From patchwork Mon Oct 10 12:29:52 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Kai Tietz X-Patchwork-Id: 118728 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from sourceware.org (server1.sourceware.org [209.132.180.131]) by ozlabs.org (Postfix) with SMTP id 97B3CB70BD for ; Mon, 10 Oct 2011 23:30:27 +1100 (EST) Received: (qmail 28579 invoked by alias); 10 Oct 2011 12:30:17 -0000 Received: (qmail 28526 invoked by uid 22791); 10 Oct 2011 12:30:12 -0000 X-SWARE-Spam-Status: No, hits=-1.8 required=5.0 tests=AWL, BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_AU, FREEMAIL_ENVFROM_END_DIGIT, FREEMAIL_FROM, RCVD_IN_DNSWL_LOW X-Spam-Check-By: sourceware.org Received: from mail-vx0-f175.google.com (HELO mail-vx0-f175.google.com) (209.85.220.175) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Mon, 10 Oct 2011 12:29:54 +0000 Received: by vcbfl17 with SMTP id fl17so5270738vcb.20 for ; Mon, 10 Oct 2011 05:29:53 -0700 (PDT) MIME-Version: 1.0 Received: by 10.52.91.11 with SMTP id ca11mr13099765vdb.8.1318249793038; Mon, 10 Oct 2011 05:29:53 -0700 (PDT) Received: by 10.220.180.5 with HTTP; Mon, 10 Oct 2011 05:29:52 -0700 (PDT) In-Reply-To: References: <14d7ea4a-5238-423e-8341-30e8a8db52dd@zmail06.collab.prod.int.phx2.redhat.com> Date: Mon, 10 Oct 2011 14:29:52 +0200 Message-ID: Subject: Re: [patch tree-optimization]: Improve handling of conditional-branches on targets with high branch costs From: Kai Tietz To: Richard Guenther Cc: Kai Tietz , gcc-patches@gcc.gnu.org, Richard Henderson X-IsSubscribed: yes Mailing-List: contact gcc-patches-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Id: List-Unsubscribe: List-Archive: List-Post: List-Help: Sender: gcc-patches-owner@gcc.gnu.org Delivered-To: mailing list gcc-patches@gcc.gnu.org Recent patch had a thinko on rhs of inner lhs check for TRUTH-IF. It has to be checked that the LHS code is same as outer CODE, as otherwise we wouldn't apply different TRUTH-IF only on inner RHS of LHS, which is of course wrong. static tree extract_muldiv (tree, tree, enum tree_code, tree, bool *); @@ -3500,7 +3499,7 @@ optimize_bit_field_compare (location_t l return lhs; } -/* Subroutine for fold_truthop: decode a field reference. +/* Subroutine for fold_truth_andor_1: decode a field reference. If EXP is a comparison reference, we return the innermost reference. @@ -3668,17 +3667,43 @@ sign_bit_p (tree exp, const_tree val) return NULL_TREE; } -/* Subroutine for fold_truthop: determine if an operand is simple enough +/* Subroutine for fold_truth_andor_1: determine if an operand is simple enough to be evaluated unconditionally. */ static int -simple_operand_p (const_tree exp) +simple_operand_p (tree exp) { + enum tree_code code; /* Strip any conversions that don't change the machine mode. */ STRIP_NOPS (exp); + code = TREE_CODE (exp); + + /* Handle some trivials */ + if (TREE_CODE_CLASS (code) == tcc_comparison) + return (tree_could_trap_p (exp) + && simple_operand_p (TREE_OPERAND (exp, 0)) + && simple_operand_p (TREE_OPERAND (exp, 1))); + + if (FLOAT_TYPE_P (TREE_TYPE (exp)) + && tree_could_trap_p (exp)) + return false; + + switch (code) + { + case SSA_NAME: + return true; + case TRUTH_NOT_EXPR: + return simple_operand_p (TREE_OPERAND (exp, 0)); + case BIT_NOT_EXPR: + if (TREE_CODE (TREE_TYPE (exp)) != BOOLEAN_TYPE) + return false; + return simple_operand_p (TREE_OPERAND (exp, 0)); + default: + break; + } + return (CONSTANT_CLASS_P (exp) - || TREE_CODE (exp) == SSA_NAME || (DECL_P (exp) && ! TREE_ADDRESSABLE (exp) && ! TREE_THIS_VOLATILE (exp) @@ -4888,7 +4913,7 @@ fold_range_test (location_t loc, enum tr return 0; } -/* Subroutine for fold_truthop: C is an INTEGER_CST interpreted as a P +/* Subroutine for fold_truth_andor_1: C is an INTEGER_CST interpreted as a P bit value. Arrange things so the extra bits will be set to zero if and only if C is signed-extended to its full width. If MASK is nonzero, it is an INTEGER_CST that should be AND'ed with the extra bits. */ @@ -5025,8 +5050,8 @@ merge_truthop_with_opposite_arm (locatio We return the simplified tree or 0 if no optimization is possible. */ static tree -fold_truthop (location_t loc, enum tree_code code, tree truth_type, - tree lhs, tree