From patchwork Tue May 31 01:52:46 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: HAO CHEN GUI X-Patchwork-Id: 1637182 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: bilbo.ozlabs.org; dkim=pass (1024-bit key; unprotected) header.d=gcc.gnu.org header.i=@gcc.gnu.org header.a=rsa-sha256 header.s=default header.b=yR0ygSJx; dkim-atps=neutral Authentication-Results: ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=gcc.gnu.org (client-ip=8.43.85.97; helo=sourceware.org; envelope-from=gcc-patches-bounces+incoming=patchwork.ozlabs.org@gcc.gnu.org; receiver=) Received: from sourceware.org (ip-8-43-85-97.sourceware.org [8.43.85.97]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by bilbo.ozlabs.org (Postfix) with ESMTPS id 4LBwKg6shHz9s0w for ; Tue, 31 May 2022 11:53:26 +1000 (AEST) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id B1E7D382FE48 for ; Tue, 31 May 2022 01:53:23 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org B1E7D382FE48 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1653962003; bh=Ee2mBOSYoE1tt2u2cTkRCYTlI3qyQGZ7DpCZiyTrHi4=; h=Date:To:Subject:List-Id:List-Unsubscribe:List-Archive:List-Post: List-Help:List-Subscribe:From:Reply-To:Cc:From; b=yR0ygSJx7MdA7SOjTTh15xVFsTWQkhw1pLi6rkx9LTo1hWmr5UJhOV4Ci8B6NbSqS bdR9+WOv+mgINVHiKaxnAkr4FQ2BGdVl/pp9sV24XJhCatmokIycw8ctVta1QOOi6I MYUvtSvQnaIbI7u2/tfHaMG+itTrAhNapO7lH3kI= X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from mx0a-001b2d01.pphosted.com (mx0a-001b2d01.pphosted.com [148.163.156.1]) by sourceware.org (Postfix) with ESMTPS id 9078C383065E for ; Tue, 31 May 2022 01:53:01 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 9078C383065E Received: from pps.filterd (m0098399.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.17.1.5/8.17.1.5) with ESMTP id 24V0naDd013645; Tue, 31 May 2022 01:52:57 GMT Received: from pps.reinject (localhost [127.0.0.1]) by mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 3gd8tp8rt9-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Tue, 31 May 2022 01:52:57 +0000 Received: from m0098399.ppops.net (m0098399.ppops.net [127.0.0.1]) by pps.reinject (8.17.1.5/8.17.1.5) with ESMTP id 24V1om7g000319; Tue, 31 May 2022 01:52:56 GMT Received: from ppma04ams.nl.ibm.com (63.31.33a9.ip4.static.sl-reverse.com [169.51.49.99]) by mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 3gd8tp8rsv-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Tue, 31 May 2022 01:52:56 +0000 Received: from pps.filterd (ppma04ams.nl.ibm.com [127.0.0.1]) by ppma04ams.nl.ibm.com (8.16.1.2/8.16.1.2) with SMTP id 24V1pmEq020172; Tue, 31 May 2022 01:52:54 GMT Received: from b06avi18626390.portsmouth.uk.ibm.com (b06avi18626390.portsmouth.uk.ibm.com [9.149.26.192]) by ppma04ams.nl.ibm.com with ESMTP id 3gbcae3c17-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Tue, 31 May 2022 01:52:53 +0000 Received: from d06av23.portsmouth.uk.ibm.com (d06av23.portsmouth.uk.ibm.com [9.149.105.59]) by b06avi18626390.portsmouth.uk.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 24V1cTc232899542 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Tue, 31 May 2022 01:38:29 GMT Received: from d06av23.portsmouth.uk.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id CFB3AA404D; Tue, 31 May 2022 01:52:50 +0000 (GMT) Received: from d06av23.portsmouth.uk.