Report an Error

NVIDIA GP108

Default
GP108
GP108-200-A1
GP108-200-A1
GP108-300-A1
GP108-300-A1
GP108-310-A1
GP108-310-A1
GP108 BGA
GP108 BGA
Block Diagram
Block Diagram
SM Diagram
SM Diagram
NVIDIA's GP108 GPU uses the Pascal architecture and is made using a 14 nm production process at Samsung. With a die size of 74 mm² and a transistor count of 1,800 million it is a very small chip. GP108 supports DirectX 12 (Feature Level 12_1). For GPU compute applications, OpenCL version 3.0 and CUDA 6.1 can be used. It features 384 shading units, 24 texture mapping units and 16 ROPs.

Graphics Processor

Released
May 17th, 2017
GPU Name
GP108
Codename
NV138
Architecture
Pascal
Foundry
Samsung
Process Size
14 nm
Transistors
1,800 million
Density
24.3M / mm²
Die Size
74 mm²
Package
FCBGA-595

Graphics Features

DirectX
12 (12_1)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
6.1
Shader Model
6.7
WDDM
3.1
NVENC
No Support
NVDEC
3rd Gen
PureVideo HD
VP8
VDPAU
Feature Set H

Render Config

Shading Units
384
TMUs
24
ROPs
16
SM Count
3
SFUs
96
TPCs
3
GPCs
1
L1 Cache
48 KB per SM
L2 Cache
512 KB
Max. TDP
30 W

All Pascal GPUs

NVIDIA GPU Architecture History

Graphics cards using the NVIDIA GP108 GPU

Name Chip Memory Shaders TMUs ROPs Base Clock Boost Clock Memory Clock
GP108-300-A1 2 GB 384 24 16 1228 MHz 1468 MHz 1502 MHz
GP108-650-A1 2 GB 384 24 16 1469 MHz 1532 MHz 1502 MHz
N17S-LG-A1 2 GB 384 24 16 937 MHz 1038 MHz 1253 MHz
GP108-310-A1 2 GB 384 24 16 1152 MHz 1379 MHz 1050 MHz
2 GB 256 16 16 1455 MHz 1519 MHz 1253 MHz
N17S-G0-A1 2 GB 256 16 16 1519 MHz 1531 MHz 1502 MHz
N17S-G2-A1 2 GB 384 24 16 1519 MHz 1582 MHz 1502 MHz
2 GB 384 24 16 1303 MHz 1493 MHz 1502 MHz
GP108-200-A1 2 GB 256 16 8 1228 MHz 1468 MHz 1502 MHz
GP108-200-A1 2 GB 256 16 8 1152 MHz 1380 MHz 1050 MHz
4 GB 384 24 16 1303 MHz 1493 MHz 1375 MHz

GP108 GPU Notes

NVENC: No Support
NVDEC: 3rd Gen
PureVideo HD: VP8
VDPAU: Feature Set H
Apr 29th, 2024 09:59 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts