SuperMUC Petascale System

SuperMUC is the name of the hign-end supercomputer at Leibniz-Rechenzentrum (Leibniz Supercomputing Centre) in Garching near Munich (the MUC suffix is borrowed from the Munich airport code). With more than 155.000 cores and a peak performance of 3 Petaflop/s (=10^15 Floating Point Operations per second) is one of the fastest supercomputers in the world. The system will be upgrade to more than 6 Petaflop/s in the first half of 2015.

System purpose and target users

SuperMUC strengthens the position of Germany's Gauss Centre for Supercomputing in Europe by delivering outstanding compute power and integrating it into the European High Performance Computing ecosystem. With the operation of SuperMUC, LRZ will act as an European Centre for Supercomputing and will be Tier-0 centre of PRACE, the Partnership for Advanced Computing in Europe. SuperMUC is available to all European researchers to expand the frontiers of science and engineering.


Figure: SuperMUC Phase 1 in the computer room

System Configuration Details

LRZ's target for the architecture is a combination of a large number of moderately powerful compute nodes, with a peak performance of several hundred GFlop/s each, and a small number of fat compute nodes with a large shared memory. The network interconnect between the nodes allows for perfectly linear scaling of parallel applications up to the level of more than 10,000 tasks.

SuperMUC consists of 18 Thin Node Islands and one Fat Node Island which is at first also used as the Migration System SuperMIG. Each Island contains more than 8,192 cores. All compute nodes within an individual Island are connected via a fully non-blocking Infiniband network (FDR10 for the Thin nodes / QDR for the Fat Nodes). Above the Island level, the high speed interconnect enables a bi-directional bi-section bandwidth ratio of 4:1 (intra-Island / inter-Island). In June 2014 the Intel Xeon Phi based cluster SuperMIC has been integrated into SuperMUC. Details on SuperMIC can be found under

Technical data

Installation PhasePhase 1Phase 2
Installation Date 2011 2012 2013 2015


Fat Nodes Thin Nodes Many Cores Nodes Haswell Nodes
System BladeCenter HX5 IBM System x iDataPlex Cluster Nodes NeXtScale nx360M5 WCT
Processor Type Westmere-EX
Xeon E7-4870 10C
Sandy Bridge-EP
Xeon E5-2680
Ivy-Bridge (IvyB) and Xeon Phi 5110P Haswell Xeon Processor E5-2697 v3
Nominal Freqeuncy [GHz] 2.4 2.7  1.05 2.62
Total Number of nodes 205 9216 32 3096
Total Number of cores 8200 147,456 3840 (Phi) 74,304
Total Peak Performance [PFlop/s] 0.078 3.2 0.064 (Phi) 3.6
Total Linpack Performance [PFlop/s] 0.065 2.897  n.a. ~2.6  
Total size of memory [TByte] 52 288  2.56 194
Total Number of Islands 1 18  1 6
Typical Power Consumption [MW] < 2.3  tbd
Nodes per Island 205 512  32 512
Processors per Node 4 2

 2 (IvyB) 2.6 GHz + 2 Phi 5110P

Cores per Processor 10 8  8 (IvyB) + 60 (Phi) 14
Cores per Node 40 16  16 (host) + 120 (Phi) 28
Logical CPUs per Node (Hyperthreading) 80 32  32 (host) + 480 (Phi)  56
Memory and Caches
Memory per Core [GByte]
(typically available for applications)
 4 (host) + 2 x 0.13 (Phi) 2.3
 Size of shared Memory per node [GByte] 256 32  64 (host) + 2 x 8 (Phi) 64
Bandwidth to Memory per node [Gbyte/s] 136.4 102.4  Phi: 384 137
Level 3 Cache Size (shared) [Mbyte] 4x30 2x20 4x18
Level 2 Cache Size per core [kByte] 256 256  Phi: 512 256
Level 1 Cache Size [kByte] 32 32  32 32
Latency Access Memory ~160 ~200
Level 3 Latency [cycles] ~ 30 36
Level 2 Latency [cycles]1 12 12
Level 1 Latency [cycles]1 4 4 4
Latency Access Memory ~160 ~200
Technology Infiniband FDR10  Infiniband FDR14
Intra-Island Topology non-blocking Tree non-blocking Tree
Inter-Island Topology Pruned Tree 4:1 Pruned Tree 4:1
Bisection bandwidth of Interconnect [TByte/s] 35.6  
Login Servers for users 5 6
Service and management Servers 12 12
Size of parallel storage (SCRATCH/WORK) [Pbyte] 10 +5
Size of NAS storage (HOME) [PByte] 1.5 (+ 1.5 for replication) +2  (+2 for replication)
Aggregated bandwidth to/from parallel storage [GByte/s] 200 +100
Aggregated bandwidth to/from NAS storage [GByte/s] 10 +5
Capacity of Archive and Backup Storage [PByte] > 30
System Software
Operating System Suse Linux Enterprise Server (SLES)
Batchsystem IBM Loadleveler
Parallel Filesystem for SCRATCH and WORK IBM GPFS
File System for HOME NetApp NAS
Archive and Backup Software IBM TSM
System Management xCat from IBM
Monitoring Icinga, Splunk

