Product Compare
NVIDIA Tesla K20s vs NVIDIA GeForce RTX 3070 Ti
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Feb 2013 | May 2021 |
| Generation | Tesla | GeForce 30 |
| Type | Professional | Desktop |
| Bus Interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1300 MHz | 1188 MHz |
| Base Clock | 1575 MHz | |
| Boost Clock | 1770 MHz | |
| Memory | ||
| Memory Size | 5GB | 8GB |
| Memory Type | GDDR5 | GDDR6X |
| Memory Bus | 320bit | 256bit |
| Bandwidth | 208.0GB/s | 608.3GB/s |
| Render Config | ||
| Shading Units | 2496 | 6144 |
| TMUs | 208 | 192 |
| ROPs | 40 | 96 |
| L1 Cache | 16 KB (per SMX) | 128 KB (per SM) |
| L2 Cache | 1280 KB | 4 MB |
| SM Count | 48 | |
| Tensor Cores | 192 | |
| RT Cores | 48 | |
| Theoretical Performance | ||
| Pixel Rate | 29.90 GPixel/s | 169.9 GPixel/s |
| Texture Rate | 119.6 GTexel/s | 339.8 GTexel/s |
| FP32 (float) | 2.870 TFLOPS | 21.75 TFLOPS |
| FP64 (double) | 956.8 GFLOPS | 339.8 GFLOPS |
| FP16 (half) | 21.75 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GK110 | GA104 |
| Architecture | Kepler | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 28 nm | 8 nm |
| Transistors | 7.08 billion | 17.4 billion |
| Die Size | 561 mm² | 392 mm² |
| GPU Variant | GA104-400-A1 | |
| Board Design | ||
| TDP | 225W | 290W |
| Suggested PSU | 550 W | 600 W |
| Outputs | No outputs | 1x HDMI 2.13x DisplayPort 1.4a |
| Power Connectors | 1x 12-pin | |
| Graphics Features | ||
| DirectX | 12 (11_0) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.3 |
| CUDA | 3.5 | 8.6 |
| Shader Model | 5.1 | 6.6 |