Report an Error

NVIDIA TU104B

Default
TU104B
Block Diagram
Block Diagram
SM Diagram
SM Diagram
NVIDIA's TU104B GPU uses the Turing architecture and is made using a 12 nm production process at TSMC. With a die size of 545 mm² and a transistor count of 13,600 million it is a very big chip. TU104B supports DirectX 12.0 (Feature Level 12_1). It features 2944 shading units, 184 texture mapping units and 64 ROPs. Also included are 368 tensor cores which help improve the speed of machine learning applications. The GPU also contains 46 raytracing acceleration cores.
Further reading: Turing Architecture Whitepaper

Graphics Processor

GPU Name
TU104B
Architecture
Turing
Foundry
TSMC
Process Size
12 nm
Transistors
13,600 million
Density
25.0M / mm²
Die Size
545 mm²
Codename
NV164
Released
Jan 29th, 2019

Graphics Features

DirectX
12.0 (12_1)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.103
CUDA
7.5
Shader Model
6.4
PureVideo HD
VP10
VDPAU
Feature Set J

Render Config

Shading Units
2944
TMUs
184
ROPs
64
SM Count
46
Tensor Cores
368
RT Cores
46
GPCs
6
TPCs
24
SFUs
768
Tex L1 Cache
32 KB per SM
L1 Cache
64 KB per SM
L2 Cache
4096 KB
Max. TDP
150 W

All Turing GPUs

Graphics cards using the NVIDIA TU104B GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Boost Clock Memory Clock
NVIDIA GeForce RTX 2080 Mobile N18E-G3-A1 8 GB 2944 184 64 1380 MHz 1590 MHz 1500 MHz
NVIDIA GeForce RTX 2080 Max-Q N18E-G3-A1 8 GB 2944 184 64 735 MHz 1095 MHz 1500 MHz