NVIDIA A40 PCIe vs NVIDIA Quadro RTX 6000
Grafikprozessor
| GPU Name | GA102 | TU102 |
|---|---|---|
| Architektur | Ampere | Turing |
| Hersteller | Samsung | TSMC |
| Prozessgröße | 8 nm | 12 nm |
| Transistoren | 28,300 million | 18,600 million |
| Chipgröße | 628 mm² | 754 mm² |
| GPU Variante | — | TU102-875-A1 |
Grafikkarte
| Veröffentlichungsdatum | Oct 5th, 2020 | Aug 13th, 2018 |
|---|---|---|
| gpu.details.availability | 2021 | — |
| Generation | Tesla | Quadro |
| Produktion | Active | Active |
| Businterface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| Originalpreis | — | 6,299 USD |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1305 MHz | 1440 MHz |
|---|---|---|
| Boost-Takt | 1740 MHz | 1770 MHz |
| Speicher-Taktung | 1812 MHz 14.5 Gbps effective | 1750 MHz 14 Gbps effective |
Speicher
| Speichergröße | 48 GB | 24 GB |
|---|---|---|
| Speichertyp | GDDR6 | GDDR6 |
| Speicherbus | 384 bit | 384 bit |
| Bandbreite | 695.8 GB/s | 672.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 10752 | 4608 |
|---|---|---|
| TMUs | 336 | 288 |
| ROPs | 112 | 96 |
| Anzahl SM | 84 | 72 |
| Tensor Cores | 336 | 576 |
| RT-Kerne | 84 | 72 |
| Cache L1 | 128 KB (per SM) | 64 KB (per SM) |
| Cache L2 | 6 MB | 6 MB |
Theoretische Leistung
| Pixelrate | 194.9 GPixel/s | 169.9 GPixel/s |
|---|---|---|
| Texturrate | 584.6 GTexel/s | 509.8 GTexel/s |
| FP16 (half) Leistung | 37.42 TFLOPS (1:1) | 32.62 TFLOPS (2:1) |
| FP32 (float) Leistung | 37.42 TFLOPS | 16.31 TFLOPS |
| FP64 (double) Leistung | 1,169 GFLOPS (1:32) | 509.8 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | Dual-slot | Dual-slot |
|---|---|---|
| Länge | 267 mm 10.5 inches | 267 mm 10.5 inches |
| Breite | 112 mm 4.4 inches | 111 mm 4.4 inches |
| TDP | 300 W | 260 W |
| Vorgeschlagenes Netzteil | 700 W | 600 W |
| Ausgabe | 3x DisplayPort | 4x DisplayPort1x USB Type-C |
| Stromverbindung | 8-pin EPS | 1x 6-pin + 1x 8-pin |
| Board-Nummer | — | PG150 SKU 510 |
Grafik-Features
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 8.6 | 7.5 |
| Shader-Modell | 6.6 | 6.6 |