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 935F3A4051; Tue, 31 May 2022 01:52:48 +0000 (GMT) Received: from [9.197.232.7] (unknown [9.197.232.7]) by d06av23.portsmouth.uk.ibm.com (Postfix) with ESMTP; Tue, 31 May 2022 01:52:48 +0000 (GMT) Message-ID: Date: Tue, 31 May 2022 09:52:46 +0800 MIME-Version: 1.0 User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101 Thunderbird/91.9.1 Content-Language: en-US To: gcc-patches Subject: [PATCH v5, rs6000] Add V1TI into vector comparison expand [PR103316] X-TM-AS-GCONF: 00 X-Proofpoint-ORIG-GUID: sMO0I48Y_wUEZZBTxKjWbbsUnlNU8fae X-Proofpoint-GUID: Avn-ovB2Yj5gKfNie60m72Tpw-3WRJLC X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.205,Aquarius:18.0.874,Hydra:6.0.517,FMLib:17.11.64.514 definitions=2022-05-30_10,2022-05-30_03,2022-02-23_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 impostorscore=0 lowpriorityscore=0 bulkscore=0 phishscore=0 mlxlogscore=999 priorityscore=1501 spamscore=0 clxscore=1015 malwarescore=0 mlxscore=0 suspectscore=0 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2204290000 definitions=main-2205310005 X-Spam-Status: No, score=-12.8 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_EF, GIT_PATCH_0, KAM_SHORT, RCVD_IN_MSPIKE_H2, SPF_HELO_NONE, SPF_PASS, TXREP, T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6 X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on server2.sourceware.org X-BeenThere: gcc-patches@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gcc-patches mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-Patchwork-Original-From: HAO CHEN GUI via Gcc-patches From: HAO CHEN GUI Reply-To: HAO CHEN GUI Cc: Peter Bergner , David , Segher Boessenkool Errors-To: gcc-patches-bounces+incoming=patchwork.ozlabs.org@gcc.gnu.org Sender: "Gcc-patches" Hi, This patch adds V1TI mode into a new mode iterator used in vector comparison shift and rotation expands. Without the patch, the comparisons between two vector __int128 are converted to scalar comparisons and code is suboptimal. The patch fixes the issue. Now all comparisons between two vector __int128 generates P10 new comparison instructions. Also the relative built-ins generate the same instructions after gimple folding. So they're added back to the folding list. This patch also merges some vector comparison shift and rotation expands for V1T1 and other vector integer modes as they have the similar patterns. The expands for V1TI only are removed. Bootstrapped and tested on ppc64 Linux BE and LE with no regressions. Is this okay for trunk? Any recommendations? Thanks a lot. ChangeLog 2022-05-24 Haochen Gui gcc/ PR target/103316 * config/rs6000/rs6000-builtin.cc (rs6000_gimple_fold_builtin): Enable gimple folding for RS6000_BIF_VCMPEQUT, RS6000_BIF_VCMPNET, RS6000_BIF_CMPGE_1TI, RS6000_BIF_CMPGE_U1TI, RS6000_BIF_VCMPGTUT, RS6000_BIF_VCMPGTST, RS6000_BIF_CMPLE_1TI, RS6000_BIF_CMPLE_U1TI. * config/rs6000/vector.md (VEC_IC): New mode iterator. Add support for new Power10 V1TI instructions. (vec_cmp): Set mode iterator to VEC_IC. (vec_cmpu): Likewise. (vector_nlt): Set mode iterator to VEC_IC. (vector_nltv1ti): Remove. (vector_gtu): Set mode iterator to VEC_IC. (vector_gtuv1ti): Remove. (vector_nltu): Set mode iterator to VEC_IC. (vector_nltuv1ti): Remove. (vector_geu): Set mode iterator to VEC_IC. (vector_ngt): Likewise. (vector_ngtv1ti): Remove. (vector_ngtu): Set mode iterator to VEC_IC. (vector_ngtuv1ti): Remove. (vector_gtu__p): Set mode iterator to