Product Compare
AMD Radeon Pro 570 vs NVIDIA P106 100
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jun 2017 | Jun 2017 |
| Generation | Radeon Pro Mac | Mining GPUs |
| Type | Mobile | Desktop |
| Bus Interface | PCIe 3.0 x16 | PCIe 1.0 x16 |
| Clock Speeds | ||
| Base Clock | 1000 MHz | 1506 MHz |
| Boost Clock | 1105 MHz | 1709 MHz |
| Memory Clock | 1695 MHz | 2002 MHz |
| Memory | ||
| Memory Size | 4GB | 6GB |
| Memory Type | GDDR5 | GDDR5 |
| Memory Bus | 256bit | 192bit |
| Bandwidth | 217.0GB/s | 192.2GB/s |
| Render Config | ||
| Compute Units | 28 | |
| Shading Units | 1792 | 1280 |
| TMUs | 112 | 80 |
| ROPs | 32 | 48 |
| L1 Cache | 16 KB (per CU) | 48 KB (per SM) |
| L2 Cache | 2 MB | 1536 KB |
| SM Count | 10 | |
| Theoretical Performance | ||
| Pixel Rate | 35.36 GPixel/s | 82.03 GPixel/s |
| Texture Rate | 123.8 GTexel/s | 136.7 GTexel/s |
| FP16 (half) | 3.960 TFLOPS | 68.36 GFLOPS |
| FP32 (float) | 3.960 TFLOPS | 4.375 TFLOPS |
| FP64 (double) | 247.5 GFLOPS | 136.7 GFLOPS |
| Graphics Processor | ||
| GPU Name | Polaris 20 | GP106 |
| GPU Variant | Polaris 20 | GP106-100-A1 |
| Architecture | GCN 4.0 | Pascal |
| Foundry | GlobalFoundries | TSMC |
| Process Size | 14 nm | 16 nm |
| Transistors | 5.7 billion | 4.4 billion |
| Die Size | 232 mm² | 200 mm² |
| Board Design | ||
| TDP | 150W | 120W |
| Outputs | No outputs | No outputs |
| Power Connectors | None | 1x 6-pin |
| Suggested PSU | 300 W | |
| Graphics Features | ||
| DirectX | 12 (12_0) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.3 |
| Shader Model | 6.4 | 6.8 |
| CUDA | 6.1 | |