NVIDIA DGX-1 Volta V100 Swap Out Tray Upgrade

PNY NVIDIA DGX-1 V100 Volta GPU Swapout Upgrade Tray, Professional Upgrade for DGX-1 System w/ Pascal P100 to Volta V100

PNY
Scan code: LN85087 Manufacturer code: TCSDGX1UP2V-PB Request call
£46,541.99Item currently awaiting an ETA
Pre order
Spend over £225 and Buy Now, Pay Later or spread the cost of your finance over 24-48 months with a 10% deposit.
High End
Delivery options £11.50 By DPD DPD Delivered to your specified address. Receive SMS with one-hour delivery window. Free Collect Instore Q-Collect Place your order online and collect from our Bolton store with Q-Collect. Weekend, timed and European delivery options are available at checkout
Product Overview Education & Inception Pricing available upon request. Please contact us for further information & support.

Upgrade Your Pascal DGX-1 to the Latest Volta Architecture for Phenomenal Performance Gains
In partnership with PNY & NVIDIA, ourselves at Scan Computers International, NVIDIA’s top performing DGX partner, are able to offer the upgrade you need for your existing Pascal-based DGX-1 Deep Learning system to unlock the power of NVIDIA’s latest GPU architecture: Volta.

Packing 5120 CUDA cores per GPU vs the 3584 of the Pascal-based Tesla accelerator cards, the new Volta V100 chips pack ‘an ace up their sleeve’ in the form of 640 brand-new Tensor Cores per GPU, specifically designed to speed up the training of neural networks. Supported by 16GB of HBM2 memory per card, the 8x card Volta V100 upgrade provides you with 128GB of GPU memory across the entire system, leaving you with a total of 40,960 CUDA Cores (12,288 more than the Pascal DGX-1), and 5120 of the latest Tensor Cores, all linked together and connected to your Xeon CPUs with NVIDIA’s latest NVLink 2.0 interface.

Once upgraded to Volta, your entire DGX-1 system will be capable of 960 teraFLOPS at GPU FP16 – more than 5.5 times the performance of your existing Pascal DGX-1 running at 170 teraFLOPS.

Volta Upgrade Process
Once you have ordered your swap-out upgrade from ourselves, we will get in contact with you to arrange delivery of the upgrade tray and a visit from an engineer to professionally install your new Volta V100 hardware in your DGX-1 Deep Learning System.

The engineer will also carry out a software update on your DGX-1 during the upgrade process to ensure optimum performance with the new Volta V100 Tesla GPUs. As this is a swap-out upgrade your old Pascal-based GPU tray will be removed during the upgrade, and will be retained by the engineer for shipment back to NVIDIA.


Why Upgrade to NVIDA Volta?

The Core of AI
AI is not defined by any one industry. It exists in fields of supercomputing, healthcare, financial services, big data analytics, and gaming. It is the future of every industry and market because every enterprise needs intelligence, and the engine of AI is the NVIDIA GPU computing platform.

NVIDIA Volta™ is the new driving force behind artificial intelligence. Volta will fuel breakthroughs in every industry. Humanity’s moonshots like eradicating cancer, intelligent customer experiences, and self-driving vehicles are within reach of this next era of AI.


Ground-Breaking Innovations

640 Tensor Cores: An Exponential Leap in Performance
Every industry needs AI, and with this massive leap forward in speed, AI can now be applied to every industry. Equipped with 640 Tensor Cores, Volta delivers over 100 teraFLOPS per second (TFLOPS) of deep learning performance, over a 5X increase compared to prior generation NVIDIA Pascal™ architecture.

New GPU Architecture: Engineered for the Modern Computer
Humanity’s greatest challenges will require the most powerful computing engine for both computational and data science. With over 21 billion transistors, Volta is the most powerful GPU architecture the world has ever seen. It pairs NVIDIA® CUDA® and Tensor Cores to deliver the performance of an AI supercomputer in a GPU.

