From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from lxmtout1.gsi.de (lxmtout1.gsi.de [140.181.3.111]) by sourceware.org (Postfix) with ESMTPS id 5F3F73860760; Wed, 27 Mar 2024 12:47:57 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 5F3F73860760 Authentication-Results: sourceware.org; dmarc=pass (p=none dis=none) header.from=gsi.de Authentication-Results: sourceware.org; spf=pass smtp.mailfrom=gsi.de ARC-Filter: OpenARC Filter v1.0.0 sourceware.org 5F3F73860760 Authentication-Results: server2.sourceware.org; arc=none smtp.remote-ip=140.181.3.111 ARC-Seal: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1711543679; cv=none; b=dk/6yNNTUnIVq4K1IX408v8PcGMpr32ja+0U5G/+7Q5g7td3bITv6xXC5lEC89HtrVhVD/uvkZgxqXpvzvsLRZARQ1MHFzrbdHFRSf+zKdlgUZKVr4N8Jw8W/F73DUHuJEwKT6H3jOxFxDcMQTM9pw23a5C2KlRZ6O8u9rKyJx8= ARC-Message-Signature: i=1; a=rsa-sha256; d=sourceware.org; s=key; t=1711543679; c=relaxed/simple; bh=Nu6uVTcD1q5bBnaVysbAM9Wwf6yYXwmoKeYOzcBu1M8=; h=From:To:Subject:Date:Message-ID:MIME-Version; b=pc9dCkTpCXrfekO2Ut5vBUeAef8HEtRhARtZ7M/3mab42cjaYmQEQue0vFJyUhQ6NzyIGitL5OeC6JXy6XiXBOIbuC9maPHslY7adQBBekmvlaqo47wlzSu05RIqkxz75RjwN0G/xZvkRRsRRAyH3kArkSpWP3iHwTYhwKECOVA= ARC-Authentication-Results: i=1; server2.sourceware.org Received: from localhost (localhost [127.0.0.1]) by lxmtout1.gsi.de (Postfix) with ESMTP id 74AA9205104B; Wed, 27 Mar 2024 13:47:56 +0100 (CET) X-Virus-Scanned: Debian amavisd-new at lxmtout1.gsi.de Received: from lxmtout1.gsi.de ([127.0.0.1]) by localhost (lxmtout1.gsi.de [127.0.0.1]) (amavisd-new, port 10024) with LMTP id t-jFlBvY6puC; Wed, 27 Mar 2024 13:47:56 +0100 (CET) Received: from srvEX6.campus.gsi.de (unknown [10.10.4.96]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lxmtout1.gsi.de (Postfix) with ESMTPS id 5B1642051040; Wed, 27 Mar 2024 13:47:56 +0100 (CET) Received: from excalibur.localnet (140.181.3.12) by srvEX6.campus.gsi.de (10.10.4.96) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1544.9; Wed, 27 Mar 2024 13:47:56 +0100 From: Matthias Kretz To: , Subject: [PATCH] libstdc++: Add masked ++/-- implementation for sizeof < 16 Date: Wed, 27 Mar 2024 13:47:55 +0100 Message-ID: <4048557.taCxCBeP46@excalibur> Organization: GSI Helmholtz Center for Heavy Ion Research MIME-Version: 1.0 Content-Type: multipart/mixed; boundary="nextPart3975631.atdPhlSkOF" Content-Transfer-Encoding: 7Bit X-Originating-IP: [140.181.3.12] X-ClientProxiedBy: srvEX6.Campus.gsi.de (10.10.4.96) To srvEX6.campus.gsi.de (10.10.4.96) X-Spam-Status: No, score=-9.9 required=5.0 tests=BAYES_00,BODY_8BITS,GIT_PATCH_0,KAM_DMARC_STATUS,KAM_NUMSUBJECT,RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,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: --nextPart3975631.atdPhlSkOF Content-Transfer-Encoding: base64 Content-Type: text/plain; charset="utf-8" QW5kIG9uZSBtb3JlIHRvIGZpeCBmb2xsb3ctdXAgLyByZW1haW5pbmcgZmFpbHVyZXMuIFRlc3Rl ZCBvbiB4ODZfNjQtbGludXgtCmdudS4KCk9LIGZvciB0cnVuayBhbmQgMTM/CgotLS0tLS0tLS0t LS0gODwgLS0tLS0tLS0tLS0tLS0KClRoaXMgcmVzb2x2ZXMgZnVydGhlciBmYWlsdXJlcyAoLVdy ZXR1cm4tdHlwZSB3YXJuaW5ncykgYW5kIHRlc3QKZmFpbHVyZXMgZm9yIHdoZXJlLSogdGVzdHMg dGFyZ2V0aW5nIEFWWC01MTIuCgpTaWduZWQtb2ZmLWJ5OiBNYXR0aGlhcyBLcmV0eiA8bS5rcmV0 ekBnc2kuZGU+CgpsaWJzdGRjKystdjMvQ2hhbmdlTG9nOgoKCSogaW5jbHVkZS9leHBlcmltZW50 YWwvYml0cy9zaW1kX3g4Ni5oIChfU19tYXNrZWRfdW5hcnkpOgoJQ2FzdCBpbnB1dHMgPCAxNiBi eXRlcyB0byAxNiBieXRlIHZlY3RvcnMgYmVmb3JlIGNhbGxpbmcgdGhlCglyaWdodCBzdWJ0cmFj dGlvbiBidWlsdGluLiBCZWZvcmUgcmV0dXJuaW5nLCB0cnVuY2F0ZSB0byB0aGUKCXJldHVybiB2 ZWN0b3IgdHlwZS4KLS0tCiAuLi4vaW5jbHVkZS9leHBlcmltZW50YWwvYml0cy9zaW1kX3g4Ni5o ICAgICAgfCAyNCArKysrKysrKysrKy0tLS0tLS0tCiAxIGZpbGUgY2hhbmdlZCwgMTQgaW5zZXJ0 aW9ucygrKSwgMTAgZGVsZXRpb25zKC0pCgoKLS0K4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA 4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA 