From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=pass header.oldest-pass=0 smtp.remote-ip=52.101.48.28 ARC-Seal: i=2; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=pass; t=1792428296; b=akxiHCwRLfjHbjgMyAEAEPKkVArmZW7eBUyuIXuALkcopR11QaVbsKjPJpbQlEj9kDpa rDHrZgtu2/iQG/VnxMteP11kVdyUsdznaEoAOqPL7L3rsiScHeOTA8/ikb8Ap9ylX+3F2 j6hLkWLGsXCpXeZ6tHisOtWEGao8AnRWOSENjTlf0ap1dbCuasBqFuh+0A8CTF721lSTm 9x+qNQpx5JeKFjnKPqSMJ9LcQ/4kkVboDFljpDnQ8W4yrRaebnas3iSf2wSOMTeml54KC dDSc2yh0el546eXJQhsASM2sYQvqGi1OVt+HZL8ChNCZbgfQJxYRE+0Qe0Uf/o7kH6g== ARC-Message-Signature: i=2; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1792428296; h=DMARC-Filter:DKIM-Signature:Received:Received: X-MS-Exchange-Authentication-Results:Received-SPF:Received:Received: Received:Received:From:To:CC:Subject:Date:Message-ID:X-Mailer: In-Reply-To:References:MIME-Version:Content-Transfer-Encoding: Content-Type:X-NV-OnPremToCloud:X-EOPAttributedMessage: X-MS-PublicTrafficType:X-MS-TrafficTypeDiagnostic: X-MS-Office365-Filtering-Correlation-Id:X-MS-Exchange-SenderADCheck: X-MS-Exchange-AntiSpam-Relay:X-Microsoft-Antispam: X-Microsoft-Antispam-Message-Info:X-Forefront-Antispam-Report: X-MS-Exchange-AntiSpam-MessageData-ChunkCount: X-MS-Exchange-AntiSpam-MessageData-0:X-OriginatorOrg: X-MS-Exchange-CrossTenant-OriginalArrivalTime: X-MS-Exchange-CrossTenant-Network-Message-Id: X-MS-Exchange-CrossTenant-Id: X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: X-MS-Exchange-CrossTenant-AuthSource:X-MS-Exchange-CrossTenant-AuthAs: X-MS-Exchange-CrossTenant-FromEntityHeader: X-MS-Exchange-Transport-CrossTenantHeadersStamped; bh=hcHcxAquXwGgc21732ASMtLScSgs/GR43jv5ngYk6TM=; b=vlJytxvABYkrTCEstbBljbLzql3JN20K8xM+jf8D6SOKOstMHtB0UKjkGfmSfAyoPHtZ x07Ng4jeCSivCTst5wRqJ5NLJEm898KOw10hp4zZA7prLyyQoAEjJQ2jaS3Eo7OZ9XG1a GFpag4pBya43ufsquhHcu6ZJsP/Khdz8tAghr8tzqD5oNc17NvuaD9Ae3heSg8PuSk6dV DL4sffe9pZ2AKJjbv4kpqUUh+J7uGeFyBz7boqhYMlFz8hjQt3YZv/n41C4gXt6a3KDNI 0g6Oe7qAg6lyU/3rEuDF6MHC44AAlBuGaKB4fk3l7Hy6DG/2lKC3MBhc5uipqxNTdPw== ARC-Authentication-Results: i=2; smtp.subspace.kernel.org; dmarc=pass header.from=nvidia.com; spf=fail smtp.mailfrom=nvidia.com; dkim=pass header.d=Nvidia.com header.i=@Nvidia.com header.a=rsa-sha256 header.s=selector2 header.b="qIt5iC/h"; arc=pass header.oldest-pass=0 smtp.remote-ip=52.101.48.28 Received: from MW6PR02CU001.outbound.protection.outlook.com (mail-westus2azon11012028.outbound.protection.outlook.com [52.101.48.28]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange ECDHE (secp384r1) server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 2BB33606A31A; Mon, 19 Oct 2026 16:44:54 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 2BB33606A31A Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=nvidia.com Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=nvidia.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key, unprotected) header.d=Nvidia.com header.i=@Nvidia.com header.a=rsa-sha256 header.s=selector2 header.b=qIt5iC/h ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=CeLjFLoBFq20GIeGYNBINeBz1Em0TWBTW51oJmpzuFFEJnguD1cYKdpg1KXQED6fLdwDxzlUJ3YcGxrkUaLEUADAefF7HQIBDg0vOkfNnk500DF0BtSIdk+8e+9iWs3CQhf/+LEp9BMTu+lBqze48RHx36JwbN7bNty04NueneocNwn96aBIp68OOyH0YgJ+sha6cTYiGWAjnQg56/0hUUdrPIqnANrc4BWbCDCsrzbLJmIoSoCVNHwxrAL524M76NCgV7SCSEwBXYQWmqVVgmG+3GpP8bSAudF80ZIJGuXPXZW8TxUk4b6zSgjPGwbN+EeG4Jrw7a3cKtSL3wpBEg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=hcHcxAquXwGgc21732ASMtLScSgs/GR43jv5ngYk6TM=; b=bVHQlGmj2qbfCGmBNafhfGCUKCk75ny+gT4tZnx80kYgksitVn95ZkhKY9UpLaR9NEiqqXFLJ2P46OYAOVg3O1UevxgZN/NQ58FdWlhpRB+VojslQEhSc69L61bZx+TkMEr9w/xpP5a0iyQkAw85289j7Z8Ee+sjZG0eNHaluofzkAlHsbyJtXprL+ajf2a+yqQBZAZYMQMvYsH35GiDTqqO57Jwkmpr3BT2iM1q68or+Qjv2wS36+sNaqO2NiZ/qpBdI+fnIxtZdm6fHdIOyCd5jvjD7se8Om3RTl4E8grtGlXpfeLACHeqRQ6N0/sythS7Ro6TGBJqeBYnoe94WQ== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass (sender ip is 216.228.117.160) smtp.rcpttodomain=kernel.org smtp.mailfrom=nvidia.com; dmarc=pass (p=reject sp=reject pct=100) action=none header.from=nvidia.com; dkim=none (message not signed); arc=none (0) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=Nvidia.com; s=selector2; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=hcHcxAquXwGgc21732ASMtLScSgs/GR43jv5ngYk6TM=; b=qIt5iC/hD+63GDHhBXWieAcRXBRWMxu3c7czBiUk6j44W54HPPN8WY9nkJHpb/pi3MZAsDgJolgiYC8J/hp44vSwxdH9CXKtfkR6hX6HRJibtNtsHzKRrLWw6j659P89z7LtgdadVMBaXbG5VcaNwIfSU+K97/ffnCaE9q9ZVapldiTJPcJEnhOSP9DsHts+PlHuj/cxXyrk0U1HzNEupplNUIiTZP57Eu4vZNbjFARxHmanoCW9gqXYmMX94bXo321XFITGGn+UcA1daCcRvFBa3rHmtduElo/w7ud5CxyRl93vvKcVKRIRzySNvONjB657hOSUT4RhBrsuiaEgbQ== Received: from BN9PR03CA0595.namprd03.prod.outlook.com (2603:10b6:408:10d::30) by SA1PR12MB6750.namprd12.prod.outlook.com (2603:10b6:806:257::20) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.21.522.19; Mon, 19 Oct 2026 16:44:46 +0000 Received: from BN2PEPF00004FBE.namprd04.prod.outlook.com (2603:10b6:408:10d:cafe::1a) by BN9PR03CA0595.outlook.office365.com (2603:10b6:408:10d::30) with Microsoft SMTP Server (version=TLS1_3, cipher=TLS_AES_256_GCM_SHA384) id 15.21.522.19 via Frontend Transport; Mon, 19 Oct 2026 16:44:46 +0000 X-MS-Exchange-Authentication-Results: mx.microsoft.com 1; spf=pass (sender IP is 216.228.117.160) smtp.mailfrom=nvidia.com; dkim=none (message not signed) header.d=none;dmarc=pass action=none header.from=nvidia.com; Received-SPF: Pass (protection.outlook.com: domain of nvidia.com designates 216.228.117.160 as permitted sender) receiver=protection.outlook.com; client-ip=216.228.117.160; helo=mail.nvidia.com; pr=C Received: from mail.nvidia.com (216.228.117.160) by BN2PEPF00004FBE.mail.protection.outlook.com (10.167.243.184) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.21.522.6 via Frontend Transport; Mon, 19 Oct 2026 16:44:46 +0000 Received: from rnnvmail203.nvidia.com (10.129.68.9) by mail.nvidia.com (10.129.200.66) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.2562.56; Mon, 19 Oct 2026 09:44:22 -0700 Received: from rnnvmail202.nvidia.com (10.129.68.7) by rnnvmail203.nvidia.com (10.129.68.9) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.2562.49; Mon, 19 Oct 2026 09:44:22 -0700 Received: from build-bwicaksono-noble-20260804.internal (10.127.8.11) by mail.nvidia.com (10.129.68.7) with Microsoft SMTP Server id 15.2.2562.49 via Frontend Transport; Mon, 19 Oct 2026 09:44:21 -0700 From: Besar Wicaksono To: , , CC: , , , , , , , , , , , , , , , , , , , , , "Besar Wicaksono" Subject: [PATCH 2/6] perf jevents: Add support for NVIDIA Tegra410 UCF PMU aliasing Date: Mon, 19 Oct 2026 16:42:37 +0000 Message-ID: <20261019164241.403644-3-bwicaksono@nvidia.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20261019164241.403644-1-bwicaksono@nvidia.com> References: <20261019164241.403644-1-bwicaksono@nvidia.com> X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain X-NV-OnPremToCloud: ExternallySecured X-EOPAttributedMessage: 0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: BN2PEPF00004FBE:EE_|SA1PR12MB6750:EE_ X-MS-Office365-Filtering-Correlation-Id: 23d5d610-1657-4fce-e4c4-08df2e00489d X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|376014|7416014|36860700016|23010399003|82310400026|1800799024|261009223027099003|10067099003|56012099006|6133799003|22082099003|18002099003|11063799006|5023799004; X-Microsoft-Antispam-Message-Info: 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 X-Forefront-Antispam-Report: CIP:216.228.117.160;CTRY:US;LANG:en;SCL:1;SRV:;IPV:NLI;SFV:NSPM;H:mail.nvidia.com;PTR:dc6edge1.nvidia.com;CAT:NONE;SFS:(13230040)(376014)(7416014)(36860700016)(23010399003)(82310400026)(1800799024)(261009223027099003)(10067099003)(56012099006)(6133799003)(22082099003)(18002099003)(11063799006)(5023799004);DIR:OUT;SFP:1101; X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: SdEo0b3lyj0FkCCfJqRKB+xt59bZxoNiDIob8Wxl/cXJAdYhDOyChjVNdwMJixr9p/obAF8zAmM0cBqRUpg2zqE4Wt0q5NwbqQwHyB5ZjFNeps2v4w/EJhmnjQo3K6dkWskXn1TK89ZFcHdH//tT84j0Xa7DYuhdtjBaawtPbql7mgYefgIjCqkqI5f/H4LfMR3+ANGsz713ojJPvEXlGm3q+pVKB919fSIPwFKbPDylbPvxOAPmXGicQdssI6cMos+9cVvtcRBSP3itoVV4bc3nT1rfLX4K1g+aBsMJP+lmz1tUDiXX1yuY45NzZlDlKz3Gv3qFEZ/0jTdRKLNdlrw4nWxG/ezN/VHUnBYMR4blDjt8DL65hHGqe/Ek0SWfnUUKVqI1+v8Y54gyuYsV3LF1DAY4CPq2mdz4MHoziZ+nG7J+cAGQm2OwbIk7q0EW X-OriginatorOrg: Nvidia.com X-MS-Exchange-CrossTenant-OriginalArrivalTime: 19 Oct 2026 16:44:46.1301 (UTC) X-MS-Exchange-CrossTenant-Network-Message-Id: 23d5d610-1657-4fce-e4c4-08df2e00489d X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a;Ip=[216.228.117.160];Helo=[mail.nvidia.com] X-MS-Exchange-CrossTenant-AuthSource: BN2PEPF00004FBE.namprd04.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Anonymous X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem X-MS-Exchange-Transport-CrossTenantHeadersStamped: SA1PR12MB6750 Add alias support for NVIDIA Tegra410 UCF PMU events and metrics. Signed-off-by: Besar Wicaksono --- .../arm64/nvidia/t410/sys/uncore-ucf.json | 693 ++++++++++++++++++ 1 file changed, 693 insertions(+) create mode 100644 tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore= -ucf.json diff --git a/tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-ucf.js= on b/tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-ucf.json new file mode 100644 index 000000000000..37dae2a65fc8 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/nvidia/t410/sys/uncore-ucf.json @@ -0,0 +1,693 @@ +[ + { + "EventCode": "0x100000000", + "EventName": "UCF_CYCLES", + "BriefDescription": "Counts UCF cycles using the dedicated PMU cyc= le counter.", + "PublicDescription": "Counts UCF cycles using the PMU's dedicated = cycle counter.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x1d", + "EventName": "UCF_BUS_CYCLES", + "BriefDescription": "Counts UCF cycles using a programmable event = counter.", + "PublicDescription": "Counts UCF cycles using a programmable event= counter. The count is identical to UCF_CYCLES. Source and destination filt= ers are ignored.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x111", + "EventName": "UCF_SLC_ACCESS_RD", + "BriefDescription": "Counts read requests from a requester to the = SLC.", + "PublicDescription": "Counts read requests from a requester to the= SLC. A read is a request for which the completer returns data: dataless Ma= keReadUnique and snoop requests are not reads, and prefetches issued by the= cores' L1/L2 caches count as reads rather than as prefetch requests. Filte= rs: src_loc_cpu, src_loc_noncpu and src_rem select the request initiator: l= ocal CPU, local non-CPU device or remote socket. dst_loc_cmem, dst_loc_gmem= , dst_loc_other and dst_rem select the memory type of the request address: = local CMEM, local GMEM, local CXL memory or remote memory; local or remote = is determined by the home socket of the address. An unset group counts all.= ", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x112", + "EventName": "UCF_SLC_ACCESS_WR", + "BriefDescription": "Counts write requests from a requester to the= SLC.", + "PublicDescription": "Counts write requests from a requester to th= e SLC. A write is a request in which the requester sends data: dataless Wri= teEvictOrEvict is not a write, and CHI Write*Zero is a write because it eve= ntually consumes DRAM bandwidth although it sends no data over the interfac= e. Filters: src_loc_cpu, src_loc_noncpu and src_rem select the request init= iator: local CPU, local non-CPU device or remote socket. dst_loc_cmem, dst_= loc_gmem, dst_loc_other and dst_rem select the memory type of the request a= ddress: local CMEM, local GMEM, local CXL memory or remote memory; local or= remote is determined by the home socket of the address. An unset group cou= nts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x183", + "EventName": "UCF_SLC_ACCESS_DATALESS", + "BriefDescription": "Counts CHI Dataless requests to the SLC.", + "PublicDescription": "Counts CHI Dataless requests to the SLC. Dat= aless MakeReadUnique and WriteEvictOrEvict requests are not counted. Filter= s: src_loc_cpu, src_loc_noncpu and src_rem select the request initiator: lo= cal CPU, local non-CPU device or remote socket. dst_loc_cmem, dst_loc_gmem,= dst_loc_other and dst_rem select the memory type of the request address: l= ocal CMEM, local GMEM, local CXL memory or remote memory; local or remote i= s determined by the home socket of the address. An unset group counts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x184", + "EventName": "UCF_SLC_ACCESS_ATOMIC", + "BriefDescription": "Counts CHI Atomic requests to the SLC.", + "PublicDescription": "Counts CHI Atomic requests to the SLC. Filte= rs: src_loc_cpu, src_loc_noncpu and src_rem select the request initiator: l= ocal CPU, local non-CPU device or remote socket. dst_loc_cmem, dst_loc_gmem= , dst_loc_other and dst_rem select the memory type of the request address: = local CMEM, local GMEM, local CXL memory or remote memory; local or remote = is determined by the home socket of the address. An unset group counts all.= ", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x113", + "EventName": "UCF_SLC_BYTES_RD", + "BriefDescription": "Counts bytes transferred by the read requests= counted by UCF_SLC_ACCESS_RD.", + "PublicDescription": "Counts the bytes transferred by the read req= uests counted by UCF_SLC_ACCESS_RD, including read data sent by Direct Memo= ry Transfer (DMT) or Direct Cache Transfer (DCT). For transfers of an odd n= umber of bytes, the count is rounded to the nearest power of 2 greater than= the bytes transferred. Because reads can be smaller than 64 bytes, the cou= nt may not equal UCF_SLC_ACCESS_RD times 64. Source and destination filters= work as described for UCF_SLC_ACCESS_RD.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x114", + "EventName": "UCF_SLC_BYTES_WR", + "BriefDescription": "Counts bytes transferred by the write request= s counted by UCF_SLC_ACCESS_WR.", + "PublicDescription": "Counts the bytes transferred by the write re= quests counted by UCF_SLC_ACCESS_WR, including write data sent by Direct Wr= ite Transfer (DWT). For transfers of an odd number of bytes, the count is r= ounded to the nearest power of 2. Data returned to the SLC by a requester's= cache in response to a snoop is not counted. Because writes can be smaller= than 64 bytes, the count may not equal UCF_SLC_ACCESS_WR times 64. Source = and destination filters work as described for UCF_SLC_ACCESS_WR.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x119", + "EventName": "UCF_SLC_HIT_RD", + "BriefDescription": "Counts inbound read requests that hit in the = SLC's L3 cache or in a peer requester cache.", + "PublicDescription": "Counts inbound read requests that hit in the= SLC's L3 cache or in a peer requester cache, including one in a remote soc= ket. Some hits are still refilled from memory (see UCF_SLC_REFILL_RD). Filt= ers: src_loc_cpu, src_loc_noncpu and src_rem select the request initiator: = local CPU, local non-CPU device or remote socket. dst_loc_cmem, dst_loc_gme= m, dst_loc_other and dst_rem select the memory type of the request address:= local CMEM, local GMEM, local CXL memory or remote memory; local or remote= is determined by the home socket of the address. An unset group counts all= .", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x109", + "EventName": "UCF_SLC_REFILL_RD", + "BriefDescription": "Counts inbound read requests not supplied by = the local socket's L1, L2 or L3 caches.", + "PublicDescription": "Counts inbound read requests not supplied by= the local socket's L1, L2 or L3 caches. For remote-memory addresses, it al= so counts each Shared-to-Unique permission upgrade (dataless MakeReadUnique= ) of a cache line shared by requesters in different sockets. A refill is no= t the same as a miss: the SLC may fetch data from memory even when a reques= ter cache holds clean data, and such accesses are hits that are still refil= led. Filters: src_loc_cpu, src_loc_noncpu and src_rem select the request in= itiator: local CPU, local non-CPU device or remote socket. dst_loc_cmem, ds= t_loc_gmem, dst_loc_other and dst_rem select the memory type of the request= address: local CMEM, local GMEM, local CXL memory or remote memory; local = or remote is determined by the home socket of the address. An unset group c= ounts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x10a", + "EventName": "UCF_SLC_REFILL_WR", + "BriefDescription": "Counts inbound write requests not supplied by= the local socket's L1, L2 or L3 caches.", + "PublicDescription": "Counts inbound write requests not supplied b= y the local socket's L1, L2 or L3 caches. A write refill occurs only for a = partial write that needs the existing data; dataless write requests do not = cause a refill and are not counted. Filters: src_loc_cpu, src_loc_noncpu an= d src_rem select the request initiator: local CPU, local non-CPU device or = remote socket. dst_loc_cmem, dst_loc_gmem, dst_loc_other and dst_rem select= the memory type of the request address: local CMEM, local GMEM, local CXL = memory or remote memory; local or remote is determined by the home socket o= f the address. An unset group counts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0xf0", + "EventName": "UCF_SLC_ALLOCATE", + "BriefDescription": "Counts read, write, atomic or prefetch access= es that allocate a line in the SLC's L3 cache.", + "PublicDescription": "Counts read, write, atomic or prefetch acces= ses that allocate a line in the SLC's L3 cache. Filters: src_loc_cpu, src_l= oc_noncpu and src_rem select the request initiator: local CPU, local non-CP= U device or remote socket. dst_loc_cmem, dst_loc_gmem, dst_loc_other and ds= t_rem select the memory type of the request address: local CMEM, local GMEM= , local CXL memory or remote memory; local or remote is determined by the h= ome socket of the address. An unset group counts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0xf3", + "EventName": "UCF_SLC_WB", + "BriefDescription": "Counts SLC eviction and coherence write-backs= , and non-allocating write-backs from upstream clients.", + "PublicDescription": "Counts SLC write-backs: eviction write-backs= , coherence write-backs, and non-allocating write-backs from upstream clien= ts. Evictions include L3 cache and snoop filter evictions. A coherence writ= e-back occurs when data is dirty in the L3 cache or another requester node = cache, but a requesting agent needs clean data. A home SLC in another socke= t, or the GL2 of a connected local or remote GPU (the point of coherence fo= r GPU memory), can evict a line and snoop this SLC. A data-bearing snoop re= sponse from this SLC is not counted by this event, though it uses this SLC'= s downstream bandwidth. For a home SLC eviction, the home SLC's events coun= t the downstream write traffic it causes. Filters: src_loc_cpu, src_loc_non= cpu and src_rem select the initiator of the request that caused the write-b= ack: local CPU, local non-CPU device or remote socket. This need not be the= agent that produced or modified the data. dst_loc_cmem, dst_loc_gmem, dst_= loc_other and dst_rem select the memory type of the memory written back: lo= cal CMEM, local GMEM, local CXL memory or remote memory; local or remote is= determined by the home socket of the address. An unset group counts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x180", + "EventName": "UCF_LOCAL_SNOOP", + "BriefDescription": "Counts snoop requests sent by this SLC to loc= al fully coherent requester nodes or to an SLC in another socket.", + "PublicDescription": "Counts snoop requests sent by this SLC to fu= lly coherent requester nodes in the local socket or to an SLC in another so= cket, including an SLC that this SLC tracks as a sharing node. Invalidating= , forwarding, and non-forwarding snoops are included. Each snoop request is= counted separately, even when one transaction snoops several clients for t= he same