Quick/Comparisons
22 | Gaming | 56 |
17 | Workstation | 55 |
| — | AI/ML |
Compare with something else?
Compare Radeon 8040S with another →66 | Energy Efficiency | 45 |
28 | Quick Comparison Final Score | 55 |
| Strix Halo | Graphics Processor | Navi 32 |
| 1024 | Cores | 3840 |
| 64 / 32 | TMUs / ROPs | 240 / 96 |
| 376.14 | Blender GPU | 2417.04 |
| — | Forza Horizon 5 | 136 |
| — | The Witcher 3 | 177 |
| — | Counter-Strike 2 | 205 |
| — | Far Cry 6 | 146 |
| — | Hogwarts Legacy | 102 |
| — | Call of Duty | 164 |
| — | Ghost of Tsushima | 102 |
| — | Cyberpunk 2077 | 122 |
| — | Tomb Raider | 193 |
| — | Average FPS | 150 |
| — | 1080p High | 181 |
| — | 1080p Ultra | 150 |
| — | 1440p Ultra | 114 |
| — | 4K Ultra | 67 |
| — | Margin of Error | Low |
| 35976 | GB6 Compute Score | 148335 |
| 106.8 img/sec | Background Blur | 300.7 img/sec |
| 43.8 img/sec | Face Detection | 200.5 img/sec |
| 1.12 Gpixels/sec | Horizon Detection | 5.77 Gpixels/sec |
| 1.17 Gpixels/sec | Edge Detection | 8.05 Gpixels/sec |
| 1.07 Gpixels/sec | Gaussian Blur | 6.44 Gpixels/sec |
| 0.5 Gpixels/sec | Feature Matching | 1.25 Gpixels/sec |
| 163 Gpixels/sec | Stereo Matching | 566.4 Gpixels/sec |
| 5820.4 FPS | Particle Physics | 20533.6 FPS |
| OpenCL | API | OpenCL |
| 10431 | G3D Mark Score | 24337 |
| 1094 | G2D Mark | 1191 |
| 79 FPS | DirectX 11 | 249 FPS |
| 46 FPS | DirectX 12 | 95 FPS |
| 5066 Ops/s | GPU Compute | 13568 Ops/s |
| — | GB6 ML Single Precision | 31216 |
| — | GB6 ML Half Precision | 37266 |
| — | GB6 ML Quantized | 24564 |
| — | Image Classification (SP) | 13913 |
| — | Image Segmentation (HP) | 18416 |
| — | Image Super Resolution (Q) | 31387 |
| — | Face Detection (HP) | 51780 |
| — | Pose Estimation (Q) | 177217 |
| — | Text Classification (SP) | 3655 |
| — | Machine Translation (HP) | 6216 |
| — | Object Detection (SP) | 15073 |
| — | Depth Estimation (Q) | 57318 |
| — | Style Transfer (SP) | 347420 |
| — | Framework | ONNX |
| — | Backend | DirectML |
| 90 GPixel/s | Pixel Fill Rate | 233 GPixel/s |
| 179 GTexel/s | Texture Fill Rate | 583 GTexel/s |
| 5.7 TFLOPS | FLOPS (FP32) | 37.3 TFLOPS |
| System Shared | Memory Type | GDDR6 |
| — | Memory Size | 16 GB |
| — | Memory Clock | 2438 MHz |
| — | Effective Memory Speed | 19500 Mbps |
| — | Bus | 256-bit |
| — | ECC | No |
| — | Memory Bandwidth | 624.1 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x16 |
| 45-120 W (configurable) | TGP | 263 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 5 nm |
| 308 mm² | Die Size | 346 mm² |
| — | Transistor Count | 28 billion |
| — | Transistor Density | 80.92 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 2.2 |
| No | CUDA | — |
| Yes | Ray Tracing | Yes |
| No | DLSS | No |
| 2.1a | DisplayPort | 2.1 |
| Amd | Vendor | Amd |
| Integrated | Build | Discrete |
| January 7, 2025 | Released | September 6, 2023 |
| Laptop | Case | Desktop |
| Generic | Purpose | Gaming |
| Mid-range | Segment | High-end |
| RDNA 3.5 | Architecture | RDNA 3.0 |
| Strix Halo | GPU Codename | Navi 32 |
| -AMD Ryzen AI Max Pro 380or above | Recommended CPU | -Intel Core i5 13600Kor above |
| — | Steel Nomad Lite Score | 18090 |
| — | Time Spy | 20088 |
| — | Solar Bay | 80288 |
| — | Port Royal | 10921 |
| — | Fire Strike | 50041 |
| — | Wild Life Extreme | 37094 |
| — | Night Raid | 160328 |
| 1295 MHz | Base Clock | 1295 MHz |
| 2800 MHz | Boost Clock | 2430 MHz |
| 1024 | Shading Units | 3840 |
| 64 | Texture Mapping Units (TMUs) | 240 |
| 32 | Render Output Units (ROPs) | 96 |
| 16 | Compute Units (Pipelines) | — |
| No | Tensor Cores | — |
| 16 | Ray-tracing Cores | 60 |
| 512KB per cluster | L1 Cache | 128KB per cluster |
| 2MB shared | L2 Cache | 4MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |