| |
|
|
| |
|
|
| |
|
|
|
World-Class Computing
Performance in the Hands of Your Team
|
|
|
|
|
|
| Your data science team depends on
computing performance to gain insights and innovate
faster through the power of AI and deep learning.
Designed for your data science team, NVIDIA® DGX
Station™ is the world's fastest workstation for
leading-edge AI development. DGX Station is the only
workstation with four NVIDIA® Tesla® V100 Tensor Core GPUs, integrated
with a fully connected four-way NVIDIA
NVLink™ architecture. With 500 TFLOPS of supercomputing
performance, your entire data science team can
experience over 2X the training performance of today's
fastest workstations. |
|
|
|
|
|
|
This ground-breaking solution offers :
- 72X the performance for deep learning training, compared with
- CPU-based servers
- 100X speedup on large data set analysis, compared with a 20 node Spark
- server cluster
- 5X increase in bandwidth compared to PCIe with NVLink technology
- Maximized versatility with deep learning training and over 30,000 images per
second inferencing.
Experiment faster and iterate more frequently for effortless productivity.
|
 |
| |
|
NVIDIA DGX Station
|
|
|
|
| |
|
|
| |
SYSTEM SPECIFICATIONS -
NVIDIA DGX SOFTWARE STACK
|
|
| |
|
|
| |
|
GPUs
|
4X Tesla V100
|
|
TFLOPS (Mixed precision)
|
500
|
|
GPU Memory
|
128 GB total system
|
|
NVIDIA Tensor Cores
|
2,560
|
|
NVIDIA CUDA® Cores
|
20,480
|
|
CPU
|
Intel Xeon E5-2698 v4 2.2 GHz (20-Core)
|
|
System Memory
|
256 GB RDIMM DDR4
|
|
Storage Data:
|
3X 1.92 TB SSD RAID 0
|
|
OS:
|
1X 1.92 TB SSD
|
|
Network
|
Dual 10GBASE-T (RJ45)
|
|
Display
|
3X DisplayPort, 4K resolution
|
|
Additional Ports
|
2x eSATA, 2x USB 3.1, 4x USB 3.0
|
|
Acoustics
|
< 35 dB
|
|
System Weight
|
88 lbs / 40 kg
|
|
System Dimensions
|
518 D x 256 W x 639 H (mm)
|
|
Maximum Power Requirements
|
1,500 W
|
|
Operating Temperature Range
|
10 - 30 C
|
|
Software
|
Ubuntu Desktop Linux OS, Red Hat Enterprise Linux OS, DGX Recommended GPU
Driver, CUDA Toolkit
|
|
|
|
|
|
| |
|
|
|
|
|
|
| This integrated hardware and software solution
allows your data science team to easily access a
comprehensive catalog of NVIDIA optimized GPU-accelerated
containers that offer the fastest possible performance
for AI and data science workloads- provides access to
fully optimized DGX Software Stack. |
|
|
|
|
|
|
|
|
|
|
|
|
NVIDIA DGX-1
|
|
|
|
|
|
Inspired by the demands of AI and
data science, NVIDIA® DGX-1™ fast-tracks your AI
initiative with a solution that works right
out-of-the-box so that you can gain insights in hours
instead of months. With DGX-1 you can simply plug in,
power up, and get to work- with integrated NVIDIA deep
learning software stack.
DGX-1 removes the burden of continually optimizing your
deep learning software and delivers a ready-to-use,
optimized software stack that can save you hundreds of
thousands of dollars.
|
|
|
|
|
|
|
|
|
|
|
|
| |
SYSTEM SPECIFICATIONS - NVIDIA
DGX SOFTWARE STACK
|
|
| |
|
GPUs
|
8X NVIDIA Tesla V100
|
|
Performance (Mixed Precicion)
|
1 petaFLOPS
|
|
GPU Memory
|
256 GB total system
|
|
CPU
|
Dual 20-Core Intel Xeon E5-2698 V4 2.2 GHz
|
|
NVIDIA CUDA® Cores
|
40,960
|
|
NVIDIA Tensor Cores (on Tesla V100 based systems)
|
5,120
|
|
Power Requirement
|
3,500 W
|
|
System Memory
|
512 MB 2,133 MHz DDR4 RDIMM
|
|
Storage Data:
|
4X 1.92 TB SSD RAID 0
|
|
Operating System:
|
Canonical Ubuntu, Red Hat
Enterprise Linux
|
|
System Weight
|
134 lbs
|
|
System Dimensions
|
866 D * 444 w * 131 H (mm)
|
|
Packaging Dimensions
|
1,180 D * 730 W * 284 H (mm)
|
|
Operating Temperature Range
|
10 - 35C
|
|
|
|
|
|
| |
|
|
| |
|
|
|
|
|
|
|
|
|
NVIDIA DGX-2
|
|
|
|
|
|
| NVIDIA® DGX-2™ is the world's
first 2 petaflops system, packing the power of 16 of
the world's most advanced GPUs and accelerating the
newest deep learning model types that were previously
untrainable. With ground-breaking GPU scale, you can
train models 4X bigger on a single node.With
DGX-2,model complexity and size are no longer
constrained by the limits of traditional architectures.
Embrace model-parallel training with a networking
fabric that delivers 2.4TB/s of bisection bandwidth for
a 24X increase over prior generations. This new
interconnect superhighway enables limitless
possibilities for model types that can reap the power
of distributed training across 16 GPUs at once. |
|
|
|
|
|
|
|
|
|
|
|
| |
SYSTEM SPECIFICATIONS - NVIDIA
DGX SOFTWARE STACK
|
|
| |
|
GPUs
|
16X NVIDIA® Tesla® V100
|
|
GPU Memory
|
512GB total
|
|
Performance
|
2 petaFLOPS
|
|
NVIDIA CUDA® Cores
|
81920
|
|
NVIDIA Tensor Cores
|
10240
|
|
NVSwitches
|
12
|
|
Maximum Power Usage
|
10kW
|
|
CPU
|
Dual Intel Xeon Platinum 8168, 2.7 GHz, 24-cores
|
|
System Memory
|
1.5TB
|
|
Network
|
8X 100Gb/sec, Infiniband/100GigE, Dual 10/25/40/50/100GbE
|
|
Storage OS:
|
2X 960GB NVME SSDs
|
|
Internal Storage:
|
30TB (8X 3.84TB) NVME SSDs
|
|
Software
|
Ubuntu Linux OS, Red Hat Enterprise Linux OS (See software
stack for details)
|
|
System Weight
|
360 lbs (163.29 kgs)
|
|
Packaged System Weight
|
400lbs (181.44kgs)
|
|
System Dimensions Height:
|
17.3 in (440.0 mm), Width: 19.0 in (482.3 mm), Length: 31.3
in (795.4 mm) - No Front Bezel 32.8 in (834.0 mm) - With Front Bezel
|
|
Operating Temperature Range
|
5C to 35C (41F to 95F)
|
|
|
|
|
|
|
|
|
| |
|
|
|
|
|
|
|
|
|
|
|