cache line. Snoops generated for atomic requests or dataless reques= ts are not counted. Filters: src_loc_cpu, src_loc_noncpu and src_rem select= the initiator of the request that caused the snoop: local CPU, local non-C= PU device or remote socket. dst_loc_cmem, dst_loc_gmem, dst_loc_other and d= st_rem select the memory type of the request address: local CMEM, local GME= M, local CXL memory or remote memory; local or remote is determined by the = home socket of the address. An unset group counts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x181", + "EventName": "UCF_EXT_SNP_ACCESS", + "BriefDescription": "Counts snoop requests that a home SLC or GL2 = in another socket sends to this SLC.", + "PublicDescription": "Counts snoop requests that a home SLC or GL2= in another socket sends to this SLC. Snoops are counted whether or not the= response carries data. Filters: every counted snoop matches src_rem and ds= t_rem, since it comes from a remote initiator for an address homed in anoth= er socket. An unset source or destination group counts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x182", + "EventName": "UCF_EXT_SNP_EVICT", + "BriefDescription": "Counts snoop requests from a home SLC or GL2 = in another socket that invalidate an L3 cache or snoop filter entry in this= SLC.", + "PublicDescription": "Counts snoop requests from a home SLC or GL2= in another socket that invalidate an L3 cache entry or snoop filter entry = in this SLC. Snoops are counted whether or not the response carries data, s= o this event cannot give the number or volume of data-bearing snoop respons= es (see UCF_SLC_WB). Filters: every counted snoop matches src_rem and dst_r= em, since it comes from a remote initiator for an address homed in another = socket. An unset source or destination group counts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x121", + "EventName": "UCF_MEM_ACCESS_RD", + "BriefDescription": "Counts read requests from the SLC toward loca= l CMEM, local GMEM, local CXL memory or remote memory.", + "PublicDescription": "Counts read requests from the SLC toward loc= al CMEM, local GMEM, local CXL memory or remote memory. For remote memory i= t can overcount: it also increments for each Shared-to-Unique permission up= grade (dataless MakeReadUnique) of a cache line shared by requesters in dif= ferent sockets. To count reads from remote sources without this overcount, = count UCF_SLC_ACCESS_RD on the memory's home socket with src_rem, dst_loc_c= mem, dst_loc_gmem and dst_loc_other set. Filters: src_loc_cpu, src_loc_nonc= pu and src_rem select the request initiator: local CPU, local non-CPU devic= e or remote socket. dst_loc_cmem, dst_loc_gmem, dst_loc_other and dst_rem s= elect the memory type of the request address: local CMEM, local GMEM, local= CXL memory or remote memory; local or remote is determined by the home soc= ket of the address. An unset group counts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x122", + "EventName": "UCF_MEM_ACCESS_WR", + "BriefDescription": "Counts write requests from the SLC toward loc= al CMEM, local GMEM, local CXL memory or remote memory.", + "PublicDescription": "Counts write requests from the SLC toward lo= cal CMEM, local GMEM, local CXL memory or remote memory. It includes SLC wr= ite-backs, which are attributed as described for UCF_SLC_WB. Data-bearing s= noop responses to evictions by a home SLC in another socket or a connected = GPU's GL2 are not counted (see UCF_SLC_WB). Filters: src_loc_cpu, src_loc_n= oncpu and src_rem select the request initiator: local CPU, local non-CPU de= vice or remote socket. dst_loc_cmem, dst_loc_gmem, dst_loc_other and dst_re= m select the memory type of the request address: local CMEM, local GMEM, lo= cal CXL memory or remote memory; local or remote is determined by the home = socket of the address. An unset group counts all.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x123", + "EventName": "UCF_MEM_BYTES_RD", + "BriefDescription": "Counts bytes transferred by the read requests= counted by UCF_MEM_ACCESS_RD.", + "PublicDescription": "Counts bytes transferred by the read request= s counted by UCF_MEM_ACCESS_RD. Source and destination filters work as desc= ribed for UCF_MEM_ACCESS_RD.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "EventCode": "0x124", + "EventName": "UCF_MEM_BYTES_WR", + "BriefDescription": "Counts bytes transferred by the write request= s counted by UCF_MEM_ACCESS_WR.", + "PublicDescription": "Counts bytes transferred by the write reques= ts counted by UCF_MEM_ACCESS_WR, including write-back data attributed as de= scribed for UCF_SLC_WB. Data-bearing snoop responses to evictions by a home= SLC in another socket or a connected GPU's GL2 are not counted (see UCF_SL= C_WB). Source and destination filters work as described for UCF_MEM_ACCESS_= WR.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_freq", + "MetricGroup": "UCF_Frequency", + "MetricConstraint": "NO_GROUP_EVENTS", + "MetricExpr": "(UCF_CYCLES / aggr_nr(UCF_CYCLES)) / 1e9 / duration= _time", + "ScaleUnit": "1GHz", + "BriefDescription": "UCF clock frequency.", + "PublicDescription": "Average UCF clock frequency over the measure= ment interval.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_all_src_to_all_dst", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_All_Src_To_All_Dst", + "MetricExpr": "UCF_SLC_BYTES_RD@src_loc_cpu=3D1,src_loc_noncpu=3D1= ,src_rem=3D1,dst_loc_cmem=3D1,dst_loc_gmem=3D1,dst_loc_other=3D1,dst_rem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for r= equests from all sources to all destinations.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from local CPUs, local non-CPU devices and remote sockets for local= CMEM, local GMEM, local CXL memory and remote memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_all_src_to_all_dst", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_All_Src_To_All_Dst", + "MetricExpr": "UCF_MEM_BYTES_RD@src_loc_cpu=3D1,src_loc_noncpu=3D1= ,src_rem=3D1,dst_loc_cmem=3D1,dst_loc_gmem=3D1,dst_loc_other=3D1,dst_rem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for all = memory destinations, for requests from all initiators.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al CMEM, local GMEM, local CXL memory and remote memory, for requests initi= ated by local CPUs, local non-CPU devices and remote sockets.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_all_src_to_all_dst", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_All_Src_To_All_Dst", + "MetricExpr": "UCF_SLC_BYTES_WR@src_loc_cpu=3D1,src_loc_noncpu=3D1= ,src_rem=3D1,dst_loc_cmem=3D1,dst_loc_gmem=3D1,dst_loc_other=3D1,dst_rem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = requests from all sources to all destinations.