sysGen devCUBE User Guide Introduction devCUBE Overview
Contents
1. f your electrical 60 Hz source s power capability to avoid overloading the circuit Connector Ports Type Qty Description DisplayPort 1 per GeForce TITAN X card HDMI 1 per GeForce TITAN X card Ethernet 2 RJ45 LAN port 1 Gbps Audio 8 Mini stereo jack audio output Audio 1 Optical S PDIF output USB 12 USB 3 0 2 USB 2 0 eSATA 2 6 Gbps eSATA port Lan Port Indicator LEDs on each ethernet port indicate the connection status as described in the following tables Activity Link LED Status Description Off No link Orange Linked Orange blinking Data activity Orange blinking then steady Ready to wake Speed LED ACT LINK SPEED D LED Status Description Off 10 Mbps connection Orange 100 Mbps connection Green 1 Gbps connection2. sysGen devCUBE User Guide Introduction Background Deep learning is one of the fastest growing segments in the machine learning artificial intelligence field It uses algorithms to model high level abstractions of data in order to gain meaningful insight for practical application Such data manipulation has application in various fields such as computer vision speech recognition and language processing and audio recognition It takes tremendous processing power to efficiently process such huge amounts of data using deep learning algorithms To that end sysGen offers an all in one powerful energy efficient cool and quiet deskside solution called the sysGen devCUBE devCUBE Overview The devCUBE combines the world s best hardware software and systems engineering for deep learning in a powerful solution that can fit under your desk It is a single deskside machine comprised of e Upto Four NVIDIA GeForce TITAN X GPUs e NVIDIA DIGITS software Interactive Deep Learning GPU Training System e Pre installed Ubuntu 14 04 2 e Pre installed deep learning frameworks Caffe Torch Theano and BIDMach e NVIDIA CUDA Deep Learning Neural Network library cuDNN v2 e NVIDIA CUDA Toolkit 7 0 devCUBE Specification Feature and Architecture Summary CPU Intel Core i7 processor on an ASUS x99E WS motherboard with 64 GB DDR4 memory GPU Up to Four NVIDIA GeForce TITAN X GPUs installed with NVIDIA qualified drivers Opera
3. ting System and Software The system comes with the following software and OS pre installed on the SATA3 SSD e Ubuntu 14 04 2 e NVIDIA DIGITS Software e Caffe Torch Theano and BIDMach deep learning frameworks e NVIDIA CUDA Toolkit 7 0 including the CUDA Deep Learning Neural Network library CcuDNN v2 Storage Internal swap Frame 3x 3 5 HDD and 6x 2 5 HDD SSD drives External hot swap 8x 2 5 HDD SSD drives pre selected or 3x 3 5 HDD drives Component Specifications Components Component Qty Description Motherboard 1 ASUS X99 E WS with 4xPCle x16 slots For the full motherboard spec see http dicdnet asus com pub ASUS server e9552 x99 e ws ug for web only pdf CPU 1 Intel 6 core i7 5930K RAM 2 2x32 GB DDR4 4x8GB DDR4 DRAM 2133MHz GPU 4 GeForce TITAN X featuring e 7 teraflops of single precision computing power e 336 5 GB s of memory bandwidth and e 12 GB of memory RAID 8 Depending on HDD SSD drives Storage Data Single drives or raids possible Storage cache 1 256GB Samsung PM851 SATA 6 SSD Storage OS 1 256GB Samsung PM851 SATA 6 SSD y Power Supply Enermax MaxRevo 1500W Mechanical Component Description Height 18 458mm Width 13 332mm Depth 16 3 415mm Gross Weight 48 Ibs Power Input Comments 115 240 VAC The sysGen devCube power consumption can reach 1350W ambient temperature 17 10A 50 30 C with all system resources under a heavy load Be aware o
Download Pdf Manuals
Related Search