GPU Name | GP104 | GA107 |
---|---|---|
GPU Variante | N17E-Q5-A1 | — |
Architektur | Pascal | Ampere |
Hersteller | TSMC | Samsung |
Prozessgröße | 16 nm | 8 nm |
Transistoren | 7,200 million | unknown |
Chipgröße | 314 mm² | unknown |
Veröffentlichungsdatum | Jan 11th, 2017 | 2021 |
---|---|---|
Generation | Quadro Mobile (Px000) | Quadro Mobile (Ax000) |
Produktion | End-of-life | Active |
Businterface | MXM-B (3.0) | PCIe 4.0 x16 |
gpu.details.availability | — | 2021 |
Basis-Taktfrequenz | 1278 MHz | 1237 MHz |
---|---|---|
Boost-Takt | 1582 MHz | 1500 MHz |
Speicher-Taktung | 1502 MHz 6 Gbps effective | 1750 MHz 14 Gbps effective |
Speichergröße | 16 GB | 4 GB |
---|---|---|
Speichertyp | GDDR5 | GDDR6 |
Speicherbus | 256 bit | 128 bit |
Bandbreite | 192.3 GB/s | 224.0 GB/s |
Shading-Einheiten | 2048 | 2048 |
---|---|---|
TMUs | 128 | 64 |
ROPs | 64 | 40 |
Anzahl SM | 16 | 16 |
Cache L1 | 48 KB (per SM) | 128 KB (per SM) |
Cache L2 | 2 MB | 2 MB |
Tensor Cores | — | 64 |
RT-Kerne | — | 16 |
Pixelrate | 101.2 GPixel/s | 60.00 GPixel/s |
---|---|---|
Texturrate | 202.5 GTexel/s | 96.00 GTexel/s |
FP16 (half) Leistung | 101.2 GFLOPS (1:64) | 6.144 TFLOPS (1:1) |
FP32 (float) Leistung | 6.480 TFLOPS | 6.144 TFLOPS |
FP64 (double) Leistung | 202.5 GFLOPS (1:32) | 96.00 GFLOPS (1:64) |
Steckplatzbreite | MXM Module | IGP |
---|---|---|
TDP | 100 W | unknown |
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 | 8.6 |
Shader-Modell | 6.4 | 6.6 |