AMD Radeon Pro W5500M vs NVIDIA GeForce GTX 960A
Processeur graphique
| Nom du GPU | Navi 14 | GM107 |
|---|---|---|
| GPU variant | Navi 14 PRO XTM | N16P-GX-A1 |
| Architecture | RDNA 1.0 | Maxwell |
| Fonderie | TSMC | TSMC |
| Taille du processus | 7 nm | 28 nm |
| Transistors | 6,400 million | 1,870 million |
| Taille des matrices | 158 mm² | 148 mm² |
Graphiques mobiles
| Date de publication | Feb 10th, 2020 | Mar 13th, 2015 |
|---|---|---|
| Génération | Radeon Pro Mobile (W5x00M) | GeForce 900A |
| Production | Active | End-of-life |
| Bus interface | PCIe 4.0 x8 | MXM-B (3.0) |
| Prédécesseur | — | GeForce 800A |
Vitesse clock
| Base clock | 1000 MHz | 1029 MHz |
|---|---|---|
| Boost clock | 1700 MHz | 1085 MHz |
| Mémoire clock | 1750 MHz 14 Gbps effective | 1253 MHz 5 Gbps effective |
Mémoire
| Taille de la mémoire | 4 GB | 2 GB |
|---|---|---|
| Type de mémoire | GDDR6 | GDDR5 |
| Bus mémoire | 128 bit | 128 bit |
| Bande passante | 224.0 GB/s | 80.19 GB/s |
Render Config
| Shading units | 1408 | 640 |
|---|---|---|
| TMUs | 88 | 40 |
| ROPs | 32 | 16 |
| Compute units | 22 | — |
| Cache L2 | 2 MB | 2 MB |
| Comptage SMM | — | 5 |
| Cache L1 | — | 64 KB (per SMM) |
Performance théorique
| Taux de pixel | 54.40 GPixel/s | 17.36 GPixel/s |
|---|---|---|
| Taux de texture | 149.6 GTexel/s | 43.40 GTexel/s |
| FP16 (half) performance | 9.574 TFLOPS (2:1) | — |
| FP32 (float) performance | 4.787 TFLOPS | 1,389 GFLOPS |
| FP64 (double) performance | 299.2 GFLOPS (1:16) | 43.40 GFLOPS (1:32) |
Board Design
| TDP | 85 W | 75 W |
|---|---|---|
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | None | — |
| Taille Slot | — | MXM Module |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.5 | 5.1 |
| CUDA | — | 5.0 |
