P104 100 vs Radeon 550X

If you are going to buy a new graphics card and are choosing between P104 100 and Radeon 550X, 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 P104 100 stacks up against Radeon 550X, check out specs charts below.
P104 100
Radeon 550X

Main Specs

  P104 100 Radeon 550X
Power consumption (TDP) 50 Watt
Interface PCIe 3.0 x16 PCIe 3.0 x8
Supplementary power connectors 1x 8-pin None
Memory type GDDR5X GDDR5
Maximum RAM amount 4 GB 2 GB
Display Connectors No outputs 1x DVI, 1x HDMI, 1x DisplayPort
 
  • P104 100 is connected by PCIe 3.0 x16, and Radeon 550X uses PCIe 3.0 x8 interface.
  • P104 100 has 2 GB more memory, than Radeon 550X.
  • Both cards are used in Desktops.
  • P104 100 is build with Pascal architecture, and Radeon 550X - with GCN 4.0.
  • Core clock speed of P104 100 is 525 MHz higher, than Radeon 550X.
  • P104 100 is manufactured by 16 nm process technology, and Radeon 550X - by 14 nm process technology.
  • P104 100 is 122 mm longer, than Radeon 550X.
  • Memory clock speed of P104 100 is 3008 MHz higher, than Radeon 550X.

Game benchmarks

high / 1080p 35−40 7−8
ultra / 1080p 21−24 4−5
QHD / 1440p 16−18 0−1
4K / 2160p 10−11
low / 720p 60−65 16−18
medium / 1080p 40−45 9−10
The average gaming FPS of P104 100 in Assassin's Creed Odyssey is 355% more, than Radeon 550X.

Full Specs

  P104 100 Radeon 550X
Architecture Pascal GCN 4.0
Code name GP104 Lexa
Type Desktop Desktop
Release date 12 December 2017 27 March 2019
Pipelines 1920 512
Core clock speed 1607 MHz 1082 MHz
Boost Clock 1733 MHz 1218 MHz
Transistor count 7,200 million 2,200 million
Manufacturing process technology 16 nm 14 nm
Texture fill rate 208.0 38.98
Floating-point performance 8,873 gflops
Length 267 mm 145 mm
Memory bus width 256 Bit 128 Bit
Memory clock speed 10008 MHz 7000 MHz
Memory bandwidth 320.3 GB/s 112.0 GB/s
DirectX 12 (12_1) 12 (12_0)
Shader Model 6.4 6.4
OpenGL 4.6 4.6
OpenCL 1.2 2.0
Vulkan 1.2.131 1.2.131
CUDA 6.1