AI hardware
NVIDIA A800 SXM
FP16 throughput
3.1×10¹⁴ FLOP/s
Memory
74.5 GB
TDP
400 W
NVIDIA A800 SXM is an AI accelerator designed by NVIDIA (GPU), released in August 2022. It is built on a 7 nm process at TSMC.
It delivers 3.1×10¹⁴ FLOP/s of tensor FP16/BF16 throughput. It carries 74.5 GB of memory at 1.9 TB/s of bandwidth. Its thermal design power is 400 W.
Full record
- Manufacturer
- NVIDIA
- Type
- GPU
- Release date
- Aug 11, 2022
- Tensor FP16/BF16
- 3.1×10¹⁴ FLOP/s
- FP32
- 1.9×10¹³ FLOP/s
- FP64
- 9.7×10¹² FLOP/s
- INT8
- 6.2×10¹⁴ OP/s
- Memory
- 74.5 GB
- Memory bandwidth
- 1.9 TB
- TDP
- 400 W
- Process node
- 7 nm
- Die size (mm2)
- 826
- Foundry
- TSMC
- Tensor cores
- 432
More from NVIDIA
SourceEpoch AI, 'Machine Learning Hardware'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/machine-learning-hardware. Licensed under CC BY 4.0.
← All ai hardware