Nom du GPU | Lockhart | GA106 |
---|---|---|
Architecture | RDNA 2.0 | Ampere |
Fonderie | TSMC | Samsung |
Taille du processus | 7 nm | 8 nm |
Transistors | 8,000 million | 13,250 million |
Taille des matrices | 197 mm² | 276 mm² |
Date de publication | Nov 10th, 2020 | — |
---|---|---|
Génération | Console GPU | — |
Production | Active | — |
Prix de lancement | 299 USD | — |
GPU clock | 1565 MHz | — |
---|---|---|
Mémoire clock | 1750 MHz 14 Gbps effective | 1750 MHz 14 Gbps effective |
Base clock | — | 900 MHz |
Boost clock | — | 1425 MHz |
Taille de la mémoire | 8 GB | 6 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 128 bit | 192 bit |
Bande passante | 224.0 GB/s | 336.0 GB/s |
Shading units | 1280 | 3840 |
---|---|---|
TMUs | 80 | 120 |
ROPs | 32 | 48 |
Compute units | 20 | — |
Cache L2 | 4 MB | 3 MB |
Comptage SM | — | 30 |
Tensor cores | — | 120 |
RT cores | — | 30 |
Cache L1 | — | 128 KB (per SM) |
Taux de pixel | 50.08 GPixel/s | 68.40 GPixel/s |
---|---|---|
Taux de texture | 125.2 GTexel/s | 171.0 GTexel/s |
FP16 (half) performance | 8.013 TFLOPS (2:1) | 10.94 TFLOPS (1:1) |
FP32 (float) performance | 4.006 TFLOPS | 10.94 TFLOPS |
FP64 (double) performance | 250.4 GFLOPS (1:16) | 171.0 GFLOPS (1:64) |
Longueur | 274 mm 10.8 inches | — |
---|---|---|
Taille | 151 mm 5.9 inches | — |
Taille | 64 mm 2.5 inches | — |
Poids | 1.93 kg (4.25 lbs) | — |
TDP | 100 W | 80 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | — | None |
DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.2 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.5 | 6.6 |
CUDA | — | 8.6 |
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 |
Critiques | — | 1 in our database |