From patchwork Thu Aug 16 15:50:45 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: will schmidt X-Patchwork-Id: 958437 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=gcc.gnu.org (client-ip=209.132.180.131; helo=sourceware.org; envelope-from=gcc-patches-return-483785-incoming=patchwork.ozlabs.org@gcc.gnu.org; receiver=) Authentication-Results: ozlabs.org; dmarc=none (p=none dis=none) header.from=vnet.ibm.com Authentication-Results: ozlabs.org; dkim=pass (1024-bit key; unprotected) header.d=gcc.gnu.org header.i=@gcc.gnu.org header.b="UqwfTaPd"; dkim-atps=neutral Received: from sourceware.org (server1.sourceware.org [209.132.180.131]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 41rrR83cBHz9s3Z for ; Fri, 17 Aug 2018 01:51:16 +1000 (AEST) DomainKey-Signature: a=rsa-sha1; c=nofws; d=gcc.gnu.org; h=list-id :list-unsubscribe:list-archive:list-post:list-help:sender :subject:from:reply-to:to:cc:in-reply-to:references:content-type :date:mime-version:content-transfer-encoding:message-id; q=dns; s=default; b=W7kfNUpsTakJfXH4Iqa1LFKkulK968xFjkteuMMlbHChrhaTRd 1oHBgrUys3vlDFURbT+oSkwOMHkrZxOTADxWUW/EM6sxbM+L/2gn8Ahv/oehaTHS dsjJHoouHkEX0yRV5oE3rKOggvDtxxNc9By1ZeasCDBxaj3m844htfPgY= DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=gcc.gnu.org; h=list-id :list-unsubscribe:list-archive:list-post:list-help:sender :subject:from:reply-to:to:cc:in-reply-to:references:content-type :date:mime-version:content-transfer-encoding:message-id; s= default; bh=/uWAOOCuqlni9ZsxSCWi0A5NEwM=; b=UqwfTaPd8Qg4kUInHEbD sOVEY8+qTo+SEa2fC6ugAhZxohqG0GcKa7B6S2eLjHL4YCjoTqSHooIeWwZMoro4 PqW51Ovo0wXClnYI+gBlNyb4Yr91jGkdqcGIdvLJj8cTgoOn7uUAYaqPb8niNsP6 ILV01xOvZ8jIWjhDZk8Whr4= Received: (qmail 14953 invoked by alias); 16 Aug 2018 15:50:58 -0000 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 Received: (qmail 14578 invoked by uid 89); 16 Aug 2018 15:50:55 -0000 Authentication-Results: sourceware.org; auth=none X-Spam-SWARE-Status: No, score=-27.0 required=5.0 tests=AWL, BAYES_00, GIT_PATCH_0, GIT_PATCH_1, GIT_PATCH_2, GIT_PATCH_3, RCVD_IN_DNSWL_LOW, SPF_PASS autolearn=ham version=3.3.2 spammy=H*Ad:D*vnet.ibm.com, forced, sk:treeve, sk:tree-ve X-HELO: mx0a-001b2d01.pphosted.com Received: from mx0a-001b2d01.pphosted.com (HELO mx0a-001b2d01.pphosted.com) (148.163.156.1) by sourceware.org (qpsmtpd/0.93/v0.84-503-g423c35a) with ESMTP; Thu, 16 Aug 2018 15:50:53 +0000 Received: from pps.filterd (m0098399.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.16.0.22/8.16.0.22) with SMTP id w7GFkWgh057701 for ; Thu, 16 Aug 2018 11:50:51 -0400 Received: from e34.co.us.ibm.com (e34.co.us.ibm.com [32.97.110.152]) by mx0a-001b2d01.pphosted.com with ESMTP id 2kwbnxhksb-1 (version=TLSv1.2 cipher=AES256-GCM-SHA384 bits=256 verify=NOT) for ; Thu, 16 Aug 2018 11:50:50 -0400 Received: from localhost by e34.co.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Thu, 16 Aug 2018 09:50:49 -0600 Received: from b03cxnp08028.gho.boulder.ibm.com (9.17.130.20) by e34.co.us.ibm.com (192.168.1.134) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; (version=TLSv1/SSLv3 cipher=AES256-GCM-SHA384 bits=256/256) Thu, 16 Aug 2018 09:50:47 -0600 Received: from b03ledav005.gho.boulder.ibm.com (b03ledav005.gho.boulder.ibm.com [9.17.130.236]) by b03cxnp08028.gho.boulder.