Product Compare
NVIDIA Rubin Ultra GPU vs NVIDIA Tesla K20c
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2027 | Nov 2012 |
| Generation | Server Rubin | Tesla |
| Type | Desktop | Professional |
| Bus Interface | PCIe 6.0 x16 | PCIe 2.0 x16 |
| Clock Speeds | ||
| Base Clock | 700 MHz | |
| Boost Clock | 2267 MHz | |
| Memory Clock | 1900 MHz | 1300 MHz |
| Memory | ||
| Memory Size | 1024GB | 5GB |
| Memory Type | HBM4e | GDDR5 |
| Memory Bus | 32768bit | 320bit |
| Bandwidth | 31.1TB/s | 208.0GB/s |
| Render Config | ||
| SM Count | 448 | |
| Shading Units | 57344 | 2496 |
| TMUs | 1792 | 208 |
| ROPs | 24 | 40 |
| Tensor Cores | 1792 | |
| L1 Cache | 256 KB (per SM) | 16 KB (per SMX) |
| L2 Cache | 128 MB | 1280 KB |
| Theoretical Performance | ||
| Pixel Rate | 54.41 GPixel/s | 36.71 GPixel/s |
| Texture Rate | 4062.5 GTexel/s | 146.8 GTexel/s |
| FP16 (half) | 520.0 TFLOPS | |
| FP32 (float) | 260.0 TFLOPS | 3.524 TFLOPS |
| FP64 (double) | 65.00 TFLOPS | 1175 GFLOPS |
| Graphics Processor | ||
| GPU Name | GR110 | GK110 |
| Architecture | Rubin Ultra | Kepler |
| Foundry | TSMC | TSMC |
| Process Size | 3 nm | 28 nm |
| Transistors | 670 billion | 7.08 billion |
| Die Size | 2912 mm² | 561 mm² |
| GPU Variant | GK110-885-KA-A1 | |
| Board Design | ||
| TDP | 3600W | 225W |
| Suggested PSU | 4000 W | 550 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 1x 6-pin + 1x 8-pin | |
| Graphics Features | ||
| DirectX | N/A | 12 (11_0) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.1 |
| CUDA | 10.7 | 3.5 |
| Shader Model | N/A | 5.1 |