AMD Radeon Pro 570 vs NVIDIA Tesla M6
Graphics Processor
| GPU model | Polaris 20 | GM204 |
|---|---|---|
| GPU variant | Polaris 20 | GM204-995-A1 |
| Architecture | GCN 4.0 | Maxwell 2.0 |
| Foundry | GlobalFoundries | TSMC |
| Manufacturing process | 14 nm | 28 nm |
| Number of transistors | 5,700 million | 5,200 million |
| Die size | 232 mm² | 398 mm² |
Mobile graphics
| Release date | Jun 5th, 2017 | — |
|---|---|---|
| Generation | Radeon Pro Mac (500 Series) | — |
| Production | Active | — |
| Interface | PCIe 3.0 x16 | — |
Clocks
| Base clock | 1000 MHz | 930 MHz |
|---|---|---|
| Boost clock | 1105 MHz | 1180 MHz |
| Memory clock | 1695 MHz 6.8 Gbps effective | 1253 MHz 5 Gbps effective |
Memory Configuration
| Memory size | 4 GB | 8 GB |
|---|---|---|
| Memory type | GDDR5 | GDDR5 |
| Memory bus width | 256 bit | 256 bit |
| Bandwidth | 217.0 GB/s | 160.4 GB/s |
Render Configuration
| Shading units | 1792 | 1536 |
|---|---|---|
| TMUs | 112 | 96 |
| ROPs | 32 | 64 |
| Compute units | 28 | — |
| Cache L1 | 16 KB (per CU) | 48 KB (per SMM) |
| Cache L2 | 2 MB | 2 MB |
| SMM count | — | 12 |
Performance
| Pixel rate | 35.36 GPixel/s | 75.52 GPixel/s |
|---|---|---|
| Texture rate | 123.8 GTexel/s | 113.3 GTexel/s |
| FP16 (half) performance | 3.960 TFLOPS (1:1) | — |
| FP32 (float) performance | 3.960 TFLOPS | 3.625 TFLOPS |
| FP64 (double) performance | 247.5 GFLOPS (1:16) | 113.3 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | IGP | MXM Module |
|---|---|---|
| TDP | 150 W | 100 W |
| Outputs | No outputs | No outputs |
| Power connectors | None | None |
| Suggested PSU | — | 300 W |
API Support & Features
| DirectX | 12 (12_0) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.4 | 6.4 |
| CUDA | — | 5.2 |
Other Features
Graphics Card
| Release date | — | Aug 30th, 2015 |
|---|---|---|
| Generation | — | Tesla |
| Production | — | End-of-life |
| Interface | — | PCIe 3.0 x16 |
