Product Compare
NVIDIA Tesla P100 PCIe 16 GB vs NVIDIA RTX 4000 SFF Ada Generation
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jun 2016 | Nov 2018 |
| Generation | Tesla | Radeon Instinct |
| Type | Professional | Professional |
| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1190 MHz | 1200 MHz |
| Boost Clock | 1329 MHz | 1746 MHz |
| Memory Clock | 715 MHz | 1000 MHz |
| Memory | ||
| Memory Size | 16GB | 16GB |
| Memory Type | HBM2 | HBM2 |
| Memory Bus | 4096bit | 4096bit |
| Bandwidth | 732.2GB/s | 1.02TB/s |
| Render Config | ||
| SM Count | 56 | 48 |
| Shading Units | 3584 | 3840 |
| TMUs | 224 | 240 |
| ROPs | 96 | 64 |
| L1 Cache | 24 KB (per SM) | 16 KB (per CU) |
| L2 Cache | 4 MB | 4 MB |
| Compute Units | 60 | |
| Tensor Cores | 192 | |
| RT Cores | 48 | |
| Theoretical Performance | ||
| Pixel Rate | 127.6 GPixel/s | 111.7 GPixel/s |
| Texture Rate | 297.7 GTexel/s | 419.0 GTexel/s |
| FP16 (half) | 19.05 TFLOPS | 26.82 TFLOPS |
| FP32 (float) | 9.526 TFLOPS | 13.41 TFLOPS |
| FP64 (double) | 4.763 TFLOPS | 6.705 TFLOPS |
| Graphics Processor | ||
| GPU Name | GP100 | Vega 20 |
| GPU Variant | GP100-893-A1 | Vega 20 GLXT |
| Architecture | Pascal | GCN 5.1 |
| Foundry | TSMC | TSMC |
| Process Size | 16 nm | 7 nm |
| Transistors | 15.3 billion | 13.23 billion |
| Die Size | 610 mm² | 331 mm² |
| Board Design | ||
| TDP | 250W | 300W |
| Suggested PSU | 600 W | 700 W |
| Outputs | No outputs | 1x mini-DisplayPort 1.4a |
| Power Connectors | 1x 8-pin | 2x 8-pin |
| Graphics Features | ||
| DirectX | 12 (12_1) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.1 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 6.0 | 8.9 |
| Shader Model | 6.4 | 6.7 |