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from local CPUs, local non-CPU devices and remote sockets for loca= l CMEM, local GMEM, local CXL memory and remote memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_all_src_to_all_dst", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_All_Src_To_All_Dst", + "MetricExpr": "UCF_MEM_BYTES_WR@src_loc_cpu=3D1,src_loc_noncpu=3D1= ,src_rem=3D1,dst_loc_cmem=3D1,dst_loc_gmem=3D1,dst_loc_other=3D1,dst_rem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al and remote memory, for traffic from all initiators.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal CMEM, local GMEM, local CXL memory and remote memory, for traffic initi= ated by local CPUs, local non-CPU devices and remote sockets. Includes writ= e-backs, attributed as described for UCF_SLC_WB. Data-bearing snoop respons= es to evictions by a home SLC in another socket or a connected GPU's GL2 ar= e not counted (see UCF_SLC_WB).", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_local_cpu_to_local_cmem", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Local_CPU;UCF_BW_Local_C= MEM;UCF_BW_Local_CPU_To_Local_CMEM", + "MetricExpr": "UCF_SLC_BYTES_RD@src_loc_cpu=3D1,dst_loc_cmem=3D1@ = / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for l= ocal CPU requests to local CMEM addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from local CPUs for local CMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_local_cpu_to_local_cmem", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Local_CPU;UCF_BW_Local= _CMEM;UCF_BW_Local_CPU_To_Local_CMEM", + "MetricExpr": "UCF_MEM_BYTES_RD@src_loc_cpu=3D1,dst_loc_cmem=3D1@ = / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for loca= l CMEM, for requests initiated by local CPUs.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al CMEM, for requests initiated by local CPUs.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_local_cpu_to_local_cmem", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Local_CPU;UCF_BW_Local_C= MEM;UCF_BW_Local_CPU_To_Local_CMEM", + "MetricExpr": "UCF_SLC_BYTES_WR@src_loc_cpu=3D1,dst_loc_cmem=3D1@ = / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = local CPU requests to local CMEM addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from local CPUs for local CMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_local_cpu_to_local_cmem", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Local_CPU;UCF_BW_Local= _CMEM;UCF_BW_Local_CPU_To_Local_CMEM", + "MetricExpr": "UCF_MEM_BYTES_WR@src_loc_cpu=3D1,dst_loc_cmem=3D1@ = / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al CMEM, for traffic initiated by local CPUs.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal CMEM, for traffic initiated by local CPUs. Includes write-backs, attrib= uted as described for UCF_SLC_WB.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_local_cpu_to_local_gmem", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Local_CPU;UCF_BW_Local_G= MEM;UCF_BW_Local_CPU_To_Local_GMEM", + "MetricExpr": "UCF_SLC_BYTES_RD@src_loc_cpu=3D1,dst_loc_gmem=3D1@ = / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for l= ocal CPU requests to local GMEM addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from local CPUs for local GMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_local_cpu_to_local_gmem", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Local_CPU;UCF_BW_Local= _GMEM;UCF_BW_Local_CPU_To_Local_GMEM", + "MetricExpr": "UCF_MEM_BYTES_RD@src_loc_cpu=3D1,dst_loc_gmem=3D1@ = / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for loca= l GMEM, for requests initiated by local CPUs.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al GMEM, for requests initiated by local CPUs.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_local_cpu_to_local_gmem", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Local_CPU;UCF_BW_Local_G= MEM;UCF_BW_Local_CPU_To_Local_GMEM", + "MetricExpr": "UCF_SLC_BYTES_WR@src_loc_cpu=3D1,dst_loc_gmem=3D1@ = / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = local CPU requests to local GMEM addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from local CPUs for local GMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_local_cpu_to_local_gmem", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Local_CPU;UCF_BW_Local= _GMEM;UCF_BW_Local_CPU_To_Local_GMEM", + "MetricExpr": "UCF_MEM_BYTES_WR@src_loc_cpu=3D1,dst_loc_gmem=3D1@ = / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al GMEM, for traffic initiated by local CPUs.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal GMEM, for traffic initiated by local CPUs. Includes write-backs, attrib= uted as described for UCF_SLC_WB. Data-bearing snoop responses to evictions= by a home SLC in another socket or a connected GPU's GL2 are not counted (= see UCF_SLC_WB).", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_local_cpu_to_local_cxlmem", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Local_CPU;UCF_BW_Local_C= XLMEM;UCF_BW_Local_CPU_To_Local_CXLMEM", + "MetricExpr": "UCF_SLC_BYTES_RD@src_loc_cpu=3D1,dst_loc_other=3D1@= / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for l= ocal CPU requests to local CXL memory addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from local CPUs for local CXL memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_local_cpu_to_local_cxlmem", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Local_CPU;UCF_BW_Local= _CXLMEM;UCF_BW_Local_CPU_To_Local_CXLMEM", + "MetricExpr": "UCF_MEM_BYTES_RD@src_loc_cpu=3D1,dst_loc_other=3D1@= / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for loca= l CXL memory, for requests initiated by local CPUs.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al CXL memory, for requests initiated by local CPUs.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_local_cpu_to_local_cxlmem", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Local_CPU;UCF_BW_Local_C= XLMEM;UCF_BW_Local_CPU_To_Local_CXLMEM", + "MetricExpr": "UCF_SLC_BYTES_WR@src_loc_cpu=3D1,dst_loc_other=3D1@= / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = local CPU requests to local CXL memory addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from local CPUs for local CXL memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_local_cpu_to_local_cxlmem", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Local_CPU;UCF_BW_Local= _CXLMEM;UCF_BW_Local_CPU_To_Local_CXLMEM", + "MetricExpr": "UCF_MEM_BYTES_WR@src_loc_cpu=3D1,dst_loc_other=3D1@= / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al CXL memory, for traffic initiated by local CPUs.