NVIDIA A800 PCIe 80GB

Ampere PCIe 2022 7nm

Overview

19.5

FP32 TFLOPS

80 GB

Memory HBM2e

1.9 TB/s

Memory Bandwidth

300 W

TDP

Performance Metrics

Precision	Peak (dense)	2:4 Sparse	Bits	Type
FP64	9.7	N/A	64	Standard
FP32	19.5	N/A	32	Standard
TF32	156.0	not published	32	Standard
BF16	312.0	not published	16	Standard
FP16	312.0	not published	16	Standard
FP8	—	not published	—	Standard
FP6	—	not published	—	Standard
FP4	—	not published	—	Standard
INT8	624.0	not published	8	Standard
INT4	1248.0	not published	4	Standard

Memory Specifications

Capacity: 80 GB
Type: HBM2e
Bandwidth: 1.9 TB/s
Interface Width: —

Power & Efficiency

TDP: 300 W
Max power (Flopper estimate): ~345 W est.
FP32 dense TFLOPS per W of TDP: 0.07 TFLOPS/W
FP16 dense TFLOPS per W of TDP: 1.04 TFLOPS/W

Flopper estimate: 300 W TDP x 1.15. The vendor publishes no maximum board power for this part. Per W of TDP figures divide dense peak by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead.

Hardware Details

Vendor: NVIDIA

Architecture: Ampere

Process Node: 7nm

Form Factor: PCIe

Launch Year: 2022

Variant: PCIe 80GB

Enterprise Features

Sparsity: Yes