NVIDIA Quadro GP100 vs NVIDIA Quadro P6000
Grafikprozessor
| GPU Name | GP100 | GP102 |
|---|---|---|
| Architektur | Pascal | Pascal |
| Hersteller | TSMC | TSMC |
| Prozessgröße | 16 nm | 16 nm |
| Transistoren | 15,300 million | 11,800 million |
| Chipgröße | 610 mm² | 471 mm² |
| GPU Variante | — | GP102-875-A1 |
Grafikkarte
| Veröffentlichungsdatum | Oct 1st, 2016 | Oct 1st, 2016 |
|---|---|---|
| Generation | Quadro | Quadro |
| Produktion | End-of-life | End-of-life |
| Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Originalpreis | — | 5,999 USD |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1304 MHz | 1506 MHz |
|---|---|---|
| Boost-Takt | 1442 MHz | 1645 MHz |
| Speicher-Taktung | 715 MHz 1430 Mbps effective | 1127 MHz 9 Gbps effective |
Speicher
| Speichergröße | 16 GB | 24 GB |
|---|---|---|
| Speichertyp | HBM2 | GDDR5X |
| Speicherbus | 4096 bit | 384 bit |
| Bandbreite | 732.2 GB/s | 432.8 GB/s |
Render-Konfiguration
| Shading-Einheiten | 3584 | 3840 |
|---|---|---|
| TMUs | 224 | 240 |
| ROPs | 96 | 96 |
| Anzahl SM | 56 | 30 |
| Cache L1 | 24 KB (per SM) | 48 KB (per SM) |
| Cache L2 | 4 MB | 3 MB |
Theoretische Leistung
| Pixelrate | 138.4 GPixel/s | 157.9 GPixel/s |
|---|---|---|
| Texturrate | 323.0 GTexel/s | 394.8 GTexel/s |
| FP16 (half) Leistung | 20.67 TFLOPS (2:1) | 197.4 GFLOPS (1:64) |
| FP32 (float) Leistung | 10.34 TFLOPS | 12.63 TFLOPS |
| FP64 (double) Leistung | 5.168 TFLOPS (1:2) | 394.8 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | Dual-slot | Dual-slot |
|---|---|---|
| Länge | 267 mm 10.5 inches | 267 mm 10.5 inches |
| Breite | 111 mm 4.4 inches | 111 mm 4.4 inches |
| TDP | 235 W | 250 W |
| Vorgeschlagenes Netzteil | 550 W | 600 W |
| Ausgabe | 1x DVI4x DisplayPort | 1x DVI4x DisplayPort |
| Stromverbindung | 1x 8-pin | 1x 6-pin + 1x 8-pin |
| Board-Nummer | — | PG611 SKU 500 |
Grafik-Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 6.0 | 6.1 |
| Shader-Modell | 6.4 | 6.4 |
