Product Compare
NVIDIA Tesla K20Xm vs NVIDIA RTX 5000 Embedded Ada Generation
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2012 | Mar 2023 |
| Generation | Tesla | Ada-MW |
| Type | Professional | Mobile |
| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1300 MHz | 2250 MHz |
| Base Clock | 930 MHz | |
| Boost Clock | 1680 MHz | |
| Memory | ||
| Memory Size | 6GB | 16GB |
| Memory Type | GDDR5 | GDDR6 |
| Memory Bus | 384bit | 256bit |
| Bandwidth | 249.6GB/s | 576.0GB/s |
| Render Config | ||
| Shading Units | 2688 | 9728 |
| TMUs | 224 | 304 |
| ROPs | 48 | 112 |
| L1 Cache | 16 KB (per SMX) | 128 KB (per SM) |
| L2 Cache | 1536 KB | 64 MB |
| SM Count | 76 | |
| Tensor Cores | 304 | |
| RT Cores | 76 | |
| Theoretical Performance | ||
| Pixel Rate | 40.99 GPixel/s | 188.2 GPixel/s |
| Texture Rate | 164.0 GTexel/s | 510.7 GTexel/s |
| FP32 (float) | 3.935 TFLOPS | 32.69 TFLOPS |
| FP64 (double) | 1312 GFLOPS | 510.7 GFLOPS |
| FP16 (half) | 32.69 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GK110 | AD103 |
| Architecture | Kepler | Ada Lovelace |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 5 nm |
| Transistors | 7.08 billion | 45.9 billion |
| Die Size | 561 mm² | 379 mm² |
| Board Design | ||
| TDP | 235W | 120W |
| Suggested PSU | 550 W | |
| Outputs | No outputs | Portable Device Dependent |
| Power Connectors | None | |
| Graphics Features | ||
| DirectX | 12 (11_0) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.4 |
| CUDA | 3.5 | 8.9 |
| Shader Model | 5.1 | 6.8 |