GPU Name | TU104 | GA106 |
---|---|---|
GPU Variante | N19E-Q5-A1 | — |
Architektur | Turing | Ampere |
Hersteller | TSMC | Samsung |
Prozessgröße | 12 nm | 8 nm |
Transistoren | 13,600 million | 13,250 million |
Chipgröße | 545 mm² | 276 mm² |
Veröffentlichungsdatum | May 27th, 2019 | Unknown |
---|---|---|
Generation | Quadro Mobile (Tx000) | Quadro Mobile (Ax000) |
Produktion | Active | Active |
Businterface | PCIe 3.0 x16 | PCIe 4.0 x16 |
gpu.details.availability | — | 2021 |
Basis-Taktfrequenz | 1365 MHz | 562 MHz |
---|---|---|
Boost-Takt | 1770 MHz | 1200 MHz |
Speicher-Taktung | 1750 MHz 14 Gbps effective | 1500 MHz 12 Gbps effective |
Speichergröße | 16 GB | 6 GB |
---|---|---|
Speichertyp | GDDR6 | GDDR6 |
Speicherbus | 256 bit | 192 bit |
Bandbreite | 448.0 GB/s | 288.0 GB/s |
Shading-Einheiten | 3072 | 3328 |
---|---|---|
TMUs | 192 | 104 |
ROPs | 64 | 48 |
Anzahl SM | 48 | 26 |
Tensor Cores | 384 | 104 |
RT-Kerne | 48 | 26 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 4 MB | 3 MB |
Pixelrate | 113.3 GPixel/s | 57.60 GPixel/s |
---|---|---|
Texturrate | 339.8 GTexel/s | 124.8 GTexel/s |
FP16 (half) Leistung | 21.75 TFLOPS (2:1) | 7.987 TFLOPS (1:1) |
FP32 (float) Leistung | 10.87 TFLOPS | 7.987 TFLOPS |
FP64 (double) Leistung | 339.8 GFLOPS (1:32) | 124.8 GFLOPS (1:64) |
Steckplatzbreite | IGP | Dual-slot |
---|---|---|
TDP | 110 W | 70 W |
Ausgabe | No outputs | 4x mini-DisplayPort |
Stromverbindung | None | None |
Länge | — | 167 mm 6.6 inches |
Breite | — | 69 mm 2.7 inches |
Vorgeschlagenes Netzteil | — | 250 W |
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 | 7.5 | 8.6 |
Shader-Modell | 6.6 | 6.6 |
Veröffentlichungsdatum | — | Aug 10th, 2021 |
---|---|---|
gpu.details.availability | — | Oct, 2021 |
Generation | — | Quadro |
Produktion | — | Active |
Originalpreis | — | 449 USD |
Businterface | — | PCIe 4.0 x16 |