Report an Error

NVIDIA GA103

NVIDIA's GA103 GPU uses the Ampere architecture and is made using a 8 nm production process at Samsung. GA103 supports DirectX 12 Ultimate (Feature Level 12_2). For GPU compute applications, OpenCL version 2.0 and CUDA 8.6 can be used. Additionally, the DirectX 12 Ultimate capability guarantees support for hardware-raytracing, variable-rate shading and more, in upcoming video games. It features 8192 shading units, 256 texture mapping units and 96 ROPs. Also included are 256 tensor cores which help improve the speed of machine learning applications. The GPU also contains 64 raytracing acceleration cores.

Graphics Processor

GPU Name
GA103
Codename
NV173
Architecture
Ampere
Foundry
Samsung
Process Size
8 nm
Transistors
unknown
Die Size
unknown
Released
2021

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
2.0
Vulkan
1.2
CUDA
8.6
Shader Model
6.5
PureVideo HD
VP11
VDPAU
Feature Set k

Render Config

Shading Units
8192
TMUs
256
ROPs
96
SM Count
64
Tensor Cores
256
RT Cores
64
L1 Cache
128 KB per SM
L2 Cache
6144 KB
Max. TDP
230 W

All Ampere GPUs

NVIDIA GPU Architecture History

Graphics cards using the NVIDIA GA103 GPU

Name Chip Memory Shaders TMUs ROPs Base Clock Boost Clock Memory Clock
NVIDIA GeForce RTX 3070 Ti 10 GB 7424 232 96 1500 MHz 1725 MHz 1188 MHz
NVIDIA RTX A5000 24 GB 8192 256 96 1455 MHz 1860 MHz 2000 MHz