AMD Radeon RX 470 Mobile vs NVIDIA GeForce RTX 3060 Max-Q
Processeur graphique
| Nom du GPU | Ellesmere | GA106 |
|---|---|---|
| GPU variant | Ellesmere PRO | — |
| Architecture | GCN 4.0 | Ampere |
| Fonderie | GlobalFoundries | Samsung |
| Taille du processus | 14 nm | 8 nm |
| Transistors | 5,700 million | 13,250 million |
| Taille des matrices | 232 mm² | 276 mm² |
Graphiques mobiles
| Date de publication | Aug 4th, 2016 | Jan 12th, 2021 |
|---|---|---|
| Génération | Mobility Radeon (RX M400) | GeForce 30 Mobile |
| Production | Active | Active |
| Bus interface | MXM-B (3.0) | PCIe 4.0 x16 |
| Prédécesseur | Crystal System | GeForce 20 Mobile |
| gpu.details.availability | — | Feb 2nd, 2021 |
| Critiques | — | 1 in our database |
Vitesse clock
| Base clock | 926 MHz | 817 MHz |
|---|---|---|
| Boost clock | 1074 MHz | 1282 MHz |
| Mémoire clock | 1750 MHz 7 Gbps effective | 1500 MHz 12 Gbps effective |
Mémoire
| Taille de la mémoire | 8 GB | 6 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR6 |
| Bus mémoire | 256 bit | 192 bit |
| Bande passante | 224.0 GB/s | 288.0 GB/s |
Render Config
| Shading units | 2048 | 3840 |
|---|---|---|
| TMUs | 128 | 120 |
| ROPs | 32 | 48 |
| Compute units | 32 | — |
| Cache L1 | 16 KB (per CU) | 128 KB (per SM) |
| Cache L2 | 2 MB | 3 MB |
| Comptage SM | — | 30 |
| Tensor cores | — | 120 |
| RT cores | — | 30 |
Performance théorique
| Taux de pixel | 34.37 GPixel/s | 61.54 GPixel/s |
|---|---|---|
| Taux de texture | 137.5 GTexel/s | 153.8 GTexel/s |
| FP16 (half) performance | 4.399 TFLOPS (1:1) | 9.846 TFLOPS (1:1) |
| FP32 (float) performance | 4.399 TFLOPS | 9.846 TFLOPS |
| FP64 (double) performance | 274.9 GFLOPS (1:16) | 153.8 GFLOPS (1:64) |
Board Design
| Taille Slot | MXM Module | — |
|---|---|---|
| TDP | 85 W | 60 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | None | None |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.4 | 6.6 |
| CUDA | — | 8.6 |
