Filter By
NVIDIA Tesla Volta: The Core of AI
The new NVIDIA Volta™ GPU architecture is the new driving force behind artificial intelligence. 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.
By coupling NVIDIA Tesla Volta GPUs along with our expert systems enginerring, we have created a wide portfolio of NVIDIA Tesla Volta Solutions to help fuel breakthroughs in every industry.
Educational Discounts Available
For a limited time only, Exxact is offering educational institutions special discounts off Tesla V100 GPUs when configured in our systems below. For more information, contact our sales department here.
NVIDIA Tesla Volta GPUs
 Tesla V100 for SXM2 (16 GB/ 32GB) |  Tesla V100 for PCIe (16 GB/ 32GB) | |
|---|---|---|
| NVIDIA CUDA Cores | 5120 | 5120 |
| NVIDIA Tensor Cores | 640 | 640 |
| Double Precision Performance | 7.8 TeraFLOPS | 7 TeraFLOPS |
| Single Precision Performance | 15.7 TeraFLOPS | 14 TeraFLOPS |
| Tensor Performance | 125 TeraFLOPS | 112 TeraFLOPS |
| Interconnect Bandwidth | 300 GB/s NVLink | 32 GB/s PCIe |
| CoWoS HBM2 Stacked Memory Capacity | 16 GB / 32GB | 16 GB / 32GB |
| CoWoS HBM2 Stacked Memory Bandwidth | 900 GB/s | 900 GB/s |
| Part Number | 900-2G503-0010-000/ 900-2G503-0010-000 | 900-2G500-0010-000/ 900-2G500-0000-000 |
AI Training with NVIDIA Tesla V100
From recognizing speech to training virtual personal assistants and teaching autonomous cars to drive, data scientists are taking on increasingly complex challenges with AI. Solving these kinds of problems requires training deep learning models that are exponentially growing in complexity, in a practical amount of time.
With 640 Tensor Cores, Tesla V100 is the world’s first GPU to break the 100 teraFLOPS (TFLOPS) barrier of deep learning performance. The next generation of NVIDIA NVLink™ connects multiple V100 GPUs at up to 300 GB/s to create the world’s most powerful computing servers. AI models that would consume weeks of computing resources on previous systems can now be trained in a few days. With this dramatic reduction in training time, a whole new world of problems will now be solvable with AI.
AI Inference with NVIDIA Tesla V100
Tesla V100 is engineered to provide maximum performance in existing hyperscale server racks. With AI at its core, Tesla V100 GPU delivers 47X higher inference performance than a CPU server. This giant leap in throughput and efficiency will make the scale-out of AI services practical.
- Rack Height: 1U
- Processor Supported: 2x Intel Xeon Scalable family
- Drive Bays: 2x 2.5" Hot-Swap, 2x 2.5" Internal
- Supports up to 4x NVIDIA Tesla V100 SXM2
- Rack Height: 1U
- Processor Supported: 2x Intel E5-2600 v3/v4
- Drive Bays: 2x 2.5" Hot-Swap, 2x 2.5" Internal
- Supports up to 4x NVIDIA Tesla V100 SXM2
- Rack Height: 1U
- Processor Supported: 1x AMD EPYC 7000-Series
- Drive Bays: 2x 2.5" Hot-Swap
- Supports up to 4x Double-Wide cards
- Rack Height: 1U
- Processor Supported: 1x Intel E5-1600 v3/v4, E5-2600 v3/v4
- Drive Bays: 6x 2.5" Hot-Swap
- Coprocessors: Up to 2x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 2x Intel E5-2600 v3/v4
- Drive Bays: 2x 2.5" Hot-swap, 2x 2.5" internal
- Coprocessors: Up to 4x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 2x Intel E5-2600 v3/v4
- Drive Bays: 4x 2.5" Hot-Swap
- Coprocessors: Up to 3x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 1x Intel E5-1600 v3/v4, E5-2600 v3/v4
- Drive Bays: 3x 3.5" Hot-Swap
- Coprocessors: Up to 2x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 2x AMD EPYC 7000-Series
- Drive Bays: 2x 2.5" Hot-Swap, 2x 2.5" Internal
- Coprocessor: Up to 4x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 2x AMD EPYC 7000-Series
- Drive Bays:: 10x 2.5" Hot-Swap
- Coprocessor: Up to 1x NVIDIA Tesla Volta GPU
- Rack Height: 1U
- Processor Supported: 2x Intel Xeon Scalable family
- Drive Bays: 2x 2.5" Hot-Swap, 2x 2.5" Internal
- Corocessor: Up to 4x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 2x Intel Xeon Scalable family
- Ethernet Technology: 10GBASE-T
- Coprocessor: Up to 4x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 2x Intel Xeon Scalable family
- Drive Bays: 4x 2.5" Hot-Swap
- Coprocessor: Up to 3x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 1x Intel Xeon Scalable family
- Drive Bays: 6x 2.5" Hot-Swap
- Coprocessor: Up to 2x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 1x Intel Xeon Scalable family
- Drive Bays: 3x 3.5" Hot-Swap
- Coprocessor: Up to 2x NVIDIA Tesla Volta GPUs
- Rack Height: 1U
- Processor Supported: 1x Intel Xeon Scalable family
- Drive Bays: 2x 2.5" Hot-Swap
- Coprocessor: Up to 4x NVIDIA Tesla Volta GPUs