From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp-out1.suse.de (smtp-out1.suse.de [195.135.220.28]) by sourceware.org (Postfix) with ESMTPS id 3196B3858C50 for ; Fri, 14 Oct 2022 09:51:22 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 3196B3858C50 Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=suse.de Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=suse.de Received: from imap2.suse-dmz.suse.de (imap2.suse-dmz.suse.de [192.168.254.74]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-521) server-digest SHA512) (No client certificate requested) by smtp-out1.suse.de (Postfix) with ESMTPS id E336F219EE for ; Fri, 14 Oct 2022 09:51:20 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=suse.de; s=susede2_rsa; t=1665741080; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc: mime-version:mime-version:content-type:content-type; bh=BWogg2MFSQ0jzz79UQPrDIvQxlPq9VeeM+cleioGQe0=; b=TmtgY0C+cACwLnHypcNkeS4cpGv9fnIv5RDfHMgrP28r55EnBK5Woo7ijadNqWEGExc+j2 xf7jQm8zfe9kFJiyvcw4qWwtjklZgw1+7Pwivv0fYDHfkHVXdrhSueiMF+671RJN7RMnZH wqx2tmZZ8kBJRDbUUVMD6/oLIvjAw48= DKIM-Signature: v=1; a=ed25519-sha256; c=relaxed/relaxed; d=suse.de; s=susede2_ed25519; t=1665741080; h=from:from:reply-to:date:date:message-id:message-id:to:to:cc: mime-version:mime-version:content-type:content-type; bh=BWogg2MFSQ0jzz79UQPrDIvQxlPq9VeeM+cleioGQe0=; b=P6eq+l3yRNS/0FLCNHqTzsNjyA22wCvh953RdTk4nt9HsExPfx0gLI314e8Jioqx965ZYe P/xmf3XWrIp47XDg== Received: from imap2.suse-dmz.suse.de (imap2.suse-dmz.suse.de [192.168.254.74]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (P-521) server-digest SHA512) (No client certificate requested) by imap2.suse-dmz.suse.de (Postfix) with ESMTPS id D070313A4A for ; Fri, 14 Oct 2022 09:51:20 +0000 (UTC) Received: from dovecot-director2.suse.de ([192.168.254.65]) by imap2.suse-dmz.suse.de with ESMTPSA id fLjAMRgxSWOiLgAAMHmgww (envelope-from ) for ; Fri, 14 Oct 2022 09:51:20 +0000 Date: Fri, 14 Oct 2022 11:51:20 +0200 (CEST) From: Richard Biener To: gcc-patches@gcc.gnu.org Subject: [PATCH] tree-optimization/107254 - check and support live lanes from permutes MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Message-Id: <20221014095120.D070313A4A@imap2.suse-dmz.suse.de> X-Spam-Status: No, score=-11.8 required=5.0 tests=BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,GIT_PATCH_0,SPF_HELO_NONE,SPF_PASS,TXREP autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org List-Id: The following fixes an omission from adding SLP permute nodes which is live lanes originating from those. We have to check that we can extract the lane and have to actually code generate them. Bootstrapped on x86_64-unknown-linux-gnu, testing in progress. PR tree-optimization/107254 * tree-vect-slp.cc (vect_slp_analyze_node_operations_1): For permutes also analyze live lanes. (vect_schedule_slp_node): For permutes also code generate live lane extracts. * gfortran.dg/vect/pr107254.f90: New testcase. --- gcc/testsuite/gfortran.dg/vect/pr107254.f90 | 49 +++++++++++++++++++++ gcc/tree-vect-slp.cc | 33 +++++++++++--- 2 files changed, 77 insertions(+), 5 deletions(-) create mode 100644 gcc/testsuite/gfortran.dg/vect/pr107254.f90 diff --git a/gcc/testsuite/gfortran.dg/vect/pr107254.f90 b/gcc/testsuite/gfortran.dg/vect/pr107254.f90 new file mode 100644 index 00000000000..85bcb5f3fa2 --- /dev/null +++ b/gcc/testsuite/gfortran.dg/vect/pr107254.f90 @@ -0,0 +1,49 @@ +! { dg-do run } + +subroutine dlartg( f, g, s, r ) + implicit none + double precision :: f, g, r, s + double precision :: d, p + + d = sqrt( f*f + g*g ) + p = 1.d0 / d + if( abs( f ) > 1 ) then + s = g*sign( p, f ) + r = sign( d, f ) + else + s = g*sign( p, f ) + r = sign( d, f ) + end if +end subroutine + +subroutine dhgeqz( n, h, t ) + implicit none + integer n + double precision h( n, * ), t( n, * ) + integer jc + double precision c, s, temp, temp2, tempr + temp2 = 10d0 + call dlartg( 10d0, temp2, s, tempr ) + c = 0.9d0 + s = 1.d0 + do jc = 1, n + temp = c*h( 1, jc ) + s*h( 2, jc ) + h( 2, jc ) = -s*h( 1, jc ) + c*h( 2, jc ) + h( 1, jc ) = temp + temp2 = c*t( 1, jc ) + s*t( 2, jc ) + t( 2, jc ) = -s*t( 1, jc ) + c*t( 2, jc ) + t( 1, jc ) = temp2 + enddo +end subroutine dhgeqz + +program test + implicit none + double precision h(2,2), t(2,2) + h = 0 + t(1,1) = 1 + t(2,1) = 0 + t(1,2) = 0 + t(2,2) = 0 + call dhgeqz( 2, h, t ) + if (t(2,2).ne.0) STOP 1 +end program test diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc index cea5d50da92..e54414f6bef 100644 --- a/gcc/tree-vect-slp.cc +++ b/gcc/tree-vect-slp.cc @@ -5933,7 +5933,23 @@ vect_slp_analyze_node_operations_1 (vec_info *vinfo, slp_tree node, /* Handle purely internal nodes. */ if (SLP_TREE_CODE (node) == VEC_PERM_EXPR) - return vectorizable_slp_permutation (vinfo, NULL, node, cost_vec); + { + if (!vectorizable_slp_permutation (vinfo, NULL, node, cost_vec)) + return false; + + stmt_vec_info slp_stmt_info; + unsigned int i; + FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), i, slp_stmt_info) + { + if (STMT_VINFO_LIVE_P (slp_stmt_info) + && !vectorizable_live_operation (vinfo, + slp_stmt_info, NULL, node, + node_instance, i, + false, cost_vec)) + return false; + } + return true; + } gcc_assert (STMT_SLP_TYPE (stmt_info) != loop_vect); @@ -8900,8 +8916,6 @@ vect_schedule_slp_node (vec_info *vinfo, } } - bool done_p = false; - /* Handle purely internal nodes. */ if (SLP_TREE_CODE (node) == VEC_PERM_EXPR) { @@ -8912,9 +8926,18 @@ vect_schedule_slp_node (vec_info *vinfo, but open-code it here (partly). */ bool done = vectorizable_slp_permutation (vinfo, &si, node, NULL); gcc_assert (done); - done_p = true; + stmt_vec_info slp_stmt_info; + unsigned int i; + FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), i, slp_stmt_info) + if (STMT_VINFO_LIVE_P (slp_stmt_info)) + { + done = vectorizable_live_operation (vinfo, + slp_stmt_info, &si, node, + instance, i, true, NULL); + gcc_assert (done); + } } - if (!done_p) + else vect_transform_stmt (vinfo, stmt_info, &si, node, instance); } -- 2.35.3