Exxact | Deep Learning, HPC, AV, Distribution & More

EDU Discounts Available

Purchase a qualifying NVIDIA GPU-powered workstation or server from Exxact and gain exclusive EDU discounts.

Wide NVIDIA Platform Selection

Exxact offers a wide selection of workstation and server platforms to meet the individual compute needs of each customer's unique use case.

Standard 3 Year Warranty

Have peace of mind, focus on what matters most, knowing your system is backed by a 3 year warranty and support.

NVIDIA A100 SXM4 Based Servers

4x NVIDIA A100 Server with AMD EPYC Processors

TS2-171138844-DPN

Base Specs

CPU 2x AMD EPYC 7003 CPUs

GPU 4x NVIDIA Tesla A100 SXM4-40GB + NVLink

NET Up to 4x Mellanox InfiniBand HDR 200Gbps Cards

MEM Up to 8TB DDR4 Memory

STO Up to 60TB NVMe Storage

8x NVIDIA A100 Server with AMD EPYC Processors

TS4-195183185-DPN

Base Specs

CPU 2x AMD EPYC 7003 CPUs

GPU 8x NVIDIA Tesla A100 SXM4-40GB + NVSwitch

NET Up to 9x Mellanox InfiniBand HDR 200Gbps Cards

MEM Up to 4TB DDR4 Memory

STO Up to 60TB NVMe Storage

8x NVIDIA A100 Server with Intel Xeon Processors

TS4-168747704-DPN

Base Specs

CPU 2x Intel Xeon Scalable Family

GPU 8x NVIDIA Tesla A100 SXM4-40GB + NVSwitch

NET Up to 9x Mellanox InfiniBand HDR 200Gbps Cards

MEM Up to 4TB DDR4 Memory

STO Up to 96TB NVMe Storage

NVIDIA A100 PCIe Based Servers

4x NVIDIA A100 Server with AMD EPYC Processor

TS2-158632687-DPN

Base Specs

CPU 1x AMD EPYC 7002 CPUs

GPU Up to 4x NVIDIA A100, or A40 PCIe GPUs

MEM Up to 1TB DDR4 Memory

STO Up to 60TB NVMe Storage

8x NVIDIA A100 Server with AMD EPYC Processors

TS4-173535991-DPN

Base Specs

CPU 2x AMD EPYC 7002 CPUs

GPU Up to 8x NVIDIA A100, or A40 PCIe GPUs

MEM Up to 4TB DDR4 Memory

STO Up to 96TB NVMe Storage

10x NVIDIA A100 Server with Intel Xeon Processors

TS4-133524070-DPN

Base Specs

CPU 2x Intel Xeon CPUs

GPU Up to 8x NVIDIA A100, or A40 PCIe GPUs

MEM Up to 8TB DDR4 Memory

STO Up to 96TB NVMe Storage

High-Performance Computing with NVIDIA Tesla A100

To unlock next-generation discoveries, scientists look to simulations to better understand complex molecules for drug discovery, physics for potential new sources of energy, and atmospheric data to better predict and prepare for extreme weather patterns.

A100 introduces double-precision Tensor Cores, providing the biggest 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. HPC applications can also leverage TF32 precision in A100’s Tensor Cores to achieve up to 10x higher throughput for single-precision dense matrix multiply operations.

https://assets.exxactcorp.com/img/exx/cms/solutions/dl-and-ai/ai-servers/a100-graph-bert-large.svg

BERT pre-training throughput using Pytorch, including (2/3) Phase 1 and (1/3) Phase 2 | Phase 1 Seq Len = 128, Phase 2 Seq Len = 512; V100: NVIDIA DGX-1™ server with 8x V100 using FP32 precision; A100: DGX A100 Server with 8x A100 using TF32 precision.

https://assets.exxactcorp.com/img/exx/cms/solutions/dl-and-ai/ai-servers/a100-graph-bert-large-inference.svg

BERT Large Inference | NVIDIA T4 Tensor Core GPU: NVIDIA TensorRT (TRT) 7.1, precision = INT8, batch size = 256 | V100: TRT 7.1, precision = FP16, batch size = 256 | A100 with 7 MIG instances of 1g.5gb: pre-production TRT, batch size = 94, precision = INT8 with sparsity.