NVIDIA GeForce RTX 3080 Ti vs NVIDIA RTX A4000
Grafikprozessor
| GPU Name | GA102 | GA104 |
|---|---|---|
| GPU Variante | GA102-300-A1 | GA104-875-A1 |
| Architektur | Ampere | Ampere |
| Hersteller | TSMC | Samsung |
| Prozessgröße | 7 nm | 8 nm |
| Transistoren | 40,000 million | 17,400 million |
| Chipgröße | 627 mm² | 392 mm² |
Grafikkarte
| Veröffentlichungsdatum | 2020 | Apr 12th, 2021 |
|---|---|---|
| Generation | GeForce 30 | Quadro |
| Produktion | Unreleased | Active |
| Originalpreis | 1,399 USD | — |
| Businterface | PCIe 4.0 x16 | PCIe 4.0 x16 |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1410 MHz | 735 MHz |
|---|---|---|
| Boost-Takt | 1740 MHz | 1560 MHz |
| Speicher-Taktung | 2375 MHz 19000 MHz effective | 1750 MHz 14 Gbps effective |
Speicher
| Speichergröße | 12 GB | 16 GB |
|---|---|---|
| Speichertyp | GDDR6X | GDDR6 |
| Speicherbus | 384 bit | 256 bit |
| Bandbreite | 912.0 GB/s | 448.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 5120 | 6144 |
|---|---|---|
| TMUs | 320 | 192 |
| ROPs | 96 | 96 |
| Anzahl SM | 80 | 48 |
| Tensor Cores | 640 | 192 |
| RT-Kerne | 160 | 48 |
| Cache L1 | 192 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 6 MB | 4 MB |
Theoretische Leistung
| Pixelrate | 167.0 GPixel/s | 149.8 GPixel/s |
|---|---|---|
| Texturrate | 556.8 GTexel/s | 299.5 GTexel/s |
| FP16 (half) Leistung | 35.64 TFLOPS (2:1) | 19.17 TFLOPS (1:1) |
| FP32 (float) Leistung | 17.82 TFLOPS | 19.17 TFLOPS |
| FP64 (double) Leistung | 556.8 GFLOPS (1:32) | 599.0 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | Dual-slot | Single-slot |
|---|---|---|
| Länge | 267 mm 10.5 inches | 241 mm 9.5 inches |
| TDP | 320 W | 140 W |
| Vorgeschlagenes Netzteil | 700 W | 300 W |
| Ausgabe | 1x HDMI3x DisplayPort1x USB Type-C | 4x DisplayPort |
| Stromverbindung | 1x 12-pin | 1x 6-pin |
| Board-Nummer | PG132 SKU 20 | — |
| Breite | — | 112 mm 4.4 inches |
Grafik-Features
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2.140 | 1.2 |
| CUDA | 8.5 | 8.6 |
| Shader-Modell | 6.5 | 6.6 |
