Product Compare
NVIDIA Tesla K20X vs NVIDIA TITAN X Pascal
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2012 | Aug 2016 |
| Generation | Tesla | GeForce 10 |
| Type | Professional | Desktop |
| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1300 MHz | 1251 MHz |
| Base Clock | 1417 MHz | |
| Boost Clock | 1531 MHz | |
| Memory | ||
| Memory Size | 6GB | 12GB |
| Memory Type | GDDR5 | GDDR5X |
| Memory Bus | 384bit | 384bit |
| Bandwidth | 249.6GB/s | 480.4GB/s |
| Render Config | ||
| Shading Units | 2688 | 3584 |
| TMUs | 224 | 224 |
| ROPs | 48 | 96 |
| L1 Cache | 16 KB (per SMX) | 48 KB (per SM) |
| L2 Cache | 1536 KB | 3 MB |
| SM Count | 28 | |
| Theoretical Performance | ||
| Pixel Rate | 40.99 GPixel/s | 147.0 GPixel/s |
| Texture Rate | 164.0 GTexel/s | 342.9 GTexel/s |
| FP32 (float) | 3.935 TFLOPS | 10.97 TFLOPS |
| FP64 (double) | 1312 GFLOPS | 342.9 GFLOPS |
| FP16 (half) | 171.5 GFLOPS | |
| Graphics Processor | ||
| GPU Name | GK110 | GP102 |
| Architecture | Kepler | Pascal |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 16 nm |
| Transistors | 7.08 billion | 11.8 billion |
| Die Size | 561 mm² | 471 mm² |
| GPU Variant | GP102-400-A1 | |
| Board Design | ||
| TDP | 235W | 250W |
| Suggested PSU | 550 W | 600 W |
| Outputs | No outputs | 1x DVI1x HDMI 2.03x DisplayPort 1.4a |
| Power Connectors | 1x 6-pin + 1x 8-pin | 1x 6-pin + 1x 8-pin |
| 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 | 3.5 | 6.1 |
| Shader Model | 5.1 | 6.4 |