Systems 1: Difference between revisions

From NU HPC Wiki
Jump to navigation Jump to search
VisualWikitext
(Created page with "Key features at a glance: * 20 Compute nodes with dual AMD EPYC 7502 CPUs (32 cores / 64 threads, 2.5 MHz Base), 256 GB 8-channel DDR4-2933 RAM, CentOS 7.9 * 4 Compute nodes with dual AMD EPYC 7452 CPUs (32 cores / 64 threads, 2.3 MHz Base), 256 GB 8-channel DDR4-2933 RAM, dual NVidia Tesla V100 GPUs 32GB HBM2 RAM, CentOS 7.9 * 1 interactive login node with AMD EPYC 7502P CPU (32 cores / 64 threads, 2.5 MHz Base), 256 GB 8-chann...")
 
m (Admin moved page Systems to Systems 1 without leaving a redirect)
 
(27 intermediate revisions by the same user not shown)
Line 1: Line 1:
Key features at a glance:
[[File:Cluster nodes.png|thumb|319x319px]]
    * 20 Compute nodes with dual AMD EPYC 7502 CPUs (32 cores / 64
=== Key Features at a Glance: ===
      threads, 2.5 MHz Base), 256 GB 8-channel DDR4-2933 RAM, CentOS 7.9
 
    * 4 Compute nodes with dual AMD EPYC 7452 CPUs (32 cores / 64
* 20 Compute nodes with dual AMD EPYC 7502 CPUs (32 cores / 64 threads, 2.5 MHz Base), 256 GB 8-channel DDR4-2933 RAM, CentOS 7.9
      threads, 2.3 MHz Base), 256 GB 8-channel DDR4-2933 RAM, dual NVidia
* 4 Compute nodes with dual AMD EPYC 7452 CPUs (32 cores / 64 threads, 2.3 MHz Base), 256 GB 8-channel DDR4-2933 RAM, dual NVidia Tesla V100 GPUs 32GB HBM2 RAM, CentOS 7.9
      Tesla V100 GPUs 32GB HBM2 RAM, CentOS 7.9
* 1 interactive login node with AMD EPYC 7502P CPU (32 cores / 64 threads, 2.5 MHz Base), 256 GB 8-channel DDR4-2933 RAM, Red Hat Enterprise Linux 7.9
    * 1 interactive login node with AMD EPYC 7502P CPU (32 cores / 64
* EDR Infiniband 100 Gb/s interconnect for compute traffic
      threads, 2.5 MHz Base), 256 GB 8-channel DDR4-2933 RAM, Red Hat
* 16TB internal NVMe SSD Storage (HPE Clustered Extents File System)
      Enterprise Linux 7.9
* 144TB HPE MSA 2050 SAS HDD Array
    * EDR Infiniband 100 Gb/s interconnect for compute traffic
* Theoretical peak CPU performance of the system is 60 TFlops (double precision)
    * 16TB internal NVMe SSD Storage (HPE Clustered Extents File System)
* Theoretical peak GPU performance of the system is 65 TFlops (double precision)
    * 144TB HPE MSA 2050 SAS HDD Array
* SLURM job scheduler
    * Theoretical peak CPU performance of the system is 60 TFlops (double
 
      precision)
 
    * Theoretical peak GPU performance of the system is 65 TFlops (double
   The system is assembled in a two-rack configuration and is physically located at NU Data Center
      precision)
    * SLURM job scheduler
  Schematic view of Shabyt
  Scheme
   The system is assembled in a two-rack configuration and is physically
  located at NU Data Center
  Racks
Other NU research computing clusters
Other NU research computing clusters
  Cluster name Short description Contact details
[[File:Cluster.png|thumb|344x344px]]
  High-performance bioinformatics cluster “Q-Symphony” Hewlett-Packard
 
