AMD Radeon R9 M395X Mac Edition vs NVIDIA GeForce RTX 2070 Max-Q Refresh
Grafikprozessor
| GPU Name | Amethyst | TU106B |
|---|---|---|
| GPU Variante | Amethyst XT | — |
| Architektur | GCN 3.0 | Turing |
| Hersteller | TSMC | TSMC |
| Prozessgröße | 28 nm | 12 nm |
| Transistoren | 5,000 million | 10,800 million |
| Chipgröße | 366 mm² | 445 mm² |
Mobile Grafik
| Veröffentlichungsdatum | May 5th, 2015 | Mar 4th, 2020 |
|---|---|---|
| Generation | Crystal System (R9 M300) | GeForce 20 Mobile |
| Produktion | End-of-life | Active |
| Businterface | MXM-B (3.0) | PCIe 3.0 x16 |
| Vorgänger | Solar System | GeForce 10 Mobile |
| Nachfolger | Mobility Radeon | GeForce 30 Mobile |
Takt-Geschwindigkeiten
| GPU-Taktung | 909 MHz | — |
|---|---|---|
| Speicher-Taktung | 1365 MHz 5.5 Gbps effective | 1375 MHz 11 Gbps effective |
| Basis-Taktfrequenz | — | 900 MHz |
| Boost-Takt | — | 1125 MHz |
Speicher
| Speichergröße | 4 GB | 8 GB |
|---|---|---|
| Speichertyp | GDDR5 | GDDR6 |
| Speicherbus | 256 bit | 256 bit |
| Bandbreite | 174.7 GB/s | 352.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 2048 | 2304 |
|---|---|---|
| TMUs | 128 | 144 |
| ROPs | 32 | 64 |
| Compute Units | 32 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 512 KB | 4 MB |
| Anzahl SM | — | 36 |
| Tensor Cores | — | 288 |
| RT-Kerne | — | 36 |
Theoretische Leistung
| Pixelrate | 29.09 GPixel/s | 72.00 GPixel/s |
|---|---|---|
| Texturrate | 116.4 GTexel/s | 162.0 GTexel/s |
| FP16 (half) Leistung | 3.723 TFLOPS (1:1) | 10.37 TFLOPS (2:1) |
| FP32 (float) Leistung | 3.723 TFLOPS | 5.184 TFLOPS |
| FP64 (double) Leistung | 232.7 GFLOPS (1:16) | 162.0 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | MXM Module | MXM Module |
|---|---|---|
| TDP | 250 W | 115 W |
| Ausgabe | No outputs | No outputs |
| Stromverbindung | None | None |
| Board-Nummer | — | E4914 SKU 31 |
Grafik-Features
| DirectX | 12 (12_0) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader-Modell | 6.3 | 6.6 |
| CUDA | — | 7.5 |
