AMD Radeon R9 M390X vs AMD Radeon RX Vega M GL
Processeur graphique
| Nom du GPU | Amethyst | Polaris 22 |
|---|---|---|
| GPU variant | Amethyst XT | VegaM XL (D715A714) |
| Architecture | GCN 3.0 | GCN 4.0 |
| Fonderie | TSMC | GlobalFoundries |
| Taille du processus | 28 nm | 14 nm |
| Transistors | 5,000 million | 5,000 million |
| Taille des matrices | 366 mm² | 208 mm² |
Graphiques mobiles
| Date de publication | May 5th, 2015 | Feb 1st, 2018 |
|---|---|---|
| Génération | Crystal System (R9 M300) | Vega (Vega M) |
| Production | End-of-life | Active |
| Bus interface | PCIe 3.0 x16 | IGP |
| Prédécesseur | Solar System | — |
| Successeur | Mobility Radeon | — |
Vitesse clock
| GPU clock | 723 MHz | — |
|---|---|---|
| Mémoire clock | 1250 MHz 5 Gbps effective | 700 MHz 1400 Mbps effective |
| Base clock | — | 931 MHz |
| Boost clock | — | 1011 MHz |
Mémoire
| Taille de la mémoire | 4 GB | 4 GB |
|---|---|---|
| Type de mémoire | GDDR5 | HBM2 |
| Bus mémoire | 256 bit | 1024 bit |
| Bande passante | 160.0 GB/s | 179.2 GB/s |
Render Config
| Shading units | 2048 | 1280 |
|---|---|---|
| TMUs | 128 | 80 |
| ROPs | 32 | 32 |
| Compute units | 32 | 20 |
| Cache L1 | 16 KB (per CU) | 16 KB (per CU) |
| Cache L2 | 512 KB | 1024 KB |
Performance théorique
| Taux de pixel | 23.14 GPixel/s | 32.35 GPixel/s |
|---|---|---|
| Taux de texture | 92.54 GTexel/s | 80.88 GTexel/s |
| FP16 (half) performance | 2.961 TFLOPS (1:1) | 2.588 TFLOPS (1:1) |
| FP32 (float) performance | 2.961 TFLOPS | 2.588 TFLOPS |
| FP64 (double) performance | 185.1 GFLOPS (1:16) | 161.8 GFLOPS (1:16) |
Board Design
| Taille Slot | MXM Module | IGP |
|---|---|---|
| TDP | 75 W | 65 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | None | — |
| Board number | C608 | D136 |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (12_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 2.1 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.3 | 6.4 |
