Nom du GPU | TU106 | GA104 |
---|---|---|
GPU variant | TU106-125-A1 | GA104-775-A1 |
Architecture | Turing | Ampere |
Fonderie | TSMC | Samsung |
Taille du processus | 12 nm | 8 nm |
Transistors | 10,800 million | 17,400 million |
Taille des matrices | 445 mm² | 392 mm² |
Date de publication | Jun 18th, 2020 | — |
---|---|---|
Génération | GeForce 16 | — |
Prédécesseur | GeForce 10 | — |
Successeur | GeForce 20 | — |
Production | Active | — |
Bus interface | PCIe 3.0 x16 | — |
Base clock | 1410 MHz | 780 MHz |
---|---|---|
Boost clock | 1590 MHz | 1245 MHz |
Mémoire clock | 1500 MHz 12 Gbps effective | 1500 MHz 12 Gbps effective |
Taille de la mémoire | 4 GB | 8 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 128 bit | 256 bit |
Bande passante | 192.0 GB/s | 384.0 GB/s |
Shading units | 896 | 6144 |
---|---|---|
TMUs | 56 | 192 |
ROPs | 32 | 96 |
Comptage SM | 14 | 48 |
Tensor cores | 112 | 192 |
RT cores | 14 | 48 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 1024 KB | 4 MB |
Taux de pixel | 50.88 GPixel/s | 119.5 GPixel/s |
---|---|---|
Taux de texture | 89.04 GTexel/s | 239.0 GTexel/s |
FP16 (half) performance | 5.699 TFLOPS (2:1) | 15.30 TFLOPS (1:1) |
FP32 (float) performance | 2.849 TFLOPS | 15.30 TFLOPS |
FP64 (double) performance | 89.04 GFLOPS (1:32) | 239.0 GFLOPS (1:64) |
Taille Slot | Dual-slot | — |
---|---|---|
Longueur | 229 mm 9 inches | — |
Taille | 111 mm 4.4 inches | — |
Taille | 35 mm 1.4 inches | — |
TDP | 90 W | 80 W |
Suggestions pour le PSU | 250 W | — |
Sorties | 1x DVI1x HDMI1x DisplayPort | No outputs |
Connecteurs de puissance | 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 | 7.5 | 8.6 |
Shader model | 6.6 | 6.6 |
Date de publication | — | Jan 12th, 2021 |
---|---|---|
gpu.details.availability | — | Feb 2nd, 2021 |
Génération | — | GeForce 30 Mobile |
Prédécesseur | — | GeForce 20 Mobile |
Production | — | Active |
Bus interface | — | PCIe 4.0 x16 |