AMD Radeon Pro Vega 56 vs NVIDIA GeForce RTX 3070 Ti Mobile
Grafikprozessor
| GPU Name | Vega 10 | GA104 |
|---|---|---|
| GPU Variante | Vega 10 XL (215-0894216) | — |
| Architektur | GCN 5.0 | Ampere |
| Hersteller | GlobalFoundries | Samsung |
| Prozessgröße | 14 nm | 8 nm |
| Transistoren | 12,500 million | 17,400 million |
| Chipgröße | 495 mm² | 392 mm² |
Mobile Grafik
| Veröffentlichungsdatum | Aug 14th, 2017 | Unknown |
|---|---|---|
| Generation | Radeon Pro Mac (Vega Series) | GeForce 30 Mobile |
| Produktion | Active | Unreleased |
| Businterface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Vorgänger | — | GeForce 20 Mobile |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1138 MHz | 915 MHz |
|---|---|---|
| Boost-Takt | 1250 MHz | 1410 MHz |
| Speicher-Taktung | 786 MHz 1572 Mbps effective | 1750 MHz 14 Gbps effective |
Speicher
| Speichergröße | 8 GB | 8 GB |
|---|---|---|
| Speichertyp | HBM2 | GDDR6 |
| Speicherbus | 2048 bit | 256 bit |
| Bandbreite | 402.4 GB/s | 448.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 3584 | 5632 |
|---|---|---|
| TMUs | 224 | 176 |
| ROPs | 64 | 80 |
| Compute Units | 56 | — |
| Cache L1 | 16 KB (per CU) | 128 KB (per SM) |
| Cache L2 | 4 MB | 4 MB |
| Anzahl SM | — | 44 |
| Tensor Cores | — | 176 |
| RT-Kerne | — | 44 |
Theoretische Leistung
| Pixelrate | 80.00 GPixel/s | 112.8 GPixel/s |
|---|---|---|
| Texturrate | 280.0 GTexel/s | 248.2 GTexel/s |
| FP16 (half) Leistung | 17.92 TFLOPS (2:1) | 15.88 TFLOPS (1:1) |
| FP32 (float) Leistung | 8.960 TFLOPS | 15.88 TFLOPS |
| FP64 (double) Leistung | 560.0 GFLOPS (1:16) | 248.2 GFLOPS (1:64) |
Boarddesign
| Steckplatzbreite | IGP | — |
|---|---|---|
| TDP | 210 W | 115 W |
| Ausgabe | 1x HDMI3x DisplayPort | No outputs |
| Stromverbindung | None | None |
Grafik-Features
| DirectX | 12 (12_1) | 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 |