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal CXL memory, for traffic initiated by local CPUs. Includes write-backs, = attributed as described for UCF_SLC_WB.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_local_cpu_to_remote_mem", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Local_CPU;UCF_BW_Remote_= Memory;UCF_BW_Local_CPU_To_Remote_Memory", + "MetricExpr": "UCF_SLC_BYTES_RD@src_loc_cpu=3D1,dst_rem=3D1@ / 1e6= / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for l= ocal CPU requests to remote memory addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from local CPUs for remote memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_local_cpu_to_remote_mem", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Local_CPU;UCF_BW_Remot= e_Memory;UCF_BW_Local_CPU_To_Remote_Memory", + "MetricExpr": "UCF_MEM_BYTES_RD@src_loc_cpu=3D1,dst_rem=3D1@ / 1e6= / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for remo= te memory, for requests initiated by local CPUs.", + "PublicDescription": "Average SLC-to-memory read bandwidth for rem= ote memory, for requests initiated by local CPUs.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_local_cpu_to_remote_mem", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Local_CPU;UCF_BW_Remote_= Memory;UCF_BW_Local_CPU_To_Remote_Memory", + "MetricExpr": "UCF_SLC_BYTES_WR@src_loc_cpu=3D1,dst_rem=3D1@ / 1e6= / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = local CPU requests to remote memory addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from local CPUs for remote memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_local_cpu_to_remote_mem", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Local_CPU;UCF_BW_Remot= e_Memory;UCF_BW_Local_CPU_To_Remote_Memory", + "MetricExpr": "UCF_MEM_BYTES_WR@src_loc_cpu=3D1,dst_rem=3D1@ / 1e6= / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for rem= ote memory, for traffic initiated by local CPUs.", + "PublicDescription": "Average SLC-to-memory write bandwidth for re= mote memory, for traffic initiated by local CPUs. Includes write-backs, att= ributed as described for UCF_SLC_WB. Data-bearing snoop responses to evicti= ons by a home SLC in another socket or a connected GPU's GL2 are not counte= d (see UCF_SLC_WB).", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_local_noncpu_to_local_cmem= ", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Local_NonCPU;UCF_BW_Loca= l_CMEM;UCF_BW_Local_NonCPU_To_Local_CMEM", + "MetricExpr": "UCF_SLC_BYTES_RD@src_loc_noncpu=3D1,dst_loc_cmem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for l= ocal non-CPU requests to local CMEM addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from local non-CPU devices such as the GPU and PCIe devices for loc= al CMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_local_noncpu_to_local_cmem= ", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Local_NonCPU;UCF_BW_Lo= cal_CMEM;UCF_BW_Local_NonCPU_To_Local_CMEM", + "MetricExpr": "UCF_MEM_BYTES_RD@src_loc_noncpu=3D1,dst_loc_cmem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for loca= l CMEM, for requests initiated by local non-CPU devices.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al CMEM, for requests initiated by local non-CPU devices such as the GPU an= d PCIe devices.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_local_noncpu_to_local_cmem= ", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Local_NonCPU;UCF_BW_Loca= l_CMEM;UCF_BW_Local_NonCPU_To_Local_CMEM", + "MetricExpr": "UCF_SLC_BYTES_WR@src_loc_noncpu=3D1,dst_loc_cmem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = local non-CPU requests to local CMEM addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from local non-CPU devices such as the GPU and PCIe devices for lo= cal CMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_local_noncpu_to_local_cmem= ", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Local_NonCPU;UCF_BW_Lo= cal_CMEM;UCF_BW_Local_NonCPU_To_Local_CMEM", + "MetricExpr": "UCF_MEM_BYTES_WR@src_loc_noncpu=3D1,dst_loc_cmem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al CMEM, for traffic initiated by local non-CPU devices.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal CMEM, for traffic initiated by local non-CPU devices such as the GPU an= d PCIe devices. Includes write-backs, attributed as described for UCF_SLC_W= B.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_local_noncpu_to_local_gmem= ", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Local_NonCPU;UCF_BW_Loca= l_GMEM;UCF_BW_Local_NonCPU_To_Local_GMEM", + "MetricExpr": "UCF_SLC_BYTES_RD@src_loc_noncpu=3D1,dst_loc_gmem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for l= ocal non-CPU requests to local GMEM addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from local non-CPU devices such as the GPU and PCIe devices for loc= al GMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_local_noncpu_to_local_gmem= ", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Local_NonCPU;UCF_BW_Lo= cal_GMEM;UCF_BW_Local_NonCPU_To_Local_GMEM", + "MetricExpr": "UCF_MEM_BYTES_RD@src_loc_noncpu=3D1,dst_loc_gmem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for loca= l GMEM, for requests initiated by local non-CPU devices.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al GMEM, for requests initiated by local non-CPU devices such as the GPU an= d PCIe devices.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_local_noncpu_to_local_gmem= ", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Local_NonCPU;UCF_BW_Loca= l_GMEM;UCF_BW_Local_NonCPU_To_Local_GMEM", + "MetricExpr": "UCF_SLC_BYTES_WR@src_loc_noncpu=3D1,dst_loc_gmem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = local non-CPU requests to local GMEM addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from local non-CPU devices such as the GPU and PCIe devices for lo= cal GMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_local_noncpu_to_local_gmem= ", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Local_NonCPU;UCF_BW_Lo= cal_GMEM;UCF_BW_Local_NonCPU_To_Local_GMEM", + "MetricExpr": "UCF_MEM_BYTES_WR@src_loc_noncpu=3D1,dst_loc_gmem=3D= 1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al GMEM, for traffic initiated by local non-CPU devices.