AMD Radeon HD 8970M vs NVIDIA Tesla M4
What is the difference between AMD Radeon HD 8970M and NVIDIA Tesla M4. Find out which graphics card has better performance.
Graphics Processor (GPU)
| Neptune | GPU Name | GM206 |
| GCN 1.0 | Architecture | Maxwell 2.0 |
| TSMC | Foundry | TSMC |
| 28 nm | Process Size | 28 nm |
| 2,800 million | Transistors | 2,940 million |
| 212 mm² | Die Size | 228 mm² |
Graphics Card
| May 14th, 2013 | Release Date | Nov 10th, 2015 |
| Solar System (HD 8900M) | Family | Tesla (Mxx) |
| End-of-life | Production | Active |
| PCIe 3.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 4 GB | Memory Size | 4 GB |
| GDDR5 | Memory Type | GDDR5 |
| 256 bit | Memory Bus | 128 bit |
| 153.6 GB/s | Bandwidth | 88.00 GB/s |
Performance
| 28.80 GPixel/s | Pixel fillrate | 34.30 GPixel/s |
| 72.00 GTexel/s | Texture fillrate | 68.61 GTexel/s |
| 2.304 TFLOPS | FP32 (float) performance | 2.195 TFLOPS |
| 144.0 GFLOPS (1:16) | FP64 (double) performance | 68.61 GFLOPS (1:32) |
Clock Speeds
| 850 MHz | Base Clock | 872 MHz |
| 900 MHz | Boost Clock | 1072 MHz |
| 1200 MHz 4.8 Gbps effective | Memory Clock | 1375 MHz 5.5 Gbps effective |
Render Config
| 1280 | Shading Units | 1024 |
| 80 | TMUs | 64 |
| 32 | ROPs | 32 |
| 16 KB (per CU) | L1 Cache | 48 KB (per SMM) |
| 512 KB | L2 Cache | 1024 KB |
Board Design
| MXM Module | Slot Width | Single-slot |
| 100 W | Thermal design power (TDP) | 50 W |
| No outputs | Display Connectors | No outputs |
API support
| 12 (11_1) | DirectX | 12 (12_1) |
| 4.6 | OpenGL | 4.6 |
| 1.2 | OpenCL | 3.0 |
| 1.2 | Vulkan | 1.1 |
| 5.1 | Shader Model | 6.4 |