Cluster technical overview

Shared resource

Triton is a joint installation by a number of Aalto School of Science faculties within Science-IT project, which was founded in 2009 to facilitate the HPC Infrastructure in all of School of Science. It is now available to all Aalto researchers.

As of 2016, Triton is part of FGCI - Finnish Grid and Cloud Infrastructure (predecessor of Finnish Grid Infrastructure). Through the national grid and cloud infrastructure, Triton also becomes part of the European Grid Infrastructure.

Hardware

Node name	Number of nodes	Node type	Year	Arch (--constraint)	CPU type	Memory Configuration	Infiniband	GPUs	Disks
pe[1-48,65-81]	65	Dell PowerEdge C4130	2016	hsw avx2	2x12 core Xeon E5 2680 v3 2.50GHz	128GB DDR4-2133	FDR		900GB HDD
pe[49-64,82]	17	Dell PowerEdge C4130	2016	hsw avx2	2x12 core Xeon E5 2680 v3 2.50GHz	256GB DDR4-2133	FDR		900GB HDD
pe[83-91]	8	Dell PowerEdge C4130	2017	bdw avx2	2x14 core Xeon E5 2680 v4 2.40GHz	128GB DDR4-2400	FDR		900GB HDD
skl[1-48]	48	Dell PowerEdge C6420	2019	skl avx2 avx512	2x20 core Xeon Gold 6148 2.40GHz	192GB DDR4-2667	EDR		No disk
csl[1-48]	48	Dell PowerEdge C6420	2020	csl avx2 avx512	2x20 core Xeon Gold 6248 2.50GHz	192GB DDR4-2667	EDR		No disk
milan[1-32]	32	Dell PowerEdge C6525	2023	milan avx2	2x64 core AMD EPYC 7713 @2.0 GHz	512GB DDR4-3200	HDR-100		No disk
fn3	1	Dell PowerEdge R940	2020	avx2 avx512	4x20 core Xeon Gold 6148 2.40GHz	2TB DDR4-2666	EDR		No disk
gpu[1-10]	10	Dell PowerEdge C4140	2020	skl avx2 avx512 volta	2x8 core Intel Xeon Gold 6134 @ 3.2GHz	384GB DDR4-2667	EDR	4x V100 32GB	1.5 TB SSD
gpu[11-17,38-44]	14	Dell PowerEdge XE8545	2021, 2023	milan avx2 ampere a100	2x24 core AMD EPYC 7413 @ 2.65GHz	503GB DDR4-3200	EDR	4x A100 80GB	440 GB SSD
gpu[20-22]	3	Dell PowerEdge C4130	2016	hsw avx2 kepler	2x6 core Xeon E5 2620 v3 2.50GHz	128GB DDR4-2133	EDR	4x2 GPU K80	440 GB SSD
gpu[23-27]	5	Dell PowerEdge C4130	2017	hsw avx2 pascal	2x12 core Xeon E5-2680 v3 @ 2.5GHz	256GB DDR4-2400	EDR	4x P100	720 GB SSD
gpu[28-37]	10	Dell PowerEdge C4140	2019	skl avx2 avx512 volta	2x8 core Intel Xeon Gold 6134 @ 3.2GHz	384GB DDR4-2667	EDR	4x V100 32GB	1.5 TB SSD
dgx[1-2]	2	Nvidia DGX-1	2018	bdw avx2 volta	2x20 core Xeon E5-2698 v4 @ 2.2GHz	512GB DDR4-2133	EDR	8x V100 16GB	7 TB SSD
dgx[3-7]	5	Nvidia DGX-1	2018	bdw avx2 volta	2x20 core Xeon E5-2698 v4 @ 2.2GHz	512GB DDR4-2133	EDR	8x V100 32GB	7 TB SSD
gpuamd1	1	Dell PowerEdge R7525	2021	rome avx2 mi100	2x8 core AMD EPYC 7262 @3.2GHz	250GB DDR4-3200	EDR	3x MI100	32GB SSD
gpu[45-48]	4	Dell PowerEdge XE8640	2024	saphr avx2 h100 hopper	2x48 core Xeon Platinum 8468 2.1GHz	1024GB DDR5-4800	HDR	4x H100 SXM 80GB	21 TB SSD

All Triton computing nodes are identical in respect to software and access to common file system. Each node has its own unique host name and ip-address.

Networking

The cluster has two internal networks: Infiniband for MPI and Lustre filesystem and Gigabit Ethernet for everything else like NFS /home directories and ssh.

The internal networks are unaccessible from outside. Only the login node triton.aalto.fi has an extra Ethernet connection to outside.

High performance InfiniBand has fat-tree configuration in general. Triton has several InfiniBand segments (often called islands) distinguished based on the CPU arch. The nodes within those islands connected with different ratio like 2:1, 4:1 or 8:1, (i.e. in 4:1 case for each 4 downlinks there is 1 uplink to spine switches. The islands are ivb[1-45] 540 cores, pe[3-91] 2152 cores (keep in mind that pe[83-91] have 28 cores per node), four c[xxx-xxx] segments with 600 cores each, skl[1-48] and csl[1-48] with 1920 cores each [CHECKME]. Uplinks from those islands are mainly used for Lustre communication. Running MPI jobs possible on the entire island or its segment, but not across the cluster.

Disk arrays

All compute nodes and front-end are connected to DDN SFA12k storage system: large disk arrays with the Lustre filesystem on top of it cross-mounted under /scratch directory. The system provides about 1.8PB of disk space available to end-user.

Software

The cluster is running open source software infrastructure: CentOS 7, with SLURM as the scheduler and batch system.