NVIDIA Quadro P1000 vs NVIDIA RTX A4000
Grafikprozessor
| GPU Name | GP107 | GA104 |
|---|---|---|
| GPU Variante | GP107-860-A1 | GA104-875-A1 |
| Architektur | Pascal | Ampere |
| Hersteller | Samsung | Samsung |
| Prozessgröße | 14 nm | 8 nm |
| Transistoren | 3,300 million | 17,400 million |
| Chipgröße | 132 mm² | 392 mm² |
Grafikkarte
| Veröffentlichungsdatum | Feb 7th, 2017 | Apr 12th, 2021 |
|---|---|---|
| Generation | Quadro | Quadro |
| Produktion | End-of-life | Active |
| Businterface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1354 MHz | 735 MHz |
|---|---|---|
| Boost-Takt | 1392 MHz | 1560 MHz |
| Speicher-Taktung | 1502 MHz 6 Gbps effective | 1750 MHz 14 Gbps effective |
Speicher
| Speichergröße | 4 GB | 16 GB |
|---|---|---|
| Speichertyp | GDDR5 | GDDR6 |
| Speicherbus | 128 bit | 256 bit |
| Bandbreite | 96.13 GB/s | 448.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 512 | 6144 |
|---|---|---|
| TMUs | 32 | 192 |
| ROPs | 16 | 96 |
| Anzahl SM | 4 | 48 |
| Cache L1 | 48 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 1024 KB | 4 MB |
| Tensor Cores | — | 192 |
| RT-Kerne | — | 48 |
Theoretische Leistung
| Pixelrate | 22.27 GPixel/s | 149.8 GPixel/s |
|---|---|---|
| Texturrate | 44.54 GTexel/s | 299.5 GTexel/s |
| FP16 (half) Leistung | 22.27 GFLOPS (1:64) | 19.17 TFLOPS (1:1) |
| FP32 (float) Leistung | 1,425 GFLOPS | 19.17 TFLOPS |
| FP64 (double) Leistung | 44.54 GFLOPS (1:32) | 599.0 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | Single-slot | Single-slot |
|---|---|---|
| Länge | 150 mm 5.9 inches | 241 mm 9.5 inches |
| Breite | 69 mm 2.7 inches | 112 mm 4.4 inches |
| TDP | 47 W | 140 W |
| Vorgeschlagenes Netzteil | 200 W | 300 W |
| Ausgabe | 4x mini-DisplayPort | 4x DisplayPort |
| Stromverbindung | None | 1x 6-pin |
| Board-Nummer | PG212 SKU 502 | — |
Grafik-Features
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 6.1 | 8.6 |
| Shader-Modell | 6.4 | 6.6 |