4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA 4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSA 4pSA4pSA4pSA4pSA4pSA4pSA4pSA4pSACiBEci4gTWF0dGhpYXMgS3JldHogICAgICAgICAgICAg ICAgICAgICAgICAgICBodHRwczovL21hdHRrcmV0ei5naXRodWIuaW8KIEdTSSBIZWxtaG9sdHog Q2VudHJlIGZvciBIZWF2eSBJb24gUmVzZWFyY2ggICAgICAgICAgICAgICBodHRwczovL2dzaS5k ZQogc3Rk4oKTOjpzaW1kCuKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKU gOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKU gOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKU gOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKU gOKUgOKUgOKUgA== --nextPart3975631.atdPhlSkOF Content-Disposition: inline; filename="0001-libstdc-Add-masked-implementation-for-sizeof-16.patch" Content-Transfer-Encoding: 7Bit Content-Type: text/x-patch; charset="utf-8"; name="0001-libstdc-Add-masked-implementation-for-sizeof-16.patch" diff --git a/libstdc++-v3/include/experimental/bits/simd_x86.h b/libstdc++-v3/include/experimental/bits/simd_x86.h index 6b414486fee..517c4b4a5be 100644 --- a/libstdc++-v3/include/experimental/bits/simd_x86.h +++ b/libstdc++-v3/include/experimental/bits/simd_x86.h @@ -3508,6 +3508,9 @@ _S_masked_unary(const _SimdWrapper<_K, _Np> __k, const _SimdWrapper<_Tp, _Np> __ #ifdef __clang__ return __movm<_Np, _Tp>(__k._M_data) ? __v._M_data - __pm_one : __v._M_data; #else // __clang__ + using _TV = __vector_type_t<_Tp, _Np>; + constexpr size_t __bytes = sizeof(__v) < 16 ? 16 : sizeof(__v); + constexpr size_t __width = __bytes / sizeof(_Tp); if constexpr (is_integral_v<_Tp>) { constexpr bool __lp64 = sizeof(long) == sizeof(long long); @@ -3517,11 +3520,11 @@ _S_masked_unary(const _SimdWrapper<_K, _Np> __k, const _SimdWrapper<_Tp, _Np> __ std::conditional_t<__lp64, long long, int>, std::conditional_t< std::is_same_v<_Ip, signed char>, char, _Ip>>; - const auto __value = __vector_bitcast<_Up>(__v._M_data); + const auto __value = __intrin_bitcast<__vector_type_t<_Up, __width>>(__v._M_data); #define _GLIBCXX_SIMD_MASK_SUB(_Sizeof, _Width, _Instr) \ - if constexpr (sizeof(_Tp) == _Sizeof && sizeof(__v) == _Width) \ - return __vector_bitcast<_Tp>(__builtin_ia32_##_Instr##_mask(__value, \ - __vector_broadcast<_Np>(_Up(__pm_one)), __value, __k._M_data)) + if constexpr (sizeof(_Tp) == _Sizeof && sizeof(__value) == _Width) \ + return __intrin_bitcast<_TV>(__builtin_ia32_##_Instr##_mask(__value, \ + __vector_broadcast<__width>(_Up(__pm_one)), __value, __k._M_data)) _GLIBCXX_SIMD_MASK_SUB(1, 64, psubb512); _GLIBCXX_SIMD_MASK_SUB(1, 32, psubb256); _GLIBCXX_SIMD_MASK_SUB(1, 16, psubb128); @@ -3538,16 +3541,17 @@ _S_masked_unary(const _SimdWrapper<_K, _Np> __k, const _SimdWrapper<_Tp, _Np> __ } else { + const auto __value = __intrin_bitcast<__vector_type_t<_Tp, __width>>(__v._M_data); #define _GLIBCXX_SIMD_MASK_SUB_512(_Sizeof, _Width, _Instr) \ - if constexpr (sizeof(_Tp) == _Sizeof && sizeof(__v) == _Width) \ + if constexpr (sizeof(_Tp) == _Sizeof && sizeof(__value) == _Width) \ return __builtin_ia32_##_Instr##_mask( \ - __v._M_data, __vector_broadcast<_Np>(_Tp(__pm_one)), __v._M_data, \ + __value, __vector_broadcast<__width>(_Tp(__pm_one)), __value, \ __k._M_data, _MM_FROUND_CUR_DIRECTION) #define _GLIBCXX_SIMD_MASK_SUB(_Sizeof, _Width, _Instr) \ - if constexpr (sizeof(_Tp) == _Sizeof && sizeof(__v) == _Width) \ - return __builtin_ia32_##_Instr##_mask( \ - __v._M_data, __vector_broadcast<_Np>(_Tp(__pm_one)), __v._M_data, \ - __k._M_data) + if constexpr (sizeof(_Tp) == _Sizeof && sizeof(__value) == _Width) \ + return __intrin_bitcast<_TV>(__builtin_ia32_##_Instr##_mask( \ + __value, __vector_broadcast<__width>(_Tp(__pm_one)), __value, \ + __k._M_data)) _GLIBCXX_SIMD_MASK_SUB_512(4, 64, subps512); _GLIBCXX_SIMD_MASK_SUB(4, 32, subps256); _GLIBCXX_SIMD_MASK_SUB(4, 16, subps128); --nextPart3975631.atdPhlSkOF--