From 108779056eb4b56e715a094fac48a699d2dc91b3 Mon Sep 17 00:00:00 2001 From: Juzhe-Zhong Date: Sun, 10 Sep 2023 10:33:04 +0800 Subject: [PATCH] RISC-V: Expand fixed-vlmax/vls vector permutation in targethook When debugging FAIL: gcc.dg/pr92301.c execution test. Realize a vls vector permutation situation failed to vectorize since early return false: - /* For constant size indices, we dont't need to handle it here. - Just leave it to vec_perm. */ - if (d->perm.length ().is_constant ()) - return false; To avoid more potential failed vectorization case. Now expand it in targethook. gcc/ChangeLog: * config/riscv/riscv-v.cc (shuffle_generic_patterns): Expand fixed-vlmax/vls vector permutation. --- gcc/config/riscv/riscv-v.cc | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/gcc/config/riscv/riscv-v.cc b/gcc/config/riscv/riscv-v.cc index 8a548f5d1a27..847bc2487c84 100644 --- a/gcc/config/riscv/riscv-v.cc +++ b/gcc/config/riscv/riscv-v.cc @@ -2793,14 +2793,9 @@ shuffle_generic_patterns (struct expand_vec_perm_d *d) if (!pow2p_hwi (d->perm.encoding().npatterns ())) return false; - /* For constant size indices, we dont't need to handle it here. - Just leave it to vec_perm. */ - if (d->perm.length ().is_constant ()) - return false; - /* Permuting two SEW8 variable-length vectors need vrgatherei16.vv. Otherwise, it could overflow the index range. */ - if (GET_MODE_INNER (d->vmode) == QImode + if (!nunits.is_constant () && GET_MODE_INNER (d->vmode) == QImode && !get_vector_mode (HImode, nunits).exists (&sel_mode)) return false; @@ -2809,7 +2804,12 @@ shuffle_generic_patterns (struct expand_vec_perm_d *d) return true; rtx sel = vec_perm_indices_to_rtx (sel_mode, d->perm); - expand_vec_perm (d->target, d->op0, d->op1, force_reg (sel_mode, sel)); + /* 'mov' generte interleave vector. */ + if (!nunits.is_constant ()) + sel = force_reg (sel_mode, sel); + /* Some FIXED-VLMAX/VLS vector permutation situations call targethook + instead of expand vec_perm, we handle it directly. */ + expand_vec_perm (d->target, d->op0, d->op1, sel); return true; } -- 2.47.2