Radeon R9 Fury and P102-100 - video card comparison

Radeon R9 Fury

P102-100

Architecture

GCN 1.2 (2015−2016)

Pascal (2016−2021)

GPU code name

Fiji

GP102

Market segment

Desktop

Desktop

Release date

June 2015

February 2018

Bus support

PCIe 3.0

-

Interface

PCIe 3.0 x16

PCIe 3.0 x4

Supplementary power connectors

2x 8-pin

2x 8-pin

Bridgeless CrossFire

1

-

Boost clock speed

1000 MHz

1683 MHz

Compute units

56

-

Core clock speed

-

1582 MHz

Floating-point performance

7,168 gflops

10,125 gflops

Manufacturing process technology

28 nm

16 nm

Number of transistors

8,900 million

11,800 million

Pipelines / CUDA cores

3584

3200

Power consumption (TDP)

275 Watt

250 Watt

Texture fill rate

224.0

336.6

Memory type

High Bandwidth Memory (HBM)

GDDR5X

Maximum RAM amount

4 GB

5 GB

Memory bus width

4096 Bit

320 Bit

Memory clock speed

500 MHz

11008 MHz

Memory bandwidth

512 GB/s

440.3 GB/s

High bandwidth memory (HBM)

+

-

Shared memory

-

-

Display Connectors

1x HDMI, 3x DisplayPort

No outputs

Eyefinity

+

-

Number of Eyefinity displays

6

-

HDMI

+

-

DisplayPort support

+

-

DirectX

DirectX® 12

12 (12_1)

CUDA

-

6.1

Mantle

+

-

OpenCL

2.0

1.2

OpenGL

4.5

4.6

Shader Model

6.3

6.4

Vulkan

+

1.2.131

AppAcceleration

+

-

CrossFire

1

-

DDMA audio

+

-

Enduro

-

-

FreeSync

1

-

FRTC

1

-

HD3D

+

-

LiquidVR

1

-

PowerTune

+

-

TressFX

1

-

TrueAudio

+

-

UVD

+

-

VCE

+

-

ZeroCore

-

-