GPU Deep Learning Box with 4x NVIDIA GPUs
Deep learning is one of the fastest-growing segments of the machine learning/artificial intelligence field and a key area of innovation in computing. With researchers creating new deep learning algorithms and industries producing and collecting unprecedented amounts of data, computational capability is the key to unlocking insights from data.
The Deep Learning Development Box includes:
Four NVIDIA GPUs with high bandwidth memory. NVIDIA DIGITS software providing powerful design, training, and visualization of deep neural networks for image classification. Pre-installed standard Ubuntu 16.04, cuDNN v3, and CUDA 8.0. A single deskside machine that plugs into standard wall plug, with superior PCIe topology. The end result is faster turnaround times for experiments, the freedom to explore multiple network architectures, and accelerated dataset manipulation—all in one powerful, energy-efficient, cool, and quiet solution that fits under your desk.
Specification:
- AMD Ryzen Threadripper, up to 64 Cores
- 4x NVIDIA GeForce RTX 3070/3080/3090, RTX Quadro, Titan V or 2x RTX Titan
(7 TFlops of single precision, 336.5 GB/s of memory bandwidth, and 12 GB of memory per board)
- 8x DIMM-Sockets for up to 256 GB Quad-Channel DDR4 3200 MHz RAM
- 1 TB SSD system disk and 6 TB Harddisc as standard
- Gigabit-LAN-Ports
- 8x SATA3, 2x M.2 (PCIe Gen 4.0 x4), 1x M.2 (PCIe Gen 4.0 x4 & SATA)
- 1600W Platinum level efficiency power supply
- Pre-installed standard Ubuntu 16.04 with CUDA Toolkit and cuDNN
Remarks:
If the system is equipped with 4x High Performance GPU's, the Supermicro Case must be selected.
Liquid Cooling on request.
Weiterlesen
Beschreibung ausblenden