NVIDIA GeForce GT 635M vs NVIDIA GeForce RTX 3060 Mobile
Grafikprozessor
| GPU Name | GF108 | GA106 |
|---|---|---|
| Architektur | Fermi | Ampere |
| Hersteller | TSMC | Samsung |
| Prozessgröße | 40 nm | 8 nm |
| Transistoren | 585 million | 13,250 million |
| Chipgröße | 116 mm² | 276 mm² |
Mobile Grafik
| Veröffentlichungsdatum | Mar 22nd, 2012 | Jan 12th, 2021 |
|---|---|---|
| Generation | GeForce 600M | GeForce 30 Mobile |
| Produktion | End-of-life | Active |
| Businterface | MXM-A (3.0) | PCIe 4.0 x16 |
| Vorgänger | GeForce 500M | GeForce 20 Mobile |
| Nachfolger | GeForce 700M | — |
| gpu.details.availability | — | Feb 2nd, 2021 |
| Reviews | — | 1 in our database |
Takt-Geschwindigkeiten
| GPU-Taktung | 660 MHz | — |
|---|---|---|
| Shader-Taktung | 1320 MHz | — |
| Speicher-Taktung | 900 MHz 1800 Mbps effective | 1750 MHz 14 Gbps effective |
| Basis-Taktfrequenz | — | 900 MHz |
| Boost-Takt | — | 1425 MHz |
Speicher
| Speichergröße | 1024 MB | 6 GB |
|---|---|---|
| Speichertyp | DDR3 | GDDR6 |
| Speicherbus | 64 bit | 192 bit |
| Bandbreite | 14.40 GB/s | 336.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 96 | 3840 |
|---|---|---|
| TMUs | 16 | 120 |
| ROPs | 4 | 48 |
| Anzahl SM | 2 | 30 |
| Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 128 KB | 3 MB |
| Tensor Cores | — | 120 |
| RT-Kerne | — | 30 |
Theoretische Leistung
| Pixelrate | 2.640 GPixel/s | 68.40 GPixel/s |
|---|---|---|
| Texturrate | 10.56 GTexel/s | 171.0 GTexel/s |
| FP32 (float) Leistung | 253.4 GFLOPS | 10.94 TFLOPS |
| FP64 (double) Leistung | 21.12 GFLOPS (1:12) | 171.0 GFLOPS (1:64) |
| FP16 (half) Leistung | — | 10.94 TFLOPS (1:1) |
Boarddesign
| Steckplatzbreite | MXM Module | — |
|---|---|---|
| TDP | 33 W | 80 W |
| Ausgabe | No outputs | No outputs |
| Stromverbindung | — | None |
Grafik-Features
| DirectX | 12 (11_0) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.1 | 3.0 |
| Vulkan | — | 1.2 |
| CUDA | 2.1 | 8.6 |
| Shader-Modell | 5.1 | 6.6 |
