pchardware.org
Categories

NVIDIA · 2022

NVIDIA C870 GPU Computing Module

The NVIDIA C870 GPU Computing Module is a professional graphics card based on the Ada Lovelace architecture, released in 2022.

The NVIDIA C870 GPU Computing Module is a high-end professional graphics card built on the Ada Lovelace architecture. It features the AD102-870-A1 GPU chip manufactured on a 4 nm process, with 18176 shading units, 142 ray tracing cores, and 568 tensor cores. The card operates at a base clock of 915 MHz and a boost clock of 2505 MHz. It is equipped with 48 GB of GDDR6 memory on a 384-bit bus, providing a memory bandwidth of 960 GB/s. The module has a board power (TDP) of 300 W and connects via a PCIe 4.0 x16 interface. It supports DirectX 12.2, Vulkan 1.3, and OpenGL 4.6, and offers four DisplayPort outputs. Released on December 3, 2022, with a launch MSRP of 6799 USD, it is designed for compute-intensive workloads and professional visualization.

Specifications

Architecture unverified Ada Lovelace
GPU chip unverified AD102-870-A1
Process node unverified 4 nm
Shading units unverified 18176
Ray tracing cores unverified 142
Tensor / AI cores unverified 568
Base clock unverified 915 MHz
Boost clock unverified 2505 MHz
Memory size unverified 48 GB
Memory type unverified GDDR6
Memory bus unverified 384 bit
Memory bandwidth unverified 960 GB/s
Board power (TDP) unverified 300 W
Bus interface unverified PCIe 4.0 x16
Display outputs unverified 4× DisplayPort
DirectX support unverified 12.2
Vulkan support unverified 1.3
OpenGL support unverified 4.6
Release date unverified 2022-12-03
Release year unverified 2022
Launch MSRP unverified 6799 USD