Nom du GPU | Navi 14 | TU117 |
---|---|---|
GPU variant | Navi 14 PRO XE | TU117-300-A1 |
Architecture | RDNA 1.0 | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 7 nm | 12 nm |
Transistors | 6,400 million | 4,700 million |
Taille des matrices | 158 mm² | 200 mm² |
Date de publication | Aug 4th, 2020 | Apr 1st, 2020 |
---|---|---|
Génération | Radeon Pro Mac | GeForce 16 |
Production | Active | Active |
Bus interface | PCIe 4.0 x8 | PCIe 3.0 x16 |
Prédécesseur | — | GeForce 10 |
Successeur | — | GeForce 20 |
Prix de lancement | — | 149 USD |
Critiques | — | 45 in our database |
Base clock | 1000 MHz | 1410 MHz |
---|---|---|
Boost clock | 1650 MHz | 1590 MHz |
Mémoire clock | 1750 MHz 14 Gbps effective | 1500 MHz 12 Gbps effective |
Taille de la mémoire | 4 GB | 4 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 128 bit | 128 bit |
Bande passante | 224.0 GB/s | 192.0 GB/s |
Shading units | 1280 | 896 |
---|---|---|
TMUs | 80 | 56 |
ROPs | 32 | 32 |
Compute units | 20 | — |
Cache L2 | 2 MB | 1024 KB |
Comptage SM | — | 14 |
Cache L1 | — | 64 KB (per SM) |
Taux de pixel | 52.80 GPixel/s | 50.88 GPixel/s |
---|---|---|
Taux de texture | 132.0 GTexel/s | 89.04 GTexel/s |
FP16 (half) performance | 8.448 TFLOPS (2:1) | 5.699 TFLOPS (2:1) |
FP32 (float) performance | 4.224 TFLOPS | 2.849 TFLOPS |
FP64 (double) performance | 264.0 GFLOPS (1:16) | 89.04 GFLOPS (1:32) |
Taille Slot | IGP | Dual-slot |
---|---|---|
TDP | 85 W | 75 W |
Suggestions pour le PSU | 250 W | 250 W |
Sorties | No outputs | 1x DVI1x HDMI1x DisplayPort |
Connecteurs de puissance | None | None |
Longueur | — | 229 mm 9 inches |
Taille | — | 111 mm 4.4 inches |
Taille | — | 35 mm 1.4 inches |
Board number | — | PG177 SKU 1 |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.5 | 6.6 |
CUDA | — | 7.5 |