Nom du GPU | Navi 31 | TU117 |
---|---|---|
GPU variant | Navi 31 XTX | TU117-300-A1 |
Architecture | RDNA 3.0 | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 5 nm | 12 nm |
Transistors | unknown | 4,700 million |
Taille des matrices | unknown | 200 mm² |
Date de publication | 2022 | Apr 23rd, 2019 |
---|---|---|
Génération | Navi III | GeForce 16 |
Production | Unreleased | Active |
Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Prédécesseur | Navi II | GeForce 10 |
Successeur | — | GeForce 20 |
Prix de lancement | — | 149 USD |
Critiques | — | 45 in our database |
Base clock | 1800 MHz | 1485 MHz |
---|---|---|
Game clock | 1900 MHz | — |
Boost clock | 2000 MHz | 1665 MHz |
Mémoire clock | 2250 MHz 18 Gbps effective | 2001 MHz 8 Gbps effective |
Taille de la mémoire | 16 GB | 4 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR5 |
Bus mémoire | 256 bit | 128 bit |
Bande passante | 576.0 GB/s | 128.1 GB/s |
Shading units | 15360 | 896 |
---|---|---|
TMUs | 960 | 56 |
ROPs | 256 | 32 |
Compute units | 240 | — |
RT cores | 240 | — |
gpu.details.l0-cache | 32 KB per WGP | — |
Cache L1 | 128 KB per Array | 64 KB (per SM) |
Cache L2 | 4 MB | 1024 KB |
gpu.details.l3-cache | 512 MB | — |
Comptage SM | — | 14 |
Taux de pixel | 512.0 GPixel/s | 53.28 GPixel/s |
---|---|---|
Taux de texture | 1,920 GTexel/s | 93.24 GTexel/s |
FP16 (half) performance | 122.9 TFLOPS (2:1) | 5.967 TFLOPS (2:1) |
FP32 (float) performance | 61.44 TFLOPS | 2.984 TFLOPS |
FP64 (double) performance | 3.840 TFLOPS (1:16) | 93.24 GFLOPS (1:32) |
Taille Slot | Dual-slot | Dual-slot |
---|---|---|
Longueur | 267 mm 10.5 inches | 229 mm 9 inches |
Taille | 135 mm 5.3 inches | 111 mm 4.4 inches |
Taille | 50 mm 2 inches | 35 mm 1.4 inches |
TDP | 350 W | 75 W |
Suggestions pour le PSU | 750 W | 250 W |
Sorties | 1x HDMI3x DisplayPort | 1x DVI1x HDMI1x DisplayPort |
Connecteurs de puissance | 2x 8-pin | None |
Numéro de pièce | — | — |
Board number | — | PG174 SKU 0 |
DirectX | 12 Ultimate (12_2) | 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 |