Radeon Pro Duo vs Radeon R9 390X

If you are going to buy a new graphics card and are choosing between Radeon Pro Duo and Radeon R9 390X, there are a couple of things to consider. Cards with more VRAM in general perform better and allow you to play on higher graphics settings. Size also makes a difference. A model with a large heatsink can occupy up to three expansion slots on a motherboard. Be sure you have enough room in your PC case. When comparing GPUs with different architectures, more processing cores and even higher TFLOPS will not always translate to better performance. To help you decide which GPU you need, we have measured frame rates in a number of popular games. For more on how the Radeon Pro Duo stacks up against Radeon R9 390X, check out specs charts below.

Main Specs

  Radeon Pro Duo Radeon R9 390X
Power consumption (TDP) 350 Watt 275 Watt
Interface PCIe 3.0 x16 PCIe 3.0 x16
Supplementary power connectors 3x 8-pin 1 x 6-pin, 1 x 8-pin
Memory type High Bandwidth Memory (HBM) GDDR5
Maximum RAM amount 8 GB
Display Connectors 1x HDMI, 3x DisplayPort 2x DVI, 1x HDMI, 1x DisplayPort
  Check Price Check Price
  • Radeon Pro Duo has 27% more power consumption, than Radeon R9 390X.
  • Both video cards are using PCIe 3.0 x16 interface connection to a motherboard.
  • Both cards are used in Desktops.
  • Radeon Pro Duo is build with GCN 3.0 architecture, and Radeon R9 390X - with GCN.
  • Radeon Pro Duo and Radeon R9 390X are manufactured by 28 nm process technology.
  • Radeon Pro Duo is 2 mm longer, than Radeon R9 390X.
  • Memory clock speed of Radeon R9 390X is 550 MHz higher, than Radeon Pro Duo.

Game benchmarks

high / 1080p 50−55 50−55
ultra / 1080p 30−35 30−35
QHD / 1440p 27−30 24−27
4K / 2160p 14−16 14−16
low / 720p 75−80 75−80
medium / 1080p 60−65 55−60
The average gaming FPS of Radeon Pro Duo in Assassin's Creed Odyssey is 2% more, than Radeon R9 390X.

Full Specs

  Radeon Pro Duo Radeon R9 390X
Architecture GCN 3.0 GCN
Code name Capsaicin Grenada XT
Type Workstation Desktop
Release date 26 April 2016 16 June 2015
Pipelines 4096 2816
Boost Clock 1000 MHz 1050 MHz
Transistor count 8,900 million 6,200 million
Manufacturing process technology 28 nm 28 nm
Texture fill rate 256.0 184.8
Floating-point performance 2x 8,192 gflops 5,914 gflops
Length 277 mm 275 mm
Memory bus width 4096 Bit 512 Bit
Memory clock speed 500 MHz 1050 MHz
Memory bandwidth 512 GB/s 384 GB/s
Shared memory -
Shader Model 6.0 6.3
OpenGL 4.5 4.6
OpenCL 2.0 2.0
Vulkan + +
FreeSync + +
Bus support PCIe 3.0 PCIe 3.0
HDMI + +
Bitcoin / BTC (SHA256) 809 Mh/s 684 Mh/s
Eyefinity + +
HD3D +
PowerTune + +
TrueAudio + +
ZeroCore +
Mantle + +
Design reference reference
Bridgeless CrossFire +
Number of Eyefinity displays 6 6
DisplayPort support + +
CrossFire + +
VCE + +
DDMA audio +
Ethereum / ETH (DaggerHashimoto) 27.5 Mh/s
Compute units 128
AppAcceleration +
High bandwidth memory (HBM) -
LiquidVR +
TressFX +
UVD +
Enduro +
FRTC +
  Check Price Check Price