From patchwork Thu Mar 17 10:47:40 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Jiufu Guo X-Patchwork-Id: 52045 Return-Path: X-Original-To: patchwork@sourceware.org Delivered-To: patchwork@sourceware.org Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 6975A394FC3A for ; Thu, 17 Mar 2022 10:48:16 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 6975A394FC3A DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1647514096; bh=vTmVHCpuQXl5OirCtY06veOnVU6Uukgh6i10eD4t3NM=; h=To:Subject:Date:List-Id:List-Unsubscribe:List-Archive:List-Post: List-Help:List-Subscribe:From:Reply-To:Cc:From; b=BQOxgG9jSvpVgpc+8vzaKQ/AdAUW8F2seIoMIwiZans8yNa/k1B7PEna7nhayThUQ DDSR6GLmZxLqs6FnmAsiHhqh+wQEO61sDBQTsl1XKsE/MKYPBYtm4hGXdrXK1FLXfe +tjRui+N/eB8pdCW71YGBBFdUSRA3hNl6LbucdMI= X-Original-To: gcc-patches@gcc.gnu.org Delivered-To: gcc-patches@gcc.gnu.org Received: from mx0a-001b2d01.pphosted.com (mx0b-001b2d01.pphosted.com [148.163.158.5]) by sourceware.org (Postfix) with ESMTPS id 203B53857C4A for ; Thu, 17 Mar 2022 10:47:47 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 203B53857C4A Received: from pps.filterd (m0098414.ppops.net [127.0.0.1]) by mx0b-001b2d01.pphosted.com (8.16.1.2/8.16.1.2) with SMTP id 22H7Ntvg015263; Thu, 17 Mar 2022 10:47:46 GMT Received: from pps.reinject (localhost [127.0.0.1]) by mx0b-001b2d01.pphosted.com with ESMTP id 3ev0jh3njh-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Thu, 17 Mar 2022 10:47:46 +0000 Received: from m0098414.ppops.net (m0098414.ppops.net [127.0.0.1]) by pps.reinject (8.16.0.43/8.16.0.43) with SMTP id 22HAjula023873; Thu, 17 Mar 2022 10:47:45 GMT Received: from ppma04fra.de.ibm.com (6a.4a.5195.ip4.static.sl-reverse.com [149.81.74.106]) by mx0b-001b2d01.pphosted.com with ESMTP id 3ev0jh3nj6-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Thu, 17 Mar 2022 10:47:45 +0000 Received: from pps.filterd (ppma04fra.de.ibm.com [127.0.0.1]) by ppma04fra.de.ibm.com (8.16.1.2/8.16.1.2) with SMTP id 22HADdcA012781; Thu, 17 Mar 2022 10:47:44 GMT Received: from b06cxnps3074.portsmouth.uk.ibm.com (d06relay09.portsmouth.uk.ibm.com [9.149.109.194]) by ppma04fra.de.ibm.com with ESMTP id 3erk58sek5-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Thu, 17 Mar 2022 10:47:43 +0000 Received: from d06av22.portsmouth.uk.ibm.com (d06av22.portsmouth.uk.ibm.com [9.149.105.58]) by b06cxnps3074.portsmouth.uk.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 22HAlfL324707368 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Thu, 17 Mar 2022 10:47:41 GMT Received: from d06av22.portsmouth.uk.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id AD2984C044; Thu, 17 Mar 2022 10:47:41 +0000 (GMT) Received: from d06av22.portsmouth.uk.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id DC2534C040; Thu, 17 Mar 2022 10:47:40 +0000 (GMT) Received: from genoa.aus.stglabs.ibm.com (unknown [9.40.192.157]) by d06av22.portsmouth.uk.ibm.com (Postfix) with ESMTP; Thu, 17 Mar 2022 10:47:40 +0000 (GMT) To: gcc-patches@gcc.gnu.org Subject: [PATCH]rs6000: optimize li+rldicr+cmpd==>rotldi+cmpldi for 16bits Date: Thu, 17 Mar 2022 18:47:40 +0800 Message-Id: <20220317104740.4131405-1-guojiufu@linux.ibm.com> X-Mailer: git-send-email 2.25.1 MIME-Version: 1.0 X-TM-AS-GCONF: 00 X-Proofpoint-GUID: _wzC9Voahx4OXfgJepA_easCs5T6lGgs X-Proofpoint-ORIG-GUID: EO0e070SNZsxj3zmWdWW9lDJMnguCy2M X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.205,Aquarius:18.0.850,Hydra:6.0.425,FMLib:17.11.64.514 definitions=2022-03-17_04,2022-03-15_01,2022-02-23_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 bulkscore=0 clxscore=1015 priorityscore=1501 lowpriorityscore=0 spamscore=0 malwarescore=0 mlxlogscore=999 impostorscore=0 adultscore=0 suspectscore=0 mlxscore=0 phishscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2202240000 definitions=main-2203170062 X-Spam-Status: No, score=-11.2 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_EF, GIT_PATCH_0, KAM_SHORT, RCVD_IN_MSPIKE_H4, RCVD_IN_MSPIKE_WL, SPF_HELO_NONE, SPF_PASS, TXREP, T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.4 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) 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: Jiufu Guo via Gcc-patches From: Jiufu Guo Reply-To: Jiufu Guo Cc: dje.gcc@gmail.com, segher@kernel.crashing.org Errors-To: gcc-patches-bounces+patchwork=sourceware.org@gcc.gnu.org Sender: "Gcc-patches" When checking eq/neq with a constant which has only 16bits, then it can be optimized to check the rotated data. By this, the constant building is optimized. As the example in PR103743: For "in == 0x8000000000000000LL", this patch generates: rotldi %r3,%r3,16 cmpldi %cr0,%r3,32768 instead: li %r9,-1 rldicr %r9,%r9,0,0 cmpd %cr0,%r3,%r9 This patch pass bootstrap and regtest on ppc64 and ppc64le. Ok for trunk? Thanks! BR, Jiufu PR target/103743 gcc/ChangeLog: * config/rs6000/rs6000.cc (rot_to_16bits): New function. (rs6000_generate_compare): Compare rotated const for eq. gcc/testsuite/ChangeLog: * gcc.target/powerpc/pr103743.c: New test. * gcc.target/powerpc/pr103743_1.c: New test. --- gcc/config/rs6000/rs6000.cc | 62 +++++++++++++ gcc/testsuite/gcc.target/powerpc/pr103743.c | 48 ++++++++++ gcc/testsuite/gcc.target/powerpc/pr103743_1.c | 87 +++++++++++++++++++ 3 files changed, 197 insertions(+) create mode 100644 gcc/testsuite/gcc.target/powerpc/pr103743.c create mode 100644 gcc/testsuite/gcc.target/powerpc/pr103743_1.c diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc index 3afe78f5d04..4aa1d0ca4ab 100644 --- a/gcc/config/rs6000/rs6000.cc +++ b/gcc/config/rs6000/rs6000.cc @@ -14860,6 +14860,42 @@ rs6000_reverse_condition (machine_mode mode, enum rtx_code code) return reverse_condition (code); } +/* If SRC is a constant with only 16bits, return the number by which + the constant can be rotated to lowest 16bits. + Return 0, if SRC does not meet requirements. + Set *sgn to 1 if the rotated cst is negative, otherwise set it to 0. + Set *res_cst to the rotated constant. */ + +static int +rot_to_16bits (rtx src, machine_mode mode, bool *sgn, rtx *res_cst) +{ + if (!(src && CONST_INT_P (src))) + return 0; + + unsigned HOST_WIDE_INT C = INTVAL (src); + + /* If all 0 except low 16bits. */ + int leadz = clz_hwi (C) + 16; + rtx cst = simplify_gen_binary (ROTATE, mode, src, GEN_INT (leadz)); + if (satisfies_constraint_K (cst)) + { + *res_cst = cst; + return leadz; + } + + /* If all 1 except low 15bits. */ + leadz = clz_hwi (~C) + 15; + cst = simplify_gen_binary (ROTATE, mode, src, GEN_INT (leadz)); + if (satisfies_constraint_I (cst)) + { + *sgn = true; + *res_cst = cst; + return leadz; + } + + return 0; +} + /* Generate a compare for CODE. Return a brand-new rtx that represents the result of the compare. */ @@ -14889,6 +14925,32 @@ rs6000_generate_compare (rtx cmp, machine_mode mode) else comp_mode = CCmode; + /* "i == C" ==> "rotl(i,N) == rotl(C,N)" if rotl(C,N) only low 16bits. */ + if ((code == NE || code == EQ) && mode == DImode) + { + /* The constant would already been set to a reg in the last insn. */ + rtx_insn *last = get_last_insn_anywhere (); + rtx set = last ? single_set (last) : NULL_RTX; + rtx src = (set && SET_DEST (set) == op1) ? SET_SRC (set) : NULL_RTX; + + /* It constant may be in constant pool. */ + if (src && MEM_P (src)) + src = avoid_constant_pool_reference (src); + + rtx cst = NULL_RTX; + bool sgn = false; + int n = rot_to_16bits (src, mode, &sgn, &cst); + if (n >= 16 && n <= 48) + { + rtx dest = gen_reg_rtx (mode); + emit_insn ( + gen_rtx_SET (dest, gen_rtx_ROTATE (mode, op0, GEN_INT (n)))); + op0 = dest; + op1 = cst; + comp_mode = sgn ? CCmode : CCUNSmode; + } + } + /* If we have an unsigned compare, make sure we don't have a signed value as an immediate. */ if (comp_mode == CCUNSmode && CONST_INT_P (op1) diff --git a/gcc/testsuite/gcc.target/powerpc/pr103743.c b/gcc/testsuite/gcc.target/powerpc/pr103743.c new file mode 100644 index 00000000000..606e5e51c4f --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr103743.c @@ -0,0 +1,48 @@ +/* { dg-do compile } */ +/* { dg-require-effective-target lp64 } */ +/* { dg-options "-O2" } */ +/* { dg-final { scan-assembler-times "cmpldi" 8 } } */ +/* { dg-final { scan-assembler-times "cmpdi" 4 } } */ +/* { dg-final { scan-assembler-times "rotldi" 8 } } */ + +int foo (int a); + +int __attribute__ ((noinline)) udi_fun (unsigned long long in) +{ + if (in == (0x8642000000000000ULL)) + return foo (1); + if (in == (0x7642000000000000ULL)) + return foo (12); + if (in == (0x8000000000000000ULL)) + return foo (32); + if (in == (0x8642FFFFFFFFFFFFULL)) + return foo (46); + if (in == (0x7642FFFFFFFFFFFFULL)) + return foo (51); + if (in == (0x7567000000ULL)) + return foo (9); + if (in == (0xFFF8567FFFFFFFFFULL)) + return foo (19); + + return 0; +} + +int __attribute__ ((noinline)) di_fun (long long in) +{ + if (in == (0x8642000000000000LL)) + return foo (1); + if (in == (0x7642000000000000LL)) + return foo (12); + if (in == (0x8000000000000000LL)) + return foo (32); + if (in == (0x8642FFFFFFFFFFFFLL)) + return foo (46); + if (in == (0x7642FFFFFFFFFFFFLL)) + return foo (51); + if (in == (0x7567000000LL)) + return foo (9); + if (in == (0xFFF8567FFFFFFFFFLL)) + return foo (19); + + return 0; +} diff --git a/gcc/testsuite/gcc.target/powerpc/pr103743_1.c b/gcc/testsuite/gcc.target/powerpc/pr103743_1.c new file mode 100644 index 00000000000..56fbbe4d4f1 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/pr103743_1.c @@ -0,0 +1,87 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -std=c99" } */ + +int +foo (int a) +{ + return a + 6; +} + +int __attribute__ ((noinline)) udi_fun (unsigned long long in) +{ + if (in == (0x8642000000000000ULL)) + return foo (1); + if (in == (0x7642000000000000ULL)) + return foo (12); + if (in == (0x8000000000000000ULL)) + return foo (32); + if (in == (0x8642FFFFFFFFFFFFULL)) + return foo (46); + if (in == (0x7642FFFFFFFFFFFFULL)) + return foo (51); + if (in == (0x7567000000ULL)) + return foo (9); + if (in == (0xFFF8567FFFFFFFFFULL)) + return foo (19); + + return 0; +} + +int __attribute__ ((noinline)) di_fun (long long in) +{ + if (in == (0x8642000000000000LL)) + return foo (1); + if (in == (0x7642000000000000LL)) + return foo (12); + if (in == (0x8000000000000000LL)) + return foo (32); + if (in == (0x8642FFFFFFFFFFFFLL)) + return foo (46); + if (in == (0x7642FFFFFFFFFFFFLL)) + return foo (51); + return 0; +} + +int +main () +{ + int e = 0; + if (udi_fun (6) != 0) + e++; + if (udi_fun (0x8642000000000000ULL) != foo (1)) + e++; + if (udi_fun (0x7642000000000000ULL) != foo (12)) + e++; + if (udi_fun (0x8000000000000000ULL) != foo (32)) + e++; + if (udi_fun (0x8642FFFFFFFFFFFFULL) != foo (46)) + e++; + if (udi_fun (0x7642FFFFFFFFFFFFULL) != foo (51)) + e++; + if (udi_fun (0x7567000000ULL) != foo (9)) + e++; + if (udi_fun (0xFFF8567FFFFFFFFFULL) != foo (19)) + e++; + + if (di_fun (6) != 0) + e++; + if (di_fun (0x8642000000000000LL) != foo (1)) + e++; + if (di_fun (0x7642000000000000LL) != foo (12)) + e++; + if (di_fun (0x8000000000000000LL) != foo (32)) + e++; + if (di_fun (0x8642FFFFFFFFFFFFLL) != foo (46)) + e++; + if (di_fun (0x7642FFFFFFFFFFFFLL) != foo (51)) + e++; + if (udi_fun (0x7567000000LL) != foo (9)) + e++; + if (udi_fun (0xFFF8567FFFFFFFFFLL) != foo (19)) + e++; + + if (e) + __builtin_abort (); + return 0; +} +