GPUWorkstationReleased —

NVIDIA A800 40GB Active

40 GB HBM2 · 5120-bit · 6,912 cores

The A800 40GB Active is an Ampere-based workstation card that brings NVIDIA's GA100 data center GPU to desktop workstations for AI development, data science and HPC. Unlike passively cooled data center boards, it has its own fan for use in a standard workstation chassis. It has no display outputs and runs alongside a separate graphics card, and two cards can be joined with an NVLink bridge at 400 GB/s.

General

Manufacturer: NVIDIA
Model: A800 40GB Active
Segment: Workstation
GPU chip: GA100
Architecture: Ampere
Release date: —
Price: Search on Amazon

Memory

Memory size: 40 GB
Memory type: HBM2
Bus width: 5120-bit
Bandwidth: 1,555 GB/s
Memory clock: —

Clocks & silicon

GPU clock: —
Boost clock: —
Shader units: 6,912 CUDA Cores
Tensor / AI cores: 432
RT cores: —
Transistors: 54.2 billion
Technology (nm): 7 nm
TSMC N7
TDP / TBP: 240 W

Interface & APIs

Bus interface: PCIe 4.0 x16
SLI / multi-GPU: NVLink Bridge (2 GPUs, 400 GB/s)
DirectX: N/A (compute-only)
OpenGL: N/A (compute-only)
Vulkan: N/A (compute-only)
Other APIs: CUDA (compute capability 8.0), OpenCL 3.0

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: Third-generation Tensor Cores (432)
Peak AI TOPS: —
Notes: Third-generation Tensor Cores support FP64, TF32, BF16, FP16, INT8 and INT4; FP8 is not available on Ampere. NVIDIA rates peak Tensor performance at 623.8 TFLOPS and 1,247 AI TOPS with structured sparsity, alongside 9.7 TFLOPS FP64 and 19.5 TFLOPS FP32. Multi-Instance GPU partitions the card into up to seven 5 GB instances.

All NVIDIA GPUs →

Workstation gpus from NVIDIA announced around the same time as the NVIDIA A800 40GB Active. Add any of them to your compare list to see the specs side by side.

gpu