Nom du GPU | GA102 | GA106 |
---|---|---|
GPU variant | GA102-100-A1 | GA106-300-A1 |
Architecture | Ampere | Ampere |
Fonderie | Samsung | Samsung |
Taille du processus | 8 nm | 8 nm |
Transistors | 28,300 million | 13,250 million |
Taille des matrices | 628 mm² | 276 mm² |
Date de publication | Jul 28th, 2021 | Jan 12th, 2021 |
---|---|---|
Génération | Mining GPUs | GeForce 30 |
Production | Active | Active |
Bus interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
gpu.details.availability | — | Feb 25th, 2021 |
Prédécesseur | — | GeForce 20 |
Prix de lancement | — | 329 USD |
Critiques | — | 60 in our database |
Base clock | 1500 MHz | 1320 MHz |
---|---|---|
Boost clock | 1710 MHz | 1777 MHz |
Mémoire clock | 1188 MHz 19 Gbps effective | 1875 MHz 15 Gbps effective |
Taille de la mémoire | 10 GB | 12 GB |
---|---|---|
Type de mémoire | GDDR6X | GDDR6 |
Bus mémoire | 320 bit | 192 bit |
Bande passante | 760.3 GB/s | 360.0 GB/s |
Shading units | 6400 | 3584 |
---|---|---|
TMUs | 200 | 112 |
ROPs | 80 | 48 |
Comptage SM | 50 | 28 |
Tensor cores | 200 | 112 |
RT cores | 50 | 28 |
Cache L1 | 128 KB (per SM) | 128 KB (per SM) |
Cache L2 | 5 MB | 3 MB |
Taux de pixel | 136.8 GPixel/s | 85.30 GPixel/s |
---|---|---|
Taux de texture | 342.0 GTexel/s | 199.0 GTexel/s |
FP16 (half) performance | 21.89 TFLOPS (1:1) | 12.74 TFLOPS (1:1) |
FP32 (float) performance | 21.89 TFLOPS | 12.74 TFLOPS |
FP64 (double) performance | 342.0 GFLOPS (1:64) | 199.0 GFLOPS (1:64) |
Taille Slot | Dual-slot | Dual-slot |
---|---|---|
Longueur | 285 mm 11.2 inches | 242 mm 9.5 inches |
Taille | 112 mm 4.4 inches | 112 mm 4.4 inches |
TDP | 320 W | 170 W |
Suggestions pour le PSU | 700 W | 450 W |
Sorties | No outputs | 1x HDMI3x DisplayPort |
Connecteurs de puissance | 2x 8-pin | 1x 12-pin |
Board number | PG132 SKU 100 | PG190 SKU 60 |
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 | 8.6 | 8.6 |
Shader model | 6.6 | 6.6 |