From patchwork Tue Jun 8 18:26:40 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Bill Schmidt X-Patchwork-Id: 1489570 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=gcc.gnu.org (client-ip=2620:52:3:1:0:246e:9693:128c; helo=sourceware.org; envelope-from=gcc-patches-bounces+incoming=patchwork.ozlabs.org@gcc.gnu.org; receiver=) Authentication-Results: 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=YVnYtZnp; dkim-atps=neutral Received: from sourceware.org (server2.sourceware.org [IPv6:2620:52:3:1:0:246e:9693:128c]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 4G004K0VTJz9t6S for ; Wed, 9 Jun 2021 05:02:55 +1000 (AEST) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id 357C53982C00 for ; Tue, 8 Jun 2021 19:02:53 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 357C53982C00 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1623178973; bh=wK0C5w/vAhldgpy+bPuuswzjoj1wiHj/Wt+51Okttvo=; h=To:Subject:Date:In-Reply-To:References:In-Reply-To:References: List-Id:List-Unsubscribe:List-Archive:List-Post:List-Help: List-Subscribe:From:Reply-To:Cc:From; b=YVnYtZnp33LUUWJOl4MhUWVytyo/cBtglhI9me+DjlQykR9i+y+JYPwxPzq6na70G fB1tXDyd7rD3fOVuYECAtx6ORx3UZ0CZGflKGMulSMv0KuOPCwC3FKKOhHlPZ2AOM8 tQ7FQfkNfJLzdZ3UmXp8FGId1iLzL+yeSvDsI7J0= 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 C8E6739730F0 for ; Tue, 8 Jun 2021 18:28:06 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org C8E6739730F0 Received: from pps.filterd (m0098413.ppops.net [127.0.0.1]) by mx0b-001b2d01.pphosted.com (8.16.0.43/8.16.0.43) with SMTP id 158IKjWR041009; Tue, 8 Jun 2021 14:28:06 -0400 Received: from ppma01dal.us.ibm.com (83.d6.3fa9.ip4.static.sl-reverse.com [169.63.214.131]) by mx0b-001b2d01.pphosted.com with ESMTP id 392drd841m-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Tue, 08 Jun 2021 14:28:06 -0400 Received: from pps.filterd (ppma01dal.us.ibm.com [127.0.0.1]) by ppma01dal.us.ibm.com (8.16.1.2/8.16.1.2) with SMTP id 158IHF88027550; Tue, 8 Jun 2021 18:28:05 GMT Received: from b01cxnp23034.gho.pok.ibm.com (b01cxnp23034.gho.pok.ibm.com [9.57.198.29]) by ppma01dal.us.ibm.com with ESMTP id 3900w9frdq-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Tue, 08 Jun 2021 18:28:05 +0000 Received: from b01ledav005.gho.pok.ibm.com (b01ledav005.gho.pok.ibm.com [9.57.199.110]) by b01cxnp23034.gho.pok.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 158IS5Rw28049736 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Tue, 8 Jun 2021 18:28:05 GMT Received: from b01ledav005.gho.pok.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id E5281AE060; Tue, 8 Jun 2021 18:28:04 +0000 (GMT) Received: from b01ledav005.gho.pok.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id C3597AE06F; Tue, 8 Jun 2021 18:28:04 +0000 (GMT) Received: from localhost (unknown [9.40.194.84]) by b01ledav005.gho.pok.ibm.com (Postfix) with ESMTP; Tue, 8 Jun 2021 18:28:04 +0000 (GMT) To: gcc-patches@gcc.gnu.org Subject: [PATCH 33/55] rs6000: Add MMA builtins Date: Tue, 8 Jun 2021 13:26:40 -0500 Message-Id: X-Mailer: git-send-email 2.17.1 In-Reply-To: References: In-Reply-To: References: X-TM-AS-GCONF: 00 X-Proofpoint-ORIG-GUID: JtPfyH42gcguGTL7AH0YAPgZXI5orCwf X-Proofpoint-GUID: JtPfyH42gcguGTL7AH0YAPgZXI5orCwf X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.391, 18.0.761 definitions=2021-06-08_14:2021-06-04, 2021-06-08 signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 adultscore=0 priorityscore=1501 spamscore=0 malwarescore=0 bulkscore=0 impostorscore=0 mlxscore=0 phishscore=0 clxscore=1015 lowpriorityscore=0 mlxlogscore=999 suspectscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2104190000 definitions=main-2106080117 X-Spam-Status: No, score=-11.5 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_EF, GIT_PATCH_0, RCVD_IN_MSPIKE_H2, SPF_HELO_NONE, SPF_PASS, TXREP autolearn=ham autolearn_force=no version=3.4.2 X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) 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: Bill Schmidt via Gcc-patches From: Bill Schmidt Reply-To: Bill Schmidt Cc: segher@kernel.crashing.org Errors-To: gcc-patches-bounces+incoming=patchwork.ozlabs.org@gcc.gnu.org Sender: "Gcc-patches" 2021-03-24 Bill Schmidt gcc/ * config/rs6000/rs6000-builtin-new.def: Add mma stanza. --- gcc/config/rs6000/rs6000-builtin-new.def | 404 +++++++++++++++++++++++ 1 file changed, 404 insertions(+) diff --git a/gcc/config/rs6000/rs6000-builtin-new.def b/gcc/config/rs6000/rs6000-builtin-new.def index 4dbd47dd470..e236ca39e83 100644 --- a/gcc/config/rs6000/rs6000-builtin-new.def +++ b/gcc/config/rs6000/rs6000-builtin-new.def @@ -3221,3 +3221,407 @@ const unsigned long long __builtin_pextd (unsigned long long, unsigned long long); PEXTD pextd {} + + +[mma] + void __builtin_mma_assemble_acc (v512 *, vuc, vuc, vuc, vuc); + ASSEMBLE_ACC nothing {mma} + + v512 __builtin_mma_assemble_acc_internal (vuc, vuc, vuc, vuc); + ASSEMBLE_ACC_INTERNAL mma_assemble_acc {mma} + + void __builtin_mma_assemble_pair (v256 *, vuc, vuc); + ASSEMBLE_PAIR nothing {mma} + + v256 __builtin_mma_assemble_pair_internal (vuc, vuc); + ASSEMBLE_PAIR_INTERNAL vsx_assemble_pair {mma} + + void __builtin_mma_disassemble_acc (void *, v512 *); + DISASSEMBLE_ACC nothing {mma,quad} + + vuc __builtin_mma_disassemble_acc_internal (v512, const int<2>); + DISASSEMBLE_ACC_INTERNAL mma_disassemble_acc {mma} + + void __builtin_mma_disassemble_pair (void *, v256 *); + DISASSEMBLE_PAIR nothing {mma,pair} + + vuc __builtin_mma_disassemble_pair_internal (v256, const int<2>); + DISASSEMBLE_PAIR_INTERNAL vsx_disassemble_pair {mma} + + void __builtin_mma_pmxvbf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2 nothing {mma} + + v512 __builtin_mma_pmxvbf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2_INTERNAL mma_pmxvbf16ger2 {mma} + + void __builtin_mma_pmxvbf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2NN nothing {mma,quad} + + v512 __builtin_mma_pmxvbf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2NN_INTERNAL mma_pmxvbf16ger2nn {mma,quad} + + void __builtin_mma_pmxvbf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2NP nothing {mma,quad} + + v512 __builtin_mma_pmxvbf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2NP_INTERNAL mma_pmxvbf16ger2np {mma,quad} + + void __builtin_mma_pmxvbf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2PN nothing {mma,quad} + + v512 __builtin_mma_pmxvbf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2PN_INTERNAL mma_pmxvbf16ger2pn {mma,quad} + + void __builtin_mma_pmxvbf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2PP nothing {mma,quad} + + v512 __builtin_mma_pmxvbf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVBF16GER2PP_INTERNAL mma_pmxvbf16ger2pp {mma,quad} + + void __builtin_mma_pmxvf16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2 nothing {mma} + + v512 __builtin_mma_pmxvf16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2_INTERNAL mma_pmxvf16ger2 {mma} + + void __builtin_mma_pmxvf16ger2nn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2NN nothing {mma,quad} + + v512 __builtin_mma_pmxvf16ger2nn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2NN_INTERNAL mma_pmxvf16ger2nn {mma,quad} + + void __builtin_mma_pmxvf16ger2np (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2NP nothing {mma,quad} + + v512 __builtin_mma_pmxvf16ger2np_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2NP_INTERNAL mma_pmxvf16ger2np {mma,quad} + + void __builtin_mma_pmxvf16ger2pn (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2PN nothing {mma,quad} + + v512 __builtin_mma_pmxvf16ger2pn_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2PN_INTERNAL mma_pmxvf16ger2pn {mma,quad} + + void __builtin_mma_pmxvf16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2PP nothing {mma,quad} + + v512 __builtin_mma_pmxvf16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVF16GER2PP_INTERNAL mma_pmxvf16ger2pp {mma,quad} + + void __builtin_mma_pmxvf32ger (v512 *, vuc, vuc, const int<4>, const int<4>); + PMXVF32GER nothing {mma} + + v512 __builtin_mma_pmxvf32ger_internal (vuc, vuc, const int<4>, const int<4>); + PMXVF32GER_INTERNAL mma_pmxvf32ger {mma} + + void __builtin_mma_pmxvf32gernn (v512 *, vuc, vuc, const int<4>, const int<4>); + PMXVF32GERNN nothing {mma,quad} + + v512 __builtin_mma_pmxvf32gernn_internal (v512, vuc, vuc, const int<4>, const int<4>); + PMXVF32GERNN_INTERNAL mma_pmxvf32gernn {mma,quad} + + void __builtin_mma_pmxvf32gernp (v512 *, vuc, vuc, const int<4>, const int<4>); + PMXVF32GERNP nothing {mma,quad} + + v512 __builtin_mma_pmxvf32gernp_internal (v512, vuc, vuc, const int<4>, const int<4>); + PMXVF32GERNP_INTERNAL mma_pmxvf32gernp {mma,quad} + + void __builtin_mma_pmxvf32gerpn (v512 *, vuc, vuc, const int<4>, const int<4>); + PMXVF32GERPN nothing {mma,quad} + + v512 __builtin_mma_pmxvf32gerpn_internal (v512, vuc, vuc, const int<4>, const int<4>); + PMXVF32GERPN_INTERNAL mma_pmxvf32gerpn {mma,quad} + + void __builtin_mma_pmxvf32gerpp (v512 *, vuc, vuc, const int<4>, const int<4>); + PMXVF32GERPP nothing {mma,quad} + + v512 __builtin_mma_pmxvf32gerpp_internal (v512, vuc, vuc, const int<4>, const int<4>); + PMXVF32GERPP_INTERNAL mma_pmxvf32gerpp {mma,quad} + + void __builtin_mma_pmxvf64ger (v512 *, v256, vuc, const int<4>, const int<2>); + PMXVF64GER nothing {mma,pair} + + v512 __builtin_mma_pmxvf64ger_internal (v256, vuc, const int<4>, const int<2>); + PMXVF64GER_INTERNAL mma_pmxvf64ger {mma,pair} + + void __builtin_mma_pmxvf64gernn (v512 *, v256, vuc, const int<4>, const int<2>); + PMXVF64GERNN nothing {mma,pair,quad} + + v512 __builtin_mma_pmxvf64gernn_internal (v512, v256, vuc, const int<4>, const int<2>); + PMXVF64GERNN_INTERNAL mma_pmxvf64gernn {mma,pair,quad} + + void __builtin_mma_pmxvf64gernp (v512 *, v256, vuc, const int<4>, const int<2>); + PMXVF64GERNP nothing {mma,pair,quad} + + v512 __builtin_mma_pmxvf64gernp_internal (v512, v256, vuc, const int<4>, const int<2>); + PMXVF64GERNP_INTERNAL mma_pmxvf64gernp {mma,pair,quad} + + void __builtin_mma_pmxvf64gerpn (v512 *, v256, vuc, const int<4>, const int<2>); + PMXVF64GERPN nothing {mma,pair,quad} + + v512 __builtin_mma_pmxvf64gerpn_internal (v512, v256, vuc, const int<4>, const int<2>); + PMXVF64GERPN_INTERNAL mma_pmxvf64gerpn {mma,pair,quad} + + void __builtin_mma_pmxvf64gerpp (v512 *, v256, vuc, const int<4>, const int<2>); + PMXVF64GERPP nothing {mma,pair,quad} + + v512 __builtin_mma_pmxvf64gerpp_internal (v512, v256, vuc, const int<4>, const int<2>); + PMXVF64GERPP_INTERNAL mma_pmxvf64gerpp {mma,pair,quad} + + void __builtin_mma_pmxvi16ger2 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVI16GER2 nothing {mma} + + v512 __builtin_mma_pmxvi16ger2_internal (vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVI16GER2_INTERNAL mma_pmxvi16ger2 {mma} + + void __builtin_mma_pmxvi16ger2pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVI16GER2PP nothing {mma,quad} + + v512 __builtin_mma_pmxvi16ger2pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVI16GER2PP_INTERNAL mma_pmxvi16ger2pp {mma,quad} + + void __builtin_mma_pmxvi16ger2s (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVI16GER2S nothing {mma} + + v512 __builtin_mma_pmxvi16ger2s_internal (vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVI16GER2S_INTERNAL mma_pmxvi16ger2s {mma} + + void __builtin_mma_pmxvi16ger2spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVI16GER2SPP nothing {mma,quad} + + v512 __builtin_mma_pmxvi16ger2spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<2>); + PMXVI16GER2SPP_INTERNAL mma_pmxvi16ger2spp {mma,quad} + + void __builtin_mma_pmxvi4ger8 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<8>); + PMXVI4GER8 nothing {mma} + + v512 __builtin_mma_pmxvi4ger8_internal (vuc, vuc, const int<4>, const int<4>, const int<8>); + PMXVI4GER8_INTERNAL mma_pmxvi4ger8 {mma} + + void __builtin_mma_pmxvi4ger8pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>); + PMXVI4GER8PP nothing {mma,quad} + + v512 __builtin_mma_pmxvi4ger8pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>); + PMXVI4GER8PP_INTERNAL mma_pmxvi4ger8pp {mma,quad} + + void __builtin_mma_pmxvi8ger4 (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>); + PMXVI8GER4 nothing {mma} + + v512 __builtin_mma_pmxvi8ger4_internal (vuc, vuc, const int<4>, const int<4>, const int<4>); + PMXVI8GER4_INTERNAL mma_pmxvi8ger4 {mma} + + void __builtin_mma_pmxvi8ger4pp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>); + PMXVI8GER4PP nothing {mma,quad} + + v512 __builtin_mma_pmxvi8ger4pp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>); + PMXVI8GER4PP_INTERNAL mma_pmxvi8ger4pp {mma,quad} + + void __builtin_mma_pmxvi8ger4spp (v512 *, vuc, vuc, const int<4>, const int<4>, const int<4>); + PMXVI8GER4SPP nothing {mma,quad} + + v512 __builtin_mma_pmxvi8ger4spp_internal (v512, vuc, vuc, const int<4>, const int<4>, const int<4>); + PMXVI8GER4SPP_INTERNAL mma_pmxvi8ger4spp {mma,quad} + + void __builtin_mma_xvbf16ger2 (v512 *, vuc, vuc); + XVBF16GER2 nothing {mma} + + v512 __builtin_mma_xvbf16ger2_internal (vuc, vuc); + XVBF16GER2_INTERNAL mma_xvbf16ger2 {mma} + + void __builtin_mma_xvbf16ger2nn (v512 *, vuc, vuc); + XVBF16GER2NN nothing {mma,quad} + + v512 __builtin_mma_xvbf16ger2nn_internal (v512, vuc, vuc); + XVBF16GER2NN_INTERNAL mma_xvbf16ger2nn {mma,quad} + + void __builtin_mma_xvbf16ger2np (v512 *, vuc, vuc); + XVBF16GER2NP nothing {mma,quad} + + v512 __builtin_mma_xvbf16ger2np_internal (v512, vuc, vuc); + XVBF16GER2NP_INTERNAL mma_xvbf16ger2np {mma,quad} + + void __builtin_mma_xvbf16ger2pn (v512 *, vuc, vuc); + XVBF16GER2PN nothing {mma,quad} + + v512 __builtin_mma_xvbf16ger2pn_internal (v512, vuc, vuc); + XVBF16GER2PN_INTERNAL mma_xvbf16ger2pn {mma,quad} + + void __builtin_mma_xvbf16ger2pp (v512 *, vuc, vuc); + XVBF16GER2PP nothing {mma,quad} + + v512 __builtin_mma_xvbf16ger2pp_internal (v512, vuc, vuc); + XVBF16GER2PP_INTERNAL mma_xvbf16ger2pp {mma,quad} + + void __builtin_mma_xvf16ger2 (v512 *, vuc, vuc); + XVF16GER2 nothing {mma} + + v512 __builtin_mma_xvf16ger2_internal (vuc, vuc); + XVF16GER2_INTERNAL mma_xvf16ger2 {mma} + + void __builtin_mma_xvf16ger2nn (v512 *, vuc, vuc); + XVF16GER2NN nothing {mma,quad} + + v512 __builtin_mma_xvf16ger2nn_internal (v512, vuc, vuc); + XVF16GER2NN_INTERNAL mma_xvf16ger2nn {mma,quad} + + void __builtin_mma_xvf16ger2np (v512 *, vuc, vuc); + XVF16GER2NP nothing {mma,quad} + + v512 __builtin_mma_xvf16ger2np_internal (v512, vuc, vuc); + XVF16GER2NP_INTERNAL mma_xvf16ger2np {mma,quad} + + void __builtin_mma_xvf16ger2pn (v512 *, vuc, vuc); + XVF16GER2PN nothing {mma,quad} + + v512 __builtin_mma_xvf16ger2pn_internal (v512, vuc, vuc); + XVF16GER2PN_INTERNAL mma_xvf16ger2pn {mma,quad} + + void __builtin_mma_xvf16ger2pp (v512 *, vuc, vuc); + XVF16GER2PP nothing {mma,quad} + + v512 __builtin_mma_xvf16ger2pp_internal (v512, vuc, vuc); + XVF16GER2PP_INTERNAL mma_xvf16ger2pp {mma,quad} + + void __builtin_mma_xvf32ger (v512 *, vuc, vuc); + XVF32GER nothing {mma} + + v512 __builtin_mma_xvf32ger_internal (vuc, vuc); + XVF32GER_INTERNAL mma_xvf32ger {mma} + + void __builtin_mma_xvf32gernn (v512 *, vuc, vuc); + XVF32GERNN nothing {mma,quad} + + v512 __builtin_mma_xvf32gernn_internal (v512, vuc, vuc); + XVF32GERNN_INTERNAL mma_xvf32gernn {mma,quad} + + void __builtin_mma_xvf32gernp (v512 *, vuc, vuc); + XVF32GERNP nothing {mma,quad} + + v512 __builtin_mma_xvf32gernp_internal (v512, vuc, vuc); + XVF32GERNP_INTERNAL mma_xvf32gernp {mma,quad} + + void __builtin_mma_xvf32gerpn (v512 *, vuc, vuc); + XVF32GERPN nothing {mma,quad} + + v512 __builtin_mma_xvf32gerpn_internal (v512, vuc, vuc); + XVF32GERPN_INTERNAL mma_xvf32gerpn {mma,quad} + + void __builtin_mma_xvf32gerpp (v512 *, vuc, vuc); + XVF32GERPP nothing {mma,quad} + + v512 __builtin_mma_xvf32gerpp_internal (v512, vuc, vuc); + XVF32GERPP_INTERNAL mma_xvf32gerpp {mma,quad} + + void __builtin_mma_xvf64ger (v512 *, v256, vuc); + XVF64GER nothing {mma,pair} + + v512 __builtin_mma_xvf64ger_internal (v256, vuc); + XVF64GER_INTERNAL mma_xvf64ger {mma,pair} + + void __builtin_mma_xvf64gernn (v512 *, v256, vuc); + XVF64GERNN nothing {mma,pair,quad} + + v512 __builtin_mma_xvf64gernn_internal (v512, v256, vuc); + XVF64GERNN_INTERNAL