ATI Mobility Radeon HD 3870 vs NVIDIA Quadro 1000M
Processeur graphique
| Nom du GPU | M88 | GF108 |
|---|---|---|
| Architecture | TeraScale | Fermi |
| Fonderie | TSMC | TSMC |
| Taille du processus | 55 nm | 40 nm |
| Transistors | 666 million | 585 million |
| Taille des matrices | 192 mm² | 116 mm² |
| GPU variant | — | N12P-Q1 |
Graphiques mobiles
| Date de publication | Jun 4th, 2008 | Jan 13th, 2011 |
|---|---|---|
| Génération | M8x (Mobility HD 3800) | Quadro Mobile (x000M) |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 2.0 x16 | MXM-A (3.0) |
| Critiques | 2 in our database | 26 in our database |
| Prédécesseur | M7x | Quadro FX Mobile |
| Successeur | M9x | — |
Vitesse clock
| GPU clock | 660 MHz | 700 MHz |
|---|---|---|
| Mémoire clock | 850 MHz 1700 Mbps effective | 900 MHz 1800 Mbps effective |
| Shader clock | — | 1400 MHz |
Mémoire
| Taille de la mémoire | 512 MB | 2 GB |
|---|---|---|
| Type de mémoire | GDDR3 | DDR3 |
| Bus mémoire | 256 bit | 128 bit |
| Bande passante | 54.40 GB/s | 28.80 GB/s |
Render Config
| Shading units | 320 | 96 |
|---|---|---|
| TMUs | 16 | 16 |
| ROPs | 16 | 4 |
| Compute units | 4 | — |
| Cache L2 | 256 KB | 256 KB |
| Comptage SM | — | 4 |
| Cache L1 | — | 64 KB (per SM) |
Performance théorique
| Taux de pixel | 10.56 GPixel/s | 5.600 GPixel/s |
|---|---|---|
| Taux de texture | 10.56 GTexel/s | 11.20 GTexel/s |
| FP32 (float) performance | 422.4 GFLOPS | 268.8 GFLOPS |
| FP64 (double) performance | 84.48 GFLOPS (1:5) | 22.40 GFLOPS (1:12) |
Board Design
| TDP | 55 W | 45 W |
|---|---|---|
| Sorties | No outputs | No outputs |
| Taille Slot | — | MXM Module |
Caractéristiques graphiques
| DirectX | 10.1 (10_1) | 12 (11_0) |
|---|---|---|
| OpenGL | 3.3 | 4.6 |
| OpenCL | — | 1.1 |
| Vulkan | — | — |
| Shader model | 4.1 | 5.1 |
| CUDA | — | 2.1 |
