P106-100 and Radeon RX 580 OEM - video card comparison
P106-100
Radeon RX 580 OEM
Architecture
Pascal (2016−2021)
GCN 4.0 (2016−2020)
GPU code name
GP106
Ellesmere
Market segment
Desktop
Desktop
Release date
June 2017
June 2016
Interface
PCIe 3.0 x16
PCIe 3.0 x16
Supplementary power connectors
1x 6-pin
1x 6-pin
Boost clock speed
1709 MHz
1266 MHz
Core clock speed
1506 MHz
1120 MHz
Floating-point performance
4,375 gflops
5,834 gflops
Manufacturing process technology
16 nm
14 nm
Number of transistors
4,400 million
5,700 million
Pipelines / CUDA cores
1280
2304
Power consumption (TDP)
120 Watt
150 Watt
Texture fill rate
136.7
182.3
Memory type
GDDR5
GDDR5
Maximum RAM amount
6 GB
8 GB
Memory bus width
192 Bit
256 Bit
Memory clock speed
8008 MHz
8000 MHz
Memory bandwidth
192.2 GB/s
256.0 GB/s
Display Connectors
No outputs
1x HDMI, 3x DisplayPort
HDMI
-
+
DirectX
12 (12_1)
12 (12_0)
CUDA
6.1
-
OpenCL
1.2
2.0
OpenGL
4.6
4.6
Shader Model
6.4
6.4
Vulkan
1.2.131
1.2.131