AMD Radeon RX 6700M vs NVIDIA GeForce RTX 3060 Mobile
Grafikprozessor
| GPU Name | Navi 22 | GA106 |
|---|---|---|
| GPU Variante | Navi 22 | — |
| Architektur | RDNA 2.0 | Ampere |
| Hersteller | TSMC | Samsung |
| Prozessgröße | 7 nm | 8 nm |
| Transistoren | 17,200 million | 13,250 million |
| Chipgröße | 335 mm² | 276 mm² |
Mobile Grafik
| Veröffentlichungsdatum | Unknown | Jan 12th, 2021 |
|---|---|---|
| Generation | Mobility Radeon (Navi II) | GeForce 30 Mobile |
| Produktion | Active | Active |
| Businterface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| gpu.details.availability | — | Feb 2nd, 2021 |
| Vorgänger | — | GeForce 20 Mobile |
| Reviews | — | 1 in our database |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1489 MHz | 900 MHz |
|---|---|---|
| Boost-Takt | 2250 MHz | 1425 MHz |
| Speicher-Taktung | 2000 MHz 16 Gbps effective | 1750 MHz 14 Gbps effective |
Speicher
| Speichergröße | 10 GB | 6 GB |
|---|---|---|
| Speichertyp | GDDR6 | GDDR6 |
| Speicherbus | 160 bit | 192 bit |
| Bandbreite | 320.0 GB/s | 336.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 2304 | 3840 |
|---|---|---|
| TMUs | 144 | 120 |
| ROPs | 64 | 48 |
| Compute Units | 36 | — |
| RT-Kerne | 36 | 30 |
| gpu.details.l0-cache | 32 KB per WGP | — |
| Cache L1 | 128 KB per Array | 128 KB (per SM) |
| Cache L2 | 3 MB | 3 MB |
| gpu.details.l3-cache | 96 MB | — |
| Anzahl SM | — | 30 |
| Tensor Cores | — | 120 |
Theoretische Leistung
| Pixelrate | 144.0 GPixel/s | 68.40 GPixel/s |
|---|---|---|
| Texturrate | 324.0 GTexel/s | 171.0 GTexel/s |
| FP16 (half) Leistung | 20.74 TFLOPS (2:1) | 10.94 TFLOPS (1:1) |
| FP32 (float) Leistung | 10.37 TFLOPS | 10.94 TFLOPS |
| FP64 (double) Leistung | 648.0 GFLOPS (1:16) | 171.0 GFLOPS (1:64) |
Boarddesign
| Steckplatzbreite | IGP | — |
|---|---|---|
| TDP | 180 W | 80 W |
| Ausgabe | No outputs | No outputs |
| Stromverbindung | None | None |
Grafik-Features
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader-Modell | 6.5 | 6.6 |
| CUDA | — | 8.6 |
