Changes between Version 8 and Version 9 of Public/User_Guide/System_overview
- Timestamp:
- Oct 22, 2019, 12:45:49 PM (5 years ago)
Legend:
- Unmodified
- Added
- Removed
- Modified
-
Public/User_Guide/System_overview
v8 v9 37 37 === SSSM rack === 38 38 39 This rack hosts the master nodes, files servers and the storage as well network components for the Gigabit Ethernet administration and service networks. Users can access the login node via '''!deep@fz-juelich.de''' (implemented as virtual machine running on the master nodes).39 This rack hosts the master nodes, files servers and the storage as well as network components for the Gigabit Ethernet administration and service networks. Users can access the login node via '''!deep@fz-juelich.de''' (implemented as virtual machine running on the master nodes). 40 40 41 41 === CM rack === … … 63 63 64 64 65 === SDV rack === 66 67 Along with the prototype systems serveral test nodes and so called software development vehicles have been installed in the scope of the DEEP(-ER,EST) projects. These are located in the SDV rack. The following components can be accessed by the users: 68 69 65 70 * Prototype DAM [4 nodes]: `protodam[01-04]` 66 71 * 2 x Intel Xeon 'Skylake' (26 cores per socket) 67 72 * 192 GB RAM 68 73 * network: Gigabit Ethernet 69 70 === SDV rack ===71 72 Along with the prototype systems serveral test nodes and so called software development vehicles have been installed in the scope of the DEEP(-ER,EST) projects. These are located in the SDV rack. The following components can be accessed by the users:73 74 74 75 * Cluster [16 nodes]: `deeper-sdv[01-16]` … … 78 79 * network: 100 Gb/s Extoll tourmalet 79 80 80 * KNLs [ 8 nodes]: `knl[01-08]`81 * KNLs [4 nodes]: `knl[01,04-06]` 81 82 * 1 Intel Xeon Phi (64-68 cores) 82 83 * 1 NVMe with 400 GB per node (accessible through BeeGFS on demand) … … 84 85 * network: Gigabit Ethernet 85 86 87 {{{#!comment have been removed meanwhile 86 88 * KNMs [2 nodes]: `knm[01-02]` 87 89 * 1 Intel Xeon Phi - Knight Mill (72 cores) 88 90 * 16 GB MCDRAM plus 96 GB RAM per KNL 89 91 * network: Gigabit Ethernet 92 }}} 90 93 91 94 * GPU nodes for ML [3 nodes]: `ml-gpu[01-03]` … … 100 103 * details: https://www.deep-projects.eu/hardware/memory-hierarchies/49-nam 101 104 105 {{{#!comment Not available anymore 102 106 === FPGA test server === 103 107 … … 108 112 * 64 GB RAM 109 113 * 1 x Intel Arria 10 PAC 110 114 }}} 111 115 112 116 == Network overview ==