AMD Radeon Pro Vega 48 vs NVIDIA GeForce GTX 1060 Max-Q
Processeur graphique
| Nom du GPU | Vega 10 | GP106 |
|---|---|---|
| GPU variant | Vega 10 PRO | N17E-G1-A1 |
| Architecture | GCN 5.0 | Pascal |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 16 nm |
| Transistors | 12,500 million | 4,400 million |
| Taille des matrices | 495 mm² | 200 mm² |
Graphiques mobiles
| Date de publication | Mar 19th, 2019 | Jun 27th, 2017 |
|---|---|---|
| Génération | Radeon Pro Mac (Vega Series) | GeForce 10 Mobile |
| Production | Active | End-of-life |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Critiques | — | 117 in our database |
| Prédécesseur | — | GeForce 900M |
| Successeur | — | GeForce 20 Mobile |
Vitesse clock
| GPU clock | 1200 MHz | — |
|---|---|---|
| Mémoire clock | 786 MHz 1572 Mbps effective | 2002 MHz 8 Gbps effective |
| Base clock | — | 1063 MHz |
| Boost clock | — | 1480 MHz |
Mémoire
| Taille de la mémoire | 8 GB | 6 GB |
|---|---|---|
| Type de mémoire | HBM2 | GDDR5 |
| Bus mémoire | 2048 bit | 192 bit |
| Bande passante | 402.4 GB/s | 192.2 GB/s |
Render Config
| Shading units | 3072 | 1280 |
|---|---|---|
| TMUs | 192 | 80 |
| ROPs | 64 | 48 |
| Compute units | 48 | — |
| Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
| Cache L2 | 4 MB | 1536 KB |
| Comptage SM | — | 10 |
Performance théorique
| Taux de pixel | 76.80 GPixel/s | 71.04 GPixel/s |
|---|---|---|
| Taux de texture | 230.4 GTexel/s | 118.4 GTexel/s |
| FP16 (half) performance | 14.75 TFLOPS (2:1) | 59.20 GFLOPS (1:64) |
| FP32 (float) performance | 7.373 TFLOPS | 3.789 TFLOPS |
| FP64 (double) performance | 460.8 GFLOPS (1:16) | 118.4 GFLOPS (1:32) |
Board Design
| Taille Slot | IGP | MXM Module |
|---|---|---|
| TDP | unknown | 80 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | None | None |
| Board number | — | E2914 SKU 30 |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.4 | 6.4 |
| CUDA | — | 6.1 |
