Skip to main content

NVIDIA A100 (Ampere)

Product Overview

The NVIDIA A100, released in 2020, is a landmark data center AI accelerator that introduced MIG (Multi-Instance GPU) and TF32 / FP16 / BF16 Tensor Cores. Although superseded by the H100, the A100 remains the most widely deployed AI training GPU, available in 40GB and 80GB HBM2e variants.

Core Specifications

Parameter40GB Variant80GB Variant
ArchitectureAmpere GA100Ampere GA100
Process NodeTSMC 7nmTSMC 7nm
Transistor Count54 billion54 billion
Memory40 GB HBM2e80 GB HBM2e
Memory Bandwidth1,555 GB/s1,935 GB/s
CUDA Cores6,9126,912
Tensor Cores432 (3rd Gen)432 (3rd Gen)
FP3219.5 TFLOPS19.5 TFLOPS
FP649.7 TFLOPS9.7 TFLOPS
TF32 Tensor Core156 TFLOPS156 TFLOPS
FP16/BF16 Tensor Core312 TFLOPS312 TFLOPS
INT8 Tensor Core624 TOPS624 TOPS
TDP250 W / 400 W300 W / 400 W
NVLink600 GB/s600 GB/s
MIGUp to 7 instancesUp to 7 instances

Vendor Information

ParameterValue
ManufacturerNVIDIA Corporation
Official Websitehttps://www.nvidia.com
Product Pagehttps://www.nvidia.com/en-us/data-center/a100/
ReleaseJune 2020 GTC

Software & Drivers

Key Features

  • 3rd Gen Tensor Cores: Support TF32, FP16, BF16, INT8
  • MIG (Multi-Instance GPU): Partition a single GPU into up to 7 independent instances
  • Structured Sparsity: Hardware-level 2:4 sparsity acceleration
  • NVLink 3.0: 600 GB/s interconnect bandwidth

Use Cases

  • LLM training (7B–70B models)
  • Inference deployment
  • HPC scientific computing
  • Recommendation systems