GPU Name | GA107S | TU104 |
---|---|---|
Architektur | Ampere | Turing |
Hersteller | Samsung | TSMC |
Prozessgröße | 8 nm | 12 nm |
Transistoren | unknown | 13,600 million |
Chipgröße | unknown | 545 mm² |
GPU Variante | — | N19E-Q5-A1 |
Veröffentlichungsdatum | 2022 | May 27th, 2019 |
---|---|---|
Generation | GeForce 20 Mobile | Quadro Mobile (Tx000) |
Vorgänger | GeForce 10 Mobile | — |
Nachfolger | GeForce 30 Mobile | — |
Produktion | Unreleased | Active |
Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Basis-Taktfrequenz | 1155 MHz | 1365 MHz |
---|---|---|
Boost-Takt | 1477 MHz | 1770 MHz |
Speicher-Taktung | 1750 MHz 14 Gbps effective | 1750 MHz 14 Gbps effective |
Speichergröße | 4 GB | 16 GB |
---|---|---|
Speichertyp | GDDR6 | GDDR6 |
Speicherbus | 64 bit | 256 bit |
Bandbreite | 112.0 GB/s | 448.0 GB/s |
Shading-Einheiten | 2048 | 3072 |
---|---|---|
TMUs | 128 | 192 |
ROPs | 48 | 64 |
Anzahl SM | 32 | 48 |
Tensor Cores | 256 | 384 |
RT-Kerne | 32 | 48 |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 2 MB | 4 MB |
Pixelrate | 70.90 GPixel/s | 113.3 GPixel/s |
---|---|---|
Texturrate | 189.1 GTexel/s | 339.8 GTexel/s |
FP16 (half) Leistung | 12.10 TFLOPS (2:1) | 21.75 TFLOPS (2:1) |
FP32 (float) Leistung | 6.050 TFLOPS | 10.87 TFLOPS |
FP64 (double) Leistung | 189.1 GFLOPS (1:32) | 339.8 GFLOPS (1:32) |
Steckplatzbreite | Dual-slot | IGP |
---|---|---|
Länge | 229 mm 9 inches | — |
Breite | 113 mm 4.4 inches | — |
Höhe | 35 mm 1.4 inches | — |
TDP | 45 W | 110 W |
Ausgabe | 1x DVI1x HDMI2x DisplayPort | No outputs |
Stromverbindung | 1x 6-pin | None |
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 |