Quick/Comparisons
9 | Gaming | 61 |
8 | Workstation | 69 |
| — | AI/ML |
Compare with something else?
Compare Adreno X1-45 with another →93 | Energy Efficiency | 35 |
24 | Quick Comparison Final Score | 62 |
| Adreno X1 | Graphics Processor | GA102 |
| 768 | Cores | 10496 |
| 48 / 24 | TMUs / ROPs | 328 / 112 |
| — | Blender GPU | 5800.59 |
| — | Forza Horizon 5 | 125 |
| — | The Witcher 3 | 175 |
| — | Counter-Strike 2 | 212 |
| — | Far Cry 6 | 142 |
| — | Hogwarts Legacy | 106 |
| — | Call of Duty | 159 |
| — | Ghost of Tsushima | 97 |
| — | Cyberpunk 2077 | 132 |
| — | Tomb Raider | 226 |
| — | Average FPS | 153 |
| — | 1080p High | 179 |
| — | 1080p Ultra | 153 |
| — | 1440p Ultra | 119 |
| — | 4K Ultra | 70 |
| — | Margin of Error | Low |
| 9947 | GB6 Compute Score | 211669 |
| 14.2 img/sec | Background Blur | 320.8 img/sec |
| 6.82 img/sec | Face Detection | 207.2 img/sec |
| 0.56 Gpixels/sec | Horizon Detection | 10.1 Gpixels/sec |
| 0.65 Gpixels/sec | Edge Detection | 14.4 Gpixels/sec |
| 0.55 Gpixels/sec | Gaussian Blur | 11.5 Gpixels/sec |
| 0.12 Gpixels/sec | Feature Matching | 1.48 Gpixels/sec |
| 26.6 Gpixels/sec | Stereo Matching | 984.2 Gpixels/sec |
| 1746.7 FPS | Particle Physics | 27764.9 FPS |
| OpenCL | API | OpenCL |
| 1893 | G3D Mark Score | 26551 |
| 357 | G2D Mark | 1069 |
| 13 FPS | DirectX 11 | 218 FPS |
| 9 FPS | DirectX 12 | 110 FPS |
| 818 Ops/s | GPU Compute | 15117 Ops/s |
| — | GB6 ML Single Precision | 27237 |
| — | GB6 ML Half Precision | 41500 |
| — | GB6 ML Quantized | 15927 |
| — | Image Classification (SP) | 10665 |
| — | Image Segmentation (HP) | 28963 |
| — | Image Super Resolution (Q) | 22697 |
| — | Face Detection (HP) | 55232 |
| — | Pose Estimation (Q) | 128155 |
| — | Text Classification (SP) | 3152 |
| — | Machine Translation (HP) | 5088 |
| — | Object Detection (SP) | 13891 |
| — | Depth Estimation (Q) | 37984 |
| — | Style Transfer (SP) | 272000 |
| — | Framework | ONNX |
| — | Backend | DirectML |
| 27-33 GPixel/s | Pixel Fill Rate | 190 GPixel/s |
| 53-66 GTexel/s | Texture Fill Rate | 556 GTexel/s |
| 1.7-2.1 TFLOPS | FLOPS (FP32) | 35.6 TFLOPS |
| System Shared | Memory Type | GDDR6X |
| — | Memory Size | 24 GB |
| — | Memory Clock | 1219 MHz |
| — | Effective Memory Speed | 19500 Mbps |
| — | Bus | 384-bit |
| — | ECC | No |
| — | Memory Bandwidth | 936.2 GB/s |
| IGP | Interface | PCIe 4.0 x16 |
| — | TGP | 350 W |
| TSMC | Manufacturing | Samsung |
| 4 nm | Fabrication Process | 8 nm |
| — | Die Size | 628 mm² |
| — | Transistor Count | 28 billion |
| — | Transistor Density | 44.59 MTr/mm² |
| 12.1 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 3.2 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| No | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| 1.4 | DisplayPort | 1.4a |
| Qualcomm | Vendor | Nvidia |
| Integrated | Build | Discrete |
| October 24, 2023 | Released | September 24, 2020 |
| Laptop | Case | Desktop |
| Generic | Purpose | Gaming |
| Entry-level | Segment | High-end |
| Adreno X1 | Architecture | Ampere |
| Adreno X1 | GPU Codename | GA102 |
| -Qualcomm Snapdragon X (X1-26-100)or above | Recommended CPU | -Intel Core i9 12900Kor above |
| 1084 | Steel Nomad Lite Score | 21851 |
| 928 | Time Spy | 19896 |
| 5988 | Solar Bay | 97375 |
| — | Port Royal | 13631 |
| 3706 | Fire Strike | 47515 |
| 3224 | Wild Life Extreme | 43673 |
| 16550 | Night Raid | 139755 |
| 280 MHz | Base Clock | 1395 MHz |
| 1107-1367 MHz (configurable) | Boost Clock | 1695 MHz |
| 768 | Shading Units | 10496 |
| 48 | Texture Mapping Units (TMUs) | 328 |
| 24 | Render Output Units (ROPs) | 112 |
| 3 | Compute Units (Pipelines) | 82 |
| — | Tensor Cores | 328 |
| — | Ray-tracing Cores | 82 |
| 192KB per cluster | L1 Cache | 128KB per cluster |
| 1MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |