Key Architecture Highlights
- GPU Architecture: NVIDIA Ampere
- GPU memory specifications: GPU memory: 48 GB GDDR6 with error-correcting code (ECC)
- GPU memory bandwidth: 696 GB/s (Network Name)
Applications
- Virtual workstation
- 3D rendering and visualization
- AI computing
Engineering Parameters
| GPU Architecture | NVIDIA Ampere |
|---|---|
| GPU memory specifications | GPU memory: 48 GB GDDR6 with error-correcting code (ECC) |
| GPU memory bandwidth | 696 GB/s (Network Name) |
| GPU memory bus width | 384 bit |
| PCIe Interface | PCIe Gen4 x16 |
| NVLink / Interconnection | NVLink:2-way low profile (2-slot) Connectivity capacity: NVIDIA NVLink 112.5 GB/s (bidirctional) PCIe Gen4: 64GB/s |
| MIG Division | Not supported |
| Video decoding | 1 NVENC/2 NVDEC (including AV1 decoding) |
| Board power | 300 W (default) |
| Power input Interface | 8-pin CPU |
| Card form factor / cooling | card form factor: Full length (FHFL) 10.5-inch, double-slit cooling method: passive cooling (requires server wind tunnel) |
| Display interfaces | 3x DisplayPort 1.4 (default virtualization mode turns off output, enabled by management tools) |
| GPU Frequency | Base: 1305 MHz Boost: 1740 MHz |
| Operating temperature | 0 °C to 55 °C |
Warranty
manufacturer's public product information does not specify the warranty period for this model in its supply channel; applicable region, channel and actual warranty service confirmed by the supply contract.
Manufacturer information
Manufacturer informationVerified Documentation & Datasheets
Official products page
Download DocumentPB-09976-001_v08 | April 2022 NVIDIA A40 GPU Accelerator Product Brief
Download Document