The 1U GPU accelerated server (OSS-PASCAL4) sets a new standard for HPC compute power in a space efficient design. Supporting four of the latest Pascal-based NVIDIA GPUs, the OSS-PASCAL4 provides 21.2 TeraFLOPS of double precision performance for the most demanding HPC applications. For state-of-the-art deep learning workloads the OSS-PASCAL4 provides 84.8 TeraFLOPS of half precision performance. GPU management and monitoring and software are preinstalled on the OSS-PASCAL4. The GPU accelerated server also includes dual high-performance “Broadwell” E5 2698v4 2.2GHZ processors and a base configuration of 512GB of DDR4 memory scalable to 1TB. Four PCIe Gen3 slots are available for additional expansion and for scale out creating GPUltima clusters using IB or high speed Ethernet networking. The appliance also includes two 2.5” removable 1.9TB SATA SSD drives.

  • 1U Chassis
  • Dual Intel Xeon 3.2GHz CPUs
  • Up to 1TB  DDR4 LRDIMM System Memory
  • Two 2.5” 1.9TB SATA SSDs
  • Four Pascal GPU SXM2 with 80GB/s NVLink
  • Three x16 PCIe 3.0 slots
  • One x8 PCIe 3.0 slot
  • Two 2000W Titanium Power Supplies
  • Choice of Machine Learning Framework
    • Caffe
    • Torch
    • Tensorflow
    • Theano
  • MLPython
  • ML Dependencies (400MB Python)
  • cuDNN (5.0 & 5.1)
  • Caffe on Spark
  • CUDA & NVIDIA driver
  • CUB (CUDA building blocks)
  • NCCL
  • GPU Management from Bright Computing
    • Health Management
    • Workload Integration