Product Compare
NVIDIA P102 100 vs NVIDIA GeForce RTX 3050 Ti Max-Q
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Feb 2018 | May 2021 |
| Generation | Mining GPUs | GeForce 30 Mobile |
| Type | Desktop | Mobile |
| Bus Interface | PCIe 3.0 x4 | PCIe 4.0 x8 |
| Clock Speeds | ||
| Base Clock | 1582 MHz | 735 MHz |
| Boost Clock | 1683 MHz | 1035 MHz |
| Memory Clock | 1376 MHz | 1375 MHz |
| Memory | ||
| Memory Size | 5GB | 4GB |
| Memory Type | GDDR5X | GDDR6 |
| Memory Bus | 320bit | 128bit |
| Bandwidth | 440.3GB/s | 176.0GB/s |
| Render Config | ||
| SM Count | 25 | 20 |
| Shading Units | 3200 | 2560 |
| TMUs | 200 | 80 |
| ROPs | 80 | 32 |
| L1 Cache | 48 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 0 MB | 2 MB |
| Tensor Cores | 80 | |
| RT Cores | 20 | |
| Theoretical Performance | ||
| Pixel Rate | 134.6 GPixel/s | 33.12 GPixel/s |
| Texture Rate | 336.6 GTexel/s | 82.80 GTexel/s |
| FP16 (half) | 168.3 GFLOPS | 5.299 TFLOPS |
| FP32 (float) | 10.77 TFLOPS | 5.299 TFLOPS |
| FP64 (double) | 336.6 GFLOPS | 82.80 GFLOPS |
| Graphics Processor | ||
| GPU Name | GP102 | GA107 |
| GPU Variant | GP102-100-A1 | |
| Architecture | Pascal | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 16 nm | 8 nm |
| Transistors | 11.8 billion | 8.7 billion |
| Die Size | 471 mm² | 200 mm² |
| Board Design | ||
| TDP | 250W | 75W |
| Suggested PSU | 600 W | |
| Outputs | No outputs | Portable Device Dependent |
| Power Connectors | 2x 8-pin | None |
| Graphics Features | ||
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 6.1 | 8.6 |
| Shader Model | 6.4 | 6.7 |