Nom du GPU | Lexa | GM108 |
---|---|---|
GPU variant | Lexa PRO (215-0904018) | N16V-GMR1-A1 |
Architecture | GCN 4.0 | Maxwell |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 28 nm |
Transistors | 2,200 million | unknown |
Taille des matrices | 103 mm² | unknown |
Date de publication | Mar 27th, 2019 | — |
---|---|---|
Génération | Polaris | — |
Production | End-of-life | — |
Bus interface | PCIe 3.0 x8 | — |
Prédécesseur | Polaris | — |
Successeur | Vega | — |
Base clock | 1082 MHz | 978 MHz |
---|---|---|
Boost clock | 1218 MHz | 1006 MHz |
Mémoire clock | 1750 MHz 7 Gbps effective | 1253 MHz 5 Gbps effective |
Taille de la mémoire | 2 GB | 2 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR5 |
Bus mémoire | 128 bit | 64 bit |
Bande passante | 112.0 GB/s | 40.10 GB/s |
Shading units | 512 | 384 |
---|---|---|
TMUs | 32 | 24 |
ROPs | 16 | 8 |
Compute units | 8 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
Cache L2 | 512 KB | 1024 KB |
Comptage SMM | — | 3 |
Taux de pixel | 19.49 GPixel/s | 8.048 GPixel/s |
---|---|---|
Taux de texture | 38.98 GTexel/s | 24.14 GTexel/s |
FP16 (half) performance | 1,247 GFLOPS (1:1) | — |
FP32 (float) performance | 1,247 GFLOPS | 772.6 GFLOPS |
FP64 (double) performance | 77.95 GFLOPS (1:16) | 24.14 GFLOPS (1:32) |
Taille Slot | Dual-slot | IGP |
---|---|---|
Longueur | 145 mm 5.7 inches | — |
TDP | 50 W | 30 W |
Suggestions pour le PSU | 250 W | — |
Sorties | 1x DVI1x HDMI1x DisplayPort | No outputs |
Connecteurs de puissance | None | None |
Board number | D090 | — |
DirectX | 12 (12_0) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.1 |
Shader model | 6.4 | 5.1 |
CUDA | — | 5.0 |
Date de publication | — | Nov 17th, 2017 |
---|---|---|
Génération | — | GeForce MX (1xx) |
Production | — | End-of-life |
Bus interface | — | PCIe 3.0 x4 |