Nom du GPU | Raven | TU102 |
---|---|---|
Architecture | GCN 5.0 | Turing |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 12 nm |
Transistors | 4,940 million | 18,600 million |
Taille des matrices | 210 mm² | 754 mm² |
GPU variant | — | TU102-875-A1 |
Date de publication | May 10th, 2018 | — |
---|---|---|
Génération | Raven Ridge (Vega) | — |
Production | Active | — |
Bus interface | IGP | — |
Prédécesseur | Great Horned Owl | — |
Successeur | Picasso | — |
Base clock | 300 MHz | 1065 MHz |
---|---|---|
Boost clock | 1280 MHz | 1395 MHz |
Mémoire clock | System Shared | 1575 MHz 12.6 Gbps effective |
Taille de la mémoire | System Shared | 16 GB |
---|---|---|
Type de mémoire | System Shared | GDDR6 |
Bus mémoire | System Shared | 384 bit |
Bande passante | System Dependent | 604.8 GB/s |
Shading units | 384 | 4608 |
---|---|---|
TMUs | 24 | 288 |
ROPs | 8 | 96 |
Compute units | 6 | — |
Comptage SM | — | 72 |
Tensor cores | — | 576 |
RT cores | — | 72 |
Cache L1 | — | 64 KB (per SM) |
Cache L2 | — | 6 MB |
Taux de pixel | 10.24 GPixel/s | 133.9 GPixel/s |
---|---|---|
Taux de texture | 30.72 GTexel/s | 401.8 GTexel/s |
FP16 (half) performance | 1.966 TFLOPS (2:1) | 25.71 TFLOPS (2:1) |
FP32 (float) performance | 983.0 GFLOPS | 12.86 TFLOPS |
FP64 (double) performance | 61.44 GFLOPS (1:16) | 401.8 GFLOPS (1:32) |
Taille Slot | IGP | Dual-slot |
---|---|---|
TDP | 15 W | 260 W |
Sorties | No outputs | No outputs |
Longueur | — | 267 mm 10.5 inches |
Suggestions pour le PSU | — | 600 W |
Connecteurs de puissance | — | 1x 6-pin + 1x 8-pin |
Board number | — | PG150 SKU 215 |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.6 |
CUDA | — | 7.5 |
Date de publication | — | Unknown |
---|---|---|
Génération | — | GRID |
Production | — | Active |
Bus interface | — | PCIe 3.0 x16 |