VEC_IC. (vector_gtu_v1ti_p): Remove. (vrotl3): Set mode iterator to VEC_IC. Emit insns for V1TI. (vrotlv1ti3): Remove. (vashr3): Set mode iterator to VEC_IC. Emit insns for V1TI. (vashrv1ti3): Remove. gcc/testsuite/ PR target/103316 * gcc.target/powerpc/pr103316.c: New. * gcc.target/powerpc/fold-vec-cmp-int128.c: New. patch.diff diff --git a/gcc/config/rs6000/rs6000-builtin.cc b/gcc/config/rs6000/rs6000-builtin.cc index e925ba9fad9..b67f4e066a8 100644 --- a/gcc/config/rs6000/rs6000-builtin.cc +++ b/gcc/config/rs6000/rs6000-builtin.cc @@ -2000,16 +2000,14 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi) case RS6000_BIF_VCMPEQUH: case RS6000_BIF_VCMPEQUW: case RS6000_BIF_VCMPEQUD: - /* We deliberately omit RS6000_BIF_VCMPEQUT for now, because gimple - folding produces worse code for 128-bit compares. */ + case RS6000_BIF_VCMPEQUT: fold_compare_helper (gsi, EQ_EXPR, stmt); return true; case RS6000_BIF_VCMPNEB: case RS6000_BIF_VCMPNEH: case RS6000_BIF_VCMPNEW: - /* We deliberately omit RS6000_BIF_VCMPNET for now, because gimple - folding produces worse code for 128-bit compares. */ + case RS6000_BIF_VCMPNET: fold_compare_helper (gsi, NE_EXPR, stmt); return true; @@ -2021,9 +2019,8 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi) case RS6000_BIF_CMPGE_U4SI: case RS6000_BIF_CMPGE_2DI: case RS6000_BIF_CMPGE_U2DI: - /* We deliberately omit RS6000_BIF_CMPGE_1TI and RS6000_BIF_CMPGE_U1TI - for now, because gimple folding produces worse code for 128-bit - compares. */ + case RS6000_BIF_CMPGE_1TI: + case RS6000_BIF_CMPGE_U1TI: fold_compare_helper (gsi, GE_EXPR, stmt); return true; @@ -2035,9 +2032,8 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi) case RS6000_BIF_VCMPGTUW: case RS6000_BIF_VCMPGTUD: case RS6000_BIF_VCMPGTSD: - /* We deliberately omit RS6000_BIF_VCMPGTUT and RS6000_BIF_VCMPGTST - for now, because gimple folding produces worse code for 128-bit - compares. */ + case RS6000_BIF_VCMPGTUT: + case RS6000_BIF_VCMPGTST: fold_compare_helper (gsi, GT_EXPR, stmt); return true; @@ -2049,9 +2045,8 @@ rs6000_gimple_fold_builtin (gimple_stmt_iterator *gsi) case RS6000_BIF_CMPLE_U4SI: case RS6000_BIF_CMPLE_2DI: case RS6000_BIF_CMPLE_U2DI: - /* We deliberately omit RS6000_BIF_CMPLE_1TI and RS6000_BIF_CMPLE_U1TI - for now, because gimple folding produces worse code for 128-bit - compares. */ + case RS6000_BIF_CMPLE_1TI: + case RS6000_BIF_CMPLE_U1TI: fold_compare_helper (gsi, LE_EXPR, stmt); return true; diff --git a/gcc/config/rs6000/vector.md b/gcc/config/rs6000/vector.md index 4d0797c48f8..a0d33d2f604 100644 --- a/gcc/config/rs6000/vector.md +++ b/gcc/config/rs6000/vector.md @@ -26,6 +26,9 @@ ;; Vector int modes (define_mode_iterator VEC_I [V16QI V8HI V4SI V2DI]) +;; Vector int modes for comparison, shift and rotation +(define_mode_iterator VEC_IC [V16QI V8HI V4SI V2DI (V1TI "TARGET_POWER10")]) + ;; 128-bit int modes (define_mode_iterator VEC_TI [V1TI TI]) @@ -533,10 +536,10 @@ (define_expand "vcond_mask_" ;; For signed integer vectors comparison. (define_expand "vec_cmp" - [(set (match_operand:VEC_I 0 "vint_operand") + [(set (match_operand:VEC_IC 0 "vint_operand") (match_operator 1 "signed_or_equality_comparison_operator" - [(match_operand:VEC_I 2 "vint_operand") - (match_operand:VEC_I 3 "vint_operand")]))] + [(match_operand:VEC_IC 2 "vint_operand") + (match_operand:VEC_IC 3 "vint_operand")]))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" { enum