The HyperStation DLX-2V

HyperStation DLX-2V

Suitable for

Deep Learning Manufacturing & Product Design

HyperStation DLX-2V

Specification

GPU
2x NVIDIA GV100 with bi-directional NVLink interconnect
CPU
2x Intel Xeon Gold 5120
RAM
192GB Samsung ECC DDR4 2400MHz
Storage
2x Samsung PM891 512GB
4x Samsung PM863A 1.92TB SSD
2x Seagate EXOS 4TB E-Class HDD
OS
Ubuntu 16.04.3 LTS
Software
We can pre-install any framework you require, including CUDA, DIGITS, Caffe Pytorch, Tensorflow, Theano, and Torch. Simply speak to our team to discuss your options.

Dual Intel Xeon Gold 5120

The Xeon Gold Series on the 3647 socket provides great performance using faster memory, increased interconnect & accelerator engines, and all combined with advanced reliability. These Xeon Gold CPUs build on Intel’s Silver Skylake-SP models, boosting their capabilities by adding 4S-2UPI support, and raising the speed of its Two UPI Links from 9.6GT/s up to 10.4GT/s.

14 Cores
2.20 GHz

48 PCIe lanes
PCIe 3.0

6 Memory Channels
DDR4 2400 MHz

2 UPI Links
10.4 GT/s

Intel Xeon Scalable features

Error Correcting Code

Error correcting code, or ECC memory automatically detects and repairs single-bit errors on the fly to keep workstation applications running reliably and free of data corruption.

Turbo Boost 2.0

Dynamically increase the processor's frequency, as needed, by taking advantage of thermal and power headroom when operating below specified limits.

Hyper-Threading

Delivers two processing threads per physical core. Highly threaded hyper-applications can get more work done in parallel, completing tasks sooner.

QuickAssist Technology

Intel QAT enables hardware acceleration for cryptography and data compression, freeing the host processor to focus on other critical workloads.

Omni-Path Architecture

High speed integrated data interconnect fabric for cost-effective deployment of HPC clusters.

Speed Shift

Delivers dramatically responsiveness with single-threaded, transient (short duration) workloads by allowing the processor to more quickly select its best operating frequency and voltage for optimal performance and power efficiency.

Intel Ultra Path Interconnect (Intel UPI)

The previous generation of Intel Xeon processors utilised Intel QPI, which has been replaced on the Intel Xeon processor Scalable family with Intel UPI.

With up to 3 UPI channels in a 2 socket configuration, Intel UPI improves inter-CPU bandwidth for I/O-intensive workloads, resulting in data rates from 9.6GT/s (Gigatransfers per second) to 10.4GT/s.

Dual NVIDIA Quadro GV100

The NVIDIA Quadro GV100 reinvents the workstation to meet the demands of AI-enhanced design and visualisation workflows. It’s powered by NVIDIA Volta, delivering extreme memory capacity, scalability, and performance that designers, architects, and scientists need to create, build, and solve the impossible.

Groundbreaking innovations

640 Tensor Cores

Quadro GV100 utilises 640 Tensor Cores; each Tensor Core performs 64 floating points fused multiply-add (FMA) operations per clock, and each SM conducts a total of 1024 individual floating point operations per clock.

Volta GPU Architecture

Based on state-of-the-art 12nm FFN (FinFET NVIDIA) high-performance manufacturing process customised for NVIDIA to incorporate 5120 CUDA cores, the Quadro GV100 GPU is the most powerful computing platform for HPC, AI, VR and graphics workloads on professional desktops.

High-Speed HBM2 Memory

Built with Volta’s vastly optimised 32GB HBM2 memory subsystem for the industry’s fastest graphics memory (870 GB/s peak bandwidth), Quadro GV100 is the ideal platform for latency-sensitive applications handling large datasets. Quadro GV100 offers 2x memory capacity and delivers 20% more memory bandwidth compared to the previous generation.

Bi-directional NVLink

PCIe bandwidth is increasingly becoming the bottleneck at the multi-GPU system level, driving the need for a faster and more scalable multiprocessor interconnect.

NVIDIA NVLink is the world's first high-speed GPU interconnect offering a significantly faster alternative for multi-GPU systems than traditional PCIe-based solutions.

The HyperStation DLX-2V utilises NVLink across two groups of 2 GPUs, enabling GPU-to-GPU bidirectional data transfer rates of up to 200 GB/sec with 2x NVLink bridges per pair.

Platform Benefits

Multi-GPU support

Support for up to 4x full length, double width GPUs.

Cooling

Cooling support for up to 205W CPUs.

Scalability

Delivers two processing threads per physical core. Highly threaded hyper-applications can get more work done in parallel, completing tasks sooner.

Customisable

All of our workstations are fully customisable. Ensuring you only get (and pay for) exactly what you need.

Ready to go

All Novatech Deep Learning systems can come with Ubuntu 16.04 server LTS operating system, and the following framework can be pre-installed: CUDA, DIGITS, Caffe, Caffe2, CNTK, Pytorch, Tensorflow, Theano, Torch, and Keras.

