Product Compare
Intel Data Center GPU Max 1550 vs NVIDIA Tesla P100 DGXS
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2023 | Apr 2016 |
| Generation | Data Center GPU | Tesla |
| Type | Professional | Professional |
| Bus Interface | PCIe 5.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 900 MHz | 1328 MHz |
| Boost Clock | 1600 MHz | 1480 MHz |
| Memory Clock | 1600 MHz | 715 MHz |
| Memory | ||
| Memory Size | 128GB | 16GB |
| Memory Type | HBM2e | HBM2 |
| Memory Bus | 8192bit | 4096bit |
| Bandwidth | 3.28TB/s | 732.2GB/s |
| Render Config | ||
| Shading Units | 16384 | 3584 |
| TMUs | 1024 | 224 |
| ROPs | 0 | 96 |
| Tensor Cores | 1024 | |
| RT Cores | 128 | |
| L1 Cache | 64 KB (per EU) | 24 KB (per SM) |
| L2 Cache | 408 MB | 4 MB |
| SM Count | 56 | |
| Theoretical Performance | ||
| Pixel Rate | 0 MPixel/s | 142.1 GPixel/s |
| Texture Rate | 1638.4 GTexel/s | 331.5 GTexel/s |
| FP16 (half) | 52.43 TFLOPS | 21.22 TFLOPS |
| FP32 (float) | 52.43 TFLOPS | 10.61 TFLOPS |
| FP64 (double) | 52.43 TFLOPS | 5.304 TFLOPS |
| Graphics Processor | ||
| GPU Name | Ponte Vecchio | GP100 |
| Architecture | Generation 12.5 | Pascal |
| Foundry | Intel | TSMC |
| Process Size | 10 nm | 16 nm |
| Transistors | 100 billion | 15.3 billion |
| Die Size | 1280 mm² | 610 mm² |
| Board Design | ||
| TDP | 600W | 300W |
| Suggested PSU | 1000 W | 700 W |
| Outputs | No outputs | No outputs |
| Power Connectors | None | |
| Graphics Features | ||
| DirectX | 12 (12_1) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.3 |
| Shader Model | 6.6 | 6.4 |
| CUDA | 6.0 | |