Nom du GPU | NV18 | TU106 |
---|---|---|
Architecture | Celsius | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 150 nm | 12 nm |
Transistors | 29 million | 10,800 million |
Taille des matrices | 65 mm² | 445 mm² |
Date de publication | May 31st, 2005 | — |
---|---|---|
Génération | Quadro NVS | — |
Production | End-of-life | — |
Bus interface | PCI | — |
Critiques | 26 in our database | — |
GPU clock | 250 MHz | — |
---|---|---|
Mémoire clock | 200 MHz 400 Mbps effective | 1500 MHz 12 Gbps effective |
Base clock | — | 600 MHz |
Boost clock | — | 1215 MHz |
Taille de la mémoire | 64 MB | 6 GB |
---|---|---|
Type de mémoire | DDR | GDDR6 |
Bus mémoire | 64 bit | 192 bit |
Bande passante | 3.200 GB/s | 288.0 GB/s |
Pixel shaders | 2 | — |
---|---|---|
Vertex shaders | 0 | — |
TMUs | 4 | 120 |
ROPs | 2 | 64 |
Shading units | — | 1920 |
Comptage SM | — | 30 |
Tensor cores | — | 240 |
RT cores | — | 30 |
Cache L1 | — | 64 KB (per SM) |
Cache L2 | — | 3 MB |
Taux de pixel | 500.0 MPixel/s | 77.76 GPixel/s |
---|---|---|
Taux de texture | 1.000 GTexel/s | 145.8 GTexel/s |
FP16 (half) performance | — | 9.331 TFLOPS (2:1) |
FP32 (float) performance | — | 4.666 TFLOPS |
FP64 (double) performance | — | 145.8 GFLOPS (1:32) |
Taille Slot | Single-slot | IGP |
---|---|---|
Longueur | 168 mm 6.6 inches | — |
TDP | 10 W | 60 W |
Suggestions pour le PSU | 200 W | — |
Sorties | 1x DVI1x S-Video | No outputs |
Connecteurs de puissance | None | None |
DirectX | 7.0 | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 1.5 | 4.6 |
OpenCL | — | 3.0 |
Vulkan | — | 1.2 |
Pixel shader | 1.1 | — |
Vertex shader | 1.1 | — |
CUDA | — | 7.5 |
Shader model | — | 6.6 |
Date de publication | — | May 27th, 2019 |
---|---|---|
Génération | — | Quadro Mobile (Tx000) |
Production | — | Active |
Bus interface | — | PCIe 3.0 x16 |