AMD Radeon Vega Frontier Edition Watercooled vs NVIDIA GRID M40
Processeur graphique
| Nom du GPU | Vega 10 | GM107 |
|---|---|---|
| GPU variant | Vega 10 XTX LCS | — |
| Architecture | GCN 5.0 | Maxwell |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 28 nm |
| Transistors | 12,500 million | 1,870 million |
| Taille des matrices | 495 mm² | 148 mm² |
Carte graphique
| Date de publication | Jul 13th, 2017 | May 18th, 2016 |
|---|---|---|
| Génération | Radeon Pro | GRID |
| Production | Active | End-of-life |
| Prix de lancement | 1,489 USD | — |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Vitesse clock
| Base clock | 1382 MHz | — |
|---|---|---|
| Boost clock | 1600 MHz | — |
| Mémoire clock | 945 MHz 1890 Mbps effective | 1300 MHz 5.2 Gbps effective |
| GPU clock | — | 1033 MHz |
Mémoire
| Taille de la mémoire | 16 GB | 8 GB |
|---|---|---|
| Type de mémoire | HBM2 | GDDR5 |
| Bus mémoire | 2048 bit | 128 bit |
| Bande passante | 483.8 GB/s | 83.20 GB/s |
Render Config
| Shading units | 4096 | 384 |
|---|---|---|
| TMUs | 256 | 32 |
| ROPs | 64 | 16 |
| Compute units | 64 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
| Cache L2 | 4 MB | 2 MB |
| Comptage SMM | — | 3 |
Performance théorique
| Taux de pixel | 102.4 GPixel/s | 16.53 GPixel/s |
|---|---|---|
| Taux de texture | 409.6 GTexel/s | 33.06 GTexel/s |
| FP16 (half) performance | 26.21 TFLOPS (2:1) | — |
| FP32 (float) performance | 13.11 TFLOPS | 793.3 GFLOPS |
| FP64 (double) performance | 819.2 GFLOPS (1:16) | 24.79 GFLOPS (1:32) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 267 mm 10.5 inches | — |
| Taille | 111 mm 4.4 inches | — |
| TDP | 375 W | 50 W |
| Suggestions pour le PSU | 750 W | 250 W |
| Sorties | 1x HDMI3x DisplayPort | No outputs |
| Connecteurs de puissance | 2x 8-pin | — |
| Board number | D050-12 | — |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 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 |
