Quick/Comparisons
13 | Gaming | 81 |
22 | Workstation | 75 |
12 | AI/ML |
Compare with something else?
Compare Radeon RX 570 with another →74 |
32 | Energy Efficiency | 43 |
16 | Quick Comparison Final Score | 77 |
| Polaris 20 | Graphics Processor | Navi 31 |
| 2048 | Cores | 6144 |
| 128 / 32 | TMUs / ROPs | 384 / 192 |
| 329.21 | Blender GPU | 4055.35 |
| 36 | Forza Horizon 5 | 174 |
| 34 | The Witcher 3 | 256 |
| 43 | Counter-Strike 2 | 232 |
| 40 | Far Cry 6 | 182 |
| 22 | Hogwarts Legacy | 137 |
| 36 | Call of Duty | 255 |
| 21 | Ghost of Tsushima | 138 |
| 26 | Cyberpunk 2077 | 181 |
| 42 | Tomb Raider | 277 |
| 33 | Average FPS | 204 |
| 45 | 1080p High | 241 |
| 33 | 1080p Ultra | 204 |
| 23 | 1440p Ultra | 159 |
| 12 | 4K Ultra | 94 |
| Low | Margin of Error | Low |
| 37147 | GB6 Compute Score | 224686 |
| 55.7 img/sec | Background Blur | 423.9 img/sec |
| 31.3 img/sec | Face Detection | 270.8 img/sec |
| 1.41 Gpixels/sec | Horizon Detection | 9.23 Gpixels/sec |
| 2.82 Gpixels/sec | Edge Detection | 13.7 Gpixels/sec |
| 2.57 Gpixels/sec | Gaussian Blur | 11.1 Gpixels/sec |
| 0.31 Gpixels/sec | Feature Matching | 1.74 Gpixels/sec |
| 143.2 Gpixels/sec | Stereo Matching | 871 Gpixels/sec |
| 5080.1 FPS | Particle Physics | 29891.2 FPS |
| OpenCL | API | OpenCL |
| 7922 | G3D Mark Score | 31406 |
| 724 | G2D Mark | 1285 |
| 55 FPS | DirectX 11 | 356 FPS |
| 39 FPS | DirectX 12 | 133 FPS |
| 2890 Ops/s | GPU Compute | 17768 Ops/s |
| 6885 | GB6 ML Single Precision | 42092 |
| 7446 | GB6 ML Half Precision | 50673 |
| 4931 | GB6 ML Quantized | 32874 |
| 2676 | Image Classification (SP) | 18608 |
| 3757 | Image Segmentation (HP) | 25385 |
| 6179 | Image Super Resolution (Q) | 45641 |
| 10752 | Face Detection (HP) | 71321 |
| 35488 | Pose Estimation (Q) | 257258 |
| 1051 | Text Classification (SP) | 5240 |
| 1933 | Machine Translation (HP) | 7425 |
| 3048 | Object Detection (SP) | 21335 |
| 12040 | Depth Estimation (Q) | 66140 |
| 71201 | Style Transfer (SP) | 483867 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 40 GPixel/s | Pixel Fill Rate | 480 GPixel/s |
| 159 GTexel/s | Texture Fill Rate | 959 GTexel/s |
| 5.1 TFLOPS | FLOPS (FP32) | 61.4 TFLOPS |
| GDDR5 | Memory Type | GDDR6 |
| 4 GB | Memory Size | 24 GB |
| 1750 MHz | Memory Clock | 2500 MHz |
| 7000 Mbps | Effective Memory Speed | 20000 Mbps |
| 256-bit | Bus | 384-bit |
| No | ECC | No |
| 224 GB/s | Memory Bandwidth | 960 GB/s |
| PCIe 3.0 x16 | Interface | PCIe 4.0 x16 |
| 150 W | TGP | 355 W |
| GlobalFoundries | Manufacturing | TSMC |
| 14 nm | Fabrication Process | 5 nm |
| 232 mm² | Die Size | 529 mm² |
| 5 billion | Transistor Count | 57 billion |
| 21.55 MTr/mm² | Transistor Density | 107.75 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 2.2 |
| — | CUDA | — |
| No | Ray Tracing | Yes |
| No | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Amd | Vendor | Amd |
| Discrete | Build | Discrete |
| April 18, 2017 | Released | November 3, 2022 |
| Desktop | Case | Desktop |
| Gaming | Purpose | Gaming |
| Mid-range | Segment | High-end |
| GCN 4.0 | Architecture | RDNA 3.0 |
| Polaris 20 | GPU Codename | Navi 31 |
| -Intel Core i5 8500or above | Recommended CPU | -Intel Core i7 13700Kor above |
| 3702 | Steel Nomad Lite Score | 29870 |
| 3855 | Time Spy | 30766 |
| — | Solar Bay | 123758 |
| — | Port Royal | 16749 |
| 13443 | Fire Strike | 73217 |
| 7941 | Wild Life Extreme | 58530 |
| 50379 | Night Raid | 184767 |
| 1168 MHz | Base Clock | 1929 MHz |
| 1244 MHz | Boost Clock | 2498 MHz |
| 2048 | Shading Units | 6144 |
| 128 | Texture Mapping Units (TMUs) | 384 |
| 32 | Render Output Units (ROPs) | 192 |
| — | Compute Units (Pipelines) | — |
| No | Tensor Cores | — |
| No | Ray-tracing Cores | 96 |
| 16KB per cluster | L1 Cache | 256KB per cluster |
| 2MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |