AMD Radeon Pro Vega 48 vs NVIDIA GeForce GTX 1660 Mobile
Processeur graphique
| Nom du GPU | Vega 10 | TU116B |
|---|---|---|
| GPU variant | Vega 10 PRO | — |
| Architecture | GCN 5.0 | Turing |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 12 nm |
| Transistors | 12,500 million | 6,600 million |
| Taille des matrices | 495 mm² | 284 mm² |
Graphiques mobiles
| Date de publication | Mar 19th, 2019 | May 15th, 2019 |
|---|---|---|
| Génération | Radeon Pro Mac (Vega Series) | GeForce 16 Mobile |
| Production | Active | Active |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Vitesse clock
| GPU clock | 1200 MHz | — |
|---|---|---|
| Mémoire clock | 786 MHz 1572 Mbps effective | 2000 MHz 16000 MHz effective |
| Base clock | — | 1455 MHz |
| Boost clock | — | 1590 MHz |
Mémoire
| Taille de la mémoire | 8 GB | 6 GB |
|---|---|---|
| Type de mémoire | HBM2 | GDDR6 |
| Bus mémoire | 2048 bit | 192 bit |
| Bande passante | 402.4 GB/s | 384.0 GB/s |
Render Config
| Shading units | 3072 | 1280 |
|---|---|---|
| TMUs | 192 | 80 |
| ROPs | 64 | 48 |
| Compute units | 48 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 4 MB | 1536 KB |
| Comptage SM | — | 20 |
Performance théorique
| Taux de pixel | 76.80 GPixel/s | 76.32 GPixel/s |
|---|---|---|
| Taux de texture | 230.4 GTexel/s | 127.2 GTexel/s |
| FP16 (half) performance | 14.75 TFLOPS (2:1) | 8.141 TFLOPS (2:1) |
| FP32 (float) performance | 7.373 TFLOPS | 4.070 TFLOPS |
| FP64 (double) performance | 460.8 GFLOPS (1:16) | 127.2 GFLOPS (1:32) |
Board Design
| Taille Slot | IGP | — |
|---|---|---|
| TDP | unknown | unknown |
| Sorties | No outputs | 1x DVI1x HDMI3x DisplayPort |
| Connecteurs de puissance | None | None |
| Longueur | — | 229 mm 9 inches |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 1.2 |
| Vulkan | 1.2 | 1.2.140 |
| Shader model | 6.4 | 6.5 |
| CUDA | — | 7.5 |
