Radeon HD 5970 vs UHD Graphics 630

If you are going to buy a new graphics card and are choosing between Radeon HD 5970 and UHD Graphics 630, 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 HD 5970 stacks up against UHD Graphics 630, check out specs charts below.
Radeon HD 5970
UHD Graphics 630

Main Specs

  Radeon HD 5970 UHD Graphics 630
Power consumption (TDP) 294 Watt 15 Watt
Interface PCIe 2.0 x16 PCIe 3.0 x1
Supplementary power connectors 1x 6-pin + 1x 8-pin
Memory type GDDR5 System Shared
Maximum RAM amount 1 GB
Display Connectors 2x DVI, 1x mini-DisplayPort No outputs
 
  • Radeon HD 5970 has 1860% more power consumption, than UHD Graphics 630.
  • Radeon HD 5970 is connected by PCIe 2.0 x16, and UHD Graphics 630 uses PCIe 3.0 x1 interface.
  • Both cards are used in Desktops.
  • Radeon HD 5970 is build with TeraScale 2 architecture, and UHD Graphics 630 - with Gen. 9.5.
  • Core clock speed of Radeon HD 5970 is 425 MHz higher, than UHD Graphics 630.
  • Radeon HD 5970 is manufactured by 40 nm process technology, and UHD Graphics 630 - by 14 nm process technology.

Game benchmarks

high / 1080p 10−12 3−4
ultra / 1080p 6−7 1−2
QHD / 1440p 1−2 0−1
low / 720p 24−27 14−16
medium / 1080p 14−16 5−6
The average gaming FPS of Radeon HD 5970 in Assassin's Creed Odyssey is 133% more, than UHD Graphics 630.

Full Specs

  Radeon HD 5970 UHD Graphics 630
Architecture TeraScale 2 Gen. 9.5
Code name Hemlock Kaby-Lake-H-GT2
Type Desktop Desktop
Release date 18 November 2009 1 October 2017
Pipelines 1600 24
Core clock speed 725 MHz 300 MHz
Boost Clock 1150 MHz
Transistor count 2,154 million 189 million
Manufacturing process technology 40 nm 14 nm
Texture fill rate 58.00 26.45
Floating-point performance 2x 2,320.0 gflops 460.8 gflops
Length 305 mm
Memory bus width 256 Bit 64/128 Bit
Memory clock speed 4000 MHz
Memory bandwidth 128.0 GB/s
Shared memory +
DirectX 11.2 (11_0) 12 (12_1)
Shader Model 5.0 6.5
OpenGL 4.4 4.6
OpenCL 1.2 2.1
Vulkan N/A 1.1.103
Quick Sync +