Nom du GPU | Picasso | GF116 |
---|---|---|
Architecture | GCN 5.0 | Fermi 2.0 |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 40 nm |
Transistors | 4,940 million | 1,170 million |
Taille des matrices | 210 mm² | 238 mm² |
GPU variant | — | GF116-200-KA-A1 |
Date de publication | Jul 7th, 2019 | — |
---|---|---|
Génération | Picasso (Vega) | — |
Production | Active | — |
Bus interface | IGP | — |
Prédécesseur | Raven Ridge | — |
Successeur | Renoir | — |
Base clock | 300 MHz | — |
---|---|---|
Boost clock | 1400 MHz | — |
Mémoire clock | System Shared | 700 MHz 1400 Mbps effective |
GPU clock | — | 783 MHz |
Shader clock | — | 1566 MHz |
Taille de la mémoire | System Shared | 1024 MB |
---|---|---|
Type de mémoire | System Shared | DDR3 |
Bus mémoire | System Shared | 128 bit |
Bande passante | System Dependent | 22.40 GB/s |
Shading units | 704 | 144 |
---|---|---|
TMUs | 44 | 24 |
ROPs | 8 | 16 |
Compute units | 11 | — |
Comptage SM | — | 3 |
Cache L1 | — | 64 KB (per SM) |
Cache L2 | — | 256 KB |
Taux de pixel | 11.20 GPixel/s | 4.698 GPixel/s |
---|---|---|
Taux de texture | 61.60 GTexel/s | 18.79 GTexel/s |
FP16 (half) performance | 3.942 TFLOPS (2:1) | — |
FP32 (float) performance | 1.971 TFLOPS | 451.0 GFLOPS |
FP64 (double) performance | 123.2 GFLOPS (1:16) | 37.58 GFLOPS (1:12) |
Taille Slot | IGP | Dual-slot |
---|---|---|
TDP | 15 W | 106 W |
Sorties | No outputs | 2x DVI1x mini-HDMI |
Connecteurs de puissance | None | — |
Longueur | — | 210 mm 8.3 inches |
Suggestions pour le PSU | — | 300 W |
Board number | — | P1060 |
DirectX | 12 (12_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 1.1 |
Vulkan | 1.2 | — |
Shader model | 6.4 | 5.1 |
CUDA | — | 2.1 |
Date de publication | — | Jul 11th, 2012 |
---|---|---|
Génération | — | GeForce 400 |
Production | — | End-of-life |
Bus interface | — | PCIe 2.0 x16 |
Critiques | — | 80 in our database |
Prédécesseur | — | GeForce 200 |
Successeur | — | GeForce 500 |