AMD Radeon Pro 570X vs NVIDIA GeForce GTX 675M
Processeur graphique
| Nom du GPU | Polaris 20 | GF114 |
|---|---|---|
| GPU variant | Polaris 20 | N13E-GS1-A1 |
| Architecture | GCN 4.0 | Fermi 2.0 |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 40 nm |
| Transistors | 5,700 million | 1,950 million |
| Taille des matrices | 232 mm² | 332 mm² |
Graphiques mobiles
| Date de publication | Mar 18th, 2019 | Mar 22nd, 2012 |
|---|---|---|
| Génération | Radeon Pro Mac (500X Series) | GeForce 600M |
| Production | Active | End-of-life |
| Bus interface | PCIe 3.0 x16 | MXM-B (3.0) |
| Prédécesseur | — | GeForce 500M |
| Successeur | — | GeForce 700M |
Vitesse clock
| Base clock | 1000 MHz | — |
|---|---|---|
| Boost clock | 1105 MHz | — |
| Mémoire clock | 1700 MHz 6.8 Gbps effective | 750 MHz 3 Gbps effective |
| GPU clock | — | 620 MHz |
| Shader clock | — | 1240 MHz |
Mémoire
| Taille de la mémoire | 4 GB | 2 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 256 bit | 256 bit |
| Bande passante | 217.6 GB/s | 96.00 GB/s |
Render Config
| Shading units | 1792 | 384 |
|---|---|---|
| TMUs | 112 | 64 |
| ROPs | 32 | 32 |
| Compute units | 28 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 2 MB | 512 KB |
| Comptage SM | — | 8 |
Performance théorique
| Taux de pixel | 35.36 GPixel/s | 9.920 GPixel/s |
|---|---|---|
| Taux de texture | 123.8 GTexel/s | 39.68 GTexel/s |
| FP16 (half) performance | 3.960 TFLOPS (1:1) | — |
| FP32 (float) performance | 3.960 TFLOPS | 952.3 GFLOPS |
| FP64 (double) performance | 247.5 GFLOPS (1:16) | 79.36 GFLOPS (1:12) |
Board Design
| Taille Slot | IGP | MXM Module |
|---|---|---|
| TDP | 150 W | 100 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | None | — |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 1.1 |
| Vulkan | 1.2 | — |
| Shader model | 6.4 | 5.1 |
| CUDA | — | 2.1 |
