NVIDIA A100 Tensor Core GPU PCIe

The NVIDIA® A100 Tensor Core GPU in PCIe form delivers 80GB memory, third generation tensor cores, PCIe Gen4 bandwidth, and the ability to create up to 7 vGPU’s with NVIDIA’s Multi-Instance GPU (MIG) feature. The NVIDIA A100 is now shipping. Contact us for more details and to build your NVIDIA A100 based solution.

XENON also has a range of customisable server builds designed for the NVIDIA A100. From 1 to 10 GPUs – The new XENON RADON Intel servers and the new XENON KRYPTON AMD Servers.

In performance numbers below:
* Structural sparsity enabled;
** SXM GPUs via NVIDIA HGX™ A100 server boards; PCIe GPUs via NVLink® Bridge for up to 2 GPUs.

XENON NVIDIA A100 pcie
Specifications
NVIDIA A100, PCIe
Specifications

GPU Architecture

NVIDIA A100, PCIe

NVIDIA Ampere

Specifications

Double-Precision Performance

NVIDIA A100, PCIe

  • FP64: 9.7 TFLOPS
  • FP64 Tensor Core: 19.5 TFLOPS
Specifications

Single-Precision Performance

NVIDIA A100, PCIe

  • FP32: 19.5 TFLOPS
  • Tensor Float 32 (TF32): 156 TF | 312 TFLOPS*
Specifications

Half-Precision Performance

NVIDIA A100, PCIe

312 TFLOPS | 624 TFLOPS*

Specifications

Bfloat16

NVIDIA A100, PCIe

312 TFLOPS | 624 TFLOPS*

Specifications

Integer Performance

NVIDIA A100, PCIe

  • INT8: 624 TOPS | 1,248 TOPS*
  • INT4: 1,248 TOPS | 2,496 TOPS*
Specifications

GPU Memory

NVIDIA A100, PCIe

80 GB hBM2

Specifications

Memory Bandwidth

NVIDIA A100, PCIe

1,935 GB/sec

Specifications

Error-Correcting Code

NVIDIA A100, PCIe

Yes

Specifications

Interconnect Interface

NVIDIA A100, PCIe

  • PCIe Gen4: 64 GB/ sec
  • NVIDIA NVLink®: 600 GB/sec** PCIe
Specifications

Form Factor

NVIDIA A100, PCIe

PCIe

Specifications

Multi-Instance GPU (MIG)

NVIDIA A100, PCIe

Up to 7 GPU instances

Specifications

Max Power Consumption (Thermal Design Power, or TPD)

NVIDIA A100, PCIe

300 W

Specifications

Delivered Performance for Top Apps

NVIDIA A100, PCIe

90%

Specifications

Thermal Solution

NVIDIA A100, PCIe

Passive

Specifications

Compute APIs

NVIDIA A100, PCIe

CUDA®, DirectCompute, OpenCLTM, OpenACC®

Specifications

NVIDIA A100, PCIe

Quick Quote Request

  • This field is for validation purposes and should be left unchanged.