Product Compare
NVIDIA TITAN RTX vs NVIDIA Tesla K40t
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Dec 2018 | Nov 2013 |
| Generation | GeForce 20 | Tesla Kepler |
| Type | Desktop | Professional |
| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 1350 MHz | 745 MHz |
| Boost Clock | 1770 MHz | 876 MHz |
| Memory Clock | 1750 MHz | 1502 MHz |
| Memory | ||
| Memory Size | 24GB | 12GB |
| Memory Type | GDDR6 | GDDR5 |
| Memory Bus | 384bit | 384bit |
| Bandwidth | 672.0GB/s | 288.4GB/s |
| Render Config | ||
| SM Count | 72 | |
| Shading Units | 4608 | 2880 |
| TMUs | 288 | 240 |
| ROPs | 96 | 48 |
| Tensor Cores | 576 | |
| RT Cores | 72 | |
| L1 Cache | 64 KB (per SM) | 16 KB (per SMX) |
| L2 Cache | 6 MB | 1536 KB |
| Theoretical Performance | ||
| Pixel Rate | 169.9 GPixel/s | 52.56 GPixel/s |
| Texture Rate | 509.8 GTexel/s | 210.2 GTexel/s |
| FP16 (half) | 32.62 TFLOPS | |
| FP32 (float) | 16.31 TFLOPS | 5.046 TFLOPS |
| FP64 (double) | 509.8 GFLOPS | 1.682 TFLOPS |
| Graphics Processor | ||
| GPU Name | TU102 | GK110B |
| GPU Variant | TU102-400-A1 | |
| Architecture | Turing | Kepler |
| Foundry | TSMC | TSMC |
| Process Size | 12 nm | 28 nm |
| Transistors | 18.6 billion | 7.08 billion |
| Die Size | 754 mm² | 561 mm² |
| Board Design | ||
| TDP | 280W | 245W |
| Suggested PSU | 600 W | 550 W |
| Outputs | 1x HDMI 2.03x DisplayPort 1.4a1x USB Type-C | No outputs |
| Power Connectors | 2x 8-pin | |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 (11_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.2.175 |
| CUDA | 7.5 | 3.5 |
| Shader Model | 6.6 | 6.5 (5.1) |