NVIDIA A100 PCIe: specs and benchmarks

NVIDIA started A100 PCIe sales 22 June 2020. This is Ampere architecture desktop card based on 7 nm manufacturing process and primarily aimed at gamers. 40 GB of HBM2e memory clocked at 2.4 GB/s are supplied, and together with 5120 Bit memory interface this creates a bandwidth of 1,555 GB/s.

Compatibility-wise, this is Dual-slot card attached via PCIe 4.0 x16 interface. Its manufacturer default version has a length of 267 mm. No additional power connector is required, and power consumption is at 250 Watt.

We have no data on A100 PCIe benchmark results.

Of A100 PCIe's architecture, market type and release date.

A100 PCIe's general performance parameters such as number of shaders, GPU core clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of A100 PCIe's performance, but for precise assessment you have to consider its benchmark and gaming test results.

Information on A100 PCIe's compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop video cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Parameters of memory installed on A100 PCIe: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors don't have dedicated memory and use a shared part of system RAM.

Types and number of video connectors present on A100 PCIe. As a rule, this section is relevant only for desktop reference video cards, since for notebook ones the availability of certain video outputs depends on the laptop model.

APIs supported by A100 PCIe, sometimes including their particular versions.