Nom du GPU | TU116 | GA103 |
---|---|---|
Architecture | Turing | Ampere |
Fonderie | TSMC | Samsung |
Taille du processus | 12 nm | 8 nm |
Transistors | 6,600 million | unknown |
Taille des matrices | 284 mm² | unknown |
GPU variant | — | GA103S |
Date de publication | Apr 23rd, 2019 | 2022 |
---|---|---|
Génération | GeForce 16 Mobile | GeForce 30 Mobile |
Production | Active | Unreleased |
Bus interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Prédécesseur | GeForce 10 Mobile | GeForce 20 Mobile |
Successeur | GeForce 20 Mobile | — |
gpu.details.availability | — | — |
Base clock | 1140 MHz | 975 MHz |
---|---|---|
Boost clock | 1335 MHz | 1395 MHz |
Mémoire clock | 1500 MHz 12 Gbps effective | 2000 MHz 16 Gbps effective |
Taille de la mémoire | 6 GB | 16 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 192 bit | 256 bit |
Bande passante | 288.0 GB/s | 512.0 GB/s |
Shading units | 1536 | 7424 |
---|---|---|
TMUs | 96 | 232 |
ROPs | 48 | 96 |
Comptage SM | 24 | 58 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 1536 KB | 4 MB |
Tensor cores | — | 232 |
RT cores | — | 58 |
Taux de pixel | 64.08 GPixel/s | 133.9 GPixel/s |
---|---|---|
Taux de texture | 128.2 GTexel/s | 323.6 GTexel/s |
FP16 (half) performance | 8.202 TFLOPS (2:1) | 20.71 TFLOPS (1:1) |
FP32 (float) performance | 4.101 TFLOPS | 20.71 TFLOPS |
FP64 (double) performance | 128.2 GFLOPS (1:32) | 323.6 GFLOPS (1:64) |
Taille Slot | MXM Module | — |
---|---|---|
TDP | unknown | 175 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | None |
Board number | E4914 SKU 50 | — |
DirectX | 12 (12_1) | 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 | 6.5 |