Nom du GPU | Navi 24 | TU106 |
---|---|---|
Architecture | RDNA 2.0 | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 7 nm | 12 nm |
Transistors | unknown | 10,800 million |
Taille des matrices | unknown | 445 mm² |
GPU variant | — | TU106-200A-KA-A1 |
Date de publication | Unknown | Jan 7th, 2019 |
---|---|---|
Génération | Navi II | GeForce 20 |
Prédécesseur | Navi | GeForce 10 |
Successeur | Navi III | GeForce 30 |
Production | Unreleased | Active |
Bus interface | PCIe 4.0 x8 | PCIe 3.0 x16 |
Prix de lancement | — | 349 USD |
Critiques | — | 85 in our database |
Base clock | 2200 MHz | 1365 MHz |
---|---|---|
Boost clock | 2500 MHz | 1680 MHz |
Mémoire clock | 2000 MHz 16 Gbps effective | 1750 MHz 14 Gbps effective |
Taille de la mémoire | 4 GB | 6 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 64 bit | 192 bit |
Bande passante | 128.0 GB/s | 336.0 GB/s |
Shading units | 1024 | 1920 |
---|---|---|
TMUs | 64 | 120 |
ROPs | 32 | 48 |
Compute units | 16 | — |
RT cores | 16 | 30 |
gpu.details.l0-cache | 32 KB per WGP | — |
Cache L1 | 128 KB per Array | 64 KB (per SM) |
Cache L2 | 1024 KB | 3 MB |
gpu.details.l3-cache | 16 MB | — |
Comptage SM | — | 30 |
Tensor cores | — | 240 |
Taux de pixel | 80.00 GPixel/s | 80.64 GPixel/s |
---|---|---|
Taux de texture | 160.0 GTexel/s | 201.6 GTexel/s |
FP16 (half) performance | 10.24 TFLOPS (2:1) | 12.90 TFLOPS (2:1) |
FP32 (float) performance | 5.120 TFLOPS | 6.451 TFLOPS |
FP64 (double) performance | 320.0 GFLOPS (1:16) | 201.6 GFLOPS (1:32) |
Taille Slot | Dual-slot | Dual-slot |
---|---|---|
TDP | 100 W | 160 W |
Suggestions pour le PSU | 300 W | 450 W |
Sorties | 1x HDMI2x DisplayPort | 1x DVI1x HDMI2x DisplayPort1x USB Type-C |
Connecteurs de puissance | 1x 6-pin | 1x 8-pin |
Longueur | — | 229 mm 9 inches |
Taille | — | 113 mm 4.4 inches |
Taille | — | 35 mm 1.4 inches |
Board number | — | PG160 SKU 42 |
DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.6 | 6.6 |
CUDA | — | 7.5 |