Product Compare
NVIDIA GeForce GTX 580 vs NVIDIA B200 SXM6
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2010 | Nov 2024 |
| Generation | GeForce 500 | Server Blackwell |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 2.0 x16 | PCIe 6.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1002 MHz | 2000 MHz |
| Base Clock | 120 MHz | |
| Boost Clock | 1830 MHz | |
| Memory | ||
| Memory Size | 1536MB | 180GB |
| Memory Type | GDDR5 | HBM3e |
| Memory Bus | 384bit | 8192bit |
| Bandwidth | 192.4GB/s | 8.19TB/s |
| Render Config | ||
| SM Count | 16 | 148 |
| Shading Units | 512 | 18944 |
| TMUs | 64 | 592 |
| ROPs | 48 | 24 |
| L1 Cache | 64 KB (per SM) | 256 KB (per SM) |
| L2 Cache | 768 KB | 126 MB |
| Tensor Cores | 592 | |
| Theoretical Performance | ||
| Pixel Rate | 24.70 GPixel/s | 43.92 GPixel/s |
| Texture Rate | 49.41 GTexel/s | 1083.4 GTexel/s |
| FP32 (float) | 1.581 TFLOPS | 69.34 TFLOPS |
| FP64 (double) | 197.6 GFLOPS | 34.67 TFLOPS |
| FP16 (half) | 1109.4 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GF110 | GB100 |
| GPU Variant | GF110-375-A1 | GB100-886N-A1 |
| Architecture | Fermi 2.0 | Blackwell |
| Foundry | TSMC | TSMC |
| Process Size | 40 nm | 5 nm |
| Transistors | 3 billion | 208 billion |
| Die Size | 520 mm² | 1628 mm² |
| Board Design | ||
| TDP | 244W | 1000W |
| Suggested PSU | 550 W | 1400 W |
| Outputs | 2x DVI1x mini-HDMI 1.3a | No outputs |
| Power Connectors | 1x 6-pin + 1x 8-pin | |
| Graphics Features | ||
| DirectX | 12 (11_0) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 1.1 | 3.0 |
| Vulkan | N/A | N/A |
| CUDA | 2.0 | 10.0 |
| Shader Model | 5.1 | N/A |