AMD Radeon Pro 570
- Graphics Processor
- Polaris 20
- Cores
- 1792
- TMUs
- 112
- ROPs
- 32
- Memory Size
- 4 GB
- Memory Type
- GDDR5
- Bus Width
- 256 bit
Recommended Gaming Resolutions:
- 640x480
- 1280x720
- 1366x768
- 1600x900
- 1920x1080
- 2560x1440
- 3840x2160
The Radeon Pro 570 is a professional mobile graphics chip by AMD, launched in June 2017. Built on the 14 nm process, and based on the Polaris 20 graphics processor, in its Polaris 20 variant, the chip supports DirectX 12.0. The Polaris 20 graphics processor is an average sized chip with a die area of 232 mm² and 5,700 million transistors. Unlike the fully unlocked Radeon RX 580X, which uses the same GPU but has all 2304 shaders enabled, AMD has disabled some shading units on the Radeon Pro 570 to reach the product's target shader count. It features 1792 shading units, 112 texture mapping units and 32 ROPs. AMD has paired 4 GB GDDR5 memory with the Radeon Pro 570, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 1000 MHz, which can be boosted up to 1105 MHz, memory is running at 1695 MHz.
Its power draw is rated at 120 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Rather it is intended for use in laptop/notebooks and will use the output of the host mobile device. Radeon Pro 570 is connected to the rest of the system using a PCI-Express 3.0 x16 interface.
Its power draw is rated at 120 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. Rather it is intended for use in laptop/notebooks and will use the output of the host mobile device. Radeon Pro 570 is connected to the rest of the system using a PCI-Express 3.0 x16 interface.
Graphics Processor
- GPU Name
- Polaris 20
- GPU Variant
- Polaris 20
- Architecture
- GCN 4.0
- Foundry
- GlobalFoundries
- Process Size
- 14 nm
- Transistors
- 5,700 million
- Die Size
- 232 mm²
Mobile Graphics
Relative Performance
Based on TPU review data: "Performance Summary" at 1920x1080
Performance estimated based on architecture, shader count and clocks.
Clock Speeds
- Base Clock
- 1000 MHz
- Boost Clock
- 1105 MHz
- Memory Clock
-
1695 MHz
6780 MHz effective
Memory
- Memory Size
- 4 GB
- Memory Type
- GDDR5
- Memory Bus
- 256 bit
- Bandwidth
- 217.0 GB/s
Render Config
- Shading Units
- 1792
- TMUs
- 112
- ROPs
- 32
- Compute Units
- 28
- L1 Cache
- 16 KB (per CU)
- L2 Cache
- 2 MB
Theoretical Performance
- Pixel Rate
- 35.36 GPixel/s
- Texture Rate
- 123.8 GTexel/s
- FP16 (half) performance
- 3.960 TFLOPS (1:1)
- FP32 (float) performance
- 3.960 TFLOPS
- FP64 (double) performance
- 247.5 GFLOPS (1:16)
Board Design
- Slot Width
- IGP
- TDP
- 120 W
- Outputs
- No outputs
- Power Connectors
- None
Graphics Features
- DirectX
- 12.0 (12_0)
- OpenGL
- 4.6
- OpenCL
- 2.0
- Vulkan
- 1.1.125
- Shader Model
- 6.4
Polaris 20 GPU Notes
| Architecture Codename: Arctic Islands Codename: Ellesmere CLRX Version: GCN 1.2 Graphics/Compute: GFX8 (gfx803) Display Core Engine: 11.2 Unified Video Decoder: 6.3 Video Compression Engine: 3.4 |