Nom du GPU | GA103 | GM204 |
---|---|---|
GPU variant | GA103 | — |
Architecture | Ampere | Maxwell 2.0 |
Fonderie | Samsung | TSMC |
Taille du processus | 8 nm | 28 nm |
Transistors | unknown | 5,200 million |
Taille des matrices | unknown | 398 mm² |
Date de publication | 2022 | — |
---|---|---|
gpu.details.availability | — | — |
Génération | GeForce 30 Mobile | — |
Prédécesseur | GeForce 20 Mobile | — |
Production | Unreleased | — |
Bus interface | PCIe 4.0 x16 | — |
Base clock | 585 MHz | 557 MHz |
---|---|---|
Boost clock | 1125 MHz | 1178 MHz |
Mémoire clock | 1500 MHz 12 Gbps effective | 1253 MHz 5 Gbps effective |
Taille de la mémoire | 16 GB | 8 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR5 |
Bus mémoire | 256 bit | 256 bit |
Bande passante | 384.0 GB/s | 160.4 GB/s |
Shading units | 7680 | 2048 |
---|---|---|
TMUs | 240 | 128 |
ROPs | 96 | 64 |
Comptage SM | 60 | — |
Tensor cores | 240 | — |
RT cores | 60 | — |
Cache L1 | 128 KB (per SM) | 48 KB (per SMM) |
Cache L2 | 4 MB | 2 MB |
Comptage SMM | — | 16 |
Taux de pixel | 108.0 GPixel/s | 75.39 GPixel/s |
---|---|---|
Taux de texture | 270.0 GTexel/s | 150.8 GTexel/s |
FP16 (half) performance | 17.28 TFLOPS (1:1) | — |
FP32 (float) performance | 17.28 TFLOPS | 4.825 TFLOPS |
FP64 (double) performance | 270.0 GFLOPS (1:64) | 150.8 GFLOPS (1:32) |
TDP | 95 W | 300 W |
---|---|---|
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | 1x 8-pin |
Taille Slot | — | Dual-slot |
Longueur | — | 267 mm 10.5 inches |
Suggestions pour le PSU | — | 700 W |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.1 |
CUDA | 8.6 | 5.2 |
Shader model | 6.5 | 6.4 |
Date de publication | — | Aug 30th, 2015 |
---|---|---|
Génération | — | Tesla |
Production | — | End-of-life |
Bus interface | — | PCIe 3.0 x16 |