rtx_code code = GET_CODE (operands[1]); @@ -573,10 +576,10 @@ (define_expand "vec_cmp" ;; For unsigned integer vectors comparison. (define_expand "vec_cmpu" - [(set (match_operand:VEC_I 0 "vint_operand") + [(set (match_operand:VEC_IC 0 "vint_operand") (match_operator 1 "unsigned_or_equality_comparison_operator" - [(match_operand:VEC_I 2 "vint_operand") - (match_operand:VEC_I 3 "vint_operand")]))] + [(match_operand:VEC_IC 2 "vint_operand") + (match_operand:VEC_IC 3 "vint_operand")]))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" { enum rtx_code code = GET_CODE (operands[1]); @@ -690,116 +693,65 @@ (define_expand "vector_gt" ; >= for integer vectors: swap operands and apply not-greater-than (define_expand "vector_nlt" - [(set (match_operand:VEC_I 3 "vlogical_operand") - (gt:VEC_I (match_operand:VEC_I 2 "vlogical_operand") - (match_operand:VEC_I 1 "vlogical_operand"))) - (set (match_operand:VEC_I 0 "vlogical_operand") - (not:VEC_I (match_dup 3)))] + [(set (match_operand:VEC_IC 3 "vlogical_operand") + (gt:VEC_IC (match_operand:VEC_IC 2 "vlogical_operand") + (match_operand:VEC_IC 1 "vlogical_operand"))) + (set (match_operand:VEC_IC 0 "vlogical_operand") + (not:VEC_IC (match_dup 3)))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" { operands[3] = gen_reg_rtx_and_attrs (operands[0]); }) -(define_expand "vector_nltv1ti" - [(set (match_operand:V1TI 3 "vlogical_operand") - (gt:V1TI (match_operand:V1TI 2 "vlogical_operand") - (match_operand:V1TI 1 "vlogical_operand"))) - (set (match_operand:V1TI 0 "vlogical_operand") - (not:V1TI (match_dup 3)))] - "TARGET_POWER10" -{ - operands[3] = gen_reg_rtx_and_attrs (operands[0]); -}) - (define_expand "vector_gtu" - [(set (match_operand:VEC_I 0 "vint_operand") - (gtu:VEC_I (match_operand:VEC_I 1 "vint_operand") - (match_operand:VEC_I 2 "vint_operand")))] + [(set (match_operand:VEC_IC 0 "vint_operand") + (gtu:VEC_IC (match_operand:VEC_IC 1 "vint_operand") + (match_operand:VEC_IC 2 "vint_operand")))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" "") -(define_expand "vector_gtuv1ti" - [(set (match_operand:V1TI 0 "altivec_register_operand") - (gtu:V1TI (match_operand:V1TI 1 "altivec_register_operand") - (match_operand:V1TI 2 "altivec_register_operand")))] - "TARGET_POWER10" - "") - ; >= for integer vectors: swap operands and apply not-greater-than (define_expand "vector_nltu" - [(set (match_operand:VEC_I 3 "vlogical_operand") - (gtu:VEC_I (match_operand:VEC_I 2 "vlogical_operand") - (match_operand:VEC_I 1 "vlogical_operand"))) - (set (match_operand:VEC_I 0 "vlogical_operand") - (not:VEC_I (match_dup 3)))] + [(set (match_operand:VEC_IC 3 "vlogical_operand") + (gtu:VEC_IC (match_operand:VEC_IC 2 "vlogical_operand") + (match_operand:VEC_IC 1 "vlogical_operand"))) + (set (match_operand:VEC_IC 0 "vlogical_operand") + (not:VEC_IC (match_dup 3)))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" { operands[3] = gen_reg_rtx_and_attrs (operands[0]); }) -(define_expand "vector_nltuv1ti" - [(set (match_operand:V1TI 3 "vlogical_operand") - (gtu:V1TI (match_operand:V1TI 2 "vlogical_operand") - (match_operand:V1TI 1 "vlogical_operand"))) - (set (match_operand:V1TI 0 "vlogical_operand") - (not:V1TI (match_dup 3)))] - "TARGET_POWER10" -{ - operands[3] = gen_reg_rtx_and_attrs (operands[0]); -}) - (define_expand "vector_geu" - [(set (match_operand:VEC_I 0 "vint_operand") - (geu:VEC_I (match_operand:VEC_I 