This avoids vectorizing a possibly trapping operation when lanes are handled in different BBs. I spotted this when working on the originally reported issue in PR100778.
Bootstrapped and tested on x86_64-unknown-linux-gnu, pushed. 2021-05-28 Richard Biener <rguent...@suse.de> PR tree-optimization/100778 * tree-vect-slp.c (vect_build_slp_tree_1): Prevent possibly trapping ops in different BBs. * gcc.dg/vect/bb-slp-pr100778-1.c: New testcase. --- gcc/testsuite/gcc.dg/vect/bb-slp-pr100778-1.c | 18 ++++++++++++++++++ gcc/tree-vect-slp.c | 4 ++-- 2 files changed, 20 insertions(+), 2 deletions(-) create mode 100644 gcc/testsuite/gcc.dg/vect/bb-slp-pr100778-1.c diff --git a/gcc/testsuite/gcc.dg/vect/bb-slp-pr100778-1.c b/gcc/testsuite/gcc.dg/vect/bb-slp-pr100778-1.c new file mode 100644 index 00000000000..9f8b7eecef1 --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/bb-slp-pr100778-1.c @@ -0,0 +1,18 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target vect_double } */ + +double foo (int x, double *p) +{ + double res = p[0] + p[1]; + double tem = p[0] / x; + if (x) + { + p[0] = tem; + p[1] /= x; + } + return res + tem; +} + +/* We may not SLP vectorize the FP division because it can trap and it + is distributed between two basic-blocks. */ +/* { dg-final { scan-tree-dump "Build SLP failed: different BB for PHI or possibly trapping operation in _\[0-9\]+ = _\[0-9\]+ / _\[0-9\]+;" "slp2" } } */ diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c index 0ec92b0f0ca..ca1539e63f2 100644 --- a/gcc/tree-vect-slp.c +++ b/gcc/tree-vect-slp.c @@ -1214,14 +1214,14 @@ vect_build_slp_tree_1 (vec_info *vinfo, unsigned char *swap, } } - if (phi_p + if ((phi_p || gimple_could_trap_p (stmt_info->stmt)) && (gimple_bb (first_stmt_info->stmt) != gimple_bb (stmt_info->stmt))) { if (dump_enabled_p ()) dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location, "Build SLP failed: different BB for PHI " - "in %G", stmt); + "or possibly trapping operation in %G", stmt); /* Mismatch. */ continue; } -- 2.26.2