Nom du GPU | Navi 10 | TU104 |
---|---|---|
Architecture | RDNA 1.0 | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 7 nm | 12 nm |
Transistors | 10,300 million | 13,600 million |
Taille des matrices | 251 mm² | 545 mm² |
GPU variant | — | N18E-G3 |
Date de publication | Nov 19th, 2019 | — |
---|---|---|
Génération | Radeon Pro | — |
Production | Active | — |
Prix de lancement | 799 USD | — |
Bus interface | PCIe 4.0 x16 | — |
Base clock | 1400 MHz | 1365 MHz |
---|---|---|
Boost clock | 1880 MHz | 1560 MHz |
Mémoire clock | 1750 MHz 14 Gbps effective | 1750 MHz 14 Gbps effective |
Taille de la mémoire | 8 GB | 8 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 256 bit | 256 bit |
Bande passante | 448.0 GB/s | 448.0 GB/s |
Shading units | 2304 | 3072 |
---|---|---|
TMUs | 144 | 192 |
ROPs | 64 | 64 |
Compute units | 36 | — |
Cache L2 | 4 MB | 4 MB |
Comptage SM | — | 48 |
Tensor cores | — | 384 |
RT cores | — | 48 |
Cache L1 | — | 64 KB (per SM) |
Taux de pixel | 120.3 GPixel/s | 99.84 GPixel/s |
---|---|---|
Taux de texture | 270.7 GTexel/s | 299.5 GTexel/s |
FP16 (half) performance | 17.33 TFLOPS (2:1) | 19.17 TFLOPS (2:1) |
FP32 (float) performance | 8.663 TFLOPS | 9.585 TFLOPS |
FP64 (double) performance | 541.4 GFLOPS (1:16) | 299.5 GFLOPS (1:32) |
Taille Slot | Dual-slot | Dual-slot |
---|---|---|
Longueur | 267 mm 10.5 inches | — |
Taille | 111 mm 4.4 inches | — |
TDP | 205 W | 150 W |
Suggestions pour le PSU | 550 W | — |
Sorties | 5x mini-DisplayPort1x USB Type-C | No outputs |
Connecteurs de puissance | 1x 6-pin + 1x 8-pin | None |
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 | 6.5 | 6.6 |
CUDA | — | 7.5 |
Date de publication | — | Apr 2nd, 2020 |
---|---|---|
Génération | — | GeForce 20 Mobile |
Production | — | Active |
Bus interface | — | PCIe 3.0 x16 |
Prédécesseur | — | GeForce 10 Mobile |
Successeur | — | GeForce 30 Mobile |