1 "vint_operand") - (match_operand:VEC_I 2 "vint_operand")))] + [(set (match_operand:VEC_IC 0 "vint_operand") + (geu:VEC_IC (match_operand:VEC_IC 1 "vint_operand") + (match_operand:VEC_IC 2 "vint_operand")))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" "") ; <= for integer vectors: apply not-greater-than (define_expand "vector_ngt" - [(set (match_operand:VEC_I 3 "vlogical_operand") - (gt:VEC_I (match_operand:VEC_I 1 "vlogical_operand") - (match_operand:VEC_I 2 "vlogical_operand"))) - (set (match_operand:VEC_I 0 "vlogical_operand") - (not:VEC_I (match_dup 3)))] + [(set (match_operand:VEC_IC 3 "vlogical_operand") + (gt:VEC_IC (match_operand:VEC_IC 1 "vlogical_operand") + (match_operand:VEC_IC 2 "vlogical_operand"))) + (set (match_operand:VEC_IC 0 "vlogical_operand") + (not:VEC_IC (match_dup 3)))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" { operands[3] = gen_reg_rtx_and_attrs (operands[0]); }) -(define_expand "vector_ngtv1ti" - [(set (match_operand:V1TI 3 "vlogical_operand") - (gt:V1TI (match_operand:V1TI 1 "vlogical_operand") - (match_operand:V1TI 2 "vlogical_operand"))) - (set (match_operand:V1TI 0 "vlogical_operand") - (not:V1TI (match_dup 3)))] - "TARGET_POWER10" -{ - operands[3] = gen_reg_rtx_and_attrs (operands[0]); -}) - (define_expand "vector_ngtu" - [(set (match_operand:VEC_I 3 "vlogical_operand") - (gtu:VEC_I (match_operand:VEC_I 1 "vlogical_operand") - (match_operand:VEC_I 2 "vlogical_operand"))) - (set (match_operand:VEC_I 0 "vlogical_operand") - (not:VEC_I (match_dup 3)))] + [(set (match_operand:VEC_IC 3 "vlogical_operand") + (gtu:VEC_IC (match_operand:VEC_IC 1 "vlogical_operand") + (match_operand:VEC_IC 2 "vlogical_operand"))) + (set (match_operand:VEC_IC 0 "vlogical_operand") + (not:VEC_IC (match_dup 3)))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" { operands[3] = gen_reg_rtx_and_attrs (operands[0]); }) -(define_expand "vector_ngtuv1ti" - [(set (match_operand:V1TI 3 "vlogical_operand") - (gtu:V1TI (match_operand:V1TI 1 "vlogical_operand") - (match_operand:V1TI 2 "vlogical_operand"))) - (set (match_operand:V1TI 0 "vlogical_operand") - (not:V1TI (match_dup 3)))] - "TARGET_POWER10" -{ - operands[3] = gen_reg_rtx_and_attrs (operands[0]); -}) - ; There are 14 possible vector FP comparison operators, gt and eq of them have ; been expanded above, so just support 12 remaining operators here. @@ -1189,27 +1141,15 @@ (define_expand "vector_ge__p" (define_expand "vector_gtu__p" [(parallel [(set (reg:CC CR6_REGNO) - (unspec:CC [(gtu:CC (match_operand:VEC_I 1 "vint_operand") - (match_operand:VEC_I 2 "vint_operand"))] + (unspec:CC [(gtu:CC (match_operand:VEC_IC 1 "vint_operand") + (match_operand:VEC_IC 2 "vint_operand"))] UNSPEC_PREDICATE)) - (set (match_operand:VEC_I 0 "vlogical_operand") - (gtu:VEC_I (match_dup 1) - (match_dup 2)))])] + (set (match_operand:VEC_IC 0 "vlogical_operand") + (gtu:VEC_IC (match_dup 1) + (match_dup 2)))])] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" "") -(define_expand "vector_gtu_v1ti_p" - [(parallel - [(set (reg:CC CR6_REGNO) - (unspec:CC [(gtu:CC (match_operand:V1TI 1 "altivec_register_operand") - (match_operand:V1TI 2 "altivec_register_operand"))] - UNSPEC_PREDICATE)) - (set (match_operand:V1TI 0 "altivec_register_operand") - (gtu:V1TI (match_dup 1) - (match_dup 2)))])] - "TARGET_POWER10" - "") - ;; AltiVec/VSX predicates. ;; This expansion is triggered during expansion