From a4abf0fb902816a2508dda5956f407fc27821d88 Mon Sep 17 00:00:00 2001 From: Richard Biener Date: Mon, 7 Apr 2025 11:27:19 +0200 Subject: tree-optimization/119640 - ICE with vectorized shift placement When the whole shift is invariant but the shift amount needs to be converted and a vector shift used we can mess up placement of vector stmts because we do not make SLP scheduling aware of the need to insert code for it. The following mitigates this by more conservative placement of such code in vectorizable_shift. PR tree-optimization/119640 * tree-vect-stmts.cc (vectorizable_shift): Always insert code for one of our SLP operands before the code for the vector shift itself. * gcc.dg/vect/pr119640.c: New testcase. --- gcc/testsuite/gcc.dg/vect/pr119640.c | 17 +++++++++++++++++ gcc/tree-vect-stmts.cc | 11 +++++++---- 2 files changed, 24 insertions(+), 4 deletions(-) create mode 100644 gcc/testsuite/gcc.dg/vect/pr119640.c (limited to 'gcc') diff --git a/gcc/testsuite/gcc.dg/vect/pr119640.c b/gcc/testsuite/gcc.dg/vect/pr119640.c new file mode 100644 index 0000000..8872817 --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/pr119640.c @@ -0,0 +1,17 @@ +/* { dg-do compile } */ +/* { dg-additional-options "-funswitch-loops" } */ + +int save, mask_nbits; + +void execute(long imm) +{ + long shift = 0; + int destReg[4]; + for (unsigned i = 0; i < 4; i++) + { + if (imm) + shift = 1ULL << mask_nbits; + destReg[i] = shift; + save = destReg[0]; + } +} diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc index 3005ae6..7f87435 100644 --- a/gcc/tree-vect-stmts.cc +++ b/gcc/tree-vect-stmts.cc @@ -6750,13 +6750,16 @@ vectorizable_shift (vec_info *vinfo, { if (was_scalar_shift_arg) { - /* If the argument was the same in all lanes create - the correctly typed vector shift amount directly. */ + /* If the argument was the same in all lanes create the + correctly typed vector shift amount directly. Note + we made SLP scheduling think we use the original scalars, + so place the compensation code next to the shift which + is conservative. See PR119640 where it otherwise breaks. */ op1 = fold_convert (TREE_TYPE (vectype), op1); op1 = vect_init_vector (vinfo, stmt_info, op1, TREE_TYPE (vectype), - !loop_vinfo ? gsi : NULL); + gsi); vec_oprnd1 = vect_init_vector (vinfo, stmt_info, op1, vectype, - !loop_vinfo ? gsi : NULL); + gsi); vec_oprnds1.create (slp_node->vec_stmts_size); for (k = 0; k < slp_node->vec_stmts_size; k++) vec_oprnds1.quick_push (vec_oprnd1); -- cgit v1.1