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal GMEM, for traffic initiated by local non-CPU devices such as the GPU an= d PCIe devices. Includes write-backs, attributed as described for UCF_SLC_W= B. Data-bearing snoop responses to evictions by a home SLC in another socke= t or a connected GPU's GL2 are not counted (see UCF_SLC_WB).", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_local_noncpu_to_local_cxlm= em", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Local_NonCPU;UCF_BW_Loca= l_CXLMEM;UCF_BW_Local_NonCPU_To_Local_CXLMEM", + "MetricExpr": "UCF_SLC_BYTES_RD@src_loc_noncpu=3D1,dst_loc_other= =3D1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for l= ocal non-CPU requests to local CXL memory addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from local non-CPU devices such as the GPU and PCIe devices for loc= al CXL memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_local_noncpu_to_local_cxlm= em", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Local_NonCPU;UCF_BW_Lo= cal_CXLMEM;UCF_BW_Local_NonCPU_To_Local_CXLMEM", + "MetricExpr": "UCF_MEM_BYTES_RD@src_loc_noncpu=3D1,dst_loc_other= =3D1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for loca= l CXL memory, for requests initiated by local non-CPU devices.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al CXL memory, for requests initiated by local non-CPU devices such as the = GPU and PCIe devices.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_local_noncpu_to_local_cxlm= em", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Local_NonCPU;UCF_BW_Loca= l_CXLMEM;UCF_BW_Local_NonCPU_To_Local_CXLMEM", + "MetricExpr": "UCF_SLC_BYTES_WR@src_loc_noncpu=3D1,dst_loc_other= =3D1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = local non-CPU requests to local CXL memory addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from local non-CPU devices such as the GPU and PCIe devices for lo= cal CXL memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_local_noncpu_to_local_cxlm= em", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Local_NonCPU;UCF_BW_Lo= cal_CXLMEM;UCF_BW_Local_NonCPU_To_Local_CXLMEM", + "MetricExpr": "UCF_MEM_BYTES_WR@src_loc_noncpu=3D1,dst_loc_other= =3D1@ / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al CXL memory, for traffic initiated by local non-CPU devices.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal CXL memory, for traffic initiated by local non-CPU devices such as the = GPU and PCIe devices. Includes write-backs, attributed as described for UCF= _SLC_WB.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_local_noncpu_to_remote_mem= ", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Local_NonCPU;UCF_BW_Remo= te_Memory;UCF_BW_Local_NonCPU_To_Remote_Memory", + "MetricExpr": "UCF_SLC_BYTES_RD@src_loc_noncpu=3D1,dst_rem=3D1@ / = 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for l= ocal non-CPU requests to remote memory addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from local non-CPU devices such as the GPU and PCIe devices for rem= ote memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_local_noncpu_to_remote_mem= ", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Local_NonCPU;UCF_BW_Re= mote_Memory;UCF_BW_Local_NonCPU_To_Remote_Memory", + "MetricExpr": "UCF_MEM_BYTES_RD@src_loc_noncpu=3D1,dst_rem=3D1@ / = 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for remo= te memory, for requests initiated by local non-CPU devices.", + "PublicDescription": "Average SLC-to-memory read bandwidth for rem= ote memory, for requests initiated by local non-CPU devices such as the GPU= and PCIe devices.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_local_noncpu_to_remote_mem= ", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Local_NonCPU;UCF_BW_Remo= te_Memory;UCF_BW_Local_NonCPU_To_Remote_Memory", + "MetricExpr": "UCF_SLC_BYTES_WR@src_loc_noncpu=3D1,dst_rem=3D1@ / = 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = local non-CPU requests to remote memory addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from local non-CPU devices such as the GPU and PCIe devices for re= mote memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_local_noncpu_to_remote_mem= ", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Local_NonCPU;UCF_BW_Re= mote_Memory;UCF_BW_Local_NonCPU_To_Remote_Memory", + "MetricExpr": "UCF_MEM_BYTES_WR@src_loc_noncpu=3D1,dst_rem=3D1@ / = 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for rem= ote memory, for traffic initiated by local non-CPU devices.", + "PublicDescription": "Average SLC-to-memory write bandwidth for re= mote memory, for traffic initiated by local non-CPU devices such as the GPU= and PCIe devices. Includes write-backs, attributed as described for UCF_SL= C_WB. Data-bearing snoop responses to evictions by a home SLC in another so= cket or a connected GPU's GL2 are not counted (see UCF_SLC_WB).", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_remote_to_local_cmem", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Remote_Source;UCF_BW_Loc= al_CMEM;UCF_BW_Remote_To_Local_CMEM", + "MetricExpr": "UCF_SLC_BYTES_RD@src_rem=3D1,dst_loc_cmem=3D1@ / 1e= 6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for r= emote-socket requests to local CMEM addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from a remote socket for local CMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_remote_to_local_cmem", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Remote_Source;UCF_BW_L= ocal_CMEM;UCF_BW_Remote_To_Local_CMEM", + "MetricExpr": "UCF_MEM_BYTES_RD@src_rem=3D1,dst_loc_cmem=3D1@ / 1e= 6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for loca= l CMEM, for requests initiated by a remote socket.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al CMEM, for requests initiated by a remote socket.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_remote_to_local_cmem", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Remote_Source;UCF_BW_Loc= al_CMEM;UCF_BW_Remote_To_Local_CMEM", + "MetricExpr": "UCF_SLC_BYTES_WR@src_rem=3D1,dst_loc_cmem=3D1@ / 1e= 6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = remote-socket requests to local CMEM addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from a remote socket for local CMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_remote_to_local_cmem", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Remote_Source;UCF_BW_L= ocal_CMEM;UCF_BW_Remote_To_Local_CMEM", + "MetricExpr": "UCF_MEM_BYTES_WR@src_rem=3D1,dst_loc_cmem=3D1@ / 1e= 6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al CMEM, for traffic initiated by a remote socket.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal CMEM, for traffic initiated by a remote socket. Includes write-backs, a= ttributed as described for UCF_SLC_WB.