Partitions

On PC2 cluster system partitions are used to distinguish compute nodes with different hardware. That means that there is no partition with a higher priority or related things. Priorities are handled by Quality-of-Service instead.

Partitions on Noctua 2

The Noctua 2 cluster is composed of:

Node Spec	Partition	Job Time Limit	Naming	Node Count	CPU	Highest Instruction set	Sockets	Cores	SMT	Main Memory total GiB / usable MiB	Accelerators	Node-local Storage	Interconnect

Node Spec	Partition	Job Time Limit	Naming	Node Count	CPU	Highest Instruction set	Sockets	Cores	SMT	Main Memory total GiB / usable MiB	Accelerators	Node-local Storage	Interconnect
login nodes			n2login[1-6]	6	AMD Milan 7763	AVX2	1	64	on	512			Infiniband HDR 100
normal nodes	normal	21 days	n2cn[01-11][01-96]	990			2	2x64	off	256 / 240000 MiB
large-memory nodes	largemem	21 days	n2lcn01[01-66]	66						1024 / 950000
huge-memory nodes	hugemem	21 days	n2hcn01[01-05]	5	AMD Milan 7713					2048 / 1900000		12x 3 TB NVME SSDs
GPU-nodes	gpu	7 days	n2gpu12[01-32]	32	AMD Milan 7763					512 / 485000	4x NVIDIA A100 40 GB with NVLINK	1x 960 GB NVME SSD	2xInfiniband HDR 200
DGX A100	dgx	details	n2dgx01	1	AMD Rome 7742					1024 / 9500000	8x NVIDIA A100 40 GB with NVLINK	4x 3,84 TB NVME SSDs	4x Infiniband HDR 200
FPGA-nodes with Xilinx FPGAs	fpga	7 days	n2fpga[01-16]	16	AMD Milan 7713					512 / 485000	3x Xilinx Alveo U280 cards		Infiniband HDR 100
FPGA-nodes with Intel FPGAs		7 days	n2fpga[18-34]	16							2x Bittware 520N cards
FPGA-nodes with custom configurations		7 days	n2fpga17, n2fpga[35,36]	3
HACC nodes	hacc	7 days	n2hacc[01-03]	3	AMD Milan 7v13						2x Xilinx Alveo U55C cards 2x Xilinx VCK5000 cards 4x AMD Instinct MI210 cards

Partitions on Otus

The Otus cluster is composed of:

Node Spec	Partition	Job Time Limit	Naming	Count	CPU	Highest Instruction Set	Sockets	Cores	SMT	Main Memory total GiB / usable MiB	Accelerators	Node-local Storage	Interconnect

Node Spec	Partition	Job Time Limit	Naming	Count	CPU	Highest Instruction Set	Sockets	Cores	SMT	Main Memory total GiB / usable MiB	Accelerators	Node-local Storage	Interconnect
login nodes			login[1-6]	6	AMD Turin 9655	AVX-512	1	96	on	512
normal nodes	normal	21 days	cn[01-18][01-72]	636			2	2x96	off	768 / 730000			NDR200
large-memory nodes	largemem	21 days	lcn[13,14][01-24]	48						1536 / 1516800		1x 3.8 TB NVME SSD	NDR200
GPU-nodes H100	gpu	7 days	gpu10[01-24], gpu12[01-03]	27						768 / 730000	4x NVIDIA H100 94GB	1x 3.8 TB NVME SSD	NDR800
GPU-nodes A40	gpu_a40	7 days	fpga17[01-10]	10						768 / 748800	3x NVIDIA A40 48GB	1x 3.8 TB NVME SSD	NDR 200
FPGA-nodes	fpga	7 days	fpga[16,17][01-16]	22						768 / 748800	Current pilot phase FPGA setup		NDR200

Node Types and Partitions

Partitions

Partitions on Noctua 2

Partitions on Otus