AMD Radeon RX Vega M GL vs NVIDIA GRID M40
Processeur graphique
| Nom du GPU | Polaris 22 | GM107 |
|---|---|---|
| GPU variant | VegaM XL (D715A714) | — |
| Architecture | GCN 4.0 | Maxwell |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 28 nm |
| Transistors | 5,000 million | 1,870 million |
| Taille des matrices | 208 mm² | 148 mm² |
Graphiques mobiles
| Date de publication | Feb 1st, 2018 | — |
|---|---|---|
| Génération | Vega (Vega M) | — |
| Production | Active | — |
| Bus interface | IGP | — |
Vitesse clock
| Base clock | 931 MHz | — |
|---|---|---|
| Boost clock | 1011 MHz | — |
| Mémoire clock | 700 MHz 1400 Mbps effective | 1300 MHz 5.2 Gbps effective |
| GPU clock | — | 1033 MHz |
Mémoire
| Taille de la mémoire | 4 GB | 8 GB |
|---|---|---|
| Type de mémoire | HBM2 | GDDR5 |
| Bus mémoire | 1024 bit | 128 bit |
| Bande passante | 179.2 GB/s | 83.20 GB/s |
Render Config
| Shading units | 1280 | 384 |
|---|---|---|
| TMUs | 80 | 32 |
| ROPs | 32 | 16 |
| Compute units | 20 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
| Cache L2 | 1024 KB | 2 MB |
| Comptage SMM | — | 3 |
Performance théorique
| Taux de pixel | 32.35 GPixel/s | 16.53 GPixel/s |
|---|---|---|
| Taux de texture | 80.88 GTexel/s | 33.06 GTexel/s |
| FP16 (half) performance | 2.588 TFLOPS (1:1) | — |
| FP32 (float) performance | 2.588 TFLOPS | 793.3 GFLOPS |
| FP64 (double) performance | 161.8 GFLOPS (1:16) | 24.79 GFLOPS (1:32) |
Board Design
| Taille Slot | IGP | Dual-slot |
|---|---|---|
| TDP | 65 W | 50 W |
| Sorties | No outputs | No outputs |
| Board number | D136 | — |
| Suggestions pour le PSU | — | 250 W |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.4 | 5.1 |
| CUDA | — | 5.0 |
AUTRES CARACTÉRISTIQUES
Carte graphique
| Date de publication | — | May 18th, 2016 |
|---|---|---|
| Génération | — | GRID |
| Production | — | End-of-life |
| Bus interface | — | PCIe 3.0 x16 |
