Nom du GPU | Picasso | GF100 |
---|---|---|
Architecture | GCN 5.0 | Fermi |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 40 nm |
Transistors | 4,940 million | 3,100 million |
Taille des matrices | 210 mm² | 529 mm² |
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 | 783 MHz 3.1 Gbps effective |
GPU clock | — | 574 MHz |
Shader clock | — | 1150 MHz |
Taille de la mémoire | System Shared | 6 GB |
---|---|---|
Type de mémoire | System Shared | GDDR5 |
Bus mémoire | System Shared | 384 bit |
Bande passante | System Dependent | 150.3 GB/s |
Shading units | 704 | 448 |
---|---|---|
TMUs | 44 | 56 |
ROPs | 8 | 48 |
Compute units | 11 | — |
Comptage SM | — | 14 |
Cache L1 | — | 64 KB (per SM) |
Cache L2 | — | 768 KB |
Taux de pixel | 11.20 GPixel/s | 16.07 GPixel/s |
---|---|---|
Taux de texture | 61.60 GTexel/s | 32.14 GTexel/s |
FP16 (half) performance | 3.942 TFLOPS (2:1) | — |
FP32 (float) performance | 1.971 TFLOPS | 1,030 GFLOPS |
FP64 (double) performance | 123.2 GFLOPS (1:16) | 515.2 GFLOPS (1:2) |
Taille Slot | IGP | Dual-slot |
---|---|---|
TDP | 15 W | 225 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | 1x 6-pin + 1x 8-pin |
Longueur | — | 248 mm 9.8 inches |
Suggestions pour le PSU | — | 550 W |
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 | — | 2.0 |
Date de publication | — | Jul 25th, 2011 |
---|---|---|
Génération | — | Tesla |
Production | — | End-of-life |
Prix de lancement | — | 3,099 USD |
Bus interface | — | PCIe 2.0 x16 |