Nom du GPU | GF106 | GA100 |
---|---|---|
GPU variant | N12E-GE-B-A1 | — |
Architecture | Fermi | Ampere |
Fonderie | TSMC | TSMC |
Taille du processus | 40 nm | 7 nm |
Transistors | 1,170 million | 54,200 million |
Taille des matrices | 238 mm² | 826 mm² |
Date de publication | Oct 27th, 2011 | — |
---|---|---|
Génération | GeForce 500M | — |
Production | End-of-life | — |
Bus interface | PCIe 2.0 x16 | — |
Prédécesseur | GeForce 400M | — |
Successeur | GeForce 600M | — |
GPU clock | 525 MHz | — |
---|---|---|
Shader clock | 1050 MHz | — |
Mémoire clock | 900 MHz 1800 Mbps effective | 1215 MHz 2.4 Gbps effective |
Base clock | — | 900 MHz |
Boost clock | — | 1005 MHz |
Taille de la mémoire | 1024 MB | 48 GB |
---|---|---|
Type de mémoire | DDR3 | HBM2E |
Bus mémoire | 128 bit | 6144 bit |
Bande passante | 28.80 GB/s | 1,866 GB/s |
Shading units | 144 | 6912 |
---|---|---|
TMUs | 24 | 432 |
ROPs | 16 | 192 |
Comptage SM | 3 | 108 |
Cache L1 | 64 KB (per SM) | 192 KB (per SM) |
Cache L2 | 256 KB | 48 MB |
Tensor cores | — | 432 |
Taux de pixel | 3.150 GPixel/s | 193.0 GPixel/s |
---|---|---|
Taux de texture | 12.60 GTexel/s | 434.2 GTexel/s |
FP32 (float) performance | 302.4 GFLOPS | 13.89 TFLOPS |
FP64 (double) performance | 25.20 GFLOPS (1:12) | 6.947 TFLOPS (1:2) |
FP16 (half) performance | — | 55.57 TFLOPS (4:1) |
TDP | 35 W | 400 W |
---|---|---|
Sorties | No outputs | No outputs |
Taille Slot | — | IGP |
Suggestions pour le PSU | — | 800 W |
Connecteurs de puissance | — | None |
DirectX | 12 (11_0) | — |
---|---|---|
OpenGL | 4.6 | — |
OpenCL | 1.1 | 3.0 |
Vulkan | — | — |
CUDA | 2.1 | 8.0 |
Shader model | 5.1 | — |
Date de publication | — | May 14th, 2020 |
---|---|---|
Génération | — | GRID |
Production | — | Active |
Bus interface | — | PCIe 4.0 x16 |