Quick/Comparisons
9 | Gaming | 61 |
8 | Workstation | 62 |
| — | AI/ML |
Compare with something else?
Compare Adreno X1-45 with another →93 | Energy Efficiency | 46 |
24 | Quick Comparison Final Score | 60 |
| Adreno X1 | Graphics Processor | AD104 |
| 768 | Cores | 7168 |
| 48 / 24 | TMUs / ROPs | 224 / 80 |
| — | Blender GPU | 6153.24 |
| — | Forza Horizon 5 | 131 |
| — | The Witcher 3 | 176 |
| — | Counter-Strike 2 | 212 |
| — | Far Cry 6 | 145 |
| — | Hogwarts Legacy | 106 |
| — | Call of Duty | 165 |
| — | Ghost of Tsushima | 100 |
| — | Cyberpunk 2077 | 131 |
| — | Tomb Raider | 226 |
| — | Average FPS | 155 |
| — | 1080p High | 183 |
| — | 1080p Ultra | 155 |
| — | 1440p Ultra | 120 |
| — | 4K Ultra | 70 |
| — | Margin of Error | Low |
| 9947 | GB6 Compute Score | 206598 |
| 14.2 img/sec | Background Blur | 359.5 img/sec |
| 6.82 img/sec | Face Detection | 210 img/sec |
| 0.56 Gpixels/sec | Horizon Detection | 7.61 Gpixels/sec |
| 0.65 Gpixels/sec | Edge Detection | 10.4 Gpixels/sec |
| 0.55 Gpixels/sec | Gaussian Blur | 11.3 Gpixels/sec |
| 0.12 Gpixels/sec | Feature Matching | 1.97 Gpixels/sec |
| 26.6 Gpixels/sec | Stereo Matching | 969.3 Gpixels/sec |
| 1746.7 FPS | Particle Physics | 29061.4 FPS |
| OpenCL | API | OpenCL |
| 1893 | G3D Mark Score | 29964 |
| 357 | G2D Mark | 1193 |
| 13 FPS | DirectX 11 | 271 FPS |
| 9 FPS | DirectX 12 | 110 FPS |
| 818 Ops/s | GPU Compute | 16985 Ops/s |
| — | GB6 ML Single Precision | 30706 |
| — | GB6 ML Half Precision | 43851 |
| — | GB6 ML Quantized | 23776 |
| — | Image Classification (SP) | 12146 |
| — | Image Segmentation (HP) | 23932 |
| — | Image Super Resolution (Q) | 36321 |
| — | Face Detection (HP) | 52836 |
| — | Pose Estimation (Q) | 179788 |
| — | Text Classification (SP) | 3371 |
| — | Machine Translation (HP) | 5017 |
| — | Object Detection (SP) | 15164 |
| — | Depth Estimation (Q) | 62500 |
| — | Style Transfer (SP) | 357489 |
| — | Framework | ONNX |
| — | Backend | DirectML |
| 27-33 GPixel/s | Pixel Fill Rate | 198 GPixel/s |
| 53-66 GTexel/s | Texture Fill Rate | 554 GTexel/s |
| 1.7-2.1 TFLOPS | FLOPS (FP32) | 35.5 TFLOPS |
| System Shared | Memory Type | GDDR6X |
| — | Memory Size | 12 GB |
| — | Memory Clock | 1313 MHz |
| — | Effective Memory Speed | 21000 Mbps |
| — | Bus | 192-bit |
| — | ECC | No |
| — | Memory Bandwidth | 504.2 GB/s |
| IGP | Interface | PCIe 4.0 x16 |
| — | TGP | 220 W |
| TSMC | Manufacturing | TSMC |
| 4 nm | Fabrication Process | 5 nm |
| — | Die Size | 294 mm² |
| — | Transistor Count | 35 billion |
| — | Transistor Density | 119.05 MTr/mm² |
| 12.1 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 3.2 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| No | CUDA | 8.9 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 3 |
| 1.4 | DisplayPort | 1.4a |
| Qualcomm | Vendor | Nvidia |
| Integrated | Build | Discrete |
| October 24, 2023 | Released | January 17, 2024 |
| Laptop | Case | Desktop |
| Generic | Purpose | Gaming |
| Entry-level | Segment | Mid-range |
| Adreno X1 | Architecture | Ada Lovelace |
| Adreno X1 | GPU Codename | AD104 |
| -Qualcomm Snapdragon X (X1-26-100)or above | Recommended CPU | -Intel Core i7 14700Kor above |
| 1084 | Steel Nomad Lite Score | 21568 |
| 928 | Time Spy | 20882 |
| 5988 | Solar Bay | 98166 |
| — | Port Royal | 13122 |
| 3706 | Fire Strike | 50092 |
| 3224 | Wild Life Extreme | 41630 |
| 16550 | Night Raid | 164777 |
| 280 MHz | Base Clock | 1980 MHz |
| 1107-1367 MHz (configurable) | Boost Clock | 2475 MHz |
| 768 | Shading Units | 7168 |
| 48 | Texture Mapping Units (TMUs) | 224 |
| 24 | Render Output Units (ROPs) | 80 |
| 3 | Compute Units (Pipelines) | 56 |
| — | Tensor Cores | 224 |
| — | Ray-tracing Cores | 56 |
| 192KB per cluster | L1 Cache | 128KB per cluster |
| 1MB shared | L2 Cache | 48MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |