CRIS-Export

TinyFat addresses applications with the demand for large main memory  and has nodes with three different types:

• 8 nodes with 2x 2x Intel Xeon E5-2643 v4 (“Broadwell”) @3.4 GHz = 12 cores/24 threads and 256 GB main memory
• 3 nodes with 2x Intel Xeon E5-2680 v4 (“Broadwell”) @2.4 GHz = 28 cores/56 threads and 512 GB main memory
• 36 nodes with 2x AMD Rome 7502 @2.5 GHz = 64 cores/128 threads and 512 GM main memory
  

All nodes have been purchased/financed by specific groups or special projects. These users have priority access and nodes may be reserved exclusively for them.

The RRZE’s "Woody" is the preferred cluster for serial/single-node throughput jobs.

The cluster has changed significantly over time. You can find more about the history in the section about history.  The current hardware configuration looks like this:

• 70 compute nodes (w11xx nodes) with Xeon E3-1240 v3 CPUs („Haswell“, 4 cores, HT disabled, 3,4 GHz base frequency), 8 GB RAM, 1 TB HDD – from 09/2013
• 64 compute nodes (w12xx/w13xx nodes) with Xeon E3-1240 v5 CPUs („Skylake“, 4 cores, HT disabled, 3,5 GHz base frequency), 32 GB RAM, 1 TB HDD – from 04/2016 and 01/2017
• 112 compute nodes (w14xx/w15xx nodes) with Xeon E3-1240 v6 CPUs („Kaby Lake“, 4 cores, HT disabled, 3,7 GHz base frequency), 32 GB RAM, 960 GB SDD – from Q3/2019
  

TinyGPU addresses the increasing demand for GPGPU-accelerated HPC systems and has nodes with six different types of GPUs (mostly of consumer type):

• 7 nodes with 2x Intel Xeon E5-2620v4 („Broadwell“, 8 Cores@2.1 GHz); 64 GB main memory; 4x NVIDIA Gefroce GTX 1080 (8 GB memory); 1.8 TB SSD
• 10 nodes with 2x Intel Xeon E5-2620v4 („Broadwell“, 8 Cores@2.1 GHz); 64 GB main memory; 4x NVIDIA Geforce GTX 1080Ti (11 GB memory); 1.8 TB SSD
• 12 nodes with 2x Intel Xeon Gold 6134 („Skylake“, 8 Cores@3.2 GHz); 96 GB main memory; 4x NVIDIA Geforce RTX 2080 Ti (11 GB memory); 1.8 TB SSD
• 4 nodes with 2x Intel Xeon Gold 6134 („Skylake“, 8 Cores@3.2 GHz); 96 GB main memory; 4x NVIDIA Tesla V100 (32 GB memory); 2.9 TB SSD
• 7 nodes with 2x Intel Xeon Gold 6226R („Cascadelake“, 16 Cores@2.9 GHz); 394 GB main memory; 8x NVIDIA Geforce RTX3080 (10 GB memory); 3,8 TB SSD
• 8 nodes with 2x AMD Epyc 7662 („Rome“, 64 Cores@2,0 GHz); 512 GB main memory; 4x NVIDIA A100 SXM4/Nvlink; 6,4 TB SSD
  

45 out of the 48 nodes have been purchased/financed by specific groups or special projects. These users have priority access and nodes may be reserved exclusively for them.

RRZE’s Emmy cluster (NEC) is a high-performance compute resource with high speed interconnect. It is intended for distributed-memory (MPI) or hybrid parallel programs with medium to high communication requirements.

• 560 compute nodes, each with two Xeon 2660v2 „Ivy Bridge“ chips (10 cores per chip + SMT) running at 2.2 GHz with 25 MB Shared Cache per chip and 64 GB of RAM.
• 2 front end nodes with the same CPUs as the compute nodes.
• 16 Nvidia K20 GPGPUs spread over 10 compute nodes plus 4 nodes each with a Nvidia V100/16GB GPGPU.
• parallel filesystem (LXFS) with a capacity of 400 TB and an aggregated parallel I/O bandwidth of > 7000 MB/s
• fat-tree InfiniBand interconnect fabric with 40 GBit/s bandwidth per link and direction
• overall peak performance of ca. 234 TFlop/s (191 TFlop/s LINPACK, using only the CPUs).
  

The Emmy cluster is named after famous mathematician Emmy Noether who was born he

The RRZE’s Meggie cluster (manufacturer: Megware) is a high-performance compute resource with high speed interconnect. It is intended for distributed-memory (MPI) or hybrid parallel programs with medium to high communication requirements.

• 728 compute nodes, each with two Intel Xeon E5-2630v4 „Broadwell“ chips (10 cores per chip) running at 2.2 GHz with 25 MB Shared Cache per chip and 64 GB of RAM.
• 2 front end nodes with the same CPUs as the compute nodes but 128 GB of RAM.
• Lustre-based parallel filesystem with a capacity of almost 1 PB and an aggregated parallel I/O bandwidth of > 9000 MB/s.
• Intel OmniPath interconnect with up to 100 GBit/s bandwidth per link and direction.
• Measured LINPACK performance of ~481 TFlop/s.
  

Meggie is a system that is designed for running parallel programs using significantly more than one node.

TinyGPU addresses the increasing demand for GPGPU-accelerated HPC systems and has nodes with six different types of GPUs (mostly of consumer type):

• 7 nodes with 2x Intel Xeon E5-2620v4 („Broadwell“, 8 Cores@2.1 GHz); 64 GB main memory; 4x NVIDIA Gefroce GTX 1080 (8 GB memory); 1.8 TB SSD
• 10 nodes with 2x Intel Xeon E5-2620v4 („Broadwell“, 8 Cores@2.1 GHz); 64 GB main memory; 4x NVIDIA Geforce GTX 1080Ti (11 GB memory); 1.8 TB SSD
• 12 nodes with 2x Intel Xeon Gold 6134 („Skylake“, 8 Cores@3.2 GHz); 96 GB main memory; 4x NVIDIA Geforce RTX 2080 Ti (11 GB memory); 1.8 TB SSD
• 4 nodes with 2x Intel Xeon Gold 6134 („Skylake“, 8 Cores@3.2 GHz); 96 GB main memory; 4x NVIDIA Tesla V100 (32 GB memory); 2.9 TB SSD
• 7 nodes with 2x Intel Xeon Gold 6226R („Cascadelake“, 16 Cores@2.9 GHz); 394 GB main memory; 8x NVIDIA Geforce RTX3080 (10 GB memory); 3,8 TB SSD
• 8 nodes with 2x AMD Epyc 7662 („Rome“, 64 Cores@2,0 GHz); 512 GB main memory; 4x NVIDIA A100 SXM4/Nvlink; 6,4 TB SSD
  

45 out of the 48 nodes have been purchased/financed by specific groups or special projects. These users have priority access and nodes may be reserved exclusively for them.