  Enterprise – Apollo (208 Cores x Intel Xeon, 3.26 TB RAM, 258 ТB RAID
{| style="border-collapse: collapse; width: 100%;"
  HDD, RedHat Linux) – max computing performance 7.5 TFlops: specifically
|-
  designed architecture optimized for bioinformatics research and
! style="background-color: #f2f2f2; text-align: left; padding: 8px; border: 1px solid #dddddd;" | Cluster name
  analysis of big genomics datasets (whole-genome/whole transcriptomes
! style="background-color: #f2f2f2; text-align: left; padding: 8px; border: 1px solid #dddddd;" | Short description
  datasets and genomics bulk datasets with more than 100 samples
! style="background-color: #f2f2f2; text-align: left; padding: 8px; border: 1px solid #dddddd;" | Contact details
  simultaneously) Ulykbek Kairov (Head of Laboratory - Leading
|-
  Researcher, Laboratory of bioinformatics and systems biology, Private
| High-performance bioinformatics cluster "Q-Symphony"
  Institution National Laboratory Astana)
| Hewlett-Packard Enterprise – Apollo<br>(208 Cores x Intel Xeon, 3.26 TB RAM, 258 TB RAID HDD, RedHat Linux)<br>Max computing performance: 7.5 TFlops<br>Optimized for bioinformatics research and big genomics datasets analysis
  Email: [11]ulykbek.kairov@nu.edu.kz
| Ulykbek Kairov<br>Head of Laboratory - Leading Researcher, Laboratory of bioinformatics and systems biology, Private Institution National Laboratory Astana<br>Email: [[mailto:ulykbek.kairov@nu.edu.kz|ulykbek.kairov@nu.edu.kz]]
  Intelligence-Cognition-Robotics GPUs 8X NVIDIA Tesla V100
|-
  Performance (Mixed Precision): 1 petaFLOPS
| Intelligence-Cognition-Robotics
  GPU Memory: 256 GB total system
| GPUs: 8X NVIDIA Tesla V100<br>Performance: 1 petaFLOPS<br>GPU Memory: 256 GB total<br>CPU: Dual 20-Core Intel Xeon, E5-2698 v4 2.2 GHz<br>...
  CPU: Dual 20-Core Intel Xeon, E5-2698 v4 2.2 GHz
| Zhandos Yessenbayev<br>Senior Researcher, Laboratory of Computational Materials Science for Energy Application, Private Institution National Laboratory Astana<br>Email: [[mailto:zhyessenbayev@nu.edu.kz|zhyessenbayev@nu.edu.kz]]
  NVIDIA CUDA Cores: 40,960
|-
  NVIDIA Tensor Cores (on Tesla V100 based systems): 5,120
| Computational resources for AI infrastructure at NU
  System Memory: 512 GB 2,133 MHz DDR4 RDIMM
| NVIDIA DGX-1 (1 supercomputer):<br>GPUs: 8 x NVIDIA Tesla V100<br>GPU Memory: 256 GB<br>CPU: ...
  Storage: 4X 1.92 TB SSD RAID 0
| Yerbol Absalyamov<br>Technical Project Coordinator, Office of the Provost - Institute of Smart Systems and Artificial Intelligence, Nazarbayev University<br>Email: [[mailto:yerbol.absalyamov@nu.edu.kz|yerbol.absalyamov@nu.edu.kz]]<br>Makat Tlebaliyev<br>Computer Engineer, Office of the Provost - Institute of Smart Systems and Artificial Intelligence, Nazarbayev University<br>Email: [[mailto:makat.tlebaliyev@nu.edu.kz|makat.tlebaliyev@nu.edu.kz]]
  Network: Dual 10 GbE, 4 IB EDR
|}
  Operating System Canonical Ubuntu, Red Hat Enterprise Linux Zhandos
  Yessenbayev (Senior Researcher, Laboratory of Computational Materials
  Science for Energy Application, Private Institution National Laboratory
  Astana)
  Email: [12]zhyessenbayev@nu.edu.kz
  Computational resources for AI infrastructure at NU NVIDIA DGX-1 (1
  supercomputer):
  GPUs:8 x NVIDIA® Tesla® V100
  GPU Memory 256 GB
  CPU Dual 20-Core Intel Xeon E5-2698 v4 2.2 GHz
  System Memory 512 GB, 2,133 MHz DDR4 RDIMM
  Storage 4X 1.92 TB SSD RAID 0
  Performance: 1PF
  NVIDIA DGX-2 (2 supercomputers):
  GPUs: 16 x NVIDIA® Tesla® V100
  GPU: Memory 512 GB total
  CPU: Dual Intel Xeon Platinum 8168, 2.7 GHz, 24-cores
  System Memory: 1.5TB DDR4 RDIMM
  Storage: 2 x 960GB NVME SSDs
  Internal Storage: 30TB (8X 3.84TB) NVME SSDs
  Performance: 4PF
  NVIDIA DGX A100 (4 supercomputers):
  DGX A100 (01,02,03,04)
  GPUs: 8 x NVIDIA A100 40 GB GPUs
  GPU: Memory 320 GB total
  CPU: Dual AMD Rome 7742, 128 cores total, 2.25 GHz (base), 3.4 GHz (max
  boost)
  System Memory: 1TB DDR4 RDIMM
  Storage: 2 x 1.92TB M.2 NVME drives
  Internal Storage: 15 TB (4x 3.84 TB) U.2 NVMe drives
  Performance: 20PF
  Total:
  NVIDIA DGX (580 Cores x Intel,AMD, 3 TB RAM, 128 ТB RAID HDD, Ubuntu) –
  max computing performance 25 PFlops: specifically designed architecture
  optimized for Deep Learning,Machine Learning,Natural Language
  Processing,Computer Vision. Yerbol Absalyamov (Technical Project
  Coordinator, Office of the Provost - Institute of Smart Systems and
  Artificial Intelligence, Nazarbayev University)
  Email: [13]yerbol.absalyamov@nu.edu.kz
  Makat Tlebaliyev (Computer Engineer, Office of the Provost - Institute
  of Smart Systems and Artificial Intelligence, Nazarbayev University)
  Email: [14]makat.tlebaliyev@nu.edu.kz����le to do so outside of the official workdays and hours.

