Sisu (sisu.csc.fi) supercomputer is the most powerful supercomputer in Finland and one of the most powerful in Northern Europe. Sisu's Cray XC40 system architecture is designed from the ground up for High Performance Computing (HPC).
Sisu targeted for massively parallel applications that can effectively run on hundreds to thousands of compute cores in parallel. Obtaining this level of scaling with even very tightly-coupled parallel computations is made possible by the extremely high-bandwidth, low-latency Aries interconnect.
The currently installed second phase of Sisu consists of nine cabinets, with a total theoretical peak performance of 1688 TFlop/s.
- 1688 compute nodes, each with two Intel Xeon E5-2690v3 (Haswell microarchitecture) 2,6GHz 12 core CPUs, totalling in 40512 cores
- 64GB of memory (2,67 GB/core) in each node
- Aries interconnect between compute nodes
Sisu's performance has been increased significantly with the second phase upgrade in August 2014.
Using more than 1024 cores for a single calculation requires that the application's scalability is demonstrated. The instructions for demonstrating the scalability on Sisu can be found here.
Taito (taito.csc.fi) supercluster is intended for serial (single core) and small to medium-size parallel jobs. There are also several "fat nodes" for jobs requiring a large amount of memory.
Taito consists of sixteen cabinets, with a total theoretical peak performance of 600 TFlop/s. Taito has been deployed in two phases, which currently coexist.
Second phase (available since January 2015):
- 407 Apollo 6000 XL230a G9 server blades, each with two twelve core Intel Haswell E5-2690v3 CPUs, for a total of 9768 cores
- 128 GB of memory on normal nodes
- 256 GB of memory on 24 "big memory" nodes
First phase (available since April 2013):
- 576 HP ProLiant SL230s servers each equipped with two eight core Intel Xeon 2.6 GHz E5-2670 CPUs, totaling in 9216 cores.
- 64 GB of memory on normal nodes
- 256 GB (16 GB/core) of memory in 16 "fat nodes"
- 1.5 TB (48 GB/core) of memory in 2 "hugemem" nodes, with 32 cores each
The compute nodes are connected with a high-bandwidth, low-latency Infiniband FDR interconnect.
A subset of the compute nodes is allocated for the Pouta cloud service. The exact amount of nodes allocated for Pouta is adjusted depending on the demand for cloud resources.
The system contains servers with Intel Xeon Phi coprocessors and NVidia GPU accelerators. These specialized processors are specifically designed for high-performance computing and can provide superior performance compared to traditional CPUs. However, to utilize the capabilities fully, one needs to either have an existing application that is compatible with the processors or perform the porting and optimization work.
CSC and other European HPC centers provide courses regularly on porting and optimizing for these architectures.
The system consists of the following:
- Two direct-liquid-cooled Bull DLC B700-series chassis and one service rack
- 36 nodes with dual Nvidia Kepler K40 GPGPUs
- 44 nodes with dual Intel Xeon Phi 7120X coprocessors
- Dual Intel Xeon E5 2620 v2 CPUs in each node
- 6 cores per CPU, 2.1GHz, Ivy Bridge microarchitecture
- 32GB of RAM in each node
Logically the Bull system is a part of Taito; there are Taito-GPU and Taito-MIC partiotions. Access and usage instructions can be found in the Taito user guide (NVidia GPU (Taito-GPU) chapter, Intel Xeon Phi (Taito-MIC) chapter).