ATI Mobility Radeon HD 4850 X2 vs NVIDIA GeForce 940A
Processeur graphique
| Nom du GPU | M98 | GM108 |
|---|---|---|
| Architecture | TeraScale | Maxwell |
| Fonderie | TSMC | TSMC |
| Taille du processus | 55 nm | 28 nm |
| Transistors | 956 million | unknown |
| Taille des matrices | 256 mm² | unknown |
| GPU variant | — | N16S-GT-S |
Graphiques mobiles
| Date de publication | Jan 9th, 2009 | Mar 13th, 2015 |
|---|---|---|
| Génération | M9x (Mobility HD 4800) | GeForce 900A |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 2.0 x16 | PCIe 3.0 x8 |
| Critiques | 2 in our database | — |
| Prédécesseur | M8x | GeForce 800A |
| Successeur | Manhattan | — |
Vitesse clock
| GPU clock | 500 MHz | — |
|---|---|---|
| Mémoire clock | 700 MHz 2.8 Gbps effective | 1001 MHz 2 Gbps effective |
| Base clock | — | 1072 MHz |
| Boost clock | — | 1176 MHz |
Mémoire
| Taille de la mémoire | 1024 MB | 2 GB |
|---|---|---|
| Type de mémoire | GDDR5 | DDR3 |
| Bus mémoire | 256 bit | 64 bit |
| Bande passante | 89.60 GB/s | 16.02 GB/s |
Render Config
| Shading units | 800 | 384 |
|---|---|---|
| TMUs | 40 | 16 |
| ROPs | 16 | 8 |
| Compute units | 10 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
| Cache L2 | 256 KB | 1024 KB |
| Comptage SMM | — | 3 |
Performance théorique
| Taux de pixel | 8.000 GPixel/s | 9.408 GPixel/s |
|---|---|---|
| Taux de texture | 20.00 GTexel/s | 18.82 GTexel/s |
| FP32 (float) performance | 800.0 GFLOPS | 903.2 GFLOPS |
| FP64 (double) performance | 160.0 GFLOPS (1:5) | 28.22 GFLOPS (1:32) |
Board Design
| TDP | unknown | 33 W |
|---|---|---|
| Sorties | No outputs | No outputs |
| Taille Slot | — | IGP |
Caractéristiques graphiques
| DirectX | 10.1 (10_1) | 12 (11_0) |
|---|---|---|
| OpenGL | 3.3 | 4.6 |
| OpenCL | 1.1 | 3.0 |
| Vulkan | — | 1.1 |
| Shader model | 4.1 | 5.1 |
| CUDA | — | 5.0 |
