Product Compare
NVIDIA GeForce GTX 580 vs AMD Radeon HD 6950
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2010 | Dec 2010 |
| Generation | GeForce 500 | Northern Islands |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1002 MHz | 1250 MHz |
| Memory | ||
| Memory Size | 1536MB | 2GB |
| Memory Type | GDDR5 | GDDR5 |
| Memory Bus | 384bit | 256bit |
| Bandwidth | 192.4GB/s | 160.0GB/s |
| Render Config | ||
| SM Count | 16 | |
| Shading Units | 512 | 1408 |
| TMUs | 64 | 88 |
| ROPs | 48 | 32 |
| L1 Cache | 64 KB (per SM) | 8 KB (per CU) |
| L2 Cache | 768 KB | 512 KB |
| Compute Units | 22 | |
| Theoretical Performance | ||
| Pixel Rate | 24.70 GPixel/s | 25.60 GPixel/s |
| Texture Rate | 49.41 GTexel/s | 70.40 GTexel/s |
| FP32 (float) | 1.581 TFLOPS | 2.253 TFLOPS |
| FP64 (double) | 197.6 GFLOPS | 563.2 GFLOPS |
| Graphics Processor | ||
| GPU Name | GF110 | Cayman |
| GPU Variant | GF110-375-A1 | Cayman PRO(215-0807019) |
| Architecture | Fermi 2.0 | TeraScale 3 |
| Foundry | TSMC | TSMC |
| Process Size | 40 nm | 40 nm |
| Transistors | 3 billion | 2.64 billion |
| Die Size | 520 mm² | 389 mm² |
| Board Design | ||
| TDP | 244W | 200W |
| Suggested PSU | 550 W | 550 W |
| Outputs | 2x DVI1x mini-HDMI 1.3a | 2x DVI1x HDMI 1.4a2x mini-DisplayPort 1.2 |
| Power Connectors | 1x 6-pin + 1x 8-pin | 2x 6-pin |
| Graphics Features | ||
| DirectX | 12 (11_0) | 11.2 (11_0) |
| OpenGL | 4.6 | 4.4 |
| OpenCL | 1.1 | 1.2 |
| Vulkan | N/A | N/A |
| CUDA | 2.0 | |
| Shader Model | 5.1 | 5.0 |