AMD Radeon Pro 580 vs NVIDIA GeForce RTX 3080 Max-Q
Grafikprozessor
| GPU Name | Ellesmere | GA104 |
|---|---|---|
| GPU Variante | Ellesmere XTA (216-0886220) | GA104-775-A1 |
| Architektur | GCN 4.0 | Ampere |
| Hersteller | GlobalFoundries | Samsung |
| Prozessgröße | 14 nm | 8 nm |
| Transistoren | 5,700 million | 17,400 million |
| Chipgröße | 232 mm² | 392 mm² |
Mobile Grafik
| Veröffentlichungsdatum | Jun 5th, 2017 | Jan 12th, 2021 |
|---|---|---|
| Generation | Radeon Pro Mac (500 Series) | GeForce 30 Mobile |
| Produktion | Active | Active |
| Businterface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| gpu.details.availability | — | Feb 2nd, 2021 |
| Vorgänger | — | GeForce 20 Mobile |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1100 MHz | 780 MHz |
|---|---|---|
| Boost-Takt | 1200 MHz | 1245 MHz |
| Speicher-Taktung | 1695 MHz 6.8 Gbps effective | 1500 MHz 12 Gbps effective |
Speicher
| Speichergröße | 8 GB | 8 GB |
|---|---|---|
| Speichertyp | GDDR5 | GDDR6 |
| Speicherbus | 256 bit | 256 bit |
| Bandbreite | 217.0 GB/s | 384.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 2304 | 6144 |
|---|---|---|
| TMUs | 144 | 192 |
| ROPs | 32 | 96 |
| Compute Units | 36 | — |
| Cache L1 | 16 KB (per CU) | 128 KB (per SM) |
| Cache L2 | 2 MB | 4 MB |
| Anzahl SM | — | 48 |
| Tensor Cores | — | 192 |
| RT-Kerne | — | 48 |
Theoretische Leistung
| Pixelrate | 38.40 GPixel/s | 119.5 GPixel/s |
|---|---|---|
| Texturrate | 172.8 GTexel/s | 239.0 GTexel/s |
| FP16 (half) Leistung | 5.530 TFLOPS (1:1) | 15.30 TFLOPS (1:1) |
| FP32 (float) Leistung | 5.530 TFLOPS | 15.30 TFLOPS |
| FP64 (double) Leistung | 345.6 GFLOPS (1:16) | 239.0 GFLOPS (1:64) |
Boarddesign
| Steckplatzbreite | IGP | — |
|---|---|---|
| TDP | 185 W | 80 W |
| Ausgabe | No outputs | No outputs |
| Stromverbindung | None | None |
Grafik-Features
| DirectX | 12 (12_0) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader-Modell | 6.4 | 6.6 |
| CUDA | — | 8.6 |