rhs) +fold_truth_andor_1 (location_t loc, enum tree_code code, tree truth_type, + tree lhs, tree rhs) { /* If this is the "or" of two comparisons, we can do something if the comparisons are NE_EXPR. If this is the "and", we can do something @@ -5054,8 +5079,6 @@ fold_truthop (location_t loc, enum tree_ tree lntype, rntype, result; HOST_WIDE_INT first_bit, end_bit; int volatilep; - tree orig_lhs = lhs, orig_rhs = rhs; - enum tree_code orig_code = code; /* Start by getting the comparison codes. Fail if anything is volatile. If one operand is a BIT_AND_EXPR with the constant one, treat it as if @@ -5119,8 +5142,7 @@ fold_truthop (location_t loc, enum tree_ /* If the RHS can be evaluated unconditionally and its operands are simple, it wins to evaluate the RHS unconditionally on machines with expensive branches. In this case, this isn't a comparison - that can be merged. Avoid doing this if the RHS is a floating-point - comparison since those can trap. */ + that can be merged. */ if (BRANCH_COST (optimize_function_for_speed_p (cfun), false) >= 2 @@ -5149,13 +5171,6 @@ fold_truthop (location_t loc, enum tree_ build2 (BIT_IOR_EXPR, TREE_TYPE (ll_arg), ll_arg, rl_arg), build_int_cst (TREE_TYPE (ll_arg), 0)); - - if (LOGICAL_OP_NON_SHORT_CIRCUIT) - { - if (code != orig_code || lhs != orig_lhs || rhs != orig_rhs) - return build2_loc (loc, code, truth_type, lhs, rhs); - return NULL_TREE; - } } /* See if the comparisons can be merged. Then get all the parameters for @@ -8380,13 +8395,46 @@ fold_truth_andor (location_t loc, enum t lhs is another similar operation, try to merge its rhs with our rhs. Then try to merge our lhs and rhs. */ if (TREE_CODE (arg0) == code - && 0 != (tem = fold_truthop (loc, code, type, - TREE_OPERAND (arg0, 1), arg1))) + && 0 != (tem = fold_truth_andor_1 (loc, code, type, + TREE_OPERAND (arg0, 1), arg1))) return fold_build2_loc (loc, code, type, TREE_OPERAND (arg0, 0), tem); - if ((tem = fold_truthop (loc, code, type, arg0, arg1)) != 0) + if ((tem = fold_truth_andor_1 (loc, code, type, arg0, arg1)) != 0) return tem; + if ((code == TRUTH_ANDIF_EXPR || code == TRUTH_ORIF_EXPR) + && (BRANCH_COST (optimize_function_for_speed_p (cfun), + false) >= 2) + && !TREE_SIDE_EFFECTS (arg1) + && LOGICAL_OP_NON_SHORT_CIRCUIT + && simple_operand_p (arg1)) + { + enum tree_code ncode = (code == TRUTH_ANDIF_EXPR ? TRUTH_AND_EXPR + : TRUTH_OR_EXPR); + + /* We don't want to pack more then two leafs to an non-IF + If tree-code of left-hand operand isn't an AND/OR-IF code and not + equal to CODE, then we don't want to add right-hand operand. + If the inner right-hand side of left-hand operand has side-effects, + or isn't simple, then we can't add to it, as otherwise we might + destroy if-sequence. */ + if (TREE_CODE (arg0) == code + /* Needed for sequence points to handle trappings, and + side-effects. */ + && !TREE_SIDE_EFFECTS (TREE_OPERAND (arg0, 1)) + && simple_operand_p (TREE_OPERAND (arg0, 1))) + { + tem = fold_build2_loc (loc, ncode, type, TREE_OPERAND (arg0, 1), + arg1); + return fold_build2_loc (loc, code, type, TREE_OPERAND (arg0, 0), + tem); + } + /* Needed for sequence points to handle trappings, and side-effects. */ + else if (!TREE_SIDE_EFFECTS (arg0) + && simple_operand_p (arg0)) + return fold_build2_loc (loc, ncode, type, arg0, arg1); + } + return NULL_TREE; } Index: gcc/gcc/fold-const.c =================================================================== --- gcc.orig/gcc/fold-const.c +++ gcc/gcc/fold-const.c @@ -111,14 +111,13 @@ static tree decode_field_reference (loca tree *, tree *); static int all_ones_mask_p (const_tree, int); static tree sign_bit_p (tree, const_tree); -static int simple_operand_p (const_tree); +static int simple_operand_p (tree); static tree range_binop (enum tree_code, tree, tree, int, tree, int); static tree range_predecessor (tree); static tree range_successor (tree); static tree fold_range_test (location_t, enum tree_code, tree, tree, tree); static tree fold_cond_expr_with_comparison (location_t, tree, tree, tree, tree); static tree unextend (tree, int, int, tree); -static tree fold_truthop (location_t, enum tree_code, tree, tree, tree); static tree optimize_minmax_comparison (location_t, enum tree_code, tree, tree, tree);