AMD Radeon RX 560X vs NVIDIA Tesla M10
Processeur graphique
| Nom du GPU | Polaris 21 | GM107 |
|---|---|---|
| GPU variant | Polaris 21 XT (215-0908004) | GM107-570-A2 |
| Architecture | GCN 4.0 | Maxwell |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 28 nm |
| Transistors | 3,000 million | 1,870 million |
| Taille des matrices | 123 mm² | 148 mm² |
Carte graphique
| Date de publication | Apr 11th, 2018 | May 18th, 2016 |
|---|---|---|
| Génération | Polaris | Tesla |
| Production | Active | End-of-life |
| Bus interface | PCIe 3.0 x8 | PCIe 3.0 x16 |
| Prédécesseur | Polaris | — |
| Successeur | Vega | — |
Vitesse clock
| Base clock | 1175 MHz | 1033 MHz |
|---|---|---|
| Boost clock | 1275 MHz | 1306 MHz |
| Mémoire clock | 1750 MHz 7 Gbps effective | 1300 MHz 5.2 Gbps effective |
Mémoire
| Taille de la mémoire | 4 GB | 8 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 128 bit | 128 bit |
| Bande passante | 112.0 GB/s | 83.20 GB/s |
Render Config
| Shading units | 1024 | 640 |
|---|---|---|
| TMUs | 64 | 40 |
| ROPs | 16 | 16 |
| Compute units | 16 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
| Cache L2 | 1024 KB | 2 MB |
| Comptage SMM | — | 5 |
Performance théorique
| Taux de pixel | 20.40 GPixel/s | 20.90 GPixel/s |
|---|---|---|
| Taux de texture | 81.60 GTexel/s | 52.24 GTexel/s |
| FP16 (half) performance | 2.611 TFLOPS (1:1) | — |
| FP32 (float) performance | 2.611 TFLOPS | 1.672 TFLOPS |
| FP64 (double) performance | 163.2 GFLOPS (1:16) | 52.24 GFLOPS (1:32) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 170 mm 6.7 inches | 267 mm 10.5 inches |
| TDP | 75 W | 225 W |
| Suggestions pour le PSU | 250 W | 550 W |
| Sorties | 1x DVI1x HDMI1x DisplayPort | No outputs |
| Connecteurs de puissance | None | 1x 8-pin |
| Board number | C994 | P2405 SKU 70 |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.4 | 5.1 |
| CUDA | — | 5.0 |
