TÜRKÇE
ENGLISH 
DEUTSCH- +90 216 455-1865
- info@compecta.com
All-In-One & Ready to Use
CompecTA SuperNova Engine X™ is a super-fast and efficient in single-root complex server solution for Deep Learning needs.
With up to 10GPUs in 4U form factor CompecTA SuperNova Engine X™ provides top deep learning & AI performance and parallelization.
It comes with Deep Learning Neural Network libraries, Deep Learning Frameworks, Operating System and Drivers pre-installed and ready to use.
Enterprise Level Support
CompecTA SuperNova Engine X™ comes with an Enterprise Level Support package from HPC experts with over 20 years of experience in the field.
We will assist you with any problem you may encounter with your system.
Free CPU Time
CompecTA SuperNova Engine X™ comes with 100 thousands hours of CPU Time on CompecTA's in-house HPC Cluster service called FeynmanGrid™.
Use this opportunity to gain experience on using HPC Clusters or performance test any application or to test some new code/application.
CompecTA SuperNova X™ Series
Super-fast & Scalable Deep Learning & AI Server Systems with up to 10-GPUs
SuperNova Engine X™ XA30 POPULAR
1,650 TFLOPS of Tensor Performance
103 TFLOPS of FP32 Performance
52 TFLOPS of FP64 Performance
3,300 TOPS of INT8 Tensor Performance
Best suited for:
High Performance Computing
AI & Deep Learning Development
Fast Neural Network Training
Fast Inferencing
Rendering
prices starting from
$93,295 (Excluding Taxes)
CNVAIS1-XA30V1
- 19" 4U Rackmount Chassis 10-way PCIe GPUs
- PCI-E 4.0 x16 Switch Dual-Root complex
- Dual INTEL Xeon CPUs (up to 80-Cores)
- 1 TB DDR4 3200MHz ECC Memory (up to 4TB)
- 10 x NVIDIA A30 24GB HBM2 Memory @ 933GB/s 165W
- 38,040 Total CUDA® Cores
- 3,240 Total Tensor Cores
- Up to 40 MIGs (Multi Instance GPUs) at 6GB each
- 4 x 3.84TB NVMe Disks
(up to 24 disks) - Ubuntu Linux 20.04 / 22.04 LTS
- NVIDIA-qualified driver
- NVIDIA® DIGITS™
- NVIDIA® CUDA® Toolkit
- NVIDIA® cuDNN™
- Caffe, Theano, Torch, BIDMach
- Anaconda Data Science Platform
- 100k CPU Time on FeynmanGrid™
- Enterprise Level Support from CompecTA® HPC Professional Services
- Infiniband HDR 200Gb/s Network
- NVIDIA® NVLink™ 2-Way Bridge
SuperNova Engine X™ XA100 BEST
3,120 TFLOPS of Tensor Performance
195 TFLOPS of FP32 Performance
97 TFLOPS of FP64 Performance
6,240 TOPS of INT8 Tensor Performance
Best suited for:
High Performance Computing
AI & Deep Learning Development
Super-fast Neural Network Training
Super-fast Inferencing
Rendering
prices starting from
$245,795 (Excluding Taxes)
CNVAIS1-XA100V2
- 19" 4U Rackmount Chassis 10-way PCIe GPUs
- PCI-E 4.0 x16 Switch Dual-Root complex
- Dual INTEL Xeon CPUs (up to 80-Cores)
- 2 TB DDR4 3200MHz ECC Memory (up to 4TB)
- 10 x NVIDIA A100 80GB HBM2 Memory @ 1935GB/s 300W
- 69,120 Total CUDA® Cores
- 4,320 Total Tensor Cores
- Up to 70 MIGs (Multi Instance GPUs) at 10GB each
- 4 x 3.84TB NVMe Disks
(up to 24 disks) - Ubuntu Linux 20.04 / 22.04 LTS
- NVIDIA-qualified driver
- NVIDIA® DIGITS™
- NVIDIA® CUDA® Toolkit
- NVIDIA® cuDNN™
- Caffe, Theano, Torch, BIDMach
- Anaconda Data Science Platform
- 100k CPU Time on FeynmanGrid™
- Enterprise Level Support from CompecTA® HPC Professional Services
- Infiniband HDR 200Gb/s Network
- NVIDIA® NVLink™ 2-Way Bridge
CompecTA SuperNova X™ Series Archived Products
Following products are no longer available to order.
