Product Compare
NVIDIA Rubin Ultra GPU vs Intel Data Center GPU Max 1100
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2027 | Jan 2023 |
| Generation | Server Rubin | Data Center GPU |
| Type | Desktop | Professional |
| Bus Interface | PCIe 6.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 700 MHz | 1000 MHz |
| Boost Clock | 2267 MHz | 1550 MHz |
| Memory Clock | 1900 MHz | 600 MHz |
| Memory | ||
| Memory Size | 1024GB | 48GB |
| Memory Type | HBM4e | HBM2e |
| Memory Bus | 32768bit | 8192bit |
| Bandwidth | 31.1TB/s | 1229GB/s |
| Render Config | ||
| SM Count | 448 | |
| Shading Units | 57344 | 7168 |
| TMUs | 1792 | 448 |
| ROPs | 24 | 0 |
| Tensor Cores | 1792 | 448 |
| L1 Cache | 256 KB (per SM) | 64 KB (per EU) |
| L2 Cache | 128 MB | 204 MB |
| RT Cores | 56 | |
| Theoretical Performance | ||
| Pixel Rate | 54.41 GPixel/s | 0 MPixel/s |
| Texture Rate | 4062.5 GTexel/s | 694.4 GTexel/s |
| FP16 (half) | 520.0 TFLOPS | 22.22 TFLOPS |
| FP32 (float) | 260.0 TFLOPS | 22.22 TFLOPS |
| FP64 (double) | 65.00 TFLOPS | 22.22 TFLOPS |
| Graphics Processor | ||
| GPU Name | GR110 | Ponte Vecchio |
| Architecture | Rubin Ultra | Generation 12.5 |
| Foundry | TSMC | Intel |
| Process Size | 3 nm | 10 nm |
| Transistors | 670 billion | 100 billion |
| Die Size | 2912 mm² | 1280 mm² |
| Board Design | ||
| TDP | 3600W | 300W |
| Suggested PSU | 4000 W | 700 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 1x 12-pin | |
| Graphics Features | ||
| DirectX | N/A | 12 (12_1) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | N/A |
| CUDA | 10.7 | |
| Shader Model | N/A | 6.6 |