Report an Error

NVIDIA TU117SB

Default
TU117SB
TU117-670-A1
TU117-670-A1
SM Diagram
SM Diagram
NVIDIA's TU117SB GPU uses the Turing architecture and is made using a 12 nm production process at TSMC. With a die size of 200 mm² and a transistor count of 4,700 million it is a medium-sized chip. TU117SB supports DirectX 12 (Feature Level 12_1). For GPU compute applications, OpenCL version 3.0 and CUDA 7.5 can be used. It features 1024 shading units, 32 texture mapping units and 16 ROPs.
Further reading: Turing Architecture Whitepaper

Graphics Processor

Released
Dec 17th, 2021
GPU Name
TU117SB
Codename
NV167
Architecture
Turing
Foundry
TSMC
Process Type
12FFN FinFET
Process Size
12 nm
Transistors
4,700 million
Density
23.5M / mm²
Die Size
200 mm²

Graphics Features

DirectX
12 (12_1)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
7.5
Shader Model
6.7
WDDM
3.1
NVENC
6th Gen
NVDEC
4th Gen
PureVideo HD
VP10
VDPAU
Feature Set J

Render Config

Shading Units
1024
TMUs
32
ROPs
16
SM Count
16
FP16 Units
2048
FP64 Units
32
TPCs
7
GPCs
2
Tex L1 Cache
32 KB per SM
L1 Cache
128 KB per SM
L2 Cache
2048 KB
Max. TDP
25 W

All Turing GPUs

NVIDIA GPU Architecture History

Graphics cards using the NVIDIA TU117SB GPU

Name Chip Memory Shaders TMUs ROPs Base Clock Boost Clock Memory Clock
TU117-670-A1 2 GB 1024 32 16 1065 MHz 1320 MHz 1500 MHz

TU117SB GPU Notes

NVENC: 6th Gen
NVDEC: 4th Gen
PureVideo HD: VP10
VDPAU: Feature Set J
May 17th, 2024 16:37 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts