AMD Radeon RX Vega M GH vs NVIDIA Tesla K20s
What is the difference between AMD Radeon RX Vega M GH and NVIDIA Tesla K20s. Find out which graphics card has better performance.
Graphics Processor (GPU)
| Polaris 22 | GPU Name | GK110 |
| GCN 4.0 | Architecture | Kepler |
| GlobalFoundries | Foundry | TSMC |
| 14 nm | Process Size | 28 nm |
| 5,000 million | Transistors | 7,080 million |
| 208 mm² | Die Size | 561 mm² |
Graphics Card
| Feb 1st, 2018 | Release Date | Feb 18th, 2013 |
| Vega (Vega M) | Family | Tesla (Kxx) |
| Active | Production | End-of-life |
| IGP | Bus Interface | PCIe 2.0 x16 |
Memory
| 4 GB | Memory Size | 5 GB |
| HBM2 | Memory Type | GDDR5 |
| 1024 bit | Memory Bus | 320 bit |
| 204.8 GB/s | Bandwidth | 208.0 GB/s |
Performance
| 76.16 GPixel/s | Pixel fillrate | 29.90 GPixel/s |
| 114.2 GTexel/s | Texture fillrate | 119.6 GTexel/s |
| 3.656 TFLOPS | FP32 (float) performance | 2.870 TFLOPS |
| 228.5 GFLOPS (1:16) | FP64 (double) performance | 956.8 GFLOPS (1:3) |
Clock Speeds
| 800 MHz 1600 Mbps effective | Memory Clock | 1300 MHz 5.2 Gbps effective |
Render Config
| 1536 | Shading Units | 2496 |
| 96 | TMUs | 208 |
| 64 | ROPs | 40 |
| 16 KB (per CU) | L1 Cache | 16 KB (per SMX) |
| 1024 KB | L2 Cache | 1280 KB |
Board Design
| IGP | Slot Width | Dual-slot |
| 100 W | Thermal design power (TDP) | 225 W |
| No outputs | Display Connectors | No outputs |
API support
| 12 (12_0) | DirectX | 12 (11_0) |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 3.0 |
| 1.2 | Vulkan | 1.1 |
| 6.4 | Shader Model | 5.1 |