From 6eed64b96d886da2518d86eae5bc0a5ed66cabe0 Mon Sep 17 00:00:00 2001 From: Richard Sandiford Date: Wed, 13 Nov 2019 09:05:59 +0000 Subject: [PATCH] Avoid accounting for non-existent vector loop versioning vect_analyze_loop_costing uses two profitability thresholds: a runtime one and a static compile-time one. The runtime one is simply the point at which the vector loop is cheaper than the scalar loop, while the static one also takes into account the cost of choosing between the scalar and vector loops at runtime. We compare this static cost against the expected execution frequency to decide whether it's worth generating any vector code at all. However, we never reclaimed the cost of applying the runtime threshold if it turned out that the vector code can always be used. And we only know whether that's true once we've calculated what the runtime threshold would be. 2019-11-13 Richard Sandiford gcc/ * tree-vectorizer.h (vect_apply_runtime_profitability_check_p): New function. * tree-vect-loop-manip.c (vect_loop_versioning): Use it. * tree-vect-loop.c (vect_analyze_loop_2): Likewise. (vect_transform_loop): Likewise. (vect_analyze_loop_costing): Don't take the cost of versioning into account for the static profitability threshold if it turns out that no versioning is needed. From-SVN: r278124 --- gcc/ChangeLog | 11 +++++++++++ gcc/tree-vect-loop-manip.c | 3 +-- gcc/tree-vect-loop.c | 34 +++++++++++++++++++++++++--------- gcc/tree-vectorizer.h | 11 +++++++++++ 4 files changed, 48 insertions(+), 11 deletions(-) diff --git a/gcc/ChangeLog b/gcc/ChangeLog index fbf586dc1b5..e7b04334fb5 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,14 @@ +2019-11-13 Richard Sandiford + + * tree-vectorizer.h (vect_apply_runtime_profitability_check_p): + New function. + * tree-vect-loop-manip.c (vect_loop_versioning): Use it. + * tree-vect-loop.c (vect_analyze_loop_2): Likewise. + (vect_transform_loop): Likewise. + (vect_analyze_loop_costing): Don't take the cost of versioning + into account for the static profitability threshold if it turns + out that no versioning is needed. + 2019-11-13 Jan Hubicka * ipa.c (cgraph_build_static_cdtor): Pass optimization_default_node diff --git a/gcc/tree-vect-loop-manip.c b/gcc/tree-vect-loop-manip.c index 559d59bbe78..beee5fe088e 100644 --- a/gcc/tree-vect-loop-manip.c +++ b/gcc/tree-vect-loop-manip.c @@ -3171,8 +3171,7 @@ vect_loop_versioning (loop_vec_info loop_vinfo) = LOOP_REQUIRES_VERSIONING_FOR_SIMD_IF_COND (loop_vinfo); unsigned th = LOOP_VINFO_COST_MODEL_THRESHOLD (loop_vinfo); - if (th >= vect_vf_for_cost (loop_vinfo) - && !LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo) + if (vect_apply_runtime_profitability_check_p (loop_vinfo) && !ordered_p (th, versioning_threshold)) cond_expr = fold_build2 (GE_EXPR, boolean_type_node, scalar_loop_iters, build_int_cst (TREE_TYPE (scalar_loop_iters), diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index 75ec9e67a5c..83fb8486640 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -1690,6 +1690,24 @@ vect_analyze_loop_costing (loop_vec_info loop_vinfo) return 0; } + /* The static profitablity threshold min_profitable_estimate includes + the cost of having to check at runtime whether the scalar loop + should be used instead. If it turns out that we don't need or want + such a check, the threshold we should use for the static estimate + is simply the point at which the vector loop becomes more profitable + than the scalar loop. */ + if (min_profitable_estimate > min_profitable_iters + && !LOOP_REQUIRES_VERSIONING (loop_vinfo) + && !LOOP_VINFO_PEELING_FOR_NITER (loop_vinfo) + && !LOOP_VINFO_PEELING_FOR_ALIGNMENT (loop_vinfo) + && !vect_apply_runtime_profitability_check_p (loop_vinfo)) + { + if (dump_enabled_p ()) + dump_printf_loc (MSG_NOTE, vect_location, "no need for a runtime" + " choice between the scalar and vector loops\n"); + min_profitable_estimate = min_profitable_iters; + } + HOST_WIDE_INT estimated_niter; /* If we are vectorizing an epilogue then we know the maximum number of @@ -2226,8 +2244,7 @@ start_over: /* Use the same condition as vect_transform_loop to decide when to use the cost to determine a versioning threshold. */ - if (th >= vect_vf_for_cost (loop_vinfo) - && !LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo) + if (vect_apply_runtime_profitability_check_p (loop_vinfo) && ordered_p (th, niters_th)) niters_th = ordered_max (poly_uint64 (th), niters_th); @@ -8250,14 +8267,13 @@ vect_transform_loop (loop_vec_info loop_vinfo) run at least the (estimated) vectorization factor number of times checking is pointless, too. */ th = LOOP_VINFO_COST_MODEL_THRESHOLD (loop_vinfo); - if (th >= vect_vf_for_cost (loop_vinfo) - && !LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)) + if (vect_apply_runtime_profitability_check_p (loop_vinfo)) { - if (dump_enabled_p ()) - dump_printf_loc (MSG_NOTE, vect_location, - "Profitability threshold is %d loop iterations.\n", - th); - check_profitability = true; + if (dump_enabled_p ()) + dump_printf_loc (MSG_NOTE, vect_location, + "Profitability threshold is %d loop iterations.\n", + th); + check_profitability = true; } /* Make sure there exists a single-predecessor exit bb. Do this before diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h index e93ccc74c66..56a9a156993 100644 --- a/gcc/tree-vectorizer.h +++ b/gcc/tree-vectorizer.h @@ -1556,6 +1556,17 @@ vect_get_scalar_dr_size (dr_vec_info *dr_info) return tree_to_uhwi (TYPE_SIZE_UNIT (TREE_TYPE (DR_REF (dr_info->dr)))); } +/* Return true if LOOP_VINFO requires a runtime check for whether the + vector loop is profitable. */ + +inline bool +vect_apply_runtime_profitability_check_p (loop_vec_info loop_vinfo) +{ + unsigned int th = LOOP_VINFO_COST_MODEL_THRESHOLD (loop_vinfo); + return (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo) + && th >= vect_vf_for_cost (loop_vinfo)); +} + /* Source location + hotness information. */ extern dump_user_location_t vect_location; -- 2.30.2