Product Compare
NVIDIA B200 SXM6 vs NVIDIA Tesla K40m
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2024 | Nov 2013 |
| Generation | Server Blackwell | Tesla |
| Type | Desktop | Professional |
| Bus Interface | PCIe 6.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 120 MHz | 745 MHz |
| Boost Clock | 1830 MHz | 876 MHz |
| Memory Clock | 2000 MHz | 1502 MHz |
| Memory | ||
| Memory Size | 180GB | 12GB |
| Memory Type | HBM3e | GDDR5 |
| Memory Bus | 8192bit | 384bit |
| Bandwidth | 8.19TB/s | 288.4GB/s |
| Render Config | ||
| SM Count | 148 | |
| Shading Units | 18944 | 2880 |
| TMUs | 592 | 240 |
| ROPs | 24 | 48 |
| Tensor Cores | 592 | |
| L1 Cache | 256 KB (per SM) | 16 KB (per SMX) |
| L2 Cache | 126 MB | 1536 KB |
| Theoretical Performance | ||
| Pixel Rate | 43.92 GPixel/s | 52.56 GPixel/s |
| Texture Rate | 1083.4 GTexel/s | 210.2 GTexel/s |
| FP16 (half) | 1109.4 TFLOPS | |
| FP32 (float) | 69.34 TFLOPS | 5.046 TFLOPS |
| FP64 (double) | 34.67 TFLOPS | 1.682 TFLOPS |
| Graphics Processor | ||
| GPU Name | GB100 | GK110B |
| GPU Variant | GB100-886N-A1 | |
| Architecture | Blackwell | Kepler |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 28 nm |
| Transistors | 208 billion | 7.08 billion |
| Die Size | 1628 mm² | 561 mm² |
| Board Design | ||
| TDP | 1000W | 245W |
| Suggested PSU | 1400 W | 550 W |
| Outputs | No outputs | No outputs |
| Graphics Features | ||
| DirectX | N/A | 12 (11_1) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.1 |
| CUDA | 10.0 | 3.5 |
| Shader Model | N/A | 5.1 |