From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 1130) id 39B1E3858D28; Tue, 31 Jan 2023 15:03:53 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 39B1E3858D28 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1675177433; bh=casvvuCBM8LT6fILBaUKd/Afik8hQphO//y/GYS6594=; h=From:To:Subject:Date:From; b=pxLGSbn70G889yQ9lQkjywvUTjF4QOBGz0OWXglvLMYOAGHoZ/o6DrOUccZe6eKxW fQwfaFpDYFJae8deOchWqYTJ23/ENWk530dXJ2lb9mOi0TNpQmI7MBIjMTMxxDsWg8 Sq5i6RhdZjGZDTmjdSKf2i0ehINez61kwQ2GNKQU= MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="utf-8" From: Richard Sandiford To: gcc-cvs@gcc.gnu.org Subject: [gcc r13-5580] vect: Fix single def-use cycle for ifn reductions [PR108608] X-Act-Checkin: gcc X-Git-Author: Richard Sandiford X-Git-Refname: refs/heads/trunk X-Git-Oldrev: 1626ec53e8c1b9c245572417d380e3ed84990cff X-Git-Newrev: 2bb444787ed17a9e786f544cdf51ee2ac6779ab2 Message-Id: <20230131150353.39B1E3858D28@sourceware.org> Date: Tue, 31 Jan 2023 15:03:53 +0000 (GMT) List-Id: https://gcc.gnu.org/g:2bb444787ed17a9e786f544cdf51ee2ac6779ab2 commit r13-5580-g2bb444787ed17a9e786f544cdf51ee2ac6779ab2 Author: Richard Sandiford Date: Tue Jan 31 15:03:43 2023 +0000 vect: Fix single def-use cycle for ifn reductions [PR108608] The patch that added support for fmin/fmax reductions didn't handle single def-use cycles. In some ways, this seems like going out of our way to make things slower, but that's a discussion for another day. gcc/ PR tree-optimization/108608 * tree-vect-loop.cc (vect_transform_reduction): Handle single def-use cycles that involve function calls rather than tree codes. gcc/testsuite/ PR tree-optimization/108608 * gcc.dg/vect/pr108608.c: New test. * gcc.target/aarch64/sve/pr108608-1.c: Likewise. Diff: --- gcc/testsuite/gcc.dg/vect/pr108608.c | 24 +++++++++++++++++++++++ gcc/testsuite/gcc.target/aarch64/sve/pr108608-1.c | 9 +++++++++ gcc/tree-vect-loop.cc | 22 ++++++++++++--------- 3 files changed, 46 insertions(+), 9 deletions(-) diff --git a/gcc/testsuite/gcc.dg/vect/pr108608.c b/gcc/testsuite/gcc.dg/vect/pr108608.c new file mode 100644 index 00000000000..e968141ba03 --- /dev/null +++ b/gcc/testsuite/gcc.dg/vect/pr108608.c @@ -0,0 +1,24 @@ +#include "tree-vect.h" + +double __attribute__((noipa)) +foo (double m, float *ptr) +{ + for (int i = 0; i < 256; i++) + m = __builtin_fmax (m, ptr[i]); + return m; +} + +int +main (void) +{ + check_vect (); + float ptr[256]; + for (int j = 0; j < 16; ++j) + { + for (int i = 0; i < 256; ++i) + ptr[i] = i == 128 + j ? 2 + j : i == 161 ? 1 : 0; + if (foo (0, ptr) != 2 + j) + __builtin_abort (); + } + return 0; +} diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pr108608-1.c b/gcc/testsuite/gcc.target/aarch64/sve/pr108608-1.c new file mode 100644 index 00000000000..0a7d485e047 --- /dev/null +++ b/gcc/testsuite/gcc.target/aarch64/sve/pr108608-1.c @@ -0,0 +1,9 @@ +/* { dg-options "-O3" } */ + +double __attribute__((noipa)) +foo (double m, float *ptr) +{ + for (int i = 0; i < 