If you require a Framework not listed, simply speak to our team and make them aware of your need.

Processor

Description :

2 X Intel® Xeon Gold 5120 Processor

Cache :

19.25 MB L3

Clockspeed :

Processor Base Frequency 2.20 GHz, Max Turbo Frequency 3.20 GHz

No. of Cores :

Memory

Description :

12 X 16GB DDR4 2400Mhz Samsung Registered DIMM Server Memory

Speed :

2400MHz

GB :

16GB

Harddrive

Description :

2 X Samsung PM863a Enterprise Sata 1.92TB SSD for Business

Description :

Samsung 512GB PM981 M.2 PCIe NVMe M.2 SSD

Description :

2 X Seagate Exos 4TB E-Class Nearline Enterprise Hard Drive 3.5" SATA III 6GBs 512E

Case

Description :

Lian-Li PC-D600WB Big-Tower

Colour :

Black

Dimensions :

382 x 525 x 415 mm (W x H x D)

Drive Bays 3 1/2" :

Drive Bays 5 1/4" :

Form Factor :

E-ATX, ATX, Micro-ATX

Drive Bays 2 1/2" :

Graphics

Description :

2 X NVIDIA Quadro GV100

Chipset :

NVIDIA Volta

Max Resolution :

7630 x 4320

Number of displays Supported :

Power Supply

Description :

Corsair AX1600i 1600W Titanium Modular Digital ATX Power Supply

Wattage / Rating :

1600W Titanium

Motherboard

Description :

ASUS Dual Scalable Xeon WS C621E SAGE EEB Workstation Motherboard

Form Factor :

EBB

CPU Support :

Dual Intel® Socket P (LGA 3647) for Intel® Xeon® Scalable Processors Family (205W)

Chipset :

Intel® C621

Audio :

Realtek® S1220A 7.1-Channel High Definition Audio CODEC *2

IO :

1 x PS/2 keyboard/mouse combo port(s) 2 x LAN (RJ45) port(s) 2 x USB 3.1 Gen 2 *4 4 x USB 3.1 Gen 1 4 x USB 2.0 1 x Optical S/PDIF out 1 x USB BIOS Flashback Button(s) 1 x 8-channel Audio I/O

LAN :

Intel® I210-AT, 2 x Gigabit LAN Controller(s)

Socket Type :

LGA 3647

USB :

2 x USB port(s) (2 at back panel, , Type-A + USB Type-C), 8 x USB 3.1 Gen 1 port(s) (4 at back panel, , 4 at mid-board), 4 x USB 2.0 port(s) (2 at back panel, , 2 at mid-board)

RAID :

Raid 0, 1, 5, 10

SATA Ports :

8 x SATA 6Gb/s port(s),

PCI-EX :

3 x PCIe 3.0 x16 (x16 mode), 2 x PCIe 3.0 x16 (Single at x16, dual at x8/x8), 2 x PCIe 3.0 x16 (x8 mode

Memory Slots :

Max Memory Capacity :

768GB, DDR4 2666/2400 MHz RDIMM, LR-DIMM Memory

Cooling

Description :

2 X Dynatron B13 Intel Active CPU Cooler

Why not Tell A Friend about this product, all you need to do is fill out their information below and click send.

Your Name

Your Email

Friends Name

Friends Email

Personal Message

HyperStation DLX-2V

Delivery options

Business Leasing

Buying for work?

HyperStation DLX-2V

HyperStation DLX-2V

Specification

Dual Intel Xeon Gold 5120

Intel Xeon Scalable features

Error Correcting Code

Turbo Boost 2.0

Hyper-Threading

QuickAssist Technology

Omni-Path Architecture

Speed Shift

Intel Ultra Path Interconnect (Intel UPI)

Dual NVIDIA Quadro GV100

640 Tensor Cores

Volta GPU Architecture

High-Speed HBM2 Memory

Bi-directional NVLink

Platform Benefits

Multi-GPU support

Cooling

Scalability

Customisable

Ready to go

Processor

Memory

Harddrive

Case

Graphics

Power Supply

Motherboard

Cooling

HyperStation DLX-2V

Delivery options

Business Leasing

Buying for work?

HyperStation DLX-2V

HyperStation DLX-2V

Specification

Dual Intel Xeon Gold 5120

Intel Xeon Scalable features

Error Correcting Code

Turbo Boost 2.0

Hyper-Threading

QuickAssist Technology

Omni-Path Architecture

Speed Shift

Intel Ultra Path Interconnect (Intel UPI)

Dual NVIDIA Quadro GV100

640 Tensor Cores

Volta GPU Architecture

High-Speed HBM2 Memory

Bi-directional NVLink

Platform Benefits

Multi-GPU support

Cooling

Scalability

Customisable

Ready to go

Processor

Memory

Harddrive

Case

Graphics

Power Supply

Motherboard

Cooling

Get the latest from Novatech