GPU Name | GP104 | TU104 |
---|---|---|
Architektur | Pascal | Turing |
Hersteller | TSMC | TSMC |
Prozessgröße | 16 nm | 12 nm |
Transistoren | 7,200 million | 13,600 million |
Chipgröße | 314 mm² | 545 mm² |
Veröffentlichungsdatum | Feb 21st, 2018 | May 27th, 2019 |
---|---|---|
Generation | Quadro Mobile (Px200) | Quadro Mobile (Tx000) |
Produktion | End-of-life | Active |
Businterface | MXM-B (3.0) | PCIe 3.0 x16 |
Basis-Taktfrequenz | 1227 MHz | 780 MHz |
---|---|---|
Boost-Takt | 1647 MHz | 1380 MHz |
Speicher-Taktung | 1502 MHz 6 Gbps effective | 1625 MHz 13 Gbps effective |
Speichergröße | 8 GB | 8 GB |
---|---|---|
Speichertyp | GDDR5 | GDDR6 |
Speicherbus | 256 bit | 256 bit |
Bandbreite | 192.3 GB/s | 416.0 GB/s |
Shading-Einheiten | 2304 | 2560 |
---|---|---|
TMUs | 144 | 160 |
ROPs | 64 | 64 |
Anzahl SM | 18 | 40 |
Cache L1 | 48 KB (per SM) | 64 KB (per SM) |
Cache L2 | 2 MB | 4 MB |
Tensor Cores | — | 320 |
RT-Kerne | — | 40 |
Pixelrate | 105.4 GPixel/s | 88.32 GPixel/s |
---|---|---|
Texturrate | 237.2 GTexel/s | 220.8 GTexel/s |
FP16 (half) Leistung | 118.6 GFLOPS (1:64) | 14.13 TFLOPS (2:1) |
FP32 (float) Leistung | 7.589 TFLOPS | 7.066 TFLOPS |
FP64 (double) Leistung | 237.2 GFLOPS (1:32) | 220.8 GFLOPS (1:32) |
Steckplatzbreite | MXM Module | IGP |
---|---|---|
TDP | 100 W | 80 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | None | None |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 6.1 | 7.5 |
Shader-Modell | 6.4 | 6.6 |