SuperNova Engine X™ XG80Ti
113 TFLOPS of FP32 Performance
450 TOPS of INT8 Performance
Best suited for:
Deep Learning Development
Good Neural Network Training
Super-fast Inferencing
NOT AVAILABLE
CNVAIS1-XG80TIV1
- GPUs under Single-Root complex
- 19" 4.5U Rackmount Chassis
- Intel® Xeon® Processor E5-2697A v4
- 512 GB DDR4 2400MHz Memory
- 10 x NVIDIA GTX 1080Ti 352-Bit 11GB GDDR5X 11 Gbps Memory
- 35,840 Total CUDA® Cores
- 4 x 512GB SATA SSD Disks
- Ubuntu 14.04 / 16.04
- NVIDIA-qualified driver
- NVIDIA® DIGITS™
- NVIDIA® CUDA® Toolkit
- NVIDIA® cuDNN™
- Caffe, Theano, Torch, BIDMach
- 100k CPU Time on FeynmanGrid™
- Enterprise Level Support from CompecTA® HPC Professional Services
Optional:
- Mellanox EDR 100Gb/s or FDR 56Gb/s Infiniband for GPU Direct RDMA
SuperNova Engine X™ XP100
187 TFLOPS of FP16 Performance
93 TFLOPS of FP32 Performance
47 TFLOPS of FP64 Performance
Best suited for:
Deep Learning Development
Super-fast Neural Network Training
Super-fast Inferencing
NOT AVAILABLE
CNVAIS1-XP100V1
- GPUs under Single-Root complex
- 19" 4U Rackmount Chassis
- Intel® Xeon® Processor E5-2697A v4
- 512 GB DDR4 2400MHz Memory
- 10 x NVIDIA Tesla P100 4096-Bit 16GB HBM2 at 732 GB/s Memory
- 35,840 Total CUDA® Cores
- 4 x 512GB SATA SSD Disks
- Ubuntu 14.04 / 16.04
- NVIDIA-qualified driver
- NVIDIA® DIGITS™
- NVIDIA® CUDA® Toolkit
- NVIDIA® cuDNN™
- Caffe, Theano, Torch, BIDMach
- 100k CPU Time on FeynmanGrid™
- Enterprise Level Support from CompecTA® HPC Professional Services
Optional:
- Mellanox EDR 100Gb/s or FDR 56Gb/s Infiniband for GPU Direct RDMA
SuperNova Engine X™ XV100
1120 TFLOPS of Tensor Performance
140 TFLOPS of FP32 Performance
70 TFLOPS of FP64 Performance
Best suited for:
Deep Learning Development
Ultra-fast Neural Network Training
Super-fast Inferencing
NOT AVAILABLE
CNVAIS1-XV100V1
- GPUs under Single-Root complex
- 19" 4U Rackmount Chassis
- Intel® Xeon® Processor E5-2697A v4
- 512 GB DDR4 2400MHz Memory
- 10 x NVIDIA Tesla V100 4096-Bit 16GB HBM2 at 900 GB/s Memory
- 51,200 Total CUDA® Cores
- 6,400 Total Tensor Cores
- 4 x 512GB SATA SSD Disks
- Ubuntu 14.04 / 16.04
- NVIDIA-qualified driver
- NVIDIA® DIGITS™
- NVIDIA® CUDA® Toolkit
- NVIDIA® cuDNN™
- Caffe, Theano, Torch, BIDMach
- 100k CPU Time on FeynmanGrid™
- Enterprise Level Support from CompecTA® HPC Professional Services
- Mellanox EDR 100Gb/s or FDR 56Gb/s Infiniband for GPU Direct RDMA
Get more information!
Our experts can answer all your questions. Please reach us via mail or phone.