NVIDIA PG506-242 vs NVIDIA Tesla P100 DGXS
What is the difference between NVIDIA PG506-242 and NVIDIA Tesla P100 DGXS. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GA100 | GPU Name | GP100 |
| Ampere | Architecture | Pascal |
| TSMC | Foundry | TSMC |
| 7 nm | Process Size | 16 nm |
| 54,200 million | Transistors | 15,300 million |
| 826 mm² | Die Size | 610 mm² |
Graphics Card
| Apr 12th, 2021 | Release Date | Apr 5th, 2016 |
| Tesla (Axx) | Family | Tesla (Pxx) |
| Active | Production | Active |
| PCIe 4.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 24 GB | Memory Size | 16 GB |
| HBM2 | Memory Type | HBM2 |
| 3072 bit | Memory Bus | 4096 bit |
| 933.1 GB/s | Bandwidth | 732.2 GB/s |
Performance
| 138.2 GPixel/s | Pixel fillrate | 142.1 GPixel/s |
| 322.6 GTexel/s | Texture fillrate | 331.5 GTexel/s |
| 10.32 TFLOPS (1:1) | FP16 (half) performance | 21.22 TFLOPS (2:1) |
| 10.32 TFLOPS | FP32 (float) performance | 10.61 TFLOPS |
| 5.161 TFLOPS (1:2) | FP64 (double) performance | 5.304 TFLOPS (1:2) |
Clock Speeds
| 930 MHz | Base Clock | 1328 MHz |
| 1440 MHz | Boost Clock | 1480 MHz |
| 1215 MHz 2.4 Gbps effective | Memory Clock | 715 MHz 1430 Mbps effective |
Render Config
| 3584 | Shading Units | 3584 |
| 224 | TMUs | 224 |
| 96 | ROPs | 96 |
| 192 KB (per SM) | L1 Cache | 24 KB (per SM) |
| 24 MB | L2 Cache | 4 MB |
| 56 | SM Count | 56 |
Board Design
| 165 W | Thermal design power (TDP) | 300 W |
| 450 W | Suggested PSU | 700 W |
| No outputs | Display Connectors | No outputs |
| 8-pin EPS | Power Connectors | None |
API support
| N/A | DirectX | 12 (12_1) |
| N/A | OpenGL | 4.6 |
| 3.0 | OpenCL | 3.0 |
| N/A | Vulkan | 1.2 |
| N/A | Shader Model | 6.4 |
| 8.0 | CUDA | 6.0 |