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id w7GFokuV11141526 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=FAIL); Thu, 16 Aug 2018 08:50:46 -0700 Received: from b03ledav005.gho.boulder.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 22609BE05F; Thu, 16 Aug 2018 09:50:46 -0600 (MDT) Received: from b03ledav005.gho.boulder.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 9CBE5BE04F; Thu, 16 Aug 2018 09:50:45 -0600 (MDT) Received: from [9.10.86.107] (unknown [9.10.86.107]) by b03ledav005.gho.boulder.ibm.com (Postfix) with ESMTP; Thu, 16 Aug 2018 09:50:45 -0600 (MDT) Subject: [PATCH, RFC, rs6000, v2] folding of vec_splat From: Will Schmidt Reply-To: will_schmidt@vnet.ibm.com To: Bill Schmidt Cc: Richard Biener , Segher Boessenkool , Bill Schmidt , David Edelsohn , GCC Patches In-Reply-To: <6E9306D6-B8A1-42F6-90E9-0E6CC7AC66FA@linux.ibm.com> References: <1533669927.4452.14.camel@brimstone.rchland.ibm.com> <6E9306D6-B8A1-42F6-90E9-0E6CC7AC66FA@linux.ibm.com> Date: Thu, 16 Aug 2018 10:50:45 -0500 Mime-Version: 1.0 x-cbid: 18081615-0016-0000-0000-0000091B9D1C X-IBM-SpamModules-Scores: X-IBM-SpamModules-Versions: BY=3.00009555; HX=3.00000242; KW=3.00000007; PH=3.00000004; SC=3.00000266; SDB=6.01074402; UDB=6.00553674; IPR=6.00854360; MB=3.00022757; MTD=3.00000008; XFM=3.00000015; UTC=2018-08-16 15:50:48 X-IBM-AV-DETECTION: SAVI=unused REMOTE=unused XFE=unused x-cbparentid: 18081615-0017-0000-0000-000040051C7F Message-Id: <1534434645.18801.8.camel@brimstone.rchland.ibm.com> X-IsSubscribed: yes Hi Enable GIMPLE folding of the vec_splat() intrinsic. (v2). This uses the tree_vec_extract() function out of tree-vect-generic.c to retrieve the splat value, which is a BIT_FIELD_REF. That function is made non-static as part of this change. Testcases are already in-tree. V2 updates, per feedback previously received. Forced arg1 into range (modulo #elements) before attempting to extract the splat value. Removed the (now unnecessary) code that did bounds-checking before calling the tree_vec_extract helper. Used arg0_type rather than lhs_type for calculating the tree size. OK for trunk? Thanks, -Will [gcc] 2018-08-16 Will Schmidt * config/rs6000/rs6000.c (rs6000_gimple_fold_builtin): Add support for early gimple folding of vec_splat(). * tree-vect-generic.c: Remove static from tree_vec_extract() definition. * gimple-fold.h: Add an extern define for tree_vec_extract(). diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c index 97b922f..ec92e6a 100644 --- a/gcc/config/rs6000/rs6000.c +++ b/gcc/config/rs6000/rs6000.c @@ -15766,10 +15766,58 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi) tree splat_tree = build_vector_from_val (TREE_TYPE (lhs), splat_value); g = gimple_build_assign (lhs, splat_tree); gimple_set_location (g, gimple_location (stmt)); gsi_replace (gsi, g, true); return true; + } + + /* Flavors of vec_splat. */ + /* a = vec_splat (b, 0x3) becomes a = { b[3],b[3],b[3],...