Product Compare
NVIDIA Tesla K40d vs AMD Radeon Graphics 448SP
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2013 | Jan 2021 |
| Generation | Tesla Kepler | Lucienne |
| Type | Professional | Integrated |
| Bus Interface | PCIe 3.0 x16 | IGP |
| Clock Speeds | ||
| Base Clock | 745 MHz | 300 MHz |
| Boost Clock | 876 MHz | 1800 MHz |
| Memory Clock | 1502 MHz | System Shared |
| Memory | ||
| Memory Size | 12GB | System Shared |
| Memory Type | GDDR5 | System Shared |
| Memory Bus | 384bit | System Shared |
| Bandwidth | 288.4GB/s | System Dependent |
| Render Config | ||
| Shading Units | 2880 | 448 |
| TMUs | 240 | 32 |
| ROPs | 48 | 8 |
| L1 Cache | 16 KB (per SMX) | |
| L2 Cache | 1536 KB | |
| Compute Units | 7 | |
| Theoretical Performance | ||
| Pixel Rate | 52.56 GPixel/s | 14.40 GPixel/s |
| Texture Rate | 210.2 GTexel/s | 57.60 GTexel/s |
| FP32 (float) | 5.046 TFLOPS | 1.613 TFLOPS |
| FP64 (double) | 1.682 TFLOPS | 100.8 GFLOPS |
| FP16 (half) | 3.226 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GK110B | Lucienne |
| Architecture | Kepler | GCN 5.1 |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 7 nm |
| Transistors | 7.08 billion | 9.8 billion |
| Die Size | 561 mm² | 156 mm² |
| Board Design | ||
| TDP | 245W | 25W |
| Suggested PSU | 550 W | |
| Outputs | No outputs | No outputs |
| Power Connectors | None | |
| Graphics Features | ||
| DirectX | 12 (11_1) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.1 |
| Vulkan | 1.2.175 | 1.2 |
| CUDA | 3.5 | |
| Shader Model | 6.5 (5.1) | 6.4 |