1:Latency is much longer, if data are also in L1 or L2 of other core.
2: With each new processor line, Intel introduces new architecture optimizations. The design of the “Haswell” architecture acknowledges that highly-parallel/vectorized applications place the highest load on the processor cores (requiring more power and thus generating more heat). While a CPU core is executing intensive vector tasks (AVX instructions), the clock speed may be reduced to keep the processor within its power limits (TDP). In effect, this may result in the processor running at a lower frequency than the “base” clock speed advertised for each model. For that reason, each “Haswell” processor model is assigned two “base” frequencies:

  • AVX mode: due to the higher power requirements of AVX instructions, clock speeds may be somewhat lower while executing AVX instructions
  • Non-AVX mode: while not executing AVX instructions, the processor will operate at what would traditionally be considered the “stock” frequency


Figure: Schematic view of SuperMUC Phase1

SuperMUC Phase1 and Phase2 are only loosely coupled through the common used GPFS and NAS File systems. It is not possible to run a job across Phase1 and Phase2. The scheduling and job classes of Phase1 and Phase2 are different. However, Phase1 and Phase2 share the same programming environment.


Figure: Schematic view of SuperMUC Phase1 + Phase2

Energy Efficiency by Warm Water cooling

SuperMUC uses a new, revolutionary form of warm water cooling developed by IBM. Active components like processors and memory are directly cooled with water that can have an inlet temperature of up to 40 degrees Celsius. The "High Temperature Liquid Cooling" together with very innovative system software promises to cut the energy consumption of the system. In addition, all LRZ buildings will be heated re-using this energy.

Why "warm" water cooling?

Typically water used in data centers has an inlet temperature of approx 16 degrees Celsius and, after leaving the system, an outlet temperature of approx. 20 degrees Celsius. To make water with 16 degrees Celsius requires complex and energy-hungry cooling equipment. At the same time there is hardly any use for the warmed-up water as it is too cold to be uses in any technical processes.

SuperMUC allows an increased inlet temperature. It is easily possible to provide water having up to 40 degrees Celsius using simple "free-cooling" equipment as outside temperatures in Germany hardly ever exceed 35 degrees Celsius. At the same time the outlet water can be made quite hot (up to 70 degrees Celsius) and re-used in other technical processes - for example to heat buildings or in other technical processes.

By reducing the number of cooling components and using free cooling LRZ expects to save several millions of Euros in cooling costs over the 5-year lifetime of the system.

Storage Systems

SuperMUC has a powerful I/O-Subsystem which helps to process large amounts of data generated by simulations.

Home file systems

Permanent storage for data and programs is provided by a 16-node NAS cluster from Netapp. This primary cluster has a capacity of 2 Petabytes and has demonstrated an aggregated throughput of more than 10 GB/s using NFSv3. Netapp's Ontap 8 "Cluster-mode" provides a single namespace for several hundred project volumes on the system. Users can access multiple snapshots of data in their home directories.

Data is regularly replicated to a separate 4-node Netapp cluster with another 2 PB of storage for recovery purposes. Replication uses Snapmirror-technology and runs with up to 2 GB/s in this setup.

Storage hardware consists of >3400 SATA-Disks with 2 TB each protected by double-parity RAID and integrated checksums.

Work and Scratch areas

For highest-performance checkpoint I/O IBM's General Parallel File System (GPFS) with 10 PB of capacity and an aggregated throughput of 200 GB/s is available. Disk storage subsystems were built by DDN.

Tape backup and archives

LRZ's tape backup and archive systems based on TSM (Tivoli Storage Manager) from IBM are used for or archiving and backup. The have been extended to provide more than 30 Petabytes of capacity to the users of SuperMUC. Digital long-term archives help to preserve results of scientific work on SuperMUC. User archives are also transferred to a disaster recovery site.

Visualization and Support systems

SuperMUC will be connected to powerful visualization systems: the new LRZ office building houses a large 4K stereoscopic powerwall as well as a 5-sided CAVE artificial virtual reality environment.

See also: