AMD Radeon Pro Vega 20 vs AMD Radeon R9 M295X
Processeur graphique
| Nom du GPU | Vega 12 | Amethyst |
|---|---|---|
| GPU variant | Vega 12 XTA | Amethyst XT |
| Architecture | GCN 5.0 | GCN 3.0 |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 28 nm |
| Transistors | unknown | 5,000 million |
| Taille des matrices | unknown | 366 mm² |
Graphiques mobiles
| Date de publication | Nov 14th, 2018 | Nov 23rd, 2014 |
|---|---|---|
| Génération | Radeon Pro Mac (Vega Series) | Crystal System (R9 M200) |
| Production | Active | End-of-life |
| Bus interface | PCIe 3.0 x16 | MXM-B (3.0) |
| Prédécesseur | — | Solar System |
| Successeur | — | Mobility Radeon |
Vitesse clock
| Base clock | 815 MHz | — |
|---|---|---|
| Boost clock | 1283 MHz | — |
| Mémoire clock | 740 MHz 1480 Mbps effective | 1250 MHz 5 Gbps effective |
| GPU clock | — | 723 MHz |
Mémoire
| Taille de la mémoire | 4 GB | 4 GB |
|---|---|---|
| Type de mémoire | HBM2 | GDDR5 |
| Bus mémoire | 1024 bit | 256 bit |
| Bande passante | 189.4 GB/s | 160.0 GB/s |
Render Config
| Shading units | 1280 | 2048 |
|---|---|---|
| TMUs | 80 | 128 |
| ROPs | 32 | 32 |
| Compute units | 20 | 32 |
| Cache L1 | 16 KB (per CU) | 16 KB (per CU) |
| Cache L2 | 1024 KB | 512 KB |
Performance théorique
| Taux de pixel | 41.06 GPixel/s | 23.14 GPixel/s |
|---|---|---|
| Taux de texture | 102.6 GTexel/s | 92.54 GTexel/s |
| FP16 (half) performance | 6.569 TFLOPS (2:1) | 2.961 TFLOPS (1:1) |
| FP32 (float) performance | 3.284 TFLOPS | 2.961 TFLOPS |
| FP64 (double) performance | 205.3 GFLOPS (1:16) | 185.1 GFLOPS (1:16) |
Board Design
| Taille Slot | IGP | MXM Module |
|---|---|---|
| TDP | 100 W | 250 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | — | None |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (12_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 2.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.3 | 6.3 |