Next Generation NVLink: Scalability for Rapid Time-to-Solution
Volta uses next generation revolutionary NVIDIA NVLink™ high-speed interconnect technology. This delivers 2X the throughput, compared to the previous generation of NVLink. This enables more advanced model and data parallel approaches for strong scaling to achieve the absolute highest application performance.

Volta-Optimized Software: GPU-Accelerated Frameworks and Applications
Data scientists are often forced to make trade-offs between model accuracy and longer run-times. With Volta-optimized CUDA and NVIDIA Deep Learning SDK libraries like cuDNN, NCCL, and TensorRT, the industry’s top frameworks and applications can easily tap into the power of Volta. This propels data scientists and researchers towards discoveries faster than before.

Important, Please Note: This is a Swap-Out upgrade. Original Pascal-based GPUs & tray will be retained by engineer for return to NVIDIA. Features Education & Inception Pricing available upon request. Please contact us for further information & support.

• Upgrade your DGX-1 to the latest Volta architecture at a more economical cost than buying a brand new Volta DGX-1 System.
• Boost your deep learning performance by over 5x, from 170 TFLOPS to 960 TFLOPS GPU FP16.
• Take advantage of the new Tensor Cores designed for neural network training.
• Professional upgrade process with professional support from an Official NVIDIA DGX-1 Partner.
• Includes 8x Tesla V100 Volta GPUs, each with 5120 CUDA Cores, 640 Tensor Cores, & 16GB of HBM2 Memory.

Important, Please Note: This is a Swap-Out upgrade. Original Pascal-based GPUs & tray will be retained by engineer for return to NVIDIA.
Specifications
Edition DGX-1 V100 Volta Upgrade Tray
Form Factor  
CPU Included No
CPU Type  
Core  
No. of Threads N/A
CPU Model  
Clock Speed N/A
Burst Frequency N/A
CPU Cooler  
CPU Socket N/A
Chipset N/A
Motherboard Form Factor  
Memory Type  
Memory Included No
Memory Capacity Included N/A
Memory Channels  
Memory Type (ECC)  
Memory Type (R/U)  
Memory Speed (Mhz)  
Max. Memory Capacity  
On-board/Integrated Graphics No
Processor/Motherboard Graphics Chip N/A
Discrete GPU Yes
GPU Chipset 8x NVIDIA Tesla V100
GPU Cores 5120 (40960 Total)
GPU Tensor Cores 640 (5120 Total)
Base GPU Speed N/A
Max. GPU Speed 1455 MHz
GPU Memory Size 16GB (128GB Total)
GPU Memory Type HBM2
GPU Memory Clock 1750 MHz
GPU Memory Bus 4096 Bit
GPU Cooler Air Cooled
SLI Multi-GPU Configuration No
Max. GPU Resolution  
Graphics Interface NVLink 2.0
Expansion Slots N/A
SATA N/A
Storage Drive Included No
Storage Drive Type  
Storage Drive Capacity N/A
Optical Drive None
Drive Bays N/A
RAID Support N/A
Internal I/O N/A
Network Interface Type  
Network Chip/Modules  
Front Panel  
Back Panel  
Cooling Fans  
Keyboard / Mouse Included No
Remote Control Included No
VESA Mountable N/A
PSU Wattage  
PSU Efficiency Rating  
PSU Redundancy N/A
Operating System Included No
Operating System N/A
Colour  
Dimensions  
Warranty

Please note your statutory rights are not affected.

For further information regarding Scan's warranty procedure please see our terms and conditions

Warranty information has not yet been updated for this product. For further information please call 0871 472 4747 or 01204 474747.

TekSpek Guides
Deep Learning Supercomputer
Deep Learning Supercomputer
Date Issued: 21st Jul 2017

The increase in processing speed for computers has opened up new avenues of research and provided deeper insights into solutions for complex problems. Such power has been harnessed to accelerate research into medicine, better predict weather patterns, perform hugely complex calculations for the oil and gas industry, and a whole host more.

Read More

Reviews
Questions & Answers
NVIDIA DGX-1 Volta V100 Swap Out Tray Upgrade
NVIDIA DGX-1 Volta V100 Swap Out Tray Upgrade