AMD Radeon R9 390 X2 vs NVIDIA GeForce RTX 2060 Max-Q Refresh
Processeur graphique
| Nom du GPU | Grenada | TU106B |
|---|---|---|
| GPU variant | Grenada PRO (215-0880030) | — |
| Architecture | GCN 2.0 | Turing |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 12 nm |
| Transistors | 6,200 million | 10,800 million |
| Taille des matrices | 438 mm² | 445 mm² |
Carte graphique
| Date de publication | Sep 3rd, 2015 | — |
|---|---|---|
| Génération | Pirate Islands | — |
| Production | End-of-life | — |
| Prix de lancement | 1,399 USD | — |
| Bus interface | PCIe 3.0 x16 | — |
| Prédécesseur | Volcanic Islands | — |
| Successeur | Arctic Islands | — |
Vitesse clock
| GPU clock | 1000 MHz | — |
|---|---|---|
| Mémoire clock | 1350 MHz 5.4 Gbps effective | 1353 MHz 10.8 Gbps effective |
| Base clock | — | 960 MHz |
| Boost clock | — | 1200 MHz |
Mémoire
| Taille de la mémoire | 8 GB | 6 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR6 |
| Bus mémoire | 512 bit | 192 bit |
| Bande passante | 345.6 GB/s | 259.8 GB/s |
Render Config
| Shading units | 2560 | 1920 |
|---|---|---|
| TMUs | 160 | 120 |
| ROPs | 64 | 48 |
| Compute units | 40 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 1024 KB | 3 MB |
| Comptage SM | — | 30 |
| Tensor cores | — | 240 |
| RT cores | — | 30 |
Performance théorique
| Taux de pixel | 64.00 GPixel/s | 57.60 GPixel/s |
|---|---|---|
| Taux de texture | 160.0 GTexel/s | 144.0 GTexel/s |
| FP32 (float) performance | 5.120 TFLOPS | 4.608 TFLOPS |
| FP64 (double) performance | 640.0 GFLOPS (1:8) | 144.0 GFLOPS (1:32) |
| FP16 (half) performance | — | 9.216 TFLOPS (2:1) |
Board Design
| Taille Slot | Triple-slot | MXM Module |
|---|---|---|
| TDP | 580 W | 115 W |
| Suggestions pour le PSU | 950 W | — |
| Sorties | 2x DVI1x HDMI1x DisplayPort | No outputs |
| Connecteurs de puissance | 4x 8-pin | None |
| Board number | C671 | E4914 SKU 31 |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.3 | 6.6 |
| CUDA | — | 7.5 |
AUTRES CARACTÉRISTIQUES
Graphiques mobiles
| Date de publication | — | Jan 29th, 2019 |
|---|---|---|
| Génération | — | GeForce 20 Mobile |
| Production | — | Active |
| Bus interface | — | PCIe 3.0 x16 |
| Prédécesseur | — | GeForce 10 Mobile |
| Successeur | — | GeForce 30 Mobile |
