ATI Radeon HD 2900 XTX vs NVIDIA NVS 310
Processeur graphique
| Nom du GPU | R600 | GF119 |
|---|---|---|
| GPU variant | R600 XTX A11 (215RGMDKA11FG) | GF119-825-A1 |
| Architecture | TeraScale | Fermi 2.0 |
| Fonderie | TSMC | TSMC |
| Taille du processus | 80 nm | 40 nm |
| Transistors | 720 million | 292 million |
| Taille des matrices | 420 mm² | 79 mm² |
Carte graphique
| Date de publication | Never Released | Jun 26th, 2012 |
|---|---|---|
| Génération | Radeon R600 | NVS |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 1.0 x16 | PCIe 2.0 x16 |
| Critiques | 63 in our database | 26 in our database |
| Prédécesseur | Radeon R500 PCIe | — |
| Successeur | Radeon R700 | — |
| Prix de lancement | — | 159 USD |
Vitesse clock
| GPU clock | 743 MHz | 523 MHz |
|---|---|---|
| Mémoire clock | 828 MHz 1656 Mbps effective | 875 MHz 1750 Mbps effective |
| Shader clock | — | 1046 MHz |
Mémoire
| Taille de la mémoire | 512 MB | 512 MB |
|---|---|---|
| Type de mémoire | GDDR3 | DDR3 |
| Bus mémoire | 512 bit | 64 bit |
| Bande passante | 106.0 GB/s | 14.00 GB/s |
Render Config
| Shading units | 320 | 48 |
|---|---|---|
| TMUs | 16 | 8 |
| ROPs | 16 | 4 |
| Compute units | 4 | — |
| Cache L2 | 256 KB | 128 KB |
| Comptage SM | — | 1 |
| Cache L1 | — | 64 KB (per SM) |
Performance théorique
| Taux de pixel | 11.89 GPixel/s | 1.046 GPixel/s |
|---|---|---|
| Taux de texture | 11.89 GTexel/s | 4.184 GTexel/s |
| FP32 (float) performance | 475.5 GFLOPS | 100.4 GFLOPS |
| FP64 (double) performance | — | 8.368 GFLOPS (1:12) |
Board Design
| Taille Slot | Dual-slot | Single-slot |
|---|---|---|
| Longueur | 315 mm 12.4 inches | 156 mm 6.1 inches |
| TDP | 240 W | 20 W |
| Suggestions pour le PSU | 550 W | 200 W |
| Sorties | 2x DVI1x S-Video | 2x DisplayPort |
| Connecteurs de puissance | 2x 6-pin | None |
| Board number | B001-31 | P2014 |
Caractéristiques graphiques
| DirectX | 10.0 (10_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 3.3 (full) 4.0 (partial) | 4.6 |
| OpenCL | — | 1.1 |
| Vulkan | — | — |
| Shader model | 4.0 | 5.1 |
| CUDA | — | 2.1 |
