- Form Factor: 4U Rackmountable / Tower
- Processor: 2x Intel Xeon Scalable family
- Drive Bays: 4x 3.5"/2.5" Hot-Swap
- Up to 5x Double-Wide cards
The TensorEX TS4-1686564-DPN is a Deep Learning & AI server supporting 2x Intel Xeon Scalable Family processors, a maximum of 768 GB DDR4 memory, and up to 4x NVIDIA Double-Wide GPUs.
GPUs have provided groundbreaking performance to accelerate deep learning research with thousands of computational cores and up to 100x application throughput when compared to CPUs alone. Exxact has developed the Deep Learning DevBox, featuring NVIDIA GPU technology coupled with state-of-the-art PCIe peer to peer interconnect technology, and a full pre-installed suite of the leading deep learning software, for developers to get a jump-start on deep learning research with the best tools that money can buy.
Features:
- Supports 2x Intel Xeon Scalable Family processors (Skylake-SP)
- 4x NVIDIA Tesla or Quadro GPUs
- Optional - 2x pairs NVLink Bridge for GV100, NVLink Bridge for GP100, NVLink Bridge for RTX 8000/6000, or NVLink Bridge for RTX 5000
- NVIDIA DIGITS software providing powerful design, training, and visualization of deep neural networks for image classification
- Pre-installed standard Ubuntu 18.04 w/ Deep Learning software stack
- Google TensorFlow software library
- Automatic software update tool included
NVIDIA Tesla GPU Options
Model | Standard Memory | Memory Bandwidth (GB/s) | CUDA Cores | Tensor Cores | Single Precision (TFLOPS) | Double Precision (TFLOPS) | Power (W) | Explore | |
---|---|---|---|---|---|---|---|---|---|
![]() | A100 40 GB PCI-E 4.0 | 40 GB HBM2e | 1555 | 6912 | 432 | 19.5 | 9.7 | 400 | Specs |
![]() | V100S 32 GB PCI-E 3.0 | 32 GB HBM2 | 1134 | 5120 | 640 | 16.4 | 8.2 | 250 | Specs |
![]() | V100 32 GB PCI-E 3.0 | 32 GB HBM2 | 900 | 5120 | 640 | 14 | 7 | 250 | Specs |
![]() | V100 16 GB PCI-E 3.0 | 16 GB HBM2 | 900 | 5120 | 640 | 14 | 7 | 250 | Specs |
![]() | P100 16 GB PCI-E 3.0 | 16 GB HBM2 | 732 | 3584 | - | 9.3 | 4.7 | 250 | Specs |
![]() | P100 12 GB PCI-E 3.0 | 12 GB HBM2 | 549 | 3584 | - | 9.3 | 4.7 | 250 | Specs |
![]() | T4 PCI-E 3.0 | 16 GB GDDR6 | 320 | 2560 | 320 | 8.1 | 0.24 | 75 | Specs |
![]() | P4 PCI-E 3.0 | 8 GB GDDR5 | 192 | 2560 | - | 5.5 | 0.17 | 75 | Specs |
NVIDIA Quadro GPU Options
Model | Standard Memory | Memory Bandwidth (GB/s) | CUDA Cores | Tensor Cores | Single Precision (TFLOPS) | Double Precision (TFLOPS) | Power (W) | Explore | |
---|---|---|---|---|---|---|---|---|---|
![]() | RTX A6000 | 48 GB GDDR6 | 768 | 10752 | 336 | TBD | TBD | 300 | Specs |
![]() | A40 | 48 GB GDDR6 | 696 | 10752 | 336 | TBD | TBD | 300 | Specs |
![]() | Quadro GV100 | 32 GB HBM2 | 870 | 5120 | 640 | 14.8 | 7.9 | 250 | Specs |
![]() | Quadro GP100 | 16 GB HBM2 | 717 | 3584 | - | 10.3 | 5.2 | 235 | Specs |
![]() | Quadro RTX 8000 | 48 GB GDDR6 | 672 | 4608 | 576 | 16.3 | 0.51 | 295 | Specs |
![]() | Quadro RTX 8000 (Passive) | 48 GB GDDR6 | 624 | 4608 | 576 | 14.9 | 0.47 | 250 | Specs |
![]() | Quadro RTX 6000 | 24 GB GDDR6 | 624 | 4608 | 576 | 16.3 | 0.51 | 295 | Specs |
![]() | Quadro RTX 6000 (Passive) | 24 GB GDDR6 | 624 | 4608 | 576 | 14.9 | 0.47 | 250 | Specs |
![]() | Quadro RTX 5000 | 16 GB GDDR6 | 870 | 3072 | 384 | 11.2 | 0.35 | 200 | Specs |
![]() | Quadro RTX 4000 | 8 GB GDDR6 | 416 | 2304 | 288 | 7.1 | 0.22 | 160 | Specs |
![]() | Quadro P6000 | 24 GB GDDR5X | 432 | 3840 | - | 12 | 0.39 | 250 | Specs |
![]() | Quadro P5000 | 16 GB GDDR5 | 288 | 2560 | - | 8.9 | 0.28 | 180 | Specs |
* Passive GPUs only for select systems that support passive cooling.
EMLI (Exxact Machine Learning Images)
Most Popular | |||
Compare*Additional NGC (NVIDIA GPU Cloud) containers can be added upon request. | Conda EMLISeparated Frameworks | Container EMLIFlexible. Reconfigurable. | DIY EMLISimple. Clean. Custom. |
---|---|---|---|
Who is it for? | For developers who want pre-installed deep learning frameworks and their dependencies in separate Python environments installed natively on the system. | For developers who want pre-installed frameworks utilizing the latest NGC containers, GPU drivers, and libraries in ready to deploy DL environments with the flexibility of containerization. | For experienced developers who want a minimalist install to set up their own private deep learning repositories or custom builds of deep learning frameworks. |
Frameworks* | |||
TensorFlow V1 | — | — | |
TensorFlow V2 | — | ||
PyTorch | — | ||
MXnet | — | ||
Caffe | — | — | |
Caffe2 | — | ||
Chainer | — | — | |
Microsoft Cognitive Toolkit | — | — | |
Libraries* | |||
NVIDIA cuDNN | |||
NVIDIA Rapids | — | ||
Keras | — | ||
Theano | — | ||
OpenCV | — | ||
Software Environments | |||
NVIDIA CUDA Toolkit | |||
NVIDIA CUDA Dev Toolkit | — | ||
NVIDIA Digits | — | ||
Anaconda | — | ||
Container Management | |||
Docker | — | ||
Drivers | |||
NVIDIA-qualified Driver | |||
Orchestration | |||
Micro-K8s | Free upgrade available | Free upgrade available | Free upgrade available |
- Bronze 31XX
- Bronze 32XX
- Silver 41XX
- Silver 42XX
- Gold 51XX
- Gold 52XX
- Gold 61XX
- Gold 62XX
- Platinum 81XX
- Platinum 82XX
- Via C621 chipset
- RAID 0, 1, 5, 10
- 10GBASE-T
- 5x PCI-E 3.0 x16 slots (Supports Double-Wide cards)
- 1x PCI-E 3.0 x16 slot
- 5x PCI-E 3.0 x8 slot
- 4x SATA3 Ports
- 2x M.2 (22110/2280 PCI-E & SATA interface)
- 2x RJ45 10GBASE-T Ethernet LAN Ports
- 1x RJ45 Dedicated IPMI Port