Product Compare
NVIDIA Quadro K5000 SYNC vs NVIDIA Tesla P100 DGXS
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2013 | Apr 2016 |
| Generation | Quadro | Tesla |
| Type | Professional | Professional |
| Bus Interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1350 MHz | 715 MHz |
| Base Clock | 1328 MHz | |
| Boost Clock | 1480 MHz | |
| Memory | ||
| Memory Size | 4GB | 16GB |
| Memory Type | GDDR5 | HBM2 |
| Memory Bus | 256bit | 4096bit |
| Bandwidth | 172.8GB/s | 732.2GB/s |
| Render Config | ||
| Shading Units | 1536 | 3584 |
| TMUs | 128 | 224 |
| ROPs | 32 | 96 |
| L1 Cache | 16 KB (per SMX) | 24 KB (per SM) |
| L2 Cache | 512 KB | 4 MB |
| SM Count | 56 | |
| Theoretical Performance | ||
| Pixel Rate | 22.59 GPixel/s | 142.1 GPixel/s |
| Texture Rate | 90.37 GTexel/s | 331.5 GTexel/s |
| FP32 (float) | 2.169 TFLOPS | 10.61 TFLOPS |
| FP64 (double) | 90.37 GFLOPS | 5.304 TFLOPS |
| FP16 (half) | 21.22 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GK104 | GP100 |
| Architecture | Kepler | Pascal |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 16 nm |
| Transistors | 3.54 billion | 15.3 billion |
| Die Size | 294 mm² | 610 mm² |
| Board Design | ||
| TDP | 122W | 300W |
| Suggested PSU | 300 W | 700 W |
| Outputs | 2x DVI2x DisplayPort 1.21x SDI | No outputs |
| Power Connectors | 2x 6-pin | None |
| Graphics Features | ||
| DirectX | 12 (11_0) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.3 |
| CUDA | 3.0 | 6.0 |
| Shader Model | 5.1 | 6.4 |