mma_xvf64gernn {mma,pair,quad} + + void __builtin_mma_xvf64gernp (v512 *, v256, vuc); + XVF64GERNP nothing {mma,pair,quad} + + v512 __builtin_mma_xvf64gernp_internal (v512, v256, vuc); + XVF64GERNP_INTERNAL mma_xvf64gernp {mma,pair,quad} + + void __builtin_mma_xvf64gerpn (v512 *, v256, vuc); + XVF64GERPN nothing {mma,pair,quad} + + v512 __builtin_mma_xvf64gerpn_internal (v512, v256, vuc); + XVF64GERPN_INTERNAL mma_xvf64gerpn {mma,pair,quad} + + void __builtin_mma_xvf64gerpp (v512 *, v256, vuc); + XVF64GERPP nothing {mma,pair,quad} + + v512 __builtin_mma_xvf64gerpp_internal (v512, v256, vuc); + XVF64GERPP_INTERNAL mma_xvf64gerpp {mma,pair,quad} + + void __builtin_mma_xvi16ger2 (v512 *, vuc, vuc); + XVI16GER2 nothing {mma} + + v512 __builtin_mma_xvi16ger2_internal (vuc, vuc); + XVI16GER2_INTERNAL mma_xvi16ger2 {mma} + + void __builtin_mma_xvi16ger2pp (v512 *, vuc, vuc); + XVI16GER2PP nothing {mma,quad} + + v512 __builtin_mma_xvi16ger2pp_internal (v512, vuc, vuc); + XVI16GER2PP_INTERNAL mma_xvi16ger2pp {mma,quad} + + void __builtin_mma_xvi16ger2s (v512 *, vuc, vuc); + XVI16GER2S nothing {mma} + + v512 __builtin_mma_xvi16ger2s_internal (vuc, vuc); + XVI16GER2S_INTERNAL mma_xvi16ger2s {mma} + + void __builtin_mma_xvi16ger2spp (v512 *, vuc, vuc); + XVI16GER2SPP nothing {mma,quad} + + v512 __builtin_mma_xvi16ger2spp_internal (v512, vuc, vuc); + XVI16GER2SPP_INTERNAL mma_xvi16ger2spp {mma,quad} + + void __builtin_mma_xvi4ger8 (v512 *, vuc, vuc); + XVI4GER8 nothing {mma} + + v512 __builtin_mma_xvi4ger8_internal (vuc, vuc); + XVI4GER8_INTERNAL mma_xvi4ger8 {mma} + + void __builtin_mma_xvi4ger8pp (v512 *, vuc, vuc); + XVI4GER8PP nothing {mma,quad} + + v512 __builtin_mma_xvi4ger8pp_internal (v512, vuc, vuc); + XVI4GER8PP_INTERNAL mma_xvi4ger8pp {mma,quad} + + void __builtin_mma_xvi8ger4 (v512 *, vuc, vuc); + XVI8GER4 nothing {mma} + + v512 __builtin_mma_xvi8ger4_internal (vuc, vuc); + XVI8GER4_INTERNAL mma_xvi8ger4 {mma} + + void __builtin_mma_xvi8ger4pp (v512 *, vuc, vuc); + XVI8GER4PP nothing {mma,quad} + + v512 __builtin_mma_xvi8ger4pp_internal (v512, vuc, vuc); + XVI8GER4PP_INTERNAL mma_xvi8ger4pp {mma,quad} + + void __builtin_mma_xvi8ger4spp (v512 *, vuc, vuc); + XVI8GER4SPP nothing {mma,quad} + + v512 __builtin_mma_xvi8ger4spp_internal (v512, vuc, vuc); + XVI8GER4SPP_INTERNAL mma_xvi8ger4spp {mma,quad} + + void __builtin_mma_xxmfacc (v512 *); + XXMFACC nothing {mma,quad} + + v512 __builtin_mma_xxmfacc_internal (v512); + XXMFACC_INTERNAL mma_xxmfacc {mma,quad} + + void __builtin_mma_xxmtacc (v512 *); + XXMTACC nothing {mma,quad} + + v512 __builtin_mma_xxmtacc_internal (v512); + XXMTACC_INTERNAL mma_xxmtacc {mma,quad} + + void __builtin_mma_xxsetaccz (v512 *); + XXSETACCZ nothing {mma} + + v512 __builtin_mma_xxsetaccz_internal (); + XXSETACCZ_INTERNAL mma_xxsetaccz {mma} + + void __builtin_vsx_assemble_pair (v256 *, vuc, vuc); + ASSEMBLE_PAIR_V nothing {mma} + + v256 __builtin_vsx_assemble_pair_internal (vuc, vuc); + ASSEMBLE_PAIR_V_INTERNAL vsx_assemble_pair {mma} + + void __builtin_vsx_disassemble_pair (void *, v256 *); + DISASSEMBLE_PAIR_V nothing {mma,pair} + + vuc __builtin_vsx_disassemble_pair_internal (v256, const int<2>); + DISASSEMBLE_PAIR_V_INTERNAL vsx_disassemble_pair {mma}