}; */ + case ALTIVEC_BUILTIN_VSPLTB: + case ALTIVEC_BUILTIN_VSPLTH: + case ALTIVEC_BUILTIN_VSPLTW: + case VSX_BUILTIN_XXSPLTD_V2DI: + case VSX_BUILTIN_XXSPLTD_V2DF: + { + arg0 = gimple_call_arg (stmt, 0); /* input vector. */ + arg1 = gimple_call_arg (stmt, 1); /* index into arg0. */ + /* Only fold the vec_splat_*() if arg1 is a constant + 5-bit unsigned literal. */ + if (TREE_CODE (arg1) != INTEGER_CST || TREE_INT_CST_LOW (arg1) > 0x1f) + return false; + lhs = gimple_call_lhs (stmt); + tree lhs_type = TREE_TYPE (lhs); + tree arg0_type = TREE_TYPE (arg0); + tree arg1_type = TREE_TYPE (arg1); + int n_elts = VECTOR_CST_NELTS (arg0); + /* force arg1 into range. */ + tree new_arg1 = build_int_cst (arg1_type, + TREE_INT_CST_LOW (arg1) % n_elts); + tree splat; + if (TREE_CODE (arg0) == VECTOR_CST) + splat = VECTOR_CST_ELT (arg0, TREE_INT_CST_LOW (new_arg1)); + else + { + /* Determine (in bits) the length and start location of the + splat value for a call to the tree_vec_extract helper. */ + int tree_size_in_bits = TREE_INT_CST_LOW (size_in_bytes (arg0_type)) + * BITS_PER_UNIT; + int splat_elem_size = tree_size_in_bits / n_elts; + int splat_start_bit = TREE_INT_CST_LOW (new_arg1) * splat_elem_size; + /* Do not attempt to early-fold if the size + specified offset into + the vector would touch outside of the source vector. */ + tree len = build_int_cst (bitsizetype, splat_elem_size); + tree start = build_int_cst (bitsizetype, splat_start_bit); + splat = tree_vec_extract (gsi, TREE_TYPE (lhs_type), arg0, + len, start); + } + /* And finally, build the new vector. */ + tree splat_tree = build_vector_from_val (lhs_type, splat); + g = gimple_build_assign (lhs, splat_tree); + gimple_set_location (g, gimple_location (stmt)); + gsi_replace (gsi, g, true); + return true; } /* vec_mergel (integrals). */ case ALTIVEC_BUILTIN_VMRGLH: case ALTIVEC_BUILTIN_VMRGLW: diff --git a/gcc/gimple-fold.h b/gcc/gimple-fold.h index 04e9bfa..e634180 100644 --- a/gcc/gimple-fold.h +++ b/gcc/gimple-fold.h @@ -59,10 +59,11 @@ extern tree gimple_fold_indirect_ref (tree); extern bool gimple_fold_builtin_sprintf (gimple_stmt_iterator *); extern bool gimple_fold_builtin_snprintf (gimple_stmt_iterator *); extern bool arith_code_with_undefined_signed_overflow (tree_code); extern gimple_seq rewrite_to_defined_overflow (gimple *); extern void replace_call_with_value (gimple_stmt_iterator *, tree); +extern tree tree_vec_extract (gimple_stmt_iterator *, tree, tree, tree, tree); /* gimple_build, functionally matching fold_buildN, outputs stmts int the provided sequence, matching and simplifying them on-the-fly. Supposed to replace force_gimple_operand (fold_buildN (...), ...). */ extern tree gimple_build (gimple_seq *, location_t, diff --git a/gcc/tree-vect-generic.c b/gcc/tree-vect-generic.c index 909f790..1c9701d 100644 --- a/gcc/tree-vect-generic.c +++ b/gcc/tree-vect-generic.c @@ -118,11 +118,11 @@ build_word_mode_vector_type (int nunits) typedef tree (*elem_op_func) (gimple_stmt_iterator *, tree, tree, tree, tree, tree, enum tree_code, tree); -static inline tree +tree tree_vec_extract (gimple_stmt_iterator *gsi, tree type, tree t, tree bitsize, tree bitpos) { if (TREE_CODE (t) == SSA_NAME) {