AMD Xbox Series X GPU vs NVIDIA GeForce RTX 2070
Processeur graphique
| Nom du GPU | Scarlett | TU106 |
|---|---|---|
| Architecture | RDNA 2.0 | Turing |
| Fonderie | TSMC | TSMC |
| Taille du processus | 7 nm | 12 nm |
| Transistors | 15,300 million | 10,800 million |
| Taille des matrices | 360 mm² | 445 mm² |
| GPU variant | — | TU106-400A-A1 |
Carte graphique
| Date de publication | Nov 10th, 2020 | Oct 17th, 2018 |
|---|---|---|
| Génération | Console GPU | GeForce 20 |
| Production | Active | Active |
| Bus interface | IGP | PCIe 3.0 x16 |
| Prix de lancement | 499 USD | 499 USD |
| Prédécesseur | — | GeForce 10 |
| Critiques | — | 73 in our database |
| Successeur | — | GeForce 30 |
Vitesse clock
| GPU clock | 1825 MHz | — |
|---|---|---|
| Mémoire clock | 1750 MHz 14 Gbps effective | 1750 MHz 14 Gbps effective |
| Base clock | — | 1410 MHz |
| Boost clock | — | 1620 MHz |
Mémoire
| Taille de la mémoire | 10 GB | 8 GB |
|---|---|---|
| Type de mémoire | GDDR6 | GDDR6 |
| Bus mémoire | 320 bit | 256 bit |
| Bande passante | 560.0 GB/s | 448.0 GB/s |
Render Config
| Shading units | 3328 | 2304 |
|---|---|---|
| TMUs | 208 | 144 |
| ROPs | 64 | 64 |
| Compute units | 52 | — |
| Cache L2 | 5 MB | 4 MB |
| Comptage SM | — | 36 |
| Tensor cores | — | 288 |
| RT cores | — | 36 |
| Cache L1 | — | 64 KB (per SM) |
Performance théorique
| Taux de pixel | 116.8 GPixel/s | 103.7 GPixel/s |
|---|---|---|
| Taux de texture | 379.6 GTexel/s | 233.3 GTexel/s |
| FP16 (half) performance | 24.29 TFLOPS (2:1) | 14.93 TFLOPS (2:1) |
| FP32 (float) performance | 12.15 TFLOPS | 7.465 TFLOPS |
| FP64 (double) performance | 759.2 GFLOPS (1:16) | 233.3 GFLOPS (1:32) |
Board Design
| Taille Slot | IGP | Dual-slot |
|---|---|---|
| Longueur | 301 mm 11.9 inches | 229 mm 9 inches |
| Taille | 151 mm 5.9 inches | 113 mm 4.4 inches |
| Taille | 151 mm 5.9 inches | 35 mm 1.4 inches |
| Poids | 4.85 kg (9.8 lbs) | — |
| TDP | 200 W | 175 W |
| Suggestions pour le PSU | 350 W | 450 W |
| Sorties | No outputs | 1x DVI1x HDMI2x DisplayPort1x USB Type-C |
| Connecteurs de puissance | — | 1x 8-pin |
| Board number | — | PG160 SKU 52 |
Caractéristiques graphiques
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.5 | 6.6 |
| CUDA | — | 7.5 |