Latest revision as of 14:03, 13 May 2024

Key Features at a Glance:

  • 20 Compute nodes with dual AMD EPYC 7502 CPUs (32 cores / 64 threads, 2.5 MHz Base), 256 GB 8-channel DDR4-2933 RAM, CentOS 7.9
  • 4 Compute nodes with dual AMD EPYC 7452 CPUs (32 cores / 64 threads, 2.3 MHz Base), 256 GB 8-channel DDR4-2933 RAM, dual NVidia Tesla V100 GPUs 32GB HBM2 RAM, CentOS 7.9
  • 1 interactive login node with AMD EPYC 7502P CPU (32 cores / 64 threads, 2.5 MHz Base), 256 GB 8-channel DDR4-2933 RAM, Red Hat Enterprise Linux 7.9
  • EDR Infiniband 100 Gb/s interconnect for compute traffic
  • 16TB internal NVMe SSD Storage (HPE Clustered Extents File System)
  • 144TB HPE MSA 2050 SAS HDD Array
  • Theoretical peak CPU performance of the system is 60 TFlops (double precision)
  • Theoretical peak GPU performance of the system is 65 TFlops (double precision)
  • SLURM job scheduler


  The system is assembled in a two-rack configuration and is physically located at NU Data Center

Other NU research computing clusters

Cluster name Short description Contact details
High-performance bioinformatics cluster "Q-Symphony" Hewlett-Packard Enterprise – Apollo
(208 Cores x Intel Xeon, 3.26 TB RAM, 258 TB RAID HDD, RedHat Linux)
Max computing performance: 7.5 TFlops
Optimized for bioinformatics research and big genomics datasets analysis 		Ulykbek Kairov
Head of Laboratory - Leading Researcher, Laboratory of bioinformatics and systems biology, Private Institution National Laboratory Astana
Email: [[1]]
Intelligence-Cognition-Robotics GPUs: 8X NVIDIA Tesla V100
Performance: 1 petaFLOPS
GPU Memory: 256 GB total
CPU: Dual 20-Core Intel Xeon, E5-2698 v4 2.2 GHz
... 		Zhandos Yessenbayev
Senior Researcher, Laboratory of Computational Materials Science for Energy Application, Private Institution National Laboratory Astana
Email: [[2]]
Computational resources for AI infrastructure at NU NVIDIA DGX-1 (1 supercomputer):
GPUs: 8 x NVIDIA Tesla V100
GPU Memory: 256 GB
CPU: ... 		Yerbol Absalyamov
Technical Project Coordinator, Office of the Provost - Institute of Smart Systems and Artificial Intelligence, Nazarbayev University
Email: [[3]]
Makat Tlebaliyev
Computer Engineer, Office of the Provost - Institute of Smart Systems and Artificial Intelligence, Nazarbayev University
Email: [[4]]
Retrieved from "https://hpc.nu.edu.kz/index.php?title=Systems_1&oldid=425"