Product Compare
NVIDIA GeForce GTX 580 vs NVIDIA RTX A2000 Max-Q 8 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2010 | Apr 2021 |
| Generation | GeForce 500 | Ampere-MW |
| Type | Desktop | Mobile |
| Bus Interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1002 MHz | 1375 MHz |
| Base Clock | 607 MHz | |
| Boost Clock | 1177 MHz | |
| Memory | ||
| Memory Size | 1536MB | 8GB |
| Memory Type | GDDR5 | GDDR6 |
| Memory Bus | 384bit | 128bit |
| Bandwidth | 192.4GB/s | 176.0GB/s |
| Render Config | ||
| SM Count | 16 | 20 |
| Shading Units | 512 | 2560 |
| TMUs | 64 | 80 |
| ROPs | 48 | 48 |
| L1 Cache | 64 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 768 KB | 2 MB |
| Tensor Cores | 80 | |
| RT Cores | 20 | |
| Theoretical Performance | ||
| Pixel Rate | 24.70 GPixel/s | 56.50 GPixel/s |
| Texture Rate | 49.41 GTexel/s | 94.16 GTexel/s |
| FP32 (float) | 1.581 TFLOPS | 6.026 TFLOPS |
| FP64 (double) | 197.6 GFLOPS | 94.16 GFLOPS |
| FP16 (half) | 6.026 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GF110 | GA107 |
| GPU Variant | GF110-375-A1 | |
| Architecture | Fermi 2.0 | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 40 nm | 8 nm |
| Transistors | 3 billion | 8.7 billion |
| Die Size | 520 mm² | 200 mm² |
| Board Design | ||
| TDP | 244W | 95W |
| Suggested PSU | 550 W | |
| Outputs | 2x DVI1x mini-HDMI 1.3a | Portable Device Dependent |
| Power Connectors | 1x 6-pin + 1x 8-pin | None |
| 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 | 8.6 |
| Shader Model | 5.1 | 6.8 |