AMD Radeon HD 8970 OEM vs NVIDIA Tesla K20s
What is the difference between AMD Radeon HD 8970 OEM and NVIDIA Tesla K20s. Find out which graphics card has better performance.
Graphics Processor (GPU)
| Tahiti | GPU Name | GK110 |
| GCN 1.0 | Architecture | Kepler |
| TSMC | Foundry | TSMC |
| 28 nm | Process Size | 28 nm |
| 4,313 million | Transistors | 7,080 million |
| 352 mm² | Die Size | 561 mm² |
Graphics Card
| Jan 8th, 2013 | Release Date | Feb 18th, 2013 |
| Sea Islands (HD 8900) | Family | Tesla (Kxx) |
| End-of-life | Production | End-of-life |
| PCIe 3.0 x16 | Bus Interface | PCIe 2.0 x16 |
Memory
| 3 GB | Memory Size | 5 GB |
| GDDR5 | Memory Type | GDDR5 |
| 384 bit | Memory Bus | 320 bit |
| 264.0 GB/s | Bandwidth | 208.0 GB/s |
Performance
| 29.60 GPixel/s | Pixel fillrate | 29.90 GPixel/s |
| 118.4 GTexel/s | Texture fillrate | 119.6 GTexel/s |
| 3.789 TFLOPS | FP32 (float) performance | 2.870 TFLOPS |
| 947.2 GFLOPS (1:4) | FP64 (double) performance | 956.8 GFLOPS (1:3) |
Clock Speeds
| 1375 MHz 5.5 Gbps effective | Memory Clock | 1300 MHz 5.2 Gbps effective |
| 925 MHz | GPU Clock | 575 MHz |
Render Config
| 2048 | Shading Units | 2496 |
| 128 | TMUs | 208 |
| 32 | ROPs | 40 |
| 16 KB (per CU) | L1 Cache | 16 KB (per SMX) |
| 768 KB | L2 Cache | 1280 KB |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 274 mm 10.8 inches | Length | 267 mm 10.5 inches |
| 250 W | Thermal design power (TDP) | 225 W |
| 600 W | Suggested PSU | 550 W |
| 1x DVI 1x HDMI 2x mini-DisplayPort | Display Connectors | No outputs |
API support
| 12 (11_1) | DirectX | 12 (11_0) |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3.0 |
| 1.2 | Vulkan | 1.1 |
| 5.1 | Shader Model | 5.1 |