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_remote_to_local_gmem", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Remote_Source;UCF_BW_Loc= al_GMEM;UCF_BW_Remote_To_Local_GMEM", + "MetricExpr": "UCF_SLC_BYTES_RD@src_rem=3D1,dst_loc_gmem=3D1@ / 1e= 6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for r= emote-socket requests to local GMEM addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from a remote socket for local GMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_remote_to_local_gmem", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Remote_Source;UCF_BW_L= ocal_GMEM;UCF_BW_Remote_To_Local_GMEM", + "MetricExpr": "UCF_MEM_BYTES_RD@src_rem=3D1,dst_loc_gmem=3D1@ / 1e= 6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for loca= l GMEM, for requests initiated by a remote socket.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al GMEM, for requests initiated by a remote socket.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_remote_to_local_gmem", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Remote_Source;UCF_BW_Loc= al_GMEM;UCF_BW_Remote_To_Local_GMEM", + "MetricExpr": "UCF_SLC_BYTES_WR@src_rem=3D1,dst_loc_gmem=3D1@ / 1e= 6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = remote-socket requests to local GMEM addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from a remote socket for local GMEM addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_remote_to_local_gmem", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Remote_Source;UCF_BW_L= ocal_GMEM;UCF_BW_Remote_To_Local_GMEM", + "MetricExpr": "UCF_MEM_BYTES_WR@src_rem=3D1,dst_loc_gmem=3D1@ / 1e= 6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al GMEM, for traffic initiated by a remote socket.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal GMEM, for traffic initiated by a remote socket. Includes write-backs, a= ttributed as described for UCF_SLC_WB. Data-bearing snoop responses to evic= tions by a home SLC in another socket or a connected GPU's GL2 are not coun= ted (see UCF_SLC_WB).", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_remote_to_local_cxlmem", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Remote_Source;UCF_BW_Loc= al_CXLMEM;UCF_BW_Remote_To_Local_CXLMEM", + "MetricExpr": "UCF_SLC_BYTES_RD@src_rem=3D1,dst_loc_other=3D1@ / 1= e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for r= emote-socket requests to local CXL memory addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from a remote socket for local CXL memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_remote_to_local_cxlmem", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Remote_Source;UCF_BW_L= ocal_CXLMEM;UCF_BW_Remote_To_Local_CXLMEM", + "MetricExpr": "UCF_MEM_BYTES_RD@src_rem=3D1,dst_loc_other=3D1@ / 1= e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for loca= l CXL memory, for requests initiated by a remote socket.", + "PublicDescription": "Average SLC-to-memory read bandwidth for loc= al CXL memory, for requests initiated by a remote socket.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_remote_to_local_cxlmem", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Remote_Source;UCF_BW_Loc= al_CXLMEM;UCF_BW_Remote_To_Local_CXLMEM", + "MetricExpr": "UCF_SLC_BYTES_WR@src_rem=3D1,dst_loc_other=3D1@ / 1= e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = remote-socket requests to local CXL memory addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from a remote socket for local CXL memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_remote_to_local_cxlmem", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Remote_Source;UCF_BW_L= ocal_CXLMEM;UCF_BW_Remote_To_Local_CXLMEM", + "MetricExpr": "UCF_MEM_BYTES_WR@src_rem=3D1,dst_loc_other=3D1@ / 1= e6 / duration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for loc= al CXL memory, for traffic initiated by a remote socket.", + "PublicDescription": "Average SLC-to-memory write bandwidth for lo= cal CXL memory, for traffic initiated by a remote socket. Includes write-ba= cks, attributed as described for UCF_SLC_WB.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_rd_bandwidth_remote_to_remote_mem", + "MetricGroup": "UCF_BW_Upstream_RD;UCF_BW_Remote_Source;UCF_BW_Rem= ote_Memory;UCF_BW_Remote_To_Remote_Memory", + "MetricExpr": "UCF_SLC_BYTES_RD@src_rem=3D1,dst_rem=3D1@ / 1e6 / d= uration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC read bandwidth for r= emote-socket requests to remote memory addresses.", + "PublicDescription": "Average requester-to-SLC read bandwidth of r= equests from a remote socket for remote memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_rd_bandwidth_remote_to_remote_mem", + "MetricGroup": "UCF_BW_Downstream_RD;UCF_BW_Remote_Source;UCF_BW_R= emote_Memory;UCF_BW_Remote_To_Remote_Memory", + "MetricExpr": "UCF_MEM_BYTES_RD@src_rem=3D1,dst_rem=3D1@ / 1e6 / d= uration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory read bandwidth for remo= te memory, for requests initiated by a remote socket.", + "PublicDescription": "Average SLC-to-memory read bandwidth for rem= ote memory, for requests initiated by a remote socket.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_slc_wr_bandwidth_remote_to_remote_mem", + "MetricGroup": "UCF_BW_Upstream_WR;UCF_BW_Remote_Source;UCF_BW_Rem= ote_Memory;UCF_BW_Remote_To_Remote_Memory", + "MetricExpr": "UCF_SLC_BYTES_WR@src_rem=3D1,dst_rem=3D1@ / 1e6 / d= uration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average requester-to-SLC write bandwidth for = remote-socket requests to remote memory addresses.", + "PublicDescription": "Average requester-to-SLC write bandwidth of = requests from a remote socket for remote memory addresses.", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + }, + { + "MetricName": "ucf_avg_mem_wr_bandwidth_remote_to_remote_mem", + "MetricGroup": "UCF_BW_Downstream_WR;UCF_BW_Remote_Source;UCF_BW_R= emote_Memory;UCF_BW_Remote_To_Remote_Memory", + "MetricExpr": "UCF_MEM_BYTES_WR@src_rem=3D1,dst_rem=3D1@ / 1e6 / d= uration_time", + "ScaleUnit": "1MB/s", + "BriefDescription": "Average SLC-to-memory write bandwidth for rem= ote memory, for traffic initiated by a remote socket.", + "PublicDescription": "Average SLC-to-memory write bandwidth for re= mote memory, for traffic initiated by a remote socket. Includes write-backs= , attributed as described for UCF_SLC_WB. Data-bearing snoop responses to e= victions by a home SLC in another socket or a connected GPU's GL2 are not c= ounted (see UCF_SLC_WB).", + "Compat": "2cf2036b", + "Unit": "nvidia_ucf_pmu_" + } +] --=20 2.43.0