AMD Radeon Pro Vega 56 vs NVIDIA GeForce GTX 1650 Max-Q
Processeur graphique
| Nom du GPU | Vega 10 | TU117 |
|---|---|---|
| GPU variant | Vega 10 XL (215-0894216) | N18P-G61-MP2 |
| Architecture | GCN 5.0 | Turing |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 12 nm |
| Transistors | 12,500 million | 4,700 million |
| Taille des matrices | 495 mm² | 200 mm² |
Graphiques mobiles
| Date de publication | Aug 14th, 2017 | Apr 15th, 2020 |
|---|---|---|
| Génération | Radeon Pro Mac (Vega Series) | GeForce 16 Mobile |
| Production | Active | Active |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Critiques | — | 45 in our database |
| Prédécesseur | — | GeForce 10 Mobile |
| Successeur | — | GeForce 20 Mobile |
Vitesse clock
| Base clock | 1138 MHz | 930 MHz |
|---|---|---|
| Boost clock | 1250 MHz | 1125 MHz |
| Mémoire clock | 786 MHz 1572 Mbps effective | 1250 MHz 10 Gbps effective |
Mémoire
| Taille de la mémoire | 8 GB | 4 GB |
|---|---|---|
| Type de mémoire | HBM2 | GDDR6 |
| Bus mémoire | 2048 bit | 128 bit |
| Bande passante | 402.4 GB/s | 160.0 GB/s |
Render Config
| Shading units | 3584 | 1024 |
|---|---|---|
| TMUs | 224 | 64 |
| ROPs | 64 | 32 |
| Compute units | 56 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 4 MB | 1024 KB |
| Comptage SM | — | 16 |
Performance théorique
| Taux de pixel | 80.00 GPixel/s | 36.00 GPixel/s |
|---|---|---|
| Taux de texture | 280.0 GTexel/s | 72.00 GTexel/s |
| FP16 (half) performance | 17.92 TFLOPS (2:1) | 4.608 TFLOPS (2:1) |
| FP32 (float) performance | 8.960 TFLOPS | 2.304 TFLOPS |
| FP64 (double) performance | 560.0 GFLOPS (1:16) | 72.00 GFLOPS (1:32) |
Board Design
| Taille Slot | IGP | — |
|---|---|---|
| TDP | 210 W | 50 W |
| Sorties | 1x HDMI3x DisplayPort | No outputs |
| Connecteurs de puissance | None | None |
| Board number | — | E4904 SKU 11 |
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 | 6.6 |
| CUDA | — | 7.5 |
