GPU Name | GA107 | GA102 |
---|---|---|
Architektur | Ampere | Ampere |
Hersteller | Samsung | Samsung |
Prozessgröße | 8 nm | 8 nm |
Transistoren | unknown | 28,300 million |
Chipgröße | unknown | 628 mm² |
GPU Variante | — | GA102-350-A1 |
Veröffentlichungsdatum | Nov 10th, 2021 | Unknown |
---|---|---|
Generation | Quadro | GeForce 30 |
Produktion | Active | Unreleased |
Businterface | PCIe 4.0 x8 | PCIe 4.0 x16 |
gpu.details.availability | — | 2022 |
Vorgänger | — | GeForce 20 |
Originalpreis | — | 1,699 USD |
Reviews | — | 55 in our database |
Basis-Taktfrequenz | 1440 MHz | 1560 MHz |
---|---|---|
Boost-Takt | 1770 MHz | 1860 MHz |
Speicher-Taktung | 1563 MHz 12.5 Gbps effective | 1325 MHz 21.2 Gbps effective |
Speichergröße | 16 GB | 24 GB |
---|---|---|
Speichertyp | GDDR6 | GDDR6X |
Speicherbus | 128 bit | 384 bit |
Bandbreite | 200.1 GB/s | 1,018 GB/s |
Shading-Einheiten | 1280 | 10752 |
---|---|---|
TMUs | 40 | 336 |
ROPs | 32 | 112 |
Anzahl SM | 10 | 84 |
Tensor Cores | 40 | 336 |
RT-Kerne | 10 | 84 |
Cache L1 | 128 KB (per SM) | 128 KB (per SM) |
Cache L2 | 2 MB | 6 MB |
Pixelrate | 56.64 GPixel/s | 208.3 GPixel/s |
---|---|---|
Texturrate | 70.80 GTexel/s | 625.0 GTexel/s |
FP16 (half) Leistung | 4.531 TFLOPS (1:1) | 40.00 TFLOPS (1:1) |
FP32 (float) Leistung | 4.531 TFLOPS | 40.00 TFLOPS |
FP64 (double) Leistung | 70.80 GFLOPS (1:64) | 625.0 GFLOPS (1:64) |
Steckplatzbreite | Single-slot | Triple-slot |
---|---|---|
TDP | 60 W | 450 W |
Vorgeschlagenes Netzteil | 250 W | 850 W |
Ausgabe | No outputs | 1x HDMI3x DisplayPort |
Stromverbindung | None | 1x 12-pin |
Board-Nummer | PG179 SKU 220 | PG132 SKU |
Länge | — | 336 mm 13.2 inches |
Breite | — | 140 mm 5.5 inches |
Höhe | — | 61 mm 2.4 inches |
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 | 8.6 |
Shader-Modell | 6.6 | 6.6 |