Nom du GPU | Baffin | GP108 |
---|---|---|
GPU variant | Baffin LE | GP108-650-A1 (N17S-G1-A1) |
Architecture | GCN 4.0 | Pascal |
Fonderie | GlobalFoundries | Samsung |
Taille du processus | 14 nm | 14 nm |
Transistors | 3,000 million | 1,800 million |
Taille des matrices | 123 mm² | 74 mm² |
Date de publication | Apr 11th, 2018 | — |
---|---|---|
Génération | Polaris | — |
Production | Active | — |
Bus interface | PCIe 3.0 x8 | — |
Prédécesseur | Polaris | — |
Successeur | Vega | — |
Base clock | 1019 MHz | 1469 MHz |
---|---|---|
Boost clock | 1071 MHz | 1532 MHz |
Mémoire clock | 1500 MHz 6 Gbps effective | 1502 MHz 6 Gbps effective |
Taille de la mémoire | 2 GB | 2 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR5 |
Bus mémoire | 128 bit | 64 bit |
Bande passante | 96.00 GB/s | 48.06 GB/s |
Shading units | 640 | 384 |
---|---|---|
TMUs | 40 | 24 |
ROPs | 16 | 16 |
Compute units | 10 | — |
Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
Cache L2 | 1024 KB | 512 KB |
Comptage SM | — | 3 |
Taux de pixel | 17.14 GPixel/s | 24.51 GPixel/s |
---|---|---|
Taux de texture | 42.84 GTexel/s | 36.77 GTexel/s |
FP16 (half) performance | 1,371 GFLOPS (1:1) | 18.38 GFLOPS (1:64) |
FP32 (float) performance | 1,371 GFLOPS | 1,177 GFLOPS |
FP64 (double) performance | 85.68 GFLOPS (1:16) | 36.77 GFLOPS (1:32) |
Taille Slot | Dual-slot | IGP |
---|---|---|
Longueur | 145 mm 5.7 inches | — |
TDP | 60 W | 25 W |
Suggestions pour le PSU | 250 W | — |
Sorties | 1x DVI1x HDMI1x DisplayPort | No outputs |
Connecteurs de puissance | None | None |
Board number | D090-21 | E2902 SKU 0 |
DirectX | 12 (12_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.4 |
CUDA | — | 6.1 |
Date de publication | — | May 17th, 2017 |
---|---|---|
Génération | — | GeForce MX (1xx) |
Production | — | End-of-life |
Bus interface | — | PCIe 3.0 x4 |