Nom du GPU | GF108 | GA106 |
---|---|---|
GPU variant | GF108-200-A1 | GA106-300-A1 |
Architecture | Fermi | Ampere |
Fonderie | TSMC | Samsung |
Taille du processus | 40 nm | 8 nm |
Transistors | 585 million | 13,250 million |
Taille des matrices | 116 mm² | 276 mm² |
Date de publication | Sep 3rd, 2010 | Jan 12th, 2021 |
---|---|---|
Génération | GeForce 400 | GeForce 30 |
Production | End-of-life | Active |
Bus interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
Prédécesseur | GeForce 200 | GeForce 20 |
Successeur | GeForce 500 | — |
gpu.details.availability | — | Feb 25th, 2021 |
Prix de lancement | — | 329 USD |
Critiques | — | 60 in our database |
GPU clock | 700 MHz | — |
---|---|---|
Shader clock | 1400 MHz | — |
Mémoire clock | 900 MHz 1800 Mbps effective | 1875 MHz 15 Gbps effective |
Base clock | — | 1320 MHz |
Boost clock | — | 1777 MHz |
Taille de la mémoire | 1024 MB | 12 GB |
---|---|---|
Type de mémoire | DDR3 | GDDR6 |
Bus mémoire | 128 bit | 192 bit |
Bande passante | 28.80 GB/s | 360.0 GB/s |
Shading units | 48 | 3584 |
---|---|---|
TMUs | 4 | 112 |
ROPs | 4 | 48 |
Comptage SM | 1 | 28 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 256 KB | 3 MB |
Tensor cores | — | 112 |
RT cores | — | 28 |
Taux de pixel | 1.400 GPixel/s | 85.30 GPixel/s |
---|---|---|
Taux de texture | 2.800 GTexel/s | 199.0 GTexel/s |
FP32 (float) performance | 134.4 GFLOPS | 12.74 TFLOPS |
FP64 (double) performance | 11.20 GFLOPS (1:12) | 199.0 GFLOPS (1:64) |
FP16 (half) performance | — | 12.74 TFLOPS (1:1) |
Taille Slot | Single-slot | Dual-slot |
---|---|---|
Longueur | 145 mm 5.7 inches | 242 mm 9.5 inches |
TDP | 50 W | 170 W |
Suggestions pour le PSU | 250 W | 450 W |
Sorties | 1x DVI1x HDMI1x VGA | 1x HDMI3x DisplayPort |
Connecteurs de puissance | None | 1x 12-pin |
Board number | P1071 | PG190 SKU 60 |
Taille | — | 112 mm 4.4 inches |
DirectX | 12 (11_0) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.1 | 3.0 |
Vulkan | — | 1.2 |
CUDA | 2.1 | 8.6 |
Shader model | 5.1 | 6.6 |