of predicate built-in @@ -1582,25 +1522,21 @@ (define_expand "vec_shr_" ;; Expanders for rotate each element in a vector (define_expand "vrotl3" - [(set (match_operand:VEC_I 0 "vint_operand") - (rotate:VEC_I (match_operand:VEC_I 1 "vint_operand") - (match_operand:VEC_I 2 "vint_operand")))] + [(set (match_operand:VEC_IC 0 "vint_operand") + (rotate:VEC_IC (match_operand:VEC_IC 1 "vint_operand") + (match_operand:VEC_IC 2 "vint_operand")))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" - "") - -(define_expand "vrotlv1ti3" - [(set (match_operand:V1TI 0 "vsx_register_operand" "=v") - (rotate:V1TI (match_operand:V1TI 1 "vsx_register_operand" "v") - (match_operand:V1TI 2 "vsx_register_operand" "v")))] - "TARGET_POWER10" { - /* Shift amount in needs to be put in bits[57:63] of 128-bit operand2. */ - rtx tmp = gen_reg_rtx (V1TImode); + /* Shift amount in needs to be put in bits[57:63] of 128-bit operand2. */ + if (mode == V1TImode) + { + rtx tmp = gen_reg_rtx (V1TImode); - emit_insn (gen_xxswapd_v1ti (tmp, operands[2])); - emit_insn (gen_altivec_vrlq (operands[0], operands[1], tmp)); - DONE; -}) + emit_insn (gen_xxswapd_v1ti (tmp, operands[2])); + emit_insn (gen_altivec_vrlq (operands[0], operands[1], tmp)); + DONE; + } + }) ;; Expanders for rotatert to make use of vrotl (define_expand "vrotr3" @@ -1663,25 +1599,20 @@ (define_expand "vlshr3" ;; Expanders for arithmetic shift right on each vector element (define_expand "vashr3" - [(set (match_operand:VEC_I 0 "vint_operand") - (ashiftrt:VEC_I (match_operand:VEC_I 1 "vint_operand") - (match_operand:VEC_I 2 "vint_operand")))] + [(set (match_operand:VEC_IC 0 "vint_operand") + (ashiftrt:VEC_IC (match_operand:VEC_IC 1 "vint_operand") + (match_operand:VEC_IC 2 "vint_operand")))] "VECTOR_UNIT_ALTIVEC_OR_VSX_P (mode)" - "") - -;; No immediate version of this 128-bit instruction -(define_expand "vashrv1ti3" - [(set (match_operand:V1TI 0 "vsx_register_operand" "=v") - (ashiftrt:V1TI (match_operand:V1TI 1 "vsx_register_operand" "v") - (match_operand:V1TI 2 "vsx_register_operand" "v")))] - "TARGET_POWER10" { - /* Shift amount in needs to be put into bits[57:63] of 128-bit operand2. */ - rtx tmp = gen_reg_rtx (V1TImode); + /* Shift amount in needs to be put in bits[57:63] of 128-bit operand2. */ + if (mode == V1TImode) + { + rtx tmp = gen_reg_rtx (V1TImode); - emit_insn (gen_xxswapd_v1ti (tmp, operands[2])); - emit_insn (gen_altivec_vsraq (operands[0], operands[1], tmp)); - DONE; + emit_insn (gen_xxswapd_v1ti (tmp, operands[2])); + emit_insn (gen_altivec_vsraq (operands[0], operands[1], tmp)); + DONE; + } }) diff --git a/gcc/testsuite/gcc.target/powerpc/fold-vec-cmp-int128.c b/gcc/testsuite/gcc.target/powerpc/fold-vec-cmp-int128.c new file mode 100644 index 00000000000..fe667b9cb50 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/fold-vec-cmp-int128.c @@ -0,0 +1,87 @@ +/* Verify that overloaded built-ins for vec_cmp with __int128 + inputs produce the right code. */ + +/* { dg-do compile } */ +/* { dg-require-effective-target power10_ok } */ +/* { dg-require-effective-target int128 } */ +/* { dg-options "-mdejagnu-cpu=power10 -O2" } */ + +#include + +vector bool __int128 +test_eq (vector signed __int128 x, vector signed __int128 y) +{ + return vec_cmpeq (x, y); +} + +vector bool __int128 +testu_eq (vector unsigned __int128 x, vector unsigned __int128 y) +{ + return vec_cmpeq (x, y); +} + +vector bool __int128 +test_ge (vector signed __int128 x, vector signed __int128 y) +{ + return vec_cmpge (x, y); +} + +vector bool __int128 +testu_ge (vector unsigned __int128 x, vector unsigned __int128 y) +{ + return vec_cmpge (x, y); +} + +vector bool __int128 +test_gt (vector signed __int128 x, vector signed __int128 y) +{ + return vec_cmpgt (x, y); +} + +vector bool __int128 +testu_gt (vector unsigned __int128 x, vector unsigned __int128 y) +{ + return vec_cmpgt (x, y); +} + +vector bool __int128 +test_le (vector signed __int128 x, vector signed __int128 y) +{ + return vec_cmple (x, y); +} + +vector bool __int128 +testu_le (vector unsigned __int128 x, vector unsigned __int128 y) +{ + return vec_cmple (x, y); +} + +vector bool __int128 +test_lt (vector signed __int128 x, vector signed __int128 y) +{ + return vec_cmplt (x, y); +} + +vector bool __int128 +testu_lt (vector unsigned __int128 x, vector unsigned __int128 y) +{ + return vec_cmplt (x, y); +} + +vector bool __int128 +test_ne (vector signed __int128 x, vector signed __int128 y) +{ + return vec_cmpne (x, y); +} + +vector bool __int128 +testu_ne (vector unsigned __int128 x, vector unsigned __int128 y) +{ + return vec_cmpne (x, y); +} + +/* { dg-final { scan-assembler-times "vcmpequq" 4 } } */ +/* { dg-final { scan-assembler-times "vcmpgtsq" 4 } } */ +/* { dg-final { scan-assembler-times "vcmpgtuq" 4 } } */ +/* { dg-final { scan-assembler-times "xxlnor" 6 } } */ + diff --git a/gcc/testsuite/gcc.target/powerpc/pr103316.c b/gcc/testsuite/gcc.target/powerpc/pr103316.c new file mode 100644 index 00000000000..9f1ba791cc5 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr103316.c @@ -0,0 +1,81 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target power10_ok } */ +/* { dg-require-effective-target int128 } */ +/* { dg-options "-mdejagnu-cpu=power10 -O2" } */ + +vector bool __int128 +test_eq (vector signed __int128 a, vector signed __int128 b) +{ + return a == b; +} + +vector bool __int128 +test_ne (vector signed __int128 a, vector signed __int128 b) +{ + return a != b; +} + +vector bool __int128 +test_gt (vector signed __int128 a, vector signed __int128 b) +{ + return a > b; +} + +vector bool __int128 +test_ge (vector signed __int128 a, vector signed __int128 b) +{ + return a >= b; +} + +vector bool __int128 +test_lt (vector signed __int128 a, vector signed __int128 b) +{ + return a < b; +} + +vector bool __int128 +test_le (vector signed __int128 a, vector signed __int128 b) +{ + return a <= b; +} + +vector bool __int128 +testu_eq (vector unsigned __int128 a, vector unsigned __int128 b) +{ + return a == b; +} + +vector bool __int128 +testu_ne (vector unsigned __int128 a, vector unsigned __int128 b) +{ + return a != b; +} + +vector bool __int128 +testu_gt (vector unsigned __int128 a, vector unsigned __int128 b) +{ + return a > b; +} + +vector bool __int128 +testu_ge (vector unsigned __int128 a, vector unsigned __int128 b) +{ + return a >= b; +} + +vector bool __int128 +testu_lt (vector unsigned __int128 a, vector unsigned __int128 b) +{ + return a < b; +} + +vector bool __int128 +testu_le (vector unsigned __int128 a, vector unsigned __int128 b) +{ + return a <= b; +} + +/* { dg-final { scan-assembler-times "vcmpequq" 4 } } */ +/* { dg-final { scan-assembler-times "vcmpgtsq" 4 } } */ +/* { dg-final { scan-assembler-times "vcmpgtuq" 4 } } */ +/* { dg-final { scan-assembler-times "xxlnor" 6 } } */