Product Compare
AMD FirePro W8100 vs NVIDIA Tesla P40
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jun 2014 | Sep 2016 |
| Generation | FirePro | Tesla Pascal |
| Type | Desktop | Professional |
| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1250 MHz | 1808 MHz |
| Base Clock | 1303 MHz | |
| Boost Clock | 1531 MHz | |
| Memory | ||
| Memory Size | 8GB | 24GB |
| Memory Type | GDDR5 | GDDR5 |
| Memory Bus | 512bit | 384bit |
| Bandwidth | 320.0GB/s | 347.1GB/s |
| Render Config | ||
| Compute Units | 40 | |
| Shading Units | 2560 | 3840 |
| TMUs | 160 | 240 |
| ROPs | 64 | 96 |
| L1 Cache | 16 KB (per CU) | 48 KB (per SM) |
| L2 Cache | 1024 KB | 3 MB |
| SM Count | 30 | |
| Theoretical Performance | ||
| Pixel Rate | 52.74 GPixel/s | 147.0 GPixel/s |
| Texture Rate | 131.8 GTexel/s | 367.4 GTexel/s |
| FP32 (float) | 4.219 TFLOPS | 11.76 TFLOPS |
| FP64 (double) | 2.109 TFLOPS | 367.4 GFLOPS |
| FP16 (half) | 183.7 GFLOPS | |
| Graphics Processor | ||
| GPU Name | Hawaii | GP102 |
| GPU Variant | Hawaii GL40 | |
| Architecture | GCN 2.0 | Pascal |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 16 nm |
| Transistors | 6.2 billion | 11.8 billion |
| Die Size | 438 mm² | 471 mm² |
| Board Design | ||
| TDP | 220W | 250W |
| Suggested PSU | 550 W | 600 W |
| Outputs | 4x DisplayPort 1.21x SDI | No outputs |
| Power Connectors | 2x 6-pin | 8-pin EPS |
| Graphics Features | ||
| DirectX | 12 (12_0) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | 1.3 |
| Shader Model | 6.3 | 6.7 |
| CUDA | 6.1 | |