From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 1923) id B7BB83858C33; Wed, 17 Jan 2024 19:14:10 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org B7BB83858C33 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1705518850; bh=uQTAyz88uOncnmmAbKwXja9hh7MsE+ygkURUtZRg/lw=; h=From:To:Subject:Date:From; b=SpsX4dnygVZFrykFGYs282Pp5lBFVr++iyrngoLC+5njBDF3qq4cF/5CBG29DJpH6 6reGNjVjuvmQTGSkVyRTVSNiXquia7vTfPUqODbrcI/zcrDboWcdtvXqM7q35rvNuv 0CqQ6cMdrHGQ1WPNWDyfPCjydVx7Q2os0IYn6tho= Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: Philipp Tomsich To: gcc-cvs@gcc.gnu.org Subject: [gcc(refs/vendors/vrull/heads/slp-improvements)] tree-optimization: use fewer lanes on VEC_PERM_EXPR for two operators X-Act-Checkin: gcc X-Git-Author: Manolis Tsamis X-Git-Refname: refs/vendors/vrull/heads/slp-improvements X-Git-Oldrev: 3f1357f3759fe6fb67345452b31768a703c84893 X-Git-Newrev: eb4b8050767b12680a96ef4d215a3440b5950957 Message-Id: <20240117191410.B7BB83858C33@sourceware.org> Date: Wed, 17 Jan 2024 19:14:10 +0000 (GMT) List-Id: https://gcc.gnu.org/g:eb4b8050767b12680a96ef4d215a3440b5950957 commit eb4b8050767b12680a96ef4d215a3440b5950957 Author: Manolis Tsamis Date: Fri Nov 17 17:42:30 2023 +0100 tree-optimization: use fewer lanes on VEC_PERM_EXPR for two operators Currently when SLP nodes are built with "two_operators == true" the VEC_PERM_EXPR that merges the result selects a lane only based on the operator found. In the case that the input nodes have duplicate elements there may be more than one ways to chose. This commit OBtries to use an existing lane if possible, which can free up lanes that can be used in other optimizations. For example, given two vectors with duplicates: A = {a1, a1, a2, a2} B = {b1, b1, b2, b2} a two_operator node with operators +, -, +, - can be built as: RES = VEC_PERM_EXPR(0, 4, 2, 6) and use 2 lanes with this commit. The existing implementation would have built a (0, 5, 2, 7) permutation and have used 4 lanes. This commit adds a case that if the current element can be found in another lane that has been used previously then that lane will be reused. This can happen when the ONE and TWO contain duplicate elements and reduces the number of 'active' lanes. Diff: --- gcc/tree-vect-slp.cc | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc index 4c56e8d1395..8d4fdc4f836 100644 --- a/gcc/tree-vect-slp.cc +++ b/gcc/tree-vect-slp.cc @@ -2859,7 +2859,25 @@ fail: gassign *ostmt = as_a (ostmt_info->stmt); if (gimple_assign_rhs_code (ostmt) != code0) { - SLP_TREE_LANE_PERMUTATION (node).safe_push (std::make_pair (1, i)); + /* If the current element can be found in another lane that has + been used previously then use that one instead. This can + happen when the ONE and TWO contain duplicate elements and + reduces the number of 'active' lanes. */ + int idx = i; + for (int alt_idx = (int) i - 1; alt_idx >= 0; alt_idx--) + { + gassign *alt_stmt = as_a (stmts[alt_idx]->stmt); + if (gimple_assign_rhs_code (alt_stmt) == code0 + && gimple_assign_rhs1 (ostmt) + == gimple_assign_rhs1 (alt_stmt) + && gimple_assign_rhs2 (ostmt) + == gimple_assign_rhs2 (alt_stmt)) + { + idx = alt_idx; + break; + } + } + SLP_TREE_LANE_PERMUTATION (node).safe_push (std::make_pair (1, idx)); ocode = gimple_assign_rhs_code (ostmt); j = i; }