256; i++) + m = __builtin_fmax (m, ptr[i]); + return m; +} diff --git a/gcc/tree-vect-loop.cc b/gcc/tree-vect-loop.cc index f0801c23671..f03af1efd0f 100644 --- a/gcc/tree-vect-loop.cc +++ b/gcc/tree-vect-loop.cc @@ -7755,8 +7755,6 @@ vect_transform_reduction (loop_vec_info loop_vinfo, gimple_match_op op; if (!gimple_extract_op (stmt_info->stmt, &op)) gcc_unreachable (); - gcc_assert (op.code.is_tree_code ()); - auto code = tree_code (op.code); /* All uses but the last are expected to be defined in the loop. The last use is the reduction variable. In case of nested cycle this @@ -7778,7 +7776,8 @@ vect_transform_reduction (loop_vec_info loop_vinfo, vec_num = 1; } - internal_fn cond_fn = get_conditional_internal_fn (code); + code_helper code = canonicalize_code (op.code, op.type); + internal_fn cond_fn = get_conditional_internal_fn (code, op.type); vec_loop_masks *masks = &LOOP_VINFO_MASKS (loop_vinfo); bool mask_by_cond_expr = use_mask_by_cond_expr_p (code, cond_fn, vectype_in); @@ -7802,9 +7801,10 @@ vect_transform_reduction (loop_vec_info loop_vinfo, if (reduction_type == FOLD_LEFT_REDUCTION) { internal_fn reduc_fn = STMT_VINFO_REDUC_FN (reduc_info); + gcc_assert (code.is_tree_code ()); return vectorize_fold_left_reduction - (loop_vinfo, stmt_info, gsi, vec_stmt, slp_node, reduc_def_phi, code, - reduc_fn, op.ops, vectype_in, reduc_index, masks); + (loop_vinfo, stmt_info, gsi, vec_stmt, slp_node, reduc_def_phi, + tree_code (code), reduc_fn, op.ops, vectype_in, reduc_index, masks); } bool single_defuse_cycle = STMT_VINFO_FORCE_SINGLE_CYCLE (reduc_info); @@ -7814,7 +7814,7 @@ vect_transform_reduction (loop_vec_info loop_vinfo, || code == SAD_EXPR); /* Create the destination vector */ - tree scalar_dest = gimple_assign_lhs (stmt_info->stmt); + tree scalar_dest = gimple_get_lhs (stmt_info->stmt); tree vec_dest = vect_create_destination_var (scalar_dest, vectype_out); vect_get_vec_defs (loop_vinfo, stmt_info, slp_node, ncopies, @@ -7849,7 +7849,7 @@ vect_transform_reduction (loop_vec_info loop_vinfo, /* Make sure that the reduction accumulator is vop[0]. */ if (reduc_index == 1) { - gcc_assert (commutative_tree_code (code)); + gcc_assert (commutative_binary_op_p (code, op.type)); std::swap (vop[0], vop[1]); } tree mask = vect_get_loop_mask (gsi, masks, vec_num * ncopies, @@ -7877,11 +7877,15 @@ vect_transform_reduction (loop_vec_info loop_vinfo, if (emulated_mixed_dot_prod) new_stmt = vect_emulate_mixed_dot_prod (loop_vinfo, stmt_info, gsi, vec_dest, vop); + else if (code.is_internal_fn ()) + new_stmt = gimple_build_call_internal (internal_fn (code), + op.num_ops, + vop[0], vop[1], vop[2]); else - new_stmt = gimple_build_assign (vec_dest, code, + new_stmt = gimple_build_assign (vec_dest, tree_code (op.code), vop[0], vop[1], vop[2]); new_temp = make_ssa_name (vec_dest, new_stmt); - gimple_assign_set_lhs (new_stmt, new_temp); + gimple_set_lhs (new_stmt, new_temp); vect_finish_stmt_generation (loop_vinfo, stmt_info, new_stmt, gsi); }