AMD Radeon Pro 5600M vs NVIDIA GeForce GTX 1070 Max-Q
Processeur graphique
| Nom du GPU | Navi 12 | GP104 |
|---|---|---|
| GPU variant | Navi 12 | N17E-G2-A1 |
| Architecture | RDNA 1.0 | Pascal |
| Fonderie | TSMC | TSMC |
| Taille du processus | 7 nm | 16 nm |
| Transistors | unknown | 7,200 million |
| Taille des matrices | unknown | 314 mm² |
Graphiques mobiles
| Date de publication | Jun 15th, 2020 | Jun 27th, 2017 |
|---|---|---|
| Génération | Radeon Pro Mac (Navi Mobile) | GeForce 10 Mobile |
| Production | Active | End-of-life |
| Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| Critiques | — | 125 in our database |
| Prédécesseur | — | GeForce 900M |
| Successeur | — | GeForce 20 Mobile |
Vitesse clock
| Base clock | 1000 MHz | 1215 MHz |
|---|---|---|
| Boost clock | 1035 MHz | 1379 MHz |
| Mémoire clock | 770 MHz 1540 Mbps effective | 2002 MHz 8 Gbps effective |
Mémoire
| Taille de la mémoire | 8 GB | 8 GB |
|---|---|---|
| Type de mémoire | HBM2 | GDDR5 |
| Bus mémoire | 2048 bit | 256 bit |
| Bande passante | 394.2 GB/s | 256.3 GB/s |
Render Config
| Shading units | 2560 | 2048 |
|---|---|---|
| TMUs | 160 | 128 |
| ROPs | 64 | 64 |
| Compute units | 40 | — |
| Cache L2 | 4 MB | 2 MB |
| Comptage SM | — | 16 |
| Cache L1 | — | 48 KB (per SM) |
Performance théorique
| Taux de pixel | 66.24 GPixel/s | 88.26 GPixel/s |
|---|---|---|
| Taux de texture | 165.6 GTexel/s | 176.5 GTexel/s |
| FP16 (half) performance | 10.60 TFLOPS (2:1) | 88.26 GFLOPS (1:64) |
| FP32 (float) performance | 5.299 TFLOPS | 5.648 TFLOPS |
| FP64 (double) performance | 331.2 GFLOPS (1:16) | 176.5 GFLOPS (1:32) |
Board Design
| Taille Slot | IGP | MXM Module |
|---|---|---|
| TDP | 50 W | 115 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | None | None |
| Board number | — | E2914 SKU 10 |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.2 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.5 | 6.4 |
| CUDA | — | 6.1 |
