Product Compare
AMD Radeon HD 6970 vs NVIDIA GeForce RTX 2080 Ti
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Dec 2010 | Sep 2018 |
| Generation | Northern Islands | GeForce 20 |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1375 MHz | 1750 MHz |
| Base Clock | 1350 MHz | |
| Boost Clock | 1545 MHz | |
| Memory | ||
| Memory Size | 2GB | 11GB |
| Memory Type | GDDR5 | GDDR6 |
| Memory Bus | 256bit | 352bit |
| Bandwidth | 176.0GB/s | 616.0GB/s |
| Render Config | ||
| Compute Units | 24 | |
| Shading Units | 1536 | 4352 |
| TMUs | 96 | 272 |
| ROPs | 32 | 88 |
| L1 Cache | 8 KB (per CU) | 64 KB (per SM) |
| L2 Cache | 512 KB | 0 MB |
| SM Count | 68 | |
| Tensor Cores | 544 | |
| RT Cores | 68 | |
| Theoretical Performance | ||
| Pixel Rate | 28.16 GPixel/s | 136.0 GPixel/s |
| Texture Rate | 84.48 GTexel/s | 420.2 GTexel/s |
| FP32 (float) | 2.703 TFLOPS | 13.45 TFLOPS |
| FP64 (double) | 675.8 GFLOPS | 420.2 GFLOPS |
| FP16 (half) | 26.90 TFLOPS | |
| Graphics Processor | ||
| GPU Name | Cayman | TU102 |
| GPU Variant | Cayman XT(215-0807007) | TU102-300A-K1-A1 |
| Architecture | TeraScale 3 | Turing |
| Foundry | TSMC | TSMC |
| Process Size | 40 nm | 12 nm |
| Transistors | 2.64 billion | 18.6 billion |
| Die Size | 389 mm² | 754 mm² |
| Board Design | ||
| TDP | 250W | 250W |
| Suggested PSU | 600 W | 600 W |
| Outputs | 2x DVI1x HDMI 1.4a2x mini-DisplayPort 1.2 | 1x HDMI 2.03x DisplayPort 1.4a1x USB Type-C |
| Power Connectors | 1x 6-pin + 1x 8-pin | 2x 8-pin |
| Graphics Features | ||
| DirectX | 11.2 (11_0) | 12 Ultimate (12_2) |
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | N/A | 1.4 |
| Shader Model | 5.0 | 6.8 |
| CUDA | 7.5 | |