Exxact TensorEX 4U HGX A100 Server - 2x AMD EPYC processor - TS4-195183185
The TensorEX TS4-195183185 is a 4U rack mountable HGX A100 server supporting 2x AMD EPYC 7002/7003 Series processors, 32x DDR4 memory slots, and 8x NVIDIA A100 Ampere GPUs (SXM4), with up to 600 GB/s NVLINK interconnect.
Facilitate any stage of Scientific research, from data preparation and 2D Image Processing to conducting complex MD simulations. Leverage GPUs to speed up calculations and research and encourage the use of AI to solve complex problems Protein Folding, building new molecules, and exponentially accelerating genome sequencing.
Engineering and Product Design applications are notorious for their compute-intensive requirements. Your system should never hold you back from designing the next big thing. Leverage high core count CPUs, ample RAM, and the top-of-the-line GPUs to enable the most enjoyable design experience in CAD applications like Solidworks and simulation applications like ANSYS.
3D design, rendering, and real-time engines have solidified their place in media and entertainment, manufacturing, and architectural design. As digital assets get larger and more complex so should your system. Exxact curates the most competent workstation or server so you can focus on being creative with your designs.
More Cores, More Cache, More Performance
AMD EPYC Processors Ignite EPYC Performance
Data centers that require the best performance, security, and scalability gravitate to AMD EPYC™. AMD EPYC™ processors are built to handle large scientific and engineering datasets - ideal for compute-intensive modeling and advanced analysis techniques. AMD EPYC™ enables fast time-to-results for HPC.
- Exceptional performance per watt and per-core performance
- 3D V-Cache™ delivers breakthrough on-die memory with up to 768MB of L3 cache (available only on 7003X-series EPYC)
Purpose Built AI Accelerators
World’s Fastest GPU at 2TB/s Bandwidth
NVIDIA A100 introduces double-precision Tensor Cores, providing the most significant milestone since the introduction of double-precision computing in GPUs for HPC. This enables researchers to reduce a 10-hour, double-precision simulation running on NVIDIA V100 Tensor Core GPUs to just four hours on A100.
- Accelerates and enables the most serious HPC and data center workloads
- With 80GBs of High Bandwidth Memory (HBM2e), A100 never skips a beat
A100 SXM4 GPU Options
|Model||Standard Memory||Memory Bandwidth (GB/s)||CUDA Cores||Tensor Cores||Single Precision (TFLOPS)||Double Precision (TFLOPS)||Power (W)||Explore|
|A100 80 GB SXM4||80 GB HBM2e||2039||6912||432||19.5||9.7||400||---|