Nom du GPU | Raven | GP104 |
---|---|---|
Architecture | GCN 5.0 | Pascal |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 16 nm |
Transistors | 4,940 million | 7,200 million |
Taille des matrices | 210 mm² | 314 mm² |
GPU variant | — | GP104-200-A1 |
Date de publication | Apr 19th, 2018 | — |
---|---|---|
Génération | Raven Ridge (Vega) | — |
Production | Active | — |
Bus interface | IGP | — |
Prédécesseur | Great Horned Owl | — |
Successeur | Picasso | — |
Base clock | 300 MHz | 1506 MHz |
---|---|---|
Boost clock | 1101 MHz | 1683 MHz |
Mémoire clock | System Shared | 1001 MHz 8 Gbps effective |
Taille de la mémoire | System Shared | 8 GB |
---|---|---|
Type de mémoire | System Shared | GDDR5X |
Bus mémoire | System Shared | 256 bit |
Bande passante | System Dependent | 256.3 GB/s |
Shading units | 512 | 1920 |
---|---|---|
TMUs | 32 | 120 |
ROPs | 8 | 64 |
Compute units | 8 | — |
Comptage SM | — | 15 |
Cache L1 | — | 48 KB (per SM) |
Cache L2 | — | 2 MB |
Taux de pixel | 8.808 GPixel/s | 107.7 GPixel/s |
---|---|---|
Taux de texture | 35.23 GTexel/s | 202.0 GTexel/s |
FP16 (half) performance | 2.255 TFLOPS (2:1) | 101.0 GFLOPS (1:64) |
FP32 (float) performance | 1,127 GFLOPS | 6.463 TFLOPS |
FP64 (double) performance | 70.46 GFLOPS (1:16) | 202.0 GFLOPS (1:32) |
Taille Slot | IGP | Dual-slot |
---|---|---|
TDP | 35 W | 150 W |
Sorties | No outputs | 1x DVI1x HDMI3x DisplayPort |
Connecteurs de puissance | None | 1x 8-pin |
Longueur | — | 267 mm 10.5 inches |
Taille | — | 112 mm 4.4 inches |
Taille | — | 40 mm 1.6 inches |
Suggestions pour le PSU | — | 450 W |
DirectX | 12 (12_1) | 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 | — | Dec 4th, 2018 |
---|---|---|
Génération | — | GeForce 10 |
Prédécesseur | — | GeForce 900 |
Successeur | — | GeForce 20 |
Production | — | End-of-life |
Bus interface | — | PCIe 3.0 x16 |
Critiques | — | 125 in our database |