loop split condition is moved between loop1 and loop2, the split bb's count and probability should also be duplicated instead of (100% vs INV), secondly, the original loop1 and loop2 count need be propotional from the original loop.
Regression tested pass, OK for master? diff base/loop-cond-split-1.c.151t.lsplit patched/loop-cond-split-1.c.151t.lsplit: ... int prephitmp_16; int prephitmp_25; <bb 2> [local count: 118111600]: if (n_7(D) > 0) goto <bb 4>; [89.00%] else goto <bb 3>; [11.00%] <bb 3> [local count: 118111600]: return; <bb 4> [local count: 105119324]: pretmp_3 = ga; - <bb 5> [local count: 955630225]: + <bb 5> [local count: 315357973]: # i_13 = PHI <i_10(20), 0(4)> # prephitmp_12 = PHI <prephitmp_5(20), pretmp_3(4)> if (prephitmp_12 != 0) goto <bb 6>; [33.00%] else goto <bb 7>; [67.00%] - <bb 6> [local count: 315357972]: + <bb 6> [local count: 104068130]: _2 = do_something (); ga = _2; - <bb 7> [local count: 955630225]: + <bb 7> [local count: 315357973]: # prephitmp_5 = PHI <prephitmp_12(5), _2(6)> i_10 = inc (i_13); if (n_7(D) > i_10) goto <bb 21>; [89.00%] else goto <bb 11>; [11.00%] <bb 11> [local count: 105119324]: goto <bb 3>; [100.00%] - <bb 21> [local count: 850510901]: + <bb 21> [local count: 280668596]: if (prephitmp_12 != 0) - goto <bb 20>; [100.00%] + goto <bb 20>; [33.00%] else - goto <bb 19>; [INV] + goto <bb 19>; [67.00%] - <bb 20> [local count: 850510901]: + <bb 20> [local count: 280668596]: goto <bb 5>; [100.00%] - <bb 19> [count: 0]: + <bb 19> [local count: 70429947]: # i_23 = PHI <i_10(21)> # prephitmp_25 = PHI <prephitmp_5(21)> - <bb 12> [local count: 955630225]: + <bb 12> [local count: 640272252]: # i_15 = PHI <i_23(19), i_22(16)> # prephitmp_16 = PHI <prephitmp_25(19), prephitmp_16(16)> i_22 = inc (i_15); if (n_7(D) > i_22) goto <bb 16>; [89.00%] else goto <bb 11>; [11.00%] - <bb 16> [local count: 850510901]: + <bb 16> [local count: 569842305]: goto <bb 12>; [100.00%] } gcc/ChangeLog: * tree-ssa-loop-split.c (split_loop): Fix incorrect probability. (do_split_loop_on_cond): Likewise. --- gcc/tree-ssa-loop-split.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/gcc/tree-ssa-loop-split.c b/gcc/tree-ssa-loop-split.c index 3f6ad046623..d30782888f3 100644 --- a/gcc/tree-ssa-loop-split.c +++ b/gcc/tree-ssa-loop-split.c @@ -575,7 +575,11 @@ split_loop (class loop *loop1) stmts2); tree cond = build2 (guard_code, boolean_type_node, guard_init, border); if (!initial_true) - cond = fold_build1 (TRUTH_NOT_EXPR, boolean_type_node, cond); + cond = fold_build1 (TRUTH_NOT_EXPR, boolean_type_node, cond); + + edge true_edge = EDGE_SUCC (bbs[i], 0)->flags & EDGE_TRUE_VALUE + ? EDGE_SUCC (bbs[i], 0) + : EDGE_SUCC (bbs[i], 1); /* Now version the loop, placing loop2 after loop1 connecting them, and fix up SSA form for that. */ @@ -583,10 +587,10 @@ split_loop (class loop *loop1) basic_block cond_bb; class loop *loop2 = loop_version (loop1, cond, &cond_bb, - profile_probability::always (), - profile_probability::always (), - profile_probability::always (), - profile_probability::always (), + true_edge->probability, + true_edge->probability.invert (), + true_edge->probability, + true_edge->probability.invert (), true); gcc_assert (loop2); @@ -1486,10 +1490,10 @@ do_split_loop_on_cond (struct loop *loop1, edge invar_branch) initialize_original_copy_tables (); struct loop *loop2 = loop_version (loop1, boolean_true_node, NULL, - profile_probability::always (), - profile_probability::never (), - profile_probability::always (), - profile_probability::always (), + invar_branch->probability.invert (), + invar_branch->probability, + invar_branch->probability.invert (), + invar_branch->probability, true); if (!loop2) { @@ -1530,6 +1534,9 @@ do_split_loop_on_cond (struct loop *loop1, edge invar_branch) to_loop1->flags |= true_invar ? EDGE_FALSE_VALUE : EDGE_TRUE_VALUE; to_loop2->flags |= true_invar ? EDGE_TRUE_VALUE : EDGE_FALSE_VALUE; + to_loop1->probability = invar_branch->probability.invert (); + to_loop2->probability = invar_branch->probability; + /* Due to introduction of a control flow edge from loop1 latch to loop2 pre-header, we should update PHIs in loop2 to reflect this connection between loop1 and loop2. */ -- 2.27.0.90.geebb51ba8c