From a54aa75ab30eb1a176ceaded507113252df24878 Mon Sep 17 00:00:00 2001 From: Richard Biener Date: Fri, 29 Nov 2024 12:14:24 +0100 Subject: tree-optimization/115438 - SLP reduction vect vs. bwaves 503.bwaves_r shows a case where the non-SLP optimization of performing the reduction adjustment with the initial value as part of the epilogue rather than including it as part of the initial vector value. It allows to break a critical dependence path. The following restores this ability for single-lane SLP. On Zen2 this turns a 2.5% regression from GCC 14 into a 2.5% improvement. PR tree-optimization/115438 * tree-vect-loop.cc (vect_transform_cycle_phi): For SLP also try to do the reduction adjustment by the initial value in the epilogue. --- gcc/tree-vect-loop.cc | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'gcc/tree-vect-loop.cc') diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index 8c9be48..5a24fb8 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -9193,6 +9193,20 @@ vect_transform_cycle_phi (loop_vec_info loop_vinfo, tree neutral_op = neutral_op_for_reduction (TREE_TYPE (vectype_out), code, initial_value); + /* Try to simplify the vector initialization by applying an + adjustment after the reduction has been performed. This + can also break a critical path but on the other hand + requires to keep the initial value live across the loop. */ + if (neutral_op + && initial_values.length () == 1 + && !reduc_info->reused_accumulator + && STMT_VINFO_DEF_TYPE (stmt_info) == vect_reduction_def + && !operand_equal_p (neutral_op, initial_values[0])) + { + STMT_VINFO_REDUC_EPILOGUE_ADJUSTMENT (reduc_info) + = initial_values[0]; + initial_values[0] = neutral_op; + } get_initial_defs_for_reduction (loop_vinfo, reduc_info, &vec_initial_defs, vec_num, stmts.length (), neutral_op); -- cgit v1.1