Product Compare
NVIDIA GeForce RTX 3080 Ti Max Q vs NVIDIA Tesla P100 SXM2
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2022 | Apr 2016 |
| Generation | GeForce 30 Mobile | Tesla |
| Type | Mobile | Professional |
| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 585 MHz | 1328 MHz |
| Boost Clock | 1125 MHz | 1480 MHz |
| Memory Clock | 1500 MHz | 715 MHz |
| Memory | ||
| Memory Size | 16GB | 16GB |
| Memory Type | GDDR6 | HBM2 |
| Memory Bus | 256bit | 4096bit |
| Bandwidth | 384.0GB/s | 732.2GB/s |
| Render Config | ||
| SM Count | 58 | 56 |
| Shading Units | 7424 | 3584 |
| TMUs | 232 | 224 |
| ROPs | 96 | 96 |
| Tensor Cores | 232 | |
| RT Cores | 58 | |
| L1 Cache | 128 KB (per SM) | 24 KB (per SM) |
| L2 Cache | 4 MB | 4 MB |
| Theoretical Performance | ||
| Pixel Rate | 108.0 GPixel/s | 142.1 GPixel/s |
| Texture Rate | 261.0 GTexel/s | 331.5 GTexel/s |
| FP16 (half) | 16.70 TFLOPS | 21.22 TFLOPS |
| FP32 (float) | 16.70 TFLOPS | 10.61 TFLOPS |
| FP64 (double) | 261.0 GFLOPS | 5.304 TFLOPS |
| Graphics Processor | ||
| GPU Name | GA103S | GP100 |
| GPU Variant | GN20-E8-A1 | GP100-890-A1 |
| Architecture | Ampere | Pascal |
| Foundry | Samsung | TSMC |
| Process Size | 8 nm | 16 nm |
| Transistors | Unknown | 15.3 billion |
| Die Size | 496 mm² | 610 mm² |
| Board Design | ||
| TDP | 80W | 300W |
| Outputs | No outputs | No outputs |
| Power Connectors | None | None |
| Suggested PSU | 700 W | |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 8.6 | 6.0 |
| Shader Model | 6.5 | 6.4 |