Radeon Pro 580 vs Radeon RX 470

If you are going to buy a new graphics card and are choosing between Radeon Pro 580 and Radeon RX 470, 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 580 stacks up against Radeon RX 470, check out specs charts below.

Main Specs

  Radeon Pro 580 Radeon RX 470
Power consumption (TDP) 150 Watt 120 Watt
Interface PCIe 3.0 x16 PCIe 3.0 x16
Supplementary power connectors None 1x 6-pin
Memory type GDDR5 GDDR5
Maximum RAM amount 8 GB 8 GB
Display Connectors No outputs 1x HDMI, 3x DisplayPort
  Check Price
  • Radeon Pro 580 has 25% more power consumption, than Radeon RX 470.
  • Both video cards are using PCIe 3.0 x16 interface connection to a motherboard.
  • Radeon Pro 580 and Radeon RX 470 have maximum RAM of 8 GB.
  • Both cards are used in Desktops.
  • Radeon Pro 580 is build with GCN 4.0 architecture, and Radeon RX 470 - with Polaris.
  • Core clock speed of Radeon Pro 580 is 174 MHz higher, than Radeon RX 470.
  • Radeon Pro 580 and Radeon RX 470 are manufactured by 14 nm process technology.
  • Both graphics cards are the same length of 241 mm.
  • Memory clock speed of Radeon Pro 580 is 180 MHz higher, than Radeon RX 470.

Game benchmarks

high / 1080p 40−45 40−45
ultra / 1080p 24−27 27−30
QHD / 1440p 20−22 21−24
4K / 2160p 10−12 10−12
low / 720p 65−70 65−70
medium / 1080p 45−50 45−50
The average gaming FPS of Radeon RX 470 in Assassin's Creed Odyssey is 2% more, than Radeon Pro 580.

Full Specs

  Radeon Pro 580 Radeon RX 470
Architecture GCN 4.0 Polaris
Code name Polaris 20 Polaris 10 Pro
Type Workstation Desktop
Release date 5 June 2017 4 August 2016
Pipelines 2304 2048
Core clock speed 1100 MHz 926 MHz
Boost Clock 1200 MHz 1206 MHz
Transistor count 5,700 million 5,700 million
Manufacturing process technology 14 nm 14 nm
Texture fill rate 172.8 154.4
Floating-point performance 6,175 gflops 4,940 gflops
Length 241 mm 241 mm
Memory bus width 256 Bit 256 Bit
Memory clock speed 6780 MHz 6600 MHz
Memory bandwidth 217.0 GB/s 211.2 GB/s
Shared memory -
DirectX 12 (12_0) 12 (12_0)
Shader Model 6.4 6.4
OpenGL 4.6 4.6
OpenCL 2.0 2.0
Vulkan 1.2.131 1.2.131
FreeSync +
Bitcoin / BTC (SHA256) 495 Mh/s
Ethereum / ETH (DaggerHashimoto) 30 Mh/s
Zcash / ZEC (Equihash) 200 Sol/s
  Check Price