2 | | || || SuperMIC || Stampede || Gordon |
3 | | || Computing Nodes || 360 || 6400 || 1024 || |
4 | | || Processor || Each computing node has two 2.8GHz 10-Core Ivy Bridge-EP E5-2680 Xeon Processors || Each computing node has two 2.7 GHz 8-core Xeon E5-2680 (Sandy Bridge) processors || Each compute node contains two 8-core 2.6 GHz Intel EM64T Xeon E5 (Sandy Bridge) processors || |
5 | | || Co-Processors || Each computing node has two Intel Xeon Phi 7120P 61-core Coprocessors(1.238GHz,16GB) ||Each compute node is configured with an Intel Xeon Phi 5110p 61-core coprocessor(1.05GHz,8GB) || none || |
6 | | || Memory || 64GB DDR3 1866MHz Ram || 32GB DDR3 1600MHz Ram , with an additional 8GB of memory on each Xeon Phi coprocessor card || 64 GB of DDR3-1333 Ram || |
7 | | || Hybrid Compute Nodes || 20 Hybrid nodes, each with two Processors + one Coprocessor + One NVIDIA Tesla K20X 6GB GPU || 128 compute nodes with NVIDIA Kepler K20 5GB GPU || none || |
8 | | || Available SUs || 2,000,000 || 175,000,000 || 25,000,000 || |
9 | | || SU Convert || 5 || 1 || 1 || |
| 2 | || || SuperMIC || Stampede || Gordon || Trestle || |
| 3 | || Computing Nodes || 360 || 6400 || 1024 || 324 || |
| 4 | || Processor || Each computing node has two 2.8GHz 10-Core Ivy Bridge-EP E5-2680 Xeon Processors || Each computing node has two 2.7 GHz 8-core Xeon E5-2680 (Sandy Bridge) processors || Each compute node contains two 8-core 2.6 GHz Intel EM64T Xeon E5 (Sandy Bridge) processors || Each compute node contains four sockets, each with a 8-core 2.4 GHz AMD Magny-Cours processor, for a total of 32 cores per node || |
| 5 | || Co-Processors || Each computing node has two Intel Xeon Phi 7120P 61-core Coprocessors(1.238GHz,16GB) ||Each compute node is configured with an Intel Xeon Phi 5110p 61-core coprocessor(1.05GHz,8GB) || none || none || |
| 6 | || Memory || 64GB DDR3 1866MHz Ram || 32GB DDR3 1600MHz Ram , with an additional 8GB of memory on each Xeon Phi coprocessor card || 64 GB of DDR3-1333 Ram || 64 GB of DDR3 Ram || |
| 7 | || Hybrid Compute Nodes || 20 Hybrid nodes, each with two Processors + one Coprocessor + One NVIDIA Tesla K20X 6GB GPU || 128 compute nodes with NVIDIA Kepler K20 5GB GPU || none || none || |
| 8 | || Available SUs || 2,000,000 || 175,000,000 || 25,000,000 || 16,000,000 || |
| 9 | || SU Convert || 5 || 1 || 1 || 2 || |