Supermicro(R) Debuts New NVIDIA Tesla GPU SuperServers Optimized for Extreme Parallel Computing
SAN JOSE, Calif., March 18, 2015 /PRNewswire/ — GPU Technology Conference — Super Micro Computer, Inc. (NASDAQ: SMCI), a global leader in high-performance, high-efficiency server, storage technology, and green computing today debuts its new 1U 4x GPU SuperServer® platform at the NVIDIA 2015 GPU Technology Conference (GTC) in San Jose, Calif. The new SYS-1028GQ-TRT supports up to 4 NVIDIA® Tesla® K80 dual-GPU accelerators (up to 300W) with a streamlined layout architecture that enables PCI-E direct connect for best signal integrity as well as elimination of complex cabling, repeaters, and GPU pre-heat for maximum airflow and cooling. The system also supports dual Intel® Xeon® E5-2600 v3 processors (up to 145W), up to 1TB ECC LRDIMM, 512GB ECC RDIMM, DDR4-2133MHz in 16 DIMM slots, 2x 2.5″ hot-swap SATA drives plus 2x 2.5″ internal drives, dual 10GBase-T ports and intelligent, cold redundant 2000W (1+1) Titanium Level high-efficiency power supplies. This high density compute platform is suited for high-performance computing clusters, 3D CAD/CAM/CAE, cloud and visualization, oil & gas, and deep learning applications.
“Supermicro is enabling a highly scalable, energy efficient future for parallel computing with our Green Computing solutions,” said Charles Liang, President and CEO of Supermicro. “Our expertise in maximizing compute density, performance and power efficiency is highlighted in our latest 1U GPU SuperServer that supports up to four NVIDIA GPU accelerators and dual CPUs powered by our highest efficiency cold redundant Titanium Level digital power supplies. With an extensive range of SuperServer platforms in 2U 6x GPU, 4U 8x GPU, 4U 4-node FatTwin 12x GPU, and 7U SuperBlade supporting 30x GPUs Supermicro offers an unrivaled range of flexible configurations to meet any scale supercomputing challenge.”
“Supermicro’s new high-density servers provide a range of computing solutions for enterprise and HPC customers,” said Sumit Gupta, general manager of Accelerated Computing at NVIDIA. “Designed to take full advantage of ultra-high performance Tesla GPU accelerators while minimizing power consumption, the servers bring new levels of energy-efficient performance for compute-intensive data analytics, deep learning and scientific applications.”
NVIDIA Tesla GPU accelerators are a key part of the NVIDIA Tesla Accelerated Computing Platform, the leading platform for accelerating data analytics, deep learning and scientific computing.