Nom du GPU | GA106 | GP104 |
---|---|---|
GPU variant | GA106-300-A1 | — |
Architecture | Ampere | Pascal |
Fonderie | Samsung | TSMC |
Taille du processus | 8 nm | 16 nm |
Transistors | 13,250 million | 7,200 million |
Taille des matrices | 276 mm² | 314 mm² |
Date de publication | Jan 12th, 2021 | — |
---|---|---|
gpu.details.availability | Feb 25th, 2021 | — |
Génération | GeForce 30 | — |
Prédécesseur | GeForce 20 | — |
Production | Active | — |
Prix de lancement | 329 USD | — |
Bus interface | PCIe 4.0 x16 | — |
Critiques | 60 in our database | — |
Base clock | 1320 MHz | 1328 MHz |
---|---|---|
Boost clock | 1777 MHz | 1543 MHz |
Mémoire clock | 1875 MHz 15 Gbps effective | 1753 MHz 7 Gbps effective |
Taille de la mémoire | 12 GB | 6 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR5 |
Bus mémoire | 192 bit | 192 bit |
Bande passante | 360.0 GB/s | 168.3 GB/s |
Shading units | 3584 | 1792 |
---|---|---|
TMUs | 112 | 112 |
ROPs | 48 | 64 |
Comptage SM | 28 | 14 |
Tensor cores | 112 | — |
RT cores | 28 | — |
Cache L1 | 128 KB (per SM) | 48 KB (per SM) |
Cache L2 | 3 MB | 1536 KB |
Taux de pixel | 85.30 GPixel/s | 98.75 GPixel/s |
---|---|---|
Taux de texture | 199.0 GTexel/s | 172.8 GTexel/s |
FP16 (half) performance | 12.74 TFLOPS (1:1) | 86.41 GFLOPS (1:64) |
FP32 (float) performance | 12.74 TFLOPS | 5.530 TFLOPS |
FP64 (double) performance | 199.0 GFLOPS (1:64) | 172.8 GFLOPS (1:32) |
Taille Slot | Dual-slot | MXM Module |
---|---|---|
Longueur | 242 mm 9.5 inches | — |
Taille | 112 mm 4.4 inches | — |
TDP | 170 W | 75 W |
Suggestions pour le PSU | 450 W | — |
Sorties | 1x HDMI3x DisplayPort | No outputs |
Connecteurs de puissance | 1x 12-pin | None |
Board number | PG190 SKU 60 | — |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 8.6 | 6.1 |
Shader model | 6.6 | 6.4 |
Date de publication | — | Feb 21st, 2018 |
---|---|---|
Génération | — | Quadro Mobile (Px200) |
Production | — | End-of-life |
Bus interface | — | MXM-B (3.0) |