From f4b17b89e807aed815626338693b26d4f65347b0 Mon Sep 17 00:00:00 2001 From: Lancelot Doan <lancelot.doan@inria.fr> Date: Wed, 7 May 2025 08:24:49 +0200 Subject: [PATCH] [Sophia][Esterel31] Regenerate g5k-checks for gpu --- .../sophia/clusters/esterel31/esterel31.json | 4 +- .../clusters/esterel31/nodes/esterel31-1.json | 70 +++++++++++++++++++ .../clusters/esterel31/nodes/esterel31-2.json | 70 +++++++++++++++++++ .../clusters/esterel31/nodes/esterel31-3.json | 70 +++++++++++++++++++ .../clusters/esterel31/nodes/esterel31-4.json | 70 +++++++++++++++++++ .../clusters/esterel31/nodes/esterel31-1.yaml | 33 +++++++++ .../clusters/esterel31/nodes/esterel31-2.yaml | 33 +++++++++ .../clusters/esterel31/nodes/esterel31-3.yaml | 33 +++++++++ .../clusters/esterel31/nodes/esterel31-4.yaml | 33 +++++++++ 9 files changed, 414 insertions(+), 2 deletions(-) diff --git a/data/grid5000/sites/sophia/clusters/esterel31/esterel31.json b/data/grid5000/sites/sophia/clusters/esterel31/esterel31.json index 42a60f2c921..76ad1f99cba 100644 --- a/data/grid5000/sites/sophia/clusters/esterel31/esterel31.json +++ b/data/grid5000/sites/sophia/clusters/esterel31/esterel31.json @@ -141,8 +141,8 @@ ], "model": "Dell PowerEdge T640", "nodes_count": 4, - "nodes_description": "2 CPUs Intel Xeon Gold 6230R, 26 cores/CPU, 384GB RAM, 446GB HDD, 3575GB HDD, 1 x 10Gb Ethernet, 1 x 40Gb InfiniBand", - "priority": 202008, + "nodes_description": "2 CPUs Intel Xeon Gold 6230R, 26 cores/CPU, 4 GPUs Quadro RTX 8000, 384GB RAM, 446GB HDD, 3575GB HDD, 1 x 10Gb Ethernet, 1 x 40Gb InfiniBand", + "priority": 202108, "queues": [ "admin", "testing" diff --git a/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-1.json b/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-1.json index c9d25725c89..90abf683131 100644 --- a/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-1.json +++ b/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-1.json @@ -20,6 +20,76 @@ "warranty_end": "2027-08-10" }, "exotic": false, + "gpu_devices": { + "nvidia0": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia0", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia1": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia1", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia2": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia2", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia3": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia3", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + } + }, "main_memory": { "ram_size": 412316860416 }, diff --git a/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-2.json b/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-2.json index 050af78860f..01b35de3721 100644 --- a/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-2.json +++ b/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-2.json @@ -20,6 +20,76 @@ "warranty_end": "2027-08-10" }, "exotic": false, + "gpu_devices": { + "nvidia0": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia0", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia1": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia1", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia2": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia2", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia3": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia3", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + } + }, "main_memory": { "ram_size": 412316860416 }, diff --git a/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-3.json b/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-3.json index f9aff51a7ea..e32572bdfc6 100644 --- a/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-3.json +++ b/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-3.json @@ -20,6 +20,76 @@ "warranty_end": "2027-08-10" }, "exotic": false, + "gpu_devices": { + "nvidia0": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia0", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia1": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia1", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia2": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia2", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia3": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia3", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + } + }, "main_memory": { "ram_size": 412316860416 }, diff --git a/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-4.json b/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-4.json index f7636072031..c179ac1ff85 100644 --- a/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-4.json +++ b/data/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-4.json @@ -20,6 +20,76 @@ "warranty_end": "2027-08-10" }, "exotic": false, + "gpu_devices": { + "nvidia0": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia0", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia1": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 0, + "device": "/dev/nvidia1", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia2": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia2", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + }, + "nvidia3": { + "compute_capability": "7.5", + "cores": 4608, + "cpu_affinity": 1, + "device": "/dev/nvidia3", + "memory": 48318382080, + "microarchitecture": "Turing", + "model": "Quadro RTX 8000", + "performance": { + "fp-16": 32620000000000, + "fp-32": 16310000000000, + "fp-64": 510000000000 + }, + "power_default_limit": "250.00 W", + "vbios_version": "90.02.4E.00.03", + "vendor": "Nvidia" + } + }, "main_memory": { "ram_size": 412316860416 }, diff --git a/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-1.yaml b/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-1.yaml index b30669cae4c..492e90f5e0e 100644 --- a/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-1.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-1.yaml @@ -16,6 +16,39 @@ esterel31-1: manufacturer: Dell Inc. name: PowerEdge T640 serial: 36ZFW53 + gpu_devices: + nvidia0: + cpu_affinity: 0 + device: "/dev/nvidia0" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia1: + cpu_affinity: 0 + device: "/dev/nvidia1" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia2: + cpu_affinity: 1 + device: "/dev/nvidia2" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia3: + cpu_affinity: 1 + device: "/dev/nvidia3" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia main_memory: ram_size: 412316860416 memory_devices: diff --git a/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-2.yaml b/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-2.yaml index 3682ff2283b..f5433594417 100644 --- a/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-2.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-2.yaml @@ -16,6 +16,39 @@ esterel31-2: manufacturer: Dell Inc. name: PowerEdge T640 serial: 46ZFW53 + gpu_devices: + nvidia0: + cpu_affinity: 0 + device: "/dev/nvidia0" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia1: + cpu_affinity: 0 + device: "/dev/nvidia1" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia2: + cpu_affinity: 1 + device: "/dev/nvidia2" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia3: + cpu_affinity: 1 + device: "/dev/nvidia3" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia main_memory: ram_size: 412316860416 memory_devices: diff --git a/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-3.yaml b/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-3.yaml index f9b81726450..78debe057ce 100644 --- a/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-3.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-3.yaml @@ -16,6 +16,39 @@ esterel31-3: manufacturer: Dell Inc. name: PowerEdge T640 serial: 56ZFW53 + gpu_devices: + nvidia0: + cpu_affinity: 0 + device: "/dev/nvidia0" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia1: + cpu_affinity: 0 + device: "/dev/nvidia1" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia2: + cpu_affinity: 1 + device: "/dev/nvidia2" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia3: + cpu_affinity: 1 + device: "/dev/nvidia3" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia main_memory: ram_size: 412316860416 memory_devices: diff --git a/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-4.yaml b/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-4.yaml index 625b7bdaf33..8b492c79f58 100644 --- a/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-4.yaml +++ b/input/grid5000/sites/sophia/clusters/esterel31/nodes/esterel31-4.yaml @@ -16,6 +16,39 @@ esterel31-4: manufacturer: Dell Inc. name: PowerEdge T640 serial: 116SF73 + gpu_devices: + nvidia0: + cpu_affinity: 0 + device: "/dev/nvidia0" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia1: + cpu_affinity: 0 + device: "/dev/nvidia1" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia2: + cpu_affinity: 1 + device: "/dev/nvidia2" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia + nvidia3: + cpu_affinity: 1 + device: "/dev/nvidia3" + memory: 48318382080 + model: Quadro RTX 8000 + power_default_limit: 250.00 W + vbios_version: 90.02.4E.00.03 + vendor: Nvidia main_memory: ram_size: 412316860416 memory_devices: -- GitLab