Product Compare
NVIDIA GeForce GTX 580 Rev. 2 vs NVIDIA CMP 50HX
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jun 2011 | Jun 2021 |
| Generation | GeForce 500 | Mining GPUs |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 2.0 x16 | PCIe 1.0 x4 |
| Clock Speeds | ||
| Memory Clock | 1002 MHz | 1750 MHz |
| Base Clock | 1350 MHz | |
| Boost Clock | 1545 MHz | |
| Memory | ||
| Memory Size | 1536MB | 10GB |
| Memory Type | GDDR5 | GDDR6 |
| Memory Bus | 384bit | 320bit |
| Bandwidth | 192.4GB/s | 560.0GB/s |
| Render Config | ||
| SM Count | 16 | 56 |
| Shading Units | 512 | 3584 |
| TMUs | 64 | 192 |
| ROPs | 48 | 80 |
| L1 Cache | 64 KB (per SM) | 64 KB (per SM) |
| L2 Cache | 768 KB | 5 MB |
| Tensor Cores | 448 | |
| RT Cores | 56 | |
| Theoretical Performance | ||
| Pixel Rate | 24.70 GPixel/s | 123.6 GPixel/s |
| Texture Rate | 49.41 GTexel/s | 296.6 GTexel/s |
| FP32 (float) | 1.581 TFLOPS | 11.07 TFLOPS |
| FP64 (double) | 197.6 GFLOPS | 346.1 GFLOPS |
| FP16 (half) | 22.15 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GF110 | TU102 |
| GPU Variant | GF110-380-A1 | TU102-100-A1 |
| Architecture | Fermi 2.0 | Turing |
| Foundry | TSMC | TSMC |
| Process Size | 40 nm | 12 nm |
| Transistors | 3 billion | 18.6 billion |
| Die Size | 520 mm² | 754 mm² |
| Board Design | ||
| TDP | 244W | 250W |
| Suggested PSU | 550 W | 600 W |
| Outputs | 2x DVI1x mini-HDMI 1.3a | No outputs |
| Power Connectors | 1x 6-pin + 1x 8-pin | 2x 8-pin |
| Graphics Features | ||
| DirectX | 12 (11_0) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.1 | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | 2.0 | 7.5 |
| Shader Model | 5.1 | 6.8 |