); + u64 u64_r = b + u64_3 + u64_4; + bar